Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1000/config.json +65 -0
- checkpoint-1000/experiment_cfg/metadata.json +195 -0
- checkpoint-1000/model-00001-of-00002.safetensors +3 -0
- checkpoint-1000/model-00002-of-00002.safetensors +3 -0
- checkpoint-1000/model.safetensors.index.json +809 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state_0.pth +3 -0
- checkpoint-1000/rng_state_1.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +733 -0
- checkpoint-1500/config.json +65 -0
- checkpoint-1500/experiment_cfg/metadata.json +195 -0
- checkpoint-1500/model-00001-of-00002.safetensors +3 -0
- checkpoint-1500/model-00002-of-00002.safetensors +3 -0
- checkpoint-1500/model.safetensors.index.json +809 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state_0.pth +3 -0
- checkpoint-1500/rng_state_1.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +1083 -0
- checkpoint-2000/config.json +65 -0
- checkpoint-2000/experiment_cfg/metadata.json +195 -0
- checkpoint-2000/model-00001-of-00002.safetensors +3 -0
- checkpoint-2000/model-00002-of-00002.safetensors +3 -0
- checkpoint-2000/model.safetensors.index.json +809 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state_0.pth +3 -0
- checkpoint-2000/rng_state_1.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +1433 -0
- checkpoint-2500/config.json +65 -0
- checkpoint-2500/experiment_cfg/metadata.json +195 -0
- checkpoint-2500/model-00001-of-00002.safetensors +3 -0
- checkpoint-2500/model-00002-of-00002.safetensors +3 -0
- checkpoint-2500/model.safetensors.index.json +809 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state_0.pth +3 -0
- checkpoint-2500/rng_state_1.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +1783 -0
- checkpoint-500/config.json +65 -0
- checkpoint-500/experiment_cfg/metadata.json +195 -0
- checkpoint-500/model-00001-of-00002.safetensors +3 -0
- checkpoint-500/model-00002-of-00002.safetensors +3 -0
- checkpoint-500/model.safetensors.index.json +809 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state_0.pth +3 -0
- checkpoint-500/rng_state_1.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +383 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/adleboy/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
|
| 3 |
+
"action_dim": 32,
|
| 4 |
+
"action_head_cfg": {
|
| 5 |
+
"action_dim": 32,
|
| 6 |
+
"action_horizon": 16,
|
| 7 |
+
"add_pos_embed": true,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"dropout": 0.2,
|
| 11 |
+
"final_dropout": true,
|
| 12 |
+
"interleave_self_attention": true,
|
| 13 |
+
"norm_type": "ada_norm",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_layers": 16,
|
| 16 |
+
"output_dim": 1024,
|
| 17 |
+
"positional_embeddings": null
|
| 18 |
+
},
|
| 19 |
+
"freeze_decode_layer": false,
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"load_pretrained_det_decode_layer_path": null,
|
| 23 |
+
"max_action_dim": 32,
|
| 24 |
+
"max_state_dim": 64,
|
| 25 |
+
"model_dtype": "float32",
|
| 26 |
+
"noise_beta_alpha": 1.5,
|
| 27 |
+
"noise_beta_beta": 1.0,
|
| 28 |
+
"noise_s": 0.999,
|
| 29 |
+
"num_inference_timesteps": 16,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true
|
| 33 |
+
},
|
| 34 |
+
"action_horizon": 16,
|
| 35 |
+
"architectures": [
|
| 36 |
+
"GR00T_N1"
|
| 37 |
+
],
|
| 38 |
+
"attn_implementation": null,
|
| 39 |
+
"backbone_cfg": {
|
| 40 |
+
"allow_reshape_visual": true,
|
| 41 |
+
"load_pretrained_det_eagle_path": null,
|
| 42 |
+
"model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 43 |
+
"processor_cfg": {
|
| 44 |
+
"max_input_tiles": 1,
|
| 45 |
+
"model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 46 |
+
"model_spec": {
|
| 47 |
+
"num_image_token": 64,
|
| 48 |
+
"template": "qwen2-chat"
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"projector_dim": 2048,
|
| 52 |
+
"remove_llm": false,
|
| 53 |
+
"reproject_vision": false,
|
| 54 |
+
"scale_image_resolution": 1,
|
| 55 |
+
"select_layer": 12,
|
| 56 |
+
"tune_llm": false,
|
| 57 |
+
"tune_visual": true
|
| 58 |
+
},
|
| 59 |
+
"compute_dtype": "bfloat16",
|
| 60 |
+
"hidden_size": 1536,
|
| 61 |
+
"model_dtype": "float32",
|
| 62 |
+
"model_type": "gr00t_n1",
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.45.2"
|
| 65 |
+
}
|
checkpoint-1000/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"single_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
122.080078125,
|
| 8 |
+
198.193359375,
|
| 9 |
+
182.28515625,
|
| 10 |
+
114.43359375,
|
| 11 |
+
262.177734375
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-95.9765625,
|
| 15 |
+
-179.912109375,
|
| 16 |
+
-258.486328125,
|
| 17 |
+
-100.01953125,
|
| 18 |
+
-179.912109375
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
9.608419418334961,
|
| 22 |
+
114.65914154052734,
|
| 23 |
+
102.69532775878906,
|
| 24 |
+
63.54849624633789,
|
| 25 |
+
-3.96468186378479
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
30.130109786987305,
|
| 29 |
+
52.885677337646484,
|
| 30 |
+
68.62229919433594,
|
| 31 |
+
26.573131561279297,
|
| 32 |
+
62.51667785644531
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-55.1953125,
|
| 36 |
+
12.196582031250038,
|
| 37 |
+
-228.779296875,
|
| 38 |
+
-40.78125,
|
| 39 |
+
-152.40234375
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
87.626953125,
|
| 43 |
+
192.041015625,
|
| 44 |
+
179.47265625,
|
| 45 |
+
108.28125,
|
| 46 |
+
155.0390625
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
105.29850769042969
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
-2.7297544479370117
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
11.653524398803711
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
17.93401336669922
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
-1.4121800661087036
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
93.88059997558594
|
| 67 |
+
]
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"action": {
|
| 71 |
+
"single_arm": {
|
| 72 |
+
"max": [
|
| 73 |
+
123.046875,
|
| 74 |
+
202.763671875,
|
| 75 |
+
190.458984375,
|
| 76 |
+
117.0703125,
|
| 77 |
+
267.802734375
|
| 78 |
+
],
|
| 79 |
+
"min": [
|
| 80 |
+
-97.646484375,
|
| 81 |
+
-179.912109375,
|
| 82 |
+
-269.6484375,
|
| 83 |
+
-102.65625,
|
| 84 |
+
-270.0
|
| 85 |
+
],
|
| 86 |
+
"mean": [
|
| 87 |
+
9.716768264770508,
|
| 88 |
+
117.07723999023438,
|
| 89 |
+
101.3852767944336,
|
| 90 |
+
63.94012451171875,
|
| 91 |
+
-4.292983531951904
|
| 92 |
+
],
|
| 93 |
+
"std": [
|
| 94 |
+
30.517000198364258,
|
| 95 |
+
52.163082122802734,
|
| 96 |
+
69.69375610351562,
|
| 97 |
+
26.988319396972656,
|
| 98 |
+
63.348819732666016
|
| 99 |
+
],
|
| 100 |
+
"q01": [
|
| 101 |
+
-55.8984375,
|
| 102 |
+
16.435546875,
|
| 103 |
+
-230.888671875,
|
| 104 |
+
-41.66015625,
|
| 105 |
+
-153.896484375
|
| 106 |
+
],
|
| 107 |
+
"q99": [
|
| 108 |
+
88.505859375,
|
| 109 |
+
195.64453125,
|
| 110 |
+
182.900390625,
|
| 111 |
+
109.599609375,
|
| 112 |
+
155.7421875
|
| 113 |
+
]
|
| 114 |
+
},
|
| 115 |
+
"gripper": {
|
| 116 |
+
"max": [
|
| 117 |
+
109.84339904785156
|
| 118 |
+
],
|
| 119 |
+
"min": [
|
| 120 |
+
-7.955596446990967
|
| 121 |
+
],
|
| 122 |
+
"mean": [
|
| 123 |
+
9.987146377563477
|
| 124 |
+
],
|
| 125 |
+
"std": [
|
| 126 |
+
18.02056121826172
|
| 127 |
+
],
|
| 128 |
+
"q01": [
|
| 129 |
+
-2.5742573738098145
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
96.20721435546875
|
| 133 |
+
]
|
| 134 |
+
}
|
| 135 |
+
}
|
| 136 |
+
},
|
| 137 |
+
"modalities": {
|
| 138 |
+
"video": {
|
| 139 |
+
"images0": {
|
| 140 |
+
"resolution": [
|
| 141 |
+
320,
|
| 142 |
+
240
|
| 143 |
+
],
|
| 144 |
+
"channels": 3,
|
| 145 |
+
"fps": 30.0
|
| 146 |
+
},
|
| 147 |
+
"images1": {
|
| 148 |
+
"resolution": [
|
| 149 |
+
320,
|
| 150 |
+
240
|
| 151 |
+
],
|
| 152 |
+
"channels": 3,
|
| 153 |
+
"fps": 30.0
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"state": {
|
| 157 |
+
"single_arm": {
|
| 158 |
+
"absolute": true,
|
| 159 |
+
"rotation_type": null,
|
| 160 |
+
"shape": [
|
| 161 |
+
5
|
| 162 |
+
],
|
| 163 |
+
"continuous": true
|
| 164 |
+
},
|
| 165 |
+
"gripper": {
|
| 166 |
+
"absolute": true,
|
| 167 |
+
"rotation_type": null,
|
| 168 |
+
"shape": [
|
| 169 |
+
1
|
| 170 |
+
],
|
| 171 |
+
"continuous": true
|
| 172 |
+
}
|
| 173 |
+
},
|
| 174 |
+
"action": {
|
| 175 |
+
"single_arm": {
|
| 176 |
+
"absolute": true,
|
| 177 |
+
"rotation_type": null,
|
| 178 |
+
"shape": [
|
| 179 |
+
5
|
| 180 |
+
],
|
| 181 |
+
"continuous": true
|
| 182 |
+
},
|
| 183 |
+
"gripper": {
|
| 184 |
+
"absolute": true,
|
| 185 |
+
"rotation_type": null,
|
| 186 |
+
"shape": [
|
| 187 |
+
1
|
| 188 |
+
],
|
| 189 |
+
"continuous": true
|
| 190 |
+
}
|
| 191 |
+
}
|
| 192 |
+
},
|
| 193 |
+
"embodiment_tag": "new_embodiment"
|
| 194 |
+
}
|
| 195 |
+
}
|
checkpoint-1000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f47664bd28dd20e108ccfb549b3f944b1f5edf23cd2bbc480d1b184726f6703c
|
| 3 |
+
size 4938446392
|
checkpoint-1000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d9e62e10c272b9cb113217a74788fb2cdb5b029ffaaf5f09772f2cd04b40ec9
|
| 3 |
+
size 3821736024
|
checkpoint-1000/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,809 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8760067008
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 7 |
+
"action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 8 |
+
"action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 9 |
+
"action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 10 |
+
"action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
|
| 11 |
+
"action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
|
| 12 |
+
"action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
|
| 13 |
+
"action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
|
| 14 |
+
"action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
|
| 15 |
+
"action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
|
| 16 |
+
"action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
|
| 17 |
+
"action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
|
| 18 |
+
"action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
|
| 19 |
+
"action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
|
| 20 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
|
| 21 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
|
| 23 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 25 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 26 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 27 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 29 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 30 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 31 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 32 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 33 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 35 |
+
"action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 37 |
+
"action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 38 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 39 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 41 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 43 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 44 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 45 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 46 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 47 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 49 |
+
"action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 50 |
+
"action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 51 |
+
"action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 53 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 56 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 57 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 59 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 60 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 61 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 63 |
+
"action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 65 |
+
"action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 66 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 67 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 68 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 69 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 70 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 71 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 73 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 74 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 75 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 77 |
+
"action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 78 |
+
"action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 79 |
+
"action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 81 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 83 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 85 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 87 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 89 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 92 |
+
"action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 93 |
+
"action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 95 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 97 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 99 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 101 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 103 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 105 |
+
"action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 107 |
+
"action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 109 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 111 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 113 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 115 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 117 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 119 |
+
"action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 121 |
+
"action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 123 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 125 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 127 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 129 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 131 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 133 |
+
"action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 135 |
+
"action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 137 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 139 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 141 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 143 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 145 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 147 |
+
"action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 149 |
+
"action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 151 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 153 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 155 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 157 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 159 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 161 |
+
"action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 165 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 167 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 171 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 177 |
+
"action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 179 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 189 |
+
"action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 191 |
+
"action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 195 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 201 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 203 |
+
"action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 215 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 219 |
+
"action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 225 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 227 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 237 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 239 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 243 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 250 |
+
"action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 251 |
+
"action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 252 |
+
"action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 253 |
+
"backbone.linear.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"backbone.linear.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
|
| 370 |
+
"backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 381 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 655 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 715 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 727 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 739 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 751 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 763 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 775 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 787 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 799 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
| 808 |
+
}
|
| 809 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0d7bf4f9e5fe7a7262a58ac60e9595e4ca5ba37a6b30bd0eed56c7b4cd000bd
|
| 3 |
+
size 10272357262
|
checkpoint-1000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8092f93550a57f38b0fa7e8a007ae754cce2b3a1edf4cb1e1c28cba4f7ca052c
|
| 3 |
+
size 14512
|
checkpoint-1000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d5fcb910e61651cf601917d58b120ba524b77a5d2f58e013729a18b481ab7bb
|
| 3 |
+
size 14512
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:454397c00ca5acd300b4df3c2af9056e1731a05e45786179d95a172ec1c03c01
|
| 3 |
+
size 1064
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.02594033722438392,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00025940337224383917,
|
| 13 |
+
"grad_norm": 13.49365234375,
|
| 14 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 15 |
+
"loss": 1.5584,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0005188067444876783,
|
| 20 |
+
"grad_norm": 2.6006040573120117,
|
| 21 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 22 |
+
"loss": 0.7111,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0007782101167315176,
|
| 27 |
+
"grad_norm": 4.435553073883057,
|
| 28 |
+
"learning_rate": 4.8e-05,
|
| 29 |
+
"loss": 0.3076,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0010376134889753567,
|
| 34 |
+
"grad_norm": 1.1146177053451538,
|
| 35 |
+
"learning_rate": 6.400000000000001e-05,
|
| 36 |
+
"loss": 0.1826,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0012970168612191958,
|
| 41 |
+
"grad_norm": 0.8707008957862854,
|
| 42 |
+
"learning_rate": 8e-05,
|
| 43 |
+
"loss": 0.1341,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0015564202334630351,
|
| 48 |
+
"grad_norm": 1.7411352396011353,
|
| 49 |
+
"learning_rate": 9.6e-05,
|
| 50 |
+
"loss": 0.1144,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0018158236057068742,
|
| 55 |
+
"grad_norm": 0.9691908955574036,
|
| 56 |
+
"learning_rate": 0.00011200000000000001,
|
| 57 |
+
"loss": 0.0831,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0020752269779507134,
|
| 62 |
+
"grad_norm": 1.0398532152175903,
|
| 63 |
+
"learning_rate": 0.00012800000000000002,
|
| 64 |
+
"loss": 0.0801,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0023346303501945525,
|
| 69 |
+
"grad_norm": 0.5252112746238708,
|
| 70 |
+
"learning_rate": 0.000144,
|
| 71 |
+
"loss": 0.081,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0025940337224383916,
|
| 76 |
+
"grad_norm": 0.6552278995513916,
|
| 77 |
+
"learning_rate": 0.00016,
|
| 78 |
+
"loss": 0.0821,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0028534370946822307,
|
| 83 |
+
"grad_norm": 0.6302046775817871,
|
| 84 |
+
"learning_rate": 0.00017600000000000002,
|
| 85 |
+
"loss": 0.0749,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0031128404669260703,
|
| 90 |
+
"grad_norm": 0.7439587712287903,
|
| 91 |
+
"learning_rate": 0.000192,
|
| 92 |
+
"loss": 0.0647,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0033722438391699094,
|
| 97 |
+
"grad_norm": 6.8584771156311035,
|
| 98 |
+
"learning_rate": 0.0001999978128380225,
|
| 99 |
+
"loss": 0.0726,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0036316472114137485,
|
| 104 |
+
"grad_norm": 2.014613389968872,
|
| 105 |
+
"learning_rate": 0.0001999803161162393,
|
| 106 |
+
"loss": 0.0936,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0038910505836575876,
|
| 111 |
+
"grad_norm": 1.3758050203323364,
|
| 112 |
+
"learning_rate": 0.00019994532573409262,
|
| 113 |
+
"loss": 0.1089,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004150453955901427,
|
| 118 |
+
"grad_norm": 1.3027769327163696,
|
| 119 |
+
"learning_rate": 0.00019989284781388617,
|
| 120 |
+
"loss": 0.0772,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.004409857328145266,
|
| 125 |
+
"grad_norm": 1.021938443183899,
|
| 126 |
+
"learning_rate": 0.00019982289153773646,
|
| 127 |
+
"loss": 0.0695,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.004669260700389105,
|
| 132 |
+
"grad_norm": 0.8069638609886169,
|
| 133 |
+
"learning_rate": 0.00019973546914596623,
|
| 134 |
+
"loss": 0.0624,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.004928664072632944,
|
| 139 |
+
"grad_norm": 0.5198134779930115,
|
| 140 |
+
"learning_rate": 0.00019963059593496268,
|
| 141 |
+
"loss": 0.0481,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.005188067444876783,
|
| 146 |
+
"grad_norm": 0.39965012669563293,
|
| 147 |
+
"learning_rate": 0.00019950829025450114,
|
| 148 |
+
"loss": 0.0493,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005447470817120622,
|
| 153 |
+
"grad_norm": 0.8152652978897095,
|
| 154 |
+
"learning_rate": 0.0001993685735045343,
|
| 155 |
+
"loss": 0.0477,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.005706874189364461,
|
| 160 |
+
"grad_norm": 0.7083427309989929,
|
| 161 |
+
"learning_rate": 0.0001992114701314478,
|
| 162 |
+
"loss": 0.0501,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0059662775616083005,
|
| 167 |
+
"grad_norm": 0.690096914768219,
|
| 168 |
+
"learning_rate": 0.000199037007623783,
|
| 169 |
+
"loss": 0.0509,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0062256809338521405,
|
| 174 |
+
"grad_norm": 0.871699869632721,
|
| 175 |
+
"learning_rate": 0.00019884521650742715,
|
| 176 |
+
"loss": 0.0464,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.00648508430609598,
|
| 181 |
+
"grad_norm": 0.6445639133453369,
|
| 182 |
+
"learning_rate": 0.00019863613034027224,
|
| 183 |
+
"loss": 0.0462,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.006744487678339819,
|
| 188 |
+
"grad_norm": 0.4920782148838043,
|
| 189 |
+
"learning_rate": 0.0001984097857063434,
|
| 190 |
+
"loss": 0.0425,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.007003891050583658,
|
| 195 |
+
"grad_norm": 0.8624788522720337,
|
| 196 |
+
"learning_rate": 0.0001981662222093976,
|
| 197 |
+
"loss": 0.0471,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007263294422827497,
|
| 202 |
+
"grad_norm": 0.5704030990600586,
|
| 203 |
+
"learning_rate": 0.00019790548246599447,
|
| 204 |
+
"loss": 0.0571,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.007522697795071336,
|
| 209 |
+
"grad_norm": 0.569247841835022,
|
| 210 |
+
"learning_rate": 0.00019762761209803927,
|
| 211 |
+
"loss": 0.0531,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.007782101167315175,
|
| 216 |
+
"grad_norm": 0.7414583563804626,
|
| 217 |
+
"learning_rate": 0.0001973326597248006,
|
| 218 |
+
"loss": 0.0455,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008041504539559013,
|
| 223 |
+
"grad_norm": 0.42905348539352417,
|
| 224 |
+
"learning_rate": 0.00019702067695440332,
|
| 225 |
+
"loss": 0.0542,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008300907911802853,
|
| 230 |
+
"grad_norm": 0.6132651567459106,
|
| 231 |
+
"learning_rate": 0.00019669171837479873,
|
| 232 |
+
"loss": 0.0439,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.008560311284046693,
|
| 237 |
+
"grad_norm": 0.44733384251594543,
|
| 238 |
+
"learning_rate": 0.00019634584154421317,
|
| 239 |
+
"loss": 0.0429,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.008819714656290532,
|
| 244 |
+
"grad_norm": 0.516659677028656,
|
| 245 |
+
"learning_rate": 0.00019598310698107702,
|
| 246 |
+
"loss": 0.0407,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.009079118028534372,
|
| 251 |
+
"grad_norm": 0.2340136468410492,
|
| 252 |
+
"learning_rate": 0.00019560357815343577,
|
| 253 |
+
"loss": 0.036,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.00933852140077821,
|
| 258 |
+
"grad_norm": 0.6629723906517029,
|
| 259 |
+
"learning_rate": 0.00019520732146784491,
|
| 260 |
+
"loss": 0.041,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.00959792477302205,
|
| 265 |
+
"grad_norm": 0.3777199387550354,
|
| 266 |
+
"learning_rate": 0.0001947944062577507,
|
| 267 |
+
"loss": 0.0414,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.009857328145265888,
|
| 272 |
+
"grad_norm": 0.44298338890075684,
|
| 273 |
+
"learning_rate": 0.00019436490477135878,
|
| 274 |
+
"loss": 0.0371,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.010116731517509728,
|
| 279 |
+
"grad_norm": 0.4530090093612671,
|
| 280 |
+
"learning_rate": 0.00019391889215899299,
|
| 281 |
+
"loss": 0.037,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.010376134889753566,
|
| 286 |
+
"grad_norm": 0.36142367124557495,
|
| 287 |
+
"learning_rate": 0.0001934564464599461,
|
| 288 |
+
"loss": 0.0387,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.010635538261997406,
|
| 293 |
+
"grad_norm": 0.36559927463531494,
|
| 294 |
+
"learning_rate": 0.00019297764858882514,
|
| 295 |
+
"loss": 0.0386,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.010894941634241245,
|
| 300 |
+
"grad_norm": 0.47660204768180847,
|
| 301 |
+
"learning_rate": 0.00019248258232139388,
|
| 302 |
+
"loss": 0.0316,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.011154345006485085,
|
| 307 |
+
"grad_norm": 0.2614981234073639,
|
| 308 |
+
"learning_rate": 0.00019197133427991436,
|
| 309 |
+
"loss": 0.0417,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011413748378728923,
|
| 314 |
+
"grad_norm": 0.44811561703681946,
|
| 315 |
+
"learning_rate": 0.00019144399391799043,
|
| 316 |
+
"loss": 0.036,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.011673151750972763,
|
| 321 |
+
"grad_norm": 0.4213508367538452,
|
| 322 |
+
"learning_rate": 0.00019090065350491626,
|
| 323 |
+
"loss": 0.0399,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.011932555123216601,
|
| 328 |
+
"grad_norm": 0.29146406054496765,
|
| 329 |
+
"learning_rate": 0.0001903414081095315,
|
| 330 |
+
"loss": 0.0376,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.012191958495460441,
|
| 335 |
+
"grad_norm": 0.2714293897151947,
|
| 336 |
+
"learning_rate": 0.00018976635558358722,
|
| 337 |
+
"loss": 0.0362,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012451361867704281,
|
| 342 |
+
"grad_norm": 0.3767367899417877,
|
| 343 |
+
"learning_rate": 0.00018917559654462474,
|
| 344 |
+
"loss": 0.0364,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01271076523994812,
|
| 349 |
+
"grad_norm": 0.36578992009162903,
|
| 350 |
+
"learning_rate": 0.00018856923435837022,
|
| 351 |
+
"loss": 0.0327,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.01297016861219196,
|
| 356 |
+
"grad_norm": 0.32976096868515015,
|
| 357 |
+
"learning_rate": 0.0001879473751206489,
|
| 358 |
+
"loss": 0.04,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.013229571984435798,
|
| 363 |
+
"grad_norm": 0.4037308990955353,
|
| 364 |
+
"learning_rate": 0.00018731012763882133,
|
| 365 |
+
"loss": 0.0365,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.013488975356679637,
|
| 370 |
+
"grad_norm": 0.3599701225757599,
|
| 371 |
+
"learning_rate": 0.00018665760341274505,
|
| 372 |
+
"loss": 0.0337,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.013748378728923476,
|
| 377 |
+
"grad_norm": 0.6167535185813904,
|
| 378 |
+
"learning_rate": 0.00018598991661526572,
|
| 379 |
+
"loss": 0.0384,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.014007782101167316,
|
| 384 |
+
"grad_norm": 0.44012153148651123,
|
| 385 |
+
"learning_rate": 0.00018530718407223974,
|
| 386 |
+
"loss": 0.0291,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.014267185473411154,
|
| 391 |
+
"grad_norm": 0.5593993663787842,
|
| 392 |
+
"learning_rate": 0.00018460952524209355,
|
| 393 |
+
"loss": 0.0328,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.014526588845654994,
|
| 398 |
+
"grad_norm": 0.3970232307910919,
|
| 399 |
+
"learning_rate": 0.00018389706219492147,
|
| 400 |
+
"loss": 0.0282,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.014785992217898832,
|
| 405 |
+
"grad_norm": 0.2354394942522049,
|
| 406 |
+
"learning_rate": 0.00018316991959112716,
|
| 407 |
+
"loss": 0.0317,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.015045395590142672,
|
| 412 |
+
"grad_norm": 0.35121485590934753,
|
| 413 |
+
"learning_rate": 0.00018242822465961176,
|
| 414 |
+
"loss": 0.0328,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.01530479896238651,
|
| 419 |
+
"grad_norm": 0.4026910066604614,
|
| 420 |
+
"learning_rate": 0.00018167210717551224,
|
| 421 |
+
"loss": 0.0346,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.01556420233463035,
|
| 426 |
+
"grad_norm": 0.36058488488197327,
|
| 427 |
+
"learning_rate": 0.00018090169943749476,
|
| 428 |
+
"loss": 0.0356,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.01582360570687419,
|
| 433 |
+
"grad_norm": 0.43329063057899475,
|
| 434 |
+
"learning_rate": 0.00018011713624460608,
|
| 435 |
+
"loss": 0.039,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.016083009079118027,
|
| 440 |
+
"grad_norm": 0.5267623662948608,
|
| 441 |
+
"learning_rate": 0.00017931855487268782,
|
| 442 |
+
"loss": 0.034,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.01634241245136187,
|
| 447 |
+
"grad_norm": 0.4230927526950836,
|
| 448 |
+
"learning_rate": 0.0001785060950503568,
|
| 449 |
+
"loss": 0.031,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.016601815823605707,
|
| 454 |
+
"grad_norm": 0.3721458613872528,
|
| 455 |
+
"learning_rate": 0.00017767989893455698,
|
| 456 |
+
"loss": 0.0306,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.016861219195849545,
|
| 461 |
+
"grad_norm": 0.4158923029899597,
|
| 462 |
+
"learning_rate": 0.00017684011108568592,
|
| 463 |
+
"loss": 0.0343,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.017120622568093387,
|
| 468 |
+
"grad_norm": 0.42805808782577515,
|
| 469 |
+
"learning_rate": 0.00017598687844230088,
|
| 470 |
+
"loss": 0.0348,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.017380025940337225,
|
| 475 |
+
"grad_norm": 0.2532889246940613,
|
| 476 |
+
"learning_rate": 0.00017512035029540885,
|
| 477 |
+
"loss": 0.0348,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.017639429312581063,
|
| 482 |
+
"grad_norm": 0.33485907316207886,
|
| 483 |
+
"learning_rate": 0.000174240678262345,
|
| 484 |
+
"loss": 0.0382,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.0178988326848249,
|
| 489 |
+
"grad_norm": 0.33811262249946594,
|
| 490 |
+
"learning_rate": 0.000173348016260244,
|
| 491 |
+
"loss": 0.0321,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.018158236057068743,
|
| 496 |
+
"grad_norm": 0.5319349765777588,
|
| 497 |
+
"learning_rate": 0.00017244252047910892,
|
| 498 |
+
"loss": 0.0369,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.01841763942931258,
|
| 503 |
+
"grad_norm": 0.1967012882232666,
|
| 504 |
+
"learning_rate": 0.00017152434935448256,
|
| 505 |
+
"loss": 0.0392,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.01867704280155642,
|
| 510 |
+
"grad_norm": 0.491212397813797,
|
| 511 |
+
"learning_rate": 0.0001705936635397259,
|
| 512 |
+
"loss": 0.034,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.018936446173800258,
|
| 517 |
+
"grad_norm": 0.3200204074382782,
|
| 518 |
+
"learning_rate": 0.00016965062587790823,
|
| 519 |
+
"loss": 0.0349,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.0191958495460441,
|
| 524 |
+
"grad_norm": 0.29090484976768494,
|
| 525 |
+
"learning_rate": 0.00016869540137331445,
|
| 526 |
+
"loss": 0.0302,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.019455252918287938,
|
| 531 |
+
"grad_norm": 0.4633236825466156,
|
| 532 |
+
"learning_rate": 0.00016772815716257412,
|
| 533 |
+
"loss": 0.0305,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.019714656290531776,
|
| 538 |
+
"grad_norm": 0.6030534505844116,
|
| 539 |
+
"learning_rate": 0.00016674906248541726,
|
| 540 |
+
"loss": 0.0331,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.019974059662775615,
|
| 545 |
+
"grad_norm": 0.28692400455474854,
|
| 546 |
+
"learning_rate": 0.00016575828865506245,
|
| 547 |
+
"loss": 0.0319,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.020233463035019456,
|
| 552 |
+
"grad_norm": 0.3799605667591095,
|
| 553 |
+
"learning_rate": 0.0001647560090282419,
|
| 554 |
+
"loss": 0.0316,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.020492866407263294,
|
| 559 |
+
"grad_norm": 0.529679536819458,
|
| 560 |
+
"learning_rate": 0.000163742398974869,
|
| 561 |
+
"loss": 0.0317,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.020752269779507133,
|
| 566 |
+
"grad_norm": 0.328056275844574,
|
| 567 |
+
"learning_rate": 0.0001627176358473537,
|
| 568 |
+
"loss": 0.0332,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.021011673151750974,
|
| 573 |
+
"grad_norm": 0.3303374648094177,
|
| 574 |
+
"learning_rate": 0.0001616818989495711,
|
| 575 |
+
"loss": 0.0323,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.021271076523994813,
|
| 580 |
+
"grad_norm": 0.23507635295391083,
|
| 581 |
+
"learning_rate": 0.00016063536950548826,
|
| 582 |
+
"loss": 0.0338,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.02153047989623865,
|
| 587 |
+
"grad_norm": 0.3870477080345154,
|
| 588 |
+
"learning_rate": 0.0001595782306274553,
|
| 589 |
+
"loss": 0.0326,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.02178988326848249,
|
| 594 |
+
"grad_norm": 0.37890198826789856,
|
| 595 |
+
"learning_rate": 0.00015851066728416618,
|
| 596 |
+
"loss": 0.0309,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.02204928664072633,
|
| 601 |
+
"grad_norm": 0.48460447788238525,
|
| 602 |
+
"learning_rate": 0.00015743286626829437,
|
| 603 |
+
"loss": 0.0351,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.02230869001297017,
|
| 608 |
+
"grad_norm": 0.38216733932495117,
|
| 609 |
+
"learning_rate": 0.00015634501616380967,
|
| 610 |
+
"loss": 0.0331,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.022568093385214007,
|
| 615 |
+
"grad_norm": 0.31668373942375183,
|
| 616 |
+
"learning_rate": 0.00015524730731298134,
|
| 617 |
+
"loss": 0.0306,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.022827496757457846,
|
| 622 |
+
"grad_norm": 0.5256275534629822,
|
| 623 |
+
"learning_rate": 0.0001541399317830738,
|
| 624 |
+
"loss": 0.0307,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.023086900129701687,
|
| 629 |
+
"grad_norm": 0.2295175939798355,
|
| 630 |
+
"learning_rate": 0.0001530230833327405,
|
| 631 |
+
"loss": 0.0297,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.023346303501945526,
|
| 636 |
+
"grad_norm": 0.35704338550567627,
|
| 637 |
+
"learning_rate": 0.00015189695737812152,
|
| 638 |
+
"loss": 0.0358,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.023605706874189364,
|
| 643 |
+
"grad_norm": 0.31458932161331177,
|
| 644 |
+
"learning_rate": 0.0001507617509586517,
|
| 645 |
+
"loss": 0.0278,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.023865110246433202,
|
| 650 |
+
"grad_norm": 0.47554951906204224,
|
| 651 |
+
"learning_rate": 0.00014961766270258422,
|
| 652 |
+
"loss": 0.0332,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.024124513618677044,
|
| 657 |
+
"grad_norm": 0.29959654808044434,
|
| 658 |
+
"learning_rate": 0.00014846489279223652,
|
| 659 |
+
"loss": 0.0268,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.024383916990920882,
|
| 664 |
+
"grad_norm": 0.31856444478034973,
|
| 665 |
+
"learning_rate": 0.0001473036429289641,
|
| 666 |
+
"loss": 0.028,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.02464332036316472,
|
| 671 |
+
"grad_norm": 0.23568253219127655,
|
| 672 |
+
"learning_rate": 0.0001461341162978688,
|
| 673 |
+
"loss": 0.0339,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.024902723735408562,
|
| 678 |
+
"grad_norm": 0.4032520055770874,
|
| 679 |
+
"learning_rate": 0.00014495651753224705,
|
| 680 |
+
"loss": 0.0291,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.0251621271076524,
|
| 685 |
+
"grad_norm": 0.36155375838279724,
|
| 686 |
+
"learning_rate": 0.00014377105267778518,
|
| 687 |
+
"loss": 0.0261,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.02542153047989624,
|
| 692 |
+
"grad_norm": 0.2985226511955261,
|
| 693 |
+
"learning_rate": 0.00014257792915650728,
|
| 694 |
+
"loss": 0.03,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.025680933852140077,
|
| 699 |
+
"grad_norm": 0.3420771658420563,
|
| 700 |
+
"learning_rate": 0.00014137735573048233,
|
| 701 |
+
"loss": 0.0318,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.02594033722438392,
|
| 706 |
+
"grad_norm": 0.19557547569274902,
|
| 707 |
+
"learning_rate": 0.00014016954246529696,
|
| 708 |
+
"loss": 0.0287,
|
| 709 |
+
"step": 1000
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 10,
|
| 713 |
+
"max_steps": 2500,
|
| 714 |
+
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 1,
|
| 716 |
+
"save_steps": 500,
|
| 717 |
+
"stateful_callbacks": {
|
| 718 |
+
"TrainerControl": {
|
| 719 |
+
"args": {
|
| 720 |
+
"should_epoch_stop": false,
|
| 721 |
+
"should_evaluate": false,
|
| 722 |
+
"should_log": false,
|
| 723 |
+
"should_save": true,
|
| 724 |
+
"should_training_stop": false
|
| 725 |
+
},
|
| 726 |
+
"attributes": {}
|
| 727 |
+
}
|
| 728 |
+
},
|
| 729 |
+
"total_flos": 1.31459956342784e+17,
|
| 730 |
+
"train_batch_size": 32,
|
| 731 |
+
"trial_name": null,
|
| 732 |
+
"trial_params": null
|
| 733 |
+
}
|
checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/adleboy/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
|
| 3 |
+
"action_dim": 32,
|
| 4 |
+
"action_head_cfg": {
|
| 5 |
+
"action_dim": 32,
|
| 6 |
+
"action_horizon": 16,
|
| 7 |
+
"add_pos_embed": true,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"dropout": 0.2,
|
| 11 |
+
"final_dropout": true,
|
| 12 |
+
"interleave_self_attention": true,
|
| 13 |
+
"norm_type": "ada_norm",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_layers": 16,
|
| 16 |
+
"output_dim": 1024,
|
| 17 |
+
"positional_embeddings": null
|
| 18 |
+
},
|
| 19 |
+
"freeze_decode_layer": false,
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"load_pretrained_det_decode_layer_path": null,
|
| 23 |
+
"max_action_dim": 32,
|
| 24 |
+
"max_state_dim": 64,
|
| 25 |
+
"model_dtype": "float32",
|
| 26 |
+
"noise_beta_alpha": 1.5,
|
| 27 |
+
"noise_beta_beta": 1.0,
|
| 28 |
+
"noise_s": 0.999,
|
| 29 |
+
"num_inference_timesteps": 16,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true
|
| 33 |
+
},
|
| 34 |
+
"action_horizon": 16,
|
| 35 |
+
"architectures": [
|
| 36 |
+
"GR00T_N1"
|
| 37 |
+
],
|
| 38 |
+
"attn_implementation": null,
|
| 39 |
+
"backbone_cfg": {
|
| 40 |
+
"allow_reshape_visual": true,
|
| 41 |
+
"load_pretrained_det_eagle_path": null,
|
| 42 |
+
"model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 43 |
+
"processor_cfg": {
|
| 44 |
+
"max_input_tiles": 1,
|
| 45 |
+
"model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 46 |
+
"model_spec": {
|
| 47 |
+
"num_image_token": 64,
|
| 48 |
+
"template": "qwen2-chat"
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"projector_dim": 2048,
|
| 52 |
+
"remove_llm": false,
|
| 53 |
+
"reproject_vision": false,
|
| 54 |
+
"scale_image_resolution": 1,
|
| 55 |
+
"select_layer": 12,
|
| 56 |
+
"tune_llm": false,
|
| 57 |
+
"tune_visual": true
|
| 58 |
+
},
|
| 59 |
+
"compute_dtype": "bfloat16",
|
| 60 |
+
"hidden_size": 1536,
|
| 61 |
+
"model_dtype": "float32",
|
| 62 |
+
"model_type": "gr00t_n1",
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.45.2"
|
| 65 |
+
}
|
checkpoint-1500/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"single_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
122.080078125,
|
| 8 |
+
198.193359375,
|
| 9 |
+
182.28515625,
|
| 10 |
+
114.43359375,
|
| 11 |
+
262.177734375
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-95.9765625,
|
| 15 |
+
-179.912109375,
|
| 16 |
+
-258.486328125,
|
| 17 |
+
-100.01953125,
|
| 18 |
+
-179.912109375
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
9.608419418334961,
|
| 22 |
+
114.65914154052734,
|
| 23 |
+
102.69532775878906,
|
| 24 |
+
63.54849624633789,
|
| 25 |
+
-3.96468186378479
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
30.130109786987305,
|
| 29 |
+
52.885677337646484,
|
| 30 |
+
68.62229919433594,
|
| 31 |
+
26.573131561279297,
|
| 32 |
+
62.51667785644531
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-55.1953125,
|
| 36 |
+
12.196582031250038,
|
| 37 |
+
-228.779296875,
|
| 38 |
+
-40.78125,
|
| 39 |
+
-152.40234375
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
87.626953125,
|
| 43 |
+
192.041015625,
|
| 44 |
+
179.47265625,
|
| 45 |
+
108.28125,
|
| 46 |
+
155.0390625
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
105.29850769042969
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
-2.7297544479370117
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
11.653524398803711
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
17.93401336669922
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
-1.4121800661087036
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
93.88059997558594
|
| 67 |
+
]
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"action": {
|
| 71 |
+
"single_arm": {
|
| 72 |
+
"max": [
|
| 73 |
+
123.046875,
|
| 74 |
+
202.763671875,
|
| 75 |
+
190.458984375,
|
| 76 |
+
117.0703125,
|
| 77 |
+
267.802734375
|
| 78 |
+
],
|
| 79 |
+
"min": [
|
| 80 |
+
-97.646484375,
|
| 81 |
+
-179.912109375,
|
| 82 |
+
-269.6484375,
|
| 83 |
+
-102.65625,
|
| 84 |
+
-270.0
|
| 85 |
+
],
|
| 86 |
+
"mean": [
|
| 87 |
+
9.716768264770508,
|
| 88 |
+
117.07723999023438,
|
| 89 |
+
101.3852767944336,
|
| 90 |
+
63.94012451171875,
|
| 91 |
+
-4.292983531951904
|
| 92 |
+
],
|
| 93 |
+
"std": [
|
| 94 |
+
30.517000198364258,
|
| 95 |
+
52.163082122802734,
|
| 96 |
+
69.69375610351562,
|
| 97 |
+
26.988319396972656,
|
| 98 |
+
63.348819732666016
|
| 99 |
+
],
|
| 100 |
+
"q01": [
|
| 101 |
+
-55.8984375,
|
| 102 |
+
16.435546875,
|
| 103 |
+
-230.888671875,
|
| 104 |
+
-41.66015625,
|
| 105 |
+
-153.896484375
|
| 106 |
+
],
|
| 107 |
+
"q99": [
|
| 108 |
+
88.505859375,
|
| 109 |
+
195.64453125,
|
| 110 |
+
182.900390625,
|
| 111 |
+
109.599609375,
|
| 112 |
+
155.7421875
|
| 113 |
+
]
|
| 114 |
+
},
|
| 115 |
+
"gripper": {
|
| 116 |
+
"max": [
|
| 117 |
+
109.84339904785156
|
| 118 |
+
],
|
| 119 |
+
"min": [
|
| 120 |
+
-7.955596446990967
|
| 121 |
+
],
|
| 122 |
+
"mean": [
|
| 123 |
+
9.987146377563477
|
| 124 |
+
],
|
| 125 |
+
"std": [
|
| 126 |
+
18.02056121826172
|
| 127 |
+
],
|
| 128 |
+
"q01": [
|
| 129 |
+
-2.5742573738098145
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
96.20721435546875
|
| 133 |
+
]
|
| 134 |
+
}
|
| 135 |
+
}
|
| 136 |
+
},
|
| 137 |
+
"modalities": {
|
| 138 |
+
"video": {
|
| 139 |
+
"images0": {
|
| 140 |
+
"resolution": [
|
| 141 |
+
320,
|
| 142 |
+
240
|
| 143 |
+
],
|
| 144 |
+
"channels": 3,
|
| 145 |
+
"fps": 30.0
|
| 146 |
+
},
|
| 147 |
+
"images1": {
|
| 148 |
+
"resolution": [
|
| 149 |
+
320,
|
| 150 |
+
240
|
| 151 |
+
],
|
| 152 |
+
"channels": 3,
|
| 153 |
+
"fps": 30.0
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"state": {
|
| 157 |
+
"single_arm": {
|
| 158 |
+
"absolute": true,
|
| 159 |
+
"rotation_type": null,
|
| 160 |
+
"shape": [
|
| 161 |
+
5
|
| 162 |
+
],
|
| 163 |
+
"continuous": true
|
| 164 |
+
},
|
| 165 |
+
"gripper": {
|
| 166 |
+
"absolute": true,
|
| 167 |
+
"rotation_type": null,
|
| 168 |
+
"shape": [
|
| 169 |
+
1
|
| 170 |
+
],
|
| 171 |
+
"continuous": true
|
| 172 |
+
}
|
| 173 |
+
},
|
| 174 |
+
"action": {
|
| 175 |
+
"single_arm": {
|
| 176 |
+
"absolute": true,
|
| 177 |
+
"rotation_type": null,
|
| 178 |
+
"shape": [
|
| 179 |
+
5
|
| 180 |
+
],
|
| 181 |
+
"continuous": true
|
| 182 |
+
},
|
| 183 |
+
"gripper": {
|
| 184 |
+
"absolute": true,
|
| 185 |
+
"rotation_type": null,
|
| 186 |
+
"shape": [
|
| 187 |
+
1
|
| 188 |
+
],
|
| 189 |
+
"continuous": true
|
| 190 |
+
}
|
| 191 |
+
}
|
| 192 |
+
},
|
| 193 |
+
"embodiment_tag": "new_embodiment"
|
| 194 |
+
}
|
| 195 |
+
}
|
checkpoint-1500/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1397525a66ef415d8def2bb14ab73cae8dd535a68e1848b18634aa7c69467975
|
| 3 |
+
size 4938446392
|
checkpoint-1500/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09614aee91e64863cd45defd728f78ebed3f1f62352e1142cad35a29b8b8eb61
|
| 3 |
+
size 3821736024
|
checkpoint-1500/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,809 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8760067008
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 7 |
+
"action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 8 |
+
"action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 9 |
+
"action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 10 |
+
"action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
|
| 11 |
+
"action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
|
| 12 |
+
"action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
|
| 13 |
+
"action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
|
| 14 |
+
"action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
|
| 15 |
+
"action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
|
| 16 |
+
"action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
|
| 17 |
+
"action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
|
| 18 |
+
"action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
|
| 19 |
+
"action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
|
| 20 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
|
| 21 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
|
| 23 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 25 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 26 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 27 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 29 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 30 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 31 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 32 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 33 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 35 |
+
"action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 37 |
+
"action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 38 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 39 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 41 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 43 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 44 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 45 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 46 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 47 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 49 |
+
"action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 50 |
+
"action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 51 |
+
"action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 53 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 56 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 57 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 59 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 60 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 61 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 63 |
+
"action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 65 |
+
"action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 66 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 67 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 68 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 69 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 70 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 71 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 73 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 74 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 75 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 77 |
+
"action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 78 |
+
"action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 79 |
+
"action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 81 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 83 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 85 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 87 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 89 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 92 |
+
"action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 93 |
+
"action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 95 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 97 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 99 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 101 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 103 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 105 |
+
"action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 107 |
+
"action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 109 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 111 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 113 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 115 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 117 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 119 |
+
"action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 121 |
+
"action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 123 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 125 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 127 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 129 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 131 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 133 |
+
"action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 135 |
+
"action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 137 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 139 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 141 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 143 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 145 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 147 |
+
"action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 149 |
+
"action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 151 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 153 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 155 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 157 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 159 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 161 |
+
"action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 165 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 167 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 171 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 177 |
+
"action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 179 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 189 |
+
"action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 191 |
+
"action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 195 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 201 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 203 |
+
"action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 215 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 219 |
+
"action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 225 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 227 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 237 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 239 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 243 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 250 |
+
"action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 251 |
+
"action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 252 |
+
"action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 253 |
+
"backbone.linear.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"backbone.linear.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
|
| 370 |
+
"backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 381 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 655 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 715 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 727 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 739 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 751 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 763 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 775 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 787 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 799 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
| 808 |
+
}
|
| 809 |
+
}
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5748c215a9c8c84b5ff7b42708d7b7ee8bc630d150192b5c707bf65e2990d021
|
| 3 |
+
size 10272357262
|
checkpoint-1500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79e249d1e72cb537e95d6506baa441d40a882b319ca87e7dcb5fb7b903e2a5f0
|
| 3 |
+
size 14512
|
checkpoint-1500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81a9bd3f413534ca67105fa1b45ac1036e7c399311bb36f6d06fca6748a85f0f
|
| 3 |
+
size 14512
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0bb08a0db4bac92f9cdc7e6c25e1dfd08f5d7f8b07c15a5b485886972a88e72
|
| 3 |
+
size 1064
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.038910505836575876,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00025940337224383917,
|
| 13 |
+
"grad_norm": 13.49365234375,
|
| 14 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 15 |
+
"loss": 1.5584,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0005188067444876783,
|
| 20 |
+
"grad_norm": 2.6006040573120117,
|
| 21 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 22 |
+
"loss": 0.7111,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0007782101167315176,
|
| 27 |
+
"grad_norm": 4.435553073883057,
|
| 28 |
+
"learning_rate": 4.8e-05,
|
| 29 |
+
"loss": 0.3076,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0010376134889753567,
|
| 34 |
+
"grad_norm": 1.1146177053451538,
|
| 35 |
+
"learning_rate": 6.400000000000001e-05,
|
| 36 |
+
"loss": 0.1826,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0012970168612191958,
|
| 41 |
+
"grad_norm": 0.8707008957862854,
|
| 42 |
+
"learning_rate": 8e-05,
|
| 43 |
+
"loss": 0.1341,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0015564202334630351,
|
| 48 |
+
"grad_norm": 1.7411352396011353,
|
| 49 |
+
"learning_rate": 9.6e-05,
|
| 50 |
+
"loss": 0.1144,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0018158236057068742,
|
| 55 |
+
"grad_norm": 0.9691908955574036,
|
| 56 |
+
"learning_rate": 0.00011200000000000001,
|
| 57 |
+
"loss": 0.0831,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0020752269779507134,
|
| 62 |
+
"grad_norm": 1.0398532152175903,
|
| 63 |
+
"learning_rate": 0.00012800000000000002,
|
| 64 |
+
"loss": 0.0801,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0023346303501945525,
|
| 69 |
+
"grad_norm": 0.5252112746238708,
|
| 70 |
+
"learning_rate": 0.000144,
|
| 71 |
+
"loss": 0.081,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0025940337224383916,
|
| 76 |
+
"grad_norm": 0.6552278995513916,
|
| 77 |
+
"learning_rate": 0.00016,
|
| 78 |
+
"loss": 0.0821,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0028534370946822307,
|
| 83 |
+
"grad_norm": 0.6302046775817871,
|
| 84 |
+
"learning_rate": 0.00017600000000000002,
|
| 85 |
+
"loss": 0.0749,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0031128404669260703,
|
| 90 |
+
"grad_norm": 0.7439587712287903,
|
| 91 |
+
"learning_rate": 0.000192,
|
| 92 |
+
"loss": 0.0647,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0033722438391699094,
|
| 97 |
+
"grad_norm": 6.8584771156311035,
|
| 98 |
+
"learning_rate": 0.0001999978128380225,
|
| 99 |
+
"loss": 0.0726,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0036316472114137485,
|
| 104 |
+
"grad_norm": 2.014613389968872,
|
| 105 |
+
"learning_rate": 0.0001999803161162393,
|
| 106 |
+
"loss": 0.0936,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0038910505836575876,
|
| 111 |
+
"grad_norm": 1.3758050203323364,
|
| 112 |
+
"learning_rate": 0.00019994532573409262,
|
| 113 |
+
"loss": 0.1089,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004150453955901427,
|
| 118 |
+
"grad_norm": 1.3027769327163696,
|
| 119 |
+
"learning_rate": 0.00019989284781388617,
|
| 120 |
+
"loss": 0.0772,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.004409857328145266,
|
| 125 |
+
"grad_norm": 1.021938443183899,
|
| 126 |
+
"learning_rate": 0.00019982289153773646,
|
| 127 |
+
"loss": 0.0695,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.004669260700389105,
|
| 132 |
+
"grad_norm": 0.8069638609886169,
|
| 133 |
+
"learning_rate": 0.00019973546914596623,
|
| 134 |
+
"loss": 0.0624,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.004928664072632944,
|
| 139 |
+
"grad_norm": 0.5198134779930115,
|
| 140 |
+
"learning_rate": 0.00019963059593496268,
|
| 141 |
+
"loss": 0.0481,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.005188067444876783,
|
| 146 |
+
"grad_norm": 0.39965012669563293,
|
| 147 |
+
"learning_rate": 0.00019950829025450114,
|
| 148 |
+
"loss": 0.0493,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005447470817120622,
|
| 153 |
+
"grad_norm": 0.8152652978897095,
|
| 154 |
+
"learning_rate": 0.0001993685735045343,
|
| 155 |
+
"loss": 0.0477,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.005706874189364461,
|
| 160 |
+
"grad_norm": 0.7083427309989929,
|
| 161 |
+
"learning_rate": 0.0001992114701314478,
|
| 162 |
+
"loss": 0.0501,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0059662775616083005,
|
| 167 |
+
"grad_norm": 0.690096914768219,
|
| 168 |
+
"learning_rate": 0.000199037007623783,
|
| 169 |
+
"loss": 0.0509,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0062256809338521405,
|
| 174 |
+
"grad_norm": 0.871699869632721,
|
| 175 |
+
"learning_rate": 0.00019884521650742715,
|
| 176 |
+
"loss": 0.0464,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.00648508430609598,
|
| 181 |
+
"grad_norm": 0.6445639133453369,
|
| 182 |
+
"learning_rate": 0.00019863613034027224,
|
| 183 |
+
"loss": 0.0462,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.006744487678339819,
|
| 188 |
+
"grad_norm": 0.4920782148838043,
|
| 189 |
+
"learning_rate": 0.0001984097857063434,
|
| 190 |
+
"loss": 0.0425,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.007003891050583658,
|
| 195 |
+
"grad_norm": 0.8624788522720337,
|
| 196 |
+
"learning_rate": 0.0001981662222093976,
|
| 197 |
+
"loss": 0.0471,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007263294422827497,
|
| 202 |
+
"grad_norm": 0.5704030990600586,
|
| 203 |
+
"learning_rate": 0.00019790548246599447,
|
| 204 |
+
"loss": 0.0571,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.007522697795071336,
|
| 209 |
+
"grad_norm": 0.569247841835022,
|
| 210 |
+
"learning_rate": 0.00019762761209803927,
|
| 211 |
+
"loss": 0.0531,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.007782101167315175,
|
| 216 |
+
"grad_norm": 0.7414583563804626,
|
| 217 |
+
"learning_rate": 0.0001973326597248006,
|
| 218 |
+
"loss": 0.0455,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008041504539559013,
|
| 223 |
+
"grad_norm": 0.42905348539352417,
|
| 224 |
+
"learning_rate": 0.00019702067695440332,
|
| 225 |
+
"loss": 0.0542,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008300907911802853,
|
| 230 |
+
"grad_norm": 0.6132651567459106,
|
| 231 |
+
"learning_rate": 0.00019669171837479873,
|
| 232 |
+
"loss": 0.0439,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.008560311284046693,
|
| 237 |
+
"grad_norm": 0.44733384251594543,
|
| 238 |
+
"learning_rate": 0.00019634584154421317,
|
| 239 |
+
"loss": 0.0429,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.008819714656290532,
|
| 244 |
+
"grad_norm": 0.516659677028656,
|
| 245 |
+
"learning_rate": 0.00019598310698107702,
|
| 246 |
+
"loss": 0.0407,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.009079118028534372,
|
| 251 |
+
"grad_norm": 0.2340136468410492,
|
| 252 |
+
"learning_rate": 0.00019560357815343577,
|
| 253 |
+
"loss": 0.036,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.00933852140077821,
|
| 258 |
+
"grad_norm": 0.6629723906517029,
|
| 259 |
+
"learning_rate": 0.00019520732146784491,
|
| 260 |
+
"loss": 0.041,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.00959792477302205,
|
| 265 |
+
"grad_norm": 0.3777199387550354,
|
| 266 |
+
"learning_rate": 0.0001947944062577507,
|
| 267 |
+
"loss": 0.0414,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.009857328145265888,
|
| 272 |
+
"grad_norm": 0.44298338890075684,
|
| 273 |
+
"learning_rate": 0.00019436490477135878,
|
| 274 |
+
"loss": 0.0371,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.010116731517509728,
|
| 279 |
+
"grad_norm": 0.4530090093612671,
|
| 280 |
+
"learning_rate": 0.00019391889215899299,
|
| 281 |
+
"loss": 0.037,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.010376134889753566,
|
| 286 |
+
"grad_norm": 0.36142367124557495,
|
| 287 |
+
"learning_rate": 0.0001934564464599461,
|
| 288 |
+
"loss": 0.0387,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.010635538261997406,
|
| 293 |
+
"grad_norm": 0.36559927463531494,
|
| 294 |
+
"learning_rate": 0.00019297764858882514,
|
| 295 |
+
"loss": 0.0386,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.010894941634241245,
|
| 300 |
+
"grad_norm": 0.47660204768180847,
|
| 301 |
+
"learning_rate": 0.00019248258232139388,
|
| 302 |
+
"loss": 0.0316,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.011154345006485085,
|
| 307 |
+
"grad_norm": 0.2614981234073639,
|
| 308 |
+
"learning_rate": 0.00019197133427991436,
|
| 309 |
+
"loss": 0.0417,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011413748378728923,
|
| 314 |
+
"grad_norm": 0.44811561703681946,
|
| 315 |
+
"learning_rate": 0.00019144399391799043,
|
| 316 |
+
"loss": 0.036,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.011673151750972763,
|
| 321 |
+
"grad_norm": 0.4213508367538452,
|
| 322 |
+
"learning_rate": 0.00019090065350491626,
|
| 323 |
+
"loss": 0.0399,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.011932555123216601,
|
| 328 |
+
"grad_norm": 0.29146406054496765,
|
| 329 |
+
"learning_rate": 0.0001903414081095315,
|
| 330 |
+
"loss": 0.0376,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.012191958495460441,
|
| 335 |
+
"grad_norm": 0.2714293897151947,
|
| 336 |
+
"learning_rate": 0.00018976635558358722,
|
| 337 |
+
"loss": 0.0362,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012451361867704281,
|
| 342 |
+
"grad_norm": 0.3767367899417877,
|
| 343 |
+
"learning_rate": 0.00018917559654462474,
|
| 344 |
+
"loss": 0.0364,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01271076523994812,
|
| 349 |
+
"grad_norm": 0.36578992009162903,
|
| 350 |
+
"learning_rate": 0.00018856923435837022,
|
| 351 |
+
"loss": 0.0327,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.01297016861219196,
|
| 356 |
+
"grad_norm": 0.32976096868515015,
|
| 357 |
+
"learning_rate": 0.0001879473751206489,
|
| 358 |
+
"loss": 0.04,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.013229571984435798,
|
| 363 |
+
"grad_norm": 0.4037308990955353,
|
| 364 |
+
"learning_rate": 0.00018731012763882133,
|
| 365 |
+
"loss": 0.0365,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.013488975356679637,
|
| 370 |
+
"grad_norm": 0.3599701225757599,
|
| 371 |
+
"learning_rate": 0.00018665760341274505,
|
| 372 |
+
"loss": 0.0337,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.013748378728923476,
|
| 377 |
+
"grad_norm": 0.6167535185813904,
|
| 378 |
+
"learning_rate": 0.00018598991661526572,
|
| 379 |
+
"loss": 0.0384,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.014007782101167316,
|
| 384 |
+
"grad_norm": 0.44012153148651123,
|
| 385 |
+
"learning_rate": 0.00018530718407223974,
|
| 386 |
+
"loss": 0.0291,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.014267185473411154,
|
| 391 |
+
"grad_norm": 0.5593993663787842,
|
| 392 |
+
"learning_rate": 0.00018460952524209355,
|
| 393 |
+
"loss": 0.0328,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.014526588845654994,
|
| 398 |
+
"grad_norm": 0.3970232307910919,
|
| 399 |
+
"learning_rate": 0.00018389706219492147,
|
| 400 |
+
"loss": 0.0282,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.014785992217898832,
|
| 405 |
+
"grad_norm": 0.2354394942522049,
|
| 406 |
+
"learning_rate": 0.00018316991959112716,
|
| 407 |
+
"loss": 0.0317,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.015045395590142672,
|
| 412 |
+
"grad_norm": 0.35121485590934753,
|
| 413 |
+
"learning_rate": 0.00018242822465961176,
|
| 414 |
+
"loss": 0.0328,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.01530479896238651,
|
| 419 |
+
"grad_norm": 0.4026910066604614,
|
| 420 |
+
"learning_rate": 0.00018167210717551224,
|
| 421 |
+
"loss": 0.0346,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.01556420233463035,
|
| 426 |
+
"grad_norm": 0.36058488488197327,
|
| 427 |
+
"learning_rate": 0.00018090169943749476,
|
| 428 |
+
"loss": 0.0356,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.01582360570687419,
|
| 433 |
+
"grad_norm": 0.43329063057899475,
|
| 434 |
+
"learning_rate": 0.00018011713624460608,
|
| 435 |
+
"loss": 0.039,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.016083009079118027,
|
| 440 |
+
"grad_norm": 0.5267623662948608,
|
| 441 |
+
"learning_rate": 0.00017931855487268782,
|
| 442 |
+
"loss": 0.034,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.01634241245136187,
|
| 447 |
+
"grad_norm": 0.4230927526950836,
|
| 448 |
+
"learning_rate": 0.0001785060950503568,
|
| 449 |
+
"loss": 0.031,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.016601815823605707,
|
| 454 |
+
"grad_norm": 0.3721458613872528,
|
| 455 |
+
"learning_rate": 0.00017767989893455698,
|
| 456 |
+
"loss": 0.0306,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.016861219195849545,
|
| 461 |
+
"grad_norm": 0.4158923029899597,
|
| 462 |
+
"learning_rate": 0.00017684011108568592,
|
| 463 |
+
"loss": 0.0343,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.017120622568093387,
|
| 468 |
+
"grad_norm": 0.42805808782577515,
|
| 469 |
+
"learning_rate": 0.00017598687844230088,
|
| 470 |
+
"loss": 0.0348,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.017380025940337225,
|
| 475 |
+
"grad_norm": 0.2532889246940613,
|
| 476 |
+
"learning_rate": 0.00017512035029540885,
|
| 477 |
+
"loss": 0.0348,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.017639429312581063,
|
| 482 |
+
"grad_norm": 0.33485907316207886,
|
| 483 |
+
"learning_rate": 0.000174240678262345,
|
| 484 |
+
"loss": 0.0382,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.0178988326848249,
|
| 489 |
+
"grad_norm": 0.33811262249946594,
|
| 490 |
+
"learning_rate": 0.000173348016260244,
|
| 491 |
+
"loss": 0.0321,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.018158236057068743,
|
| 496 |
+
"grad_norm": 0.5319349765777588,
|
| 497 |
+
"learning_rate": 0.00017244252047910892,
|
| 498 |
+
"loss": 0.0369,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.01841763942931258,
|
| 503 |
+
"grad_norm": 0.1967012882232666,
|
| 504 |
+
"learning_rate": 0.00017152434935448256,
|
| 505 |
+
"loss": 0.0392,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.01867704280155642,
|
| 510 |
+
"grad_norm": 0.491212397813797,
|
| 511 |
+
"learning_rate": 0.0001705936635397259,
|
| 512 |
+
"loss": 0.034,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.018936446173800258,
|
| 517 |
+
"grad_norm": 0.3200204074382782,
|
| 518 |
+
"learning_rate": 0.00016965062587790823,
|
| 519 |
+
"loss": 0.0349,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.0191958495460441,
|
| 524 |
+
"grad_norm": 0.29090484976768494,
|
| 525 |
+
"learning_rate": 0.00016869540137331445,
|
| 526 |
+
"loss": 0.0302,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.019455252918287938,
|
| 531 |
+
"grad_norm": 0.4633236825466156,
|
| 532 |
+
"learning_rate": 0.00016772815716257412,
|
| 533 |
+
"loss": 0.0305,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.019714656290531776,
|
| 538 |
+
"grad_norm": 0.6030534505844116,
|
| 539 |
+
"learning_rate": 0.00016674906248541726,
|
| 540 |
+
"loss": 0.0331,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.019974059662775615,
|
| 545 |
+
"grad_norm": 0.28692400455474854,
|
| 546 |
+
"learning_rate": 0.00016575828865506245,
|
| 547 |
+
"loss": 0.0319,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.020233463035019456,
|
| 552 |
+
"grad_norm": 0.3799605667591095,
|
| 553 |
+
"learning_rate": 0.0001647560090282419,
|
| 554 |
+
"loss": 0.0316,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.020492866407263294,
|
| 559 |
+
"grad_norm": 0.529679536819458,
|
| 560 |
+
"learning_rate": 0.000163742398974869,
|
| 561 |
+
"loss": 0.0317,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.020752269779507133,
|
| 566 |
+
"grad_norm": 0.328056275844574,
|
| 567 |
+
"learning_rate": 0.0001627176358473537,
|
| 568 |
+
"loss": 0.0332,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.021011673151750974,
|
| 573 |
+
"grad_norm": 0.3303374648094177,
|
| 574 |
+
"learning_rate": 0.0001616818989495711,
|
| 575 |
+
"loss": 0.0323,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.021271076523994813,
|
| 580 |
+
"grad_norm": 0.23507635295391083,
|
| 581 |
+
"learning_rate": 0.00016063536950548826,
|
| 582 |
+
"loss": 0.0338,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.02153047989623865,
|
| 587 |
+
"grad_norm": 0.3870477080345154,
|
| 588 |
+
"learning_rate": 0.0001595782306274553,
|
| 589 |
+
"loss": 0.0326,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.02178988326848249,
|
| 594 |
+
"grad_norm": 0.37890198826789856,
|
| 595 |
+
"learning_rate": 0.00015851066728416618,
|
| 596 |
+
"loss": 0.0309,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.02204928664072633,
|
| 601 |
+
"grad_norm": 0.48460447788238525,
|
| 602 |
+
"learning_rate": 0.00015743286626829437,
|
| 603 |
+
"loss": 0.0351,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.02230869001297017,
|
| 608 |
+
"grad_norm": 0.38216733932495117,
|
| 609 |
+
"learning_rate": 0.00015634501616380967,
|
| 610 |
+
"loss": 0.0331,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.022568093385214007,
|
| 615 |
+
"grad_norm": 0.31668373942375183,
|
| 616 |
+
"learning_rate": 0.00015524730731298134,
|
| 617 |
+
"loss": 0.0306,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.022827496757457846,
|
| 622 |
+
"grad_norm": 0.5256275534629822,
|
| 623 |
+
"learning_rate": 0.0001541399317830738,
|
| 624 |
+
"loss": 0.0307,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.023086900129701687,
|
| 629 |
+
"grad_norm": 0.2295175939798355,
|
| 630 |
+
"learning_rate": 0.0001530230833327405,
|
| 631 |
+
"loss": 0.0297,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.023346303501945526,
|
| 636 |
+
"grad_norm": 0.35704338550567627,
|
| 637 |
+
"learning_rate": 0.00015189695737812152,
|
| 638 |
+
"loss": 0.0358,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.023605706874189364,
|
| 643 |
+
"grad_norm": 0.31458932161331177,
|
| 644 |
+
"learning_rate": 0.0001507617509586517,
|
| 645 |
+
"loss": 0.0278,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.023865110246433202,
|
| 650 |
+
"grad_norm": 0.47554951906204224,
|
| 651 |
+
"learning_rate": 0.00014961766270258422,
|
| 652 |
+
"loss": 0.0332,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.024124513618677044,
|
| 657 |
+
"grad_norm": 0.29959654808044434,
|
| 658 |
+
"learning_rate": 0.00014846489279223652,
|
| 659 |
+
"loss": 0.0268,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.024383916990920882,
|
| 664 |
+
"grad_norm": 0.31856444478034973,
|
| 665 |
+
"learning_rate": 0.0001473036429289641,
|
| 666 |
+
"loss": 0.028,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.02464332036316472,
|
| 671 |
+
"grad_norm": 0.23568253219127655,
|
| 672 |
+
"learning_rate": 0.0001461341162978688,
|
| 673 |
+
"loss": 0.0339,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.024902723735408562,
|
| 678 |
+
"grad_norm": 0.4032520055770874,
|
| 679 |
+
"learning_rate": 0.00014495651753224705,
|
| 680 |
+
"loss": 0.0291,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.0251621271076524,
|
| 685 |
+
"grad_norm": 0.36155375838279724,
|
| 686 |
+
"learning_rate": 0.00014377105267778518,
|
| 687 |
+
"loss": 0.0261,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.02542153047989624,
|
| 692 |
+
"grad_norm": 0.2985226511955261,
|
| 693 |
+
"learning_rate": 0.00014257792915650728,
|
| 694 |
+
"loss": 0.03,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.025680933852140077,
|
| 699 |
+
"grad_norm": 0.3420771658420563,
|
| 700 |
+
"learning_rate": 0.00014137735573048233,
|
| 701 |
+
"loss": 0.0318,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.02594033722438392,
|
| 706 |
+
"grad_norm": 0.19557547569274902,
|
| 707 |
+
"learning_rate": 0.00014016954246529696,
|
| 708 |
+
"loss": 0.0287,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.026199740596627757,
|
| 713 |
+
"grad_norm": 0.2249382734298706,
|
| 714 |
+
"learning_rate": 0.00013895470069330004,
|
| 715 |
+
"loss": 0.0258,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.026459143968871595,
|
| 720 |
+
"grad_norm": 0.5154671669006348,
|
| 721 |
+
"learning_rate": 0.00013773304297662559,
|
| 722 |
+
"loss": 0.0339,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.026718547341115433,
|
| 727 |
+
"grad_norm": 0.3469725251197815,
|
| 728 |
+
"learning_rate": 0.00013650478307000057,
|
| 729 |
+
"loss": 0.032,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.026977950713359275,
|
| 734 |
+
"grad_norm": 0.34428727626800537,
|
| 735 |
+
"learning_rate": 0.00013527013588334415,
|
| 736 |
+
"loss": 0.0317,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.027237354085603113,
|
| 741 |
+
"grad_norm": 0.2862760126590729,
|
| 742 |
+
"learning_rate": 0.00013402931744416433,
|
| 743 |
+
"loss": 0.03,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.02749675745784695,
|
| 748 |
+
"grad_norm": 0.5235270261764526,
|
| 749 |
+
"learning_rate": 0.00013278254485975976,
|
| 750 |
+
"loss": 0.0368,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.02775616083009079,
|
| 755 |
+
"grad_norm": 0.2167377918958664,
|
| 756 |
+
"learning_rate": 0.00013153003627923218,
|
| 757 |
+
"loss": 0.0306,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.02801556420233463,
|
| 762 |
+
"grad_norm": 0.29817643761634827,
|
| 763 |
+
"learning_rate": 0.00013027201085531634,
|
| 764 |
+
"loss": 0.0301,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.02827496757457847,
|
| 769 |
+
"grad_norm": 0.29515424370765686,
|
| 770 |
+
"learning_rate": 0.00012900868870603503,
|
| 771 |
+
"loss": 0.0249,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.028534370946822308,
|
| 776 |
+
"grad_norm": 0.3012550473213196,
|
| 777 |
+
"learning_rate": 0.00012774029087618446,
|
| 778 |
+
"loss": 0.0264,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.028793774319066146,
|
| 783 |
+
"grad_norm": 0.31644681096076965,
|
| 784 |
+
"learning_rate": 0.00012646703929865817,
|
| 785 |
+
"loss": 0.0316,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.029053177691309988,
|
| 790 |
+
"grad_norm": 0.37952420115470886,
|
| 791 |
+
"learning_rate": 0.00012518915675561483,
|
| 792 |
+
"loss": 0.0296,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.029312581063553826,
|
| 797 |
+
"grad_norm": 0.2594399154186249,
|
| 798 |
+
"learning_rate": 0.00012390686683949798,
|
| 799 |
+
"loss": 0.0321,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.029571984435797664,
|
| 804 |
+
"grad_norm": 0.34381750226020813,
|
| 805 |
+
"learning_rate": 0.00012262039391391404,
|
| 806 |
+
"loss": 0.0305,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.029831387808041506,
|
| 811 |
+
"grad_norm": 0.2528727948665619,
|
| 812 |
+
"learning_rate": 0.0001213299630743747,
|
| 813 |
+
"loss": 0.0303,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.030090791180285344,
|
| 818 |
+
"grad_norm": 0.32746660709381104,
|
| 819 |
+
"learning_rate": 0.00012003580010891213,
|
| 820 |
+
"loss": 0.0309,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.030350194552529183,
|
| 825 |
+
"grad_norm": 0.46516871452331543,
|
| 826 |
+
"learning_rate": 0.00011873813145857249,
|
| 827 |
+
"loss": 0.0288,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.03060959792477302,
|
| 832 |
+
"grad_norm": 0.21779906749725342,
|
| 833 |
+
"learning_rate": 0.00011743718417779517,
|
| 834 |
+
"loss": 0.0268,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.030869001297016863,
|
| 839 |
+
"grad_norm": 0.2870500087738037,
|
| 840 |
+
"learning_rate": 0.00011613318589468511,
|
| 841 |
+
"loss": 0.0284,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.0311284046692607,
|
| 846 |
+
"grad_norm": 0.223075732588768,
|
| 847 |
+
"learning_rate": 0.0001148263647711842,
|
| 848 |
+
"loss": 0.0283,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.03138780804150454,
|
| 853 |
+
"grad_norm": 0.3081727921962738,
|
| 854 |
+
"learning_rate": 0.0001135169494631497,
|
| 855 |
+
"loss": 0.0319,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.03164721141374838,
|
| 860 |
+
"grad_norm": 0.48067420721054077,
|
| 861 |
+
"learning_rate": 0.00011220516908034601,
|
| 862 |
+
"loss": 0.0286,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.031906614785992216,
|
| 867 |
+
"grad_norm": 0.34588056802749634,
|
| 868 |
+
"learning_rate": 0.00011089125314635726,
|
| 869 |
+
"loss": 0.0287,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.032166018158236054,
|
| 874 |
+
"grad_norm": 0.3428352475166321,
|
| 875 |
+
"learning_rate": 0.00010957543155842702,
|
| 876 |
+
"loss": 0.025,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.0324254215304799,
|
| 881 |
+
"grad_norm": 0.4223664700984955,
|
| 882 |
+
"learning_rate": 0.00010825793454723325,
|
| 883 |
+
"loss": 0.0304,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.03268482490272374,
|
| 888 |
+
"grad_norm": 0.21455545723438263,
|
| 889 |
+
"learning_rate": 0.00010693899263660441,
|
| 890 |
+
"loss": 0.0265,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.032944228274967575,
|
| 895 |
+
"grad_norm": 0.2936132252216339,
|
| 896 |
+
"learning_rate": 0.00010561883660318455,
|
| 897 |
+
"loss": 0.0298,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.033203631647211414,
|
| 902 |
+
"grad_norm": 0.3222610056400299,
|
| 903 |
+
"learning_rate": 0.00010429769743605407,
|
| 904 |
+
"loss": 0.0333,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.03346303501945525,
|
| 909 |
+
"grad_norm": 0.42949262261390686,
|
| 910 |
+
"learning_rate": 0.00010297580629631325,
|
| 911 |
+
"loss": 0.0336,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.03372243839169909,
|
| 916 |
+
"grad_norm": 0.3103349208831787,
|
| 917 |
+
"learning_rate": 0.00010165339447663587,
|
| 918 |
+
"loss": 0.0327,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.03398184176394293,
|
| 923 |
+
"grad_norm": 0.3449970483779907,
|
| 924 |
+
"learning_rate": 0.00010033069336079952,
|
| 925 |
+
"loss": 0.0293,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.034241245136186774,
|
| 930 |
+
"grad_norm": 0.3841015100479126,
|
| 931 |
+
"learning_rate": 9.900793438320037e-05,
|
| 932 |
+
"loss": 0.0305,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.03450064850843061,
|
| 937 |
+
"grad_norm": 0.3848475515842438,
|
| 938 |
+
"learning_rate": 9.768534898835862e-05,
|
| 939 |
+
"loss": 0.026,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.03476005188067445,
|
| 944 |
+
"grad_norm": 0.43429145216941833,
|
| 945 |
+
"learning_rate": 9.636316859042259e-05,
|
| 946 |
+
"loss": 0.0294,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.03501945525291829,
|
| 951 |
+
"grad_norm": 0.2181561291217804,
|
| 952 |
+
"learning_rate": 9.504162453267777e-05,
|
| 953 |
+
"loss": 0.0275,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.03527885862516213,
|
| 958 |
+
"grad_norm": 0.4230787754058838,
|
| 959 |
+
"learning_rate": 9.372094804706867e-05,
|
| 960 |
+
"loss": 0.0273,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.035538261997405965,
|
| 965 |
+
"grad_norm": 0.273333340883255,
|
| 966 |
+
"learning_rate": 9.24013702137397e-05,
|
| 967 |
+
"loss": 0.0246,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.0357976653696498,
|
| 972 |
+
"grad_norm": 0.21888947486877441,
|
| 973 |
+
"learning_rate": 9.108312192060298e-05,
|
| 974 |
+
"loss": 0.0223,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.03605706874189364,
|
| 979 |
+
"grad_norm": 0.22308865189552307,
|
| 980 |
+
"learning_rate": 8.97664338229395e-05,
|
| 981 |
+
"loss": 0.0249,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.03631647211413749,
|
| 986 |
+
"grad_norm": 0.2270708829164505,
|
| 987 |
+
"learning_rate": 8.845153630304139e-05,
|
| 988 |
+
"loss": 0.0272,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.036575875486381325,
|
| 993 |
+
"grad_norm": 0.3046322166919708,
|
| 994 |
+
"learning_rate": 8.713865942990141e-05,
|
| 995 |
+
"loss": 0.0225,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.03683527885862516,
|
| 1000 |
+
"grad_norm": 0.31552374362945557,
|
| 1001 |
+
"learning_rate": 8.582803291895758e-05,
|
| 1002 |
+
"loss": 0.0302,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.037094682230869,
|
| 1007 |
+
"grad_norm": 0.46200478076934814,
|
| 1008 |
+
"learning_rate": 8.451988609189987e-05,
|
| 1009 |
+
"loss": 0.0272,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.03735408560311284,
|
| 1014 |
+
"grad_norm": 0.22868406772613525,
|
| 1015 |
+
"learning_rate": 8.321444783654524e-05,
|
| 1016 |
+
"loss": 0.0267,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.03761348897535668,
|
| 1021 |
+
"grad_norm": 0.23030489683151245,
|
| 1022 |
+
"learning_rate": 8.191194656678904e-05,
|
| 1023 |
+
"loss": 0.0287,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.037872892347600516,
|
| 1028 |
+
"grad_norm": 0.19943729043006897,
|
| 1029 |
+
"learning_rate": 8.061261018263919e-05,
|
| 1030 |
+
"loss": 0.0249,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.03813229571984436,
|
| 1035 |
+
"grad_norm": 0.3236585557460785,
|
| 1036 |
+
"learning_rate": 7.931666603034033e-05,
|
| 1037 |
+
"loss": 0.0261,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.0383916990920882,
|
| 1042 |
+
"grad_norm": 0.27057945728302,
|
| 1043 |
+
"learning_rate": 7.80243408625947e-05,
|
| 1044 |
+
"loss": 0.0313,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.03865110246433204,
|
| 1049 |
+
"grad_norm": 0.40263959765434265,
|
| 1050 |
+
"learning_rate": 7.673586079888698e-05,
|
| 1051 |
+
"loss": 0.0255,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.038910505836575876,
|
| 1056 |
+
"grad_norm": 0.36453911662101746,
|
| 1057 |
+
"learning_rate": 7.54514512859201e-05,
|
| 1058 |
+
"loss": 0.0306,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
}
|
| 1061 |
+
],
|
| 1062 |
+
"logging_steps": 10,
|
| 1063 |
+
"max_steps": 2500,
|
| 1064 |
+
"num_input_tokens_seen": 0,
|
| 1065 |
+
"num_train_epochs": 1,
|
| 1066 |
+
"save_steps": 500,
|
| 1067 |
+
"stateful_callbacks": {
|
| 1068 |
+
"TrainerControl": {
|
| 1069 |
+
"args": {
|
| 1070 |
+
"should_epoch_stop": false,
|
| 1071 |
+
"should_evaluate": false,
|
| 1072 |
+
"should_log": false,
|
| 1073 |
+
"should_save": true,
|
| 1074 |
+
"should_training_stop": false
|
| 1075 |
+
},
|
| 1076 |
+
"attributes": {}
|
| 1077 |
+
}
|
| 1078 |
+
},
|
| 1079 |
+
"total_flos": 1.97189934514176e+17,
|
| 1080 |
+
"train_batch_size": 32,
|
| 1081 |
+
"trial_name": null,
|
| 1082 |
+
"trial_params": null
|
| 1083 |
+
}
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/adleboy/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
|
| 3 |
+
"action_dim": 32,
|
| 4 |
+
"action_head_cfg": {
|
| 5 |
+
"action_dim": 32,
|
| 6 |
+
"action_horizon": 16,
|
| 7 |
+
"add_pos_embed": true,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"dropout": 0.2,
|
| 11 |
+
"final_dropout": true,
|
| 12 |
+
"interleave_self_attention": true,
|
| 13 |
+
"norm_type": "ada_norm",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_layers": 16,
|
| 16 |
+
"output_dim": 1024,
|
| 17 |
+
"positional_embeddings": null
|
| 18 |
+
},
|
| 19 |
+
"freeze_decode_layer": false,
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"load_pretrained_det_decode_layer_path": null,
|
| 23 |
+
"max_action_dim": 32,
|
| 24 |
+
"max_state_dim": 64,
|
| 25 |
+
"model_dtype": "float32",
|
| 26 |
+
"noise_beta_alpha": 1.5,
|
| 27 |
+
"noise_beta_beta": 1.0,
|
| 28 |
+
"noise_s": 0.999,
|
| 29 |
+
"num_inference_timesteps": 16,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true
|
| 33 |
+
},
|
| 34 |
+
"action_horizon": 16,
|
| 35 |
+
"architectures": [
|
| 36 |
+
"GR00T_N1"
|
| 37 |
+
],
|
| 38 |
+
"attn_implementation": null,
|
| 39 |
+
"backbone_cfg": {
|
| 40 |
+
"allow_reshape_visual": true,
|
| 41 |
+
"load_pretrained_det_eagle_path": null,
|
| 42 |
+
"model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 43 |
+
"processor_cfg": {
|
| 44 |
+
"max_input_tiles": 1,
|
| 45 |
+
"model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 46 |
+
"model_spec": {
|
| 47 |
+
"num_image_token": 64,
|
| 48 |
+
"template": "qwen2-chat"
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"projector_dim": 2048,
|
| 52 |
+
"remove_llm": false,
|
| 53 |
+
"reproject_vision": false,
|
| 54 |
+
"scale_image_resolution": 1,
|
| 55 |
+
"select_layer": 12,
|
| 56 |
+
"tune_llm": false,
|
| 57 |
+
"tune_visual": true
|
| 58 |
+
},
|
| 59 |
+
"compute_dtype": "bfloat16",
|
| 60 |
+
"hidden_size": 1536,
|
| 61 |
+
"model_dtype": "float32",
|
| 62 |
+
"model_type": "gr00t_n1",
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.45.2"
|
| 65 |
+
}
|
checkpoint-2000/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"single_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
122.080078125,
|
| 8 |
+
198.193359375,
|
| 9 |
+
182.28515625,
|
| 10 |
+
114.43359375,
|
| 11 |
+
262.177734375
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-95.9765625,
|
| 15 |
+
-179.912109375,
|
| 16 |
+
-258.486328125,
|
| 17 |
+
-100.01953125,
|
| 18 |
+
-179.912109375
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
9.608419418334961,
|
| 22 |
+
114.65914154052734,
|
| 23 |
+
102.69532775878906,
|
| 24 |
+
63.54849624633789,
|
| 25 |
+
-3.96468186378479
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
30.130109786987305,
|
| 29 |
+
52.885677337646484,
|
| 30 |
+
68.62229919433594,
|
| 31 |
+
26.573131561279297,
|
| 32 |
+
62.51667785644531
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-55.1953125,
|
| 36 |
+
12.196582031250038,
|
| 37 |
+
-228.779296875,
|
| 38 |
+
-40.78125,
|
| 39 |
+
-152.40234375
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
87.626953125,
|
| 43 |
+
192.041015625,
|
| 44 |
+
179.47265625,
|
| 45 |
+
108.28125,
|
| 46 |
+
155.0390625
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
105.29850769042969
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
-2.7297544479370117
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
11.653524398803711
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
17.93401336669922
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
-1.4121800661087036
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
93.88059997558594
|
| 67 |
+
]
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"action": {
|
| 71 |
+
"single_arm": {
|
| 72 |
+
"max": [
|
| 73 |
+
123.046875,
|
| 74 |
+
202.763671875,
|
| 75 |
+
190.458984375,
|
| 76 |
+
117.0703125,
|
| 77 |
+
267.802734375
|
| 78 |
+
],
|
| 79 |
+
"min": [
|
| 80 |
+
-97.646484375,
|
| 81 |
+
-179.912109375,
|
| 82 |
+
-269.6484375,
|
| 83 |
+
-102.65625,
|
| 84 |
+
-270.0
|
| 85 |
+
],
|
| 86 |
+
"mean": [
|
| 87 |
+
9.716768264770508,
|
| 88 |
+
117.07723999023438,
|
| 89 |
+
101.3852767944336,
|
| 90 |
+
63.94012451171875,
|
| 91 |
+
-4.292983531951904
|
| 92 |
+
],
|
| 93 |
+
"std": [
|
| 94 |
+
30.517000198364258,
|
| 95 |
+
52.163082122802734,
|
| 96 |
+
69.69375610351562,
|
| 97 |
+
26.988319396972656,
|
| 98 |
+
63.348819732666016
|
| 99 |
+
],
|
| 100 |
+
"q01": [
|
| 101 |
+
-55.8984375,
|
| 102 |
+
16.435546875,
|
| 103 |
+
-230.888671875,
|
| 104 |
+
-41.66015625,
|
| 105 |
+
-153.896484375
|
| 106 |
+
],
|
| 107 |
+
"q99": [
|
| 108 |
+
88.505859375,
|
| 109 |
+
195.64453125,
|
| 110 |
+
182.900390625,
|
| 111 |
+
109.599609375,
|
| 112 |
+
155.7421875
|
| 113 |
+
]
|
| 114 |
+
},
|
| 115 |
+
"gripper": {
|
| 116 |
+
"max": [
|
| 117 |
+
109.84339904785156
|
| 118 |
+
],
|
| 119 |
+
"min": [
|
| 120 |
+
-7.955596446990967
|
| 121 |
+
],
|
| 122 |
+
"mean": [
|
| 123 |
+
9.987146377563477
|
| 124 |
+
],
|
| 125 |
+
"std": [
|
| 126 |
+
18.02056121826172
|
| 127 |
+
],
|
| 128 |
+
"q01": [
|
| 129 |
+
-2.5742573738098145
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
96.20721435546875
|
| 133 |
+
]
|
| 134 |
+
}
|
| 135 |
+
}
|
| 136 |
+
},
|
| 137 |
+
"modalities": {
|
| 138 |
+
"video": {
|
| 139 |
+
"images0": {
|
| 140 |
+
"resolution": [
|
| 141 |
+
320,
|
| 142 |
+
240
|
| 143 |
+
],
|
| 144 |
+
"channels": 3,
|
| 145 |
+
"fps": 30.0
|
| 146 |
+
},
|
| 147 |
+
"images1": {
|
| 148 |
+
"resolution": [
|
| 149 |
+
320,
|
| 150 |
+
240
|
| 151 |
+
],
|
| 152 |
+
"channels": 3,
|
| 153 |
+
"fps": 30.0
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"state": {
|
| 157 |
+
"single_arm": {
|
| 158 |
+
"absolute": true,
|
| 159 |
+
"rotation_type": null,
|
| 160 |
+
"shape": [
|
| 161 |
+
5
|
| 162 |
+
],
|
| 163 |
+
"continuous": true
|
| 164 |
+
},
|
| 165 |
+
"gripper": {
|
| 166 |
+
"absolute": true,
|
| 167 |
+
"rotation_type": null,
|
| 168 |
+
"shape": [
|
| 169 |
+
1
|
| 170 |
+
],
|
| 171 |
+
"continuous": true
|
| 172 |
+
}
|
| 173 |
+
},
|
| 174 |
+
"action": {
|
| 175 |
+
"single_arm": {
|
| 176 |
+
"absolute": true,
|
| 177 |
+
"rotation_type": null,
|
| 178 |
+
"shape": [
|
| 179 |
+
5
|
| 180 |
+
],
|
| 181 |
+
"continuous": true
|
| 182 |
+
},
|
| 183 |
+
"gripper": {
|
| 184 |
+
"absolute": true,
|
| 185 |
+
"rotation_type": null,
|
| 186 |
+
"shape": [
|
| 187 |
+
1
|
| 188 |
+
],
|
| 189 |
+
"continuous": true
|
| 190 |
+
}
|
| 191 |
+
}
|
| 192 |
+
},
|
| 193 |
+
"embodiment_tag": "new_embodiment"
|
| 194 |
+
}
|
| 195 |
+
}
|
checkpoint-2000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3377cfd8569b01ed89b25b5ee085a206bddba8b4b7643c8f479967a07a59b6ef
|
| 3 |
+
size 4938446392
|
checkpoint-2000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a500eae164384e550819779dd956f061810b772ef5a88bfb7d35f3e3e881c957
|
| 3 |
+
size 3821736024
|
checkpoint-2000/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,809 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8760067008
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 7 |
+
"action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 8 |
+
"action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 9 |
+
"action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 10 |
+
"action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
|
| 11 |
+
"action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
|
| 12 |
+
"action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
|
| 13 |
+
"action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
|
| 14 |
+
"action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
|
| 15 |
+
"action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
|
| 16 |
+
"action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
|
| 17 |
+
"action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
|
| 18 |
+
"action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
|
| 19 |
+
"action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
|
| 20 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
|
| 21 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
|
| 23 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 25 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 26 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 27 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 29 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 30 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 31 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 32 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 33 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 35 |
+
"action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 37 |
+
"action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 38 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 39 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 41 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 43 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 44 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 45 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 46 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 47 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 49 |
+
"action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 50 |
+
"action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 51 |
+
"action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 53 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 56 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 57 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 59 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 60 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 61 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 63 |
+
"action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 65 |
+
"action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 66 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 67 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 68 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 69 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 70 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 71 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 73 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 74 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 75 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 77 |
+
"action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 78 |
+
"action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 79 |
+
"action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 81 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 83 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 85 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 87 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 89 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 92 |
+
"action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 93 |
+
"action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 95 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 97 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 99 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 101 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 103 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 105 |
+
"action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 107 |
+
"action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 109 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 111 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 113 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 115 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 117 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 119 |
+
"action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 121 |
+
"action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 123 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 125 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 127 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 129 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 131 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 133 |
+
"action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 135 |
+
"action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 137 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 139 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 141 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 143 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 145 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 147 |
+
"action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 149 |
+
"action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 151 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 153 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 155 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 157 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 159 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 161 |
+
"action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 165 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 167 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 171 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 177 |
+
"action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 179 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 189 |
+
"action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 191 |
+
"action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 195 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 201 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 203 |
+
"action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 215 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 219 |
+
"action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 225 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 227 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 237 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 239 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 243 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 250 |
+
"action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 251 |
+
"action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 252 |
+
"action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 253 |
+
"backbone.linear.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"backbone.linear.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
|
| 370 |
+
"backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 381 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 655 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 715 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 727 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 739 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 751 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 763 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 775 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 787 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 799 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
| 808 |
+
}
|
| 809 |
+
}
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0f06c4c9e06a447bac6de4b1069aab061169c65201d729ce283ddac5a78a395
|
| 3 |
+
size 10272357262
|
checkpoint-2000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5768dc9f43a5c74804e037facb882a6453d1ada25ad008dc67719729dba1e8c2
|
| 3 |
+
size 14512
|
checkpoint-2000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d2771cecab78a7124d295448e238b2179967c40cd7d242d92d4321c8c152b5d
|
| 3 |
+
size 14512
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c88b3aeb8ec2bf995149291b90b69667d3f268ff2f13afbeab1a220b8cc27590
|
| 3 |
+
size 1064
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,1433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.05188067444876784,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00025940337224383917,
|
| 13 |
+
"grad_norm": 13.49365234375,
|
| 14 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 15 |
+
"loss": 1.5584,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0005188067444876783,
|
| 20 |
+
"grad_norm": 2.6006040573120117,
|
| 21 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 22 |
+
"loss": 0.7111,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0007782101167315176,
|
| 27 |
+
"grad_norm": 4.435553073883057,
|
| 28 |
+
"learning_rate": 4.8e-05,
|
| 29 |
+
"loss": 0.3076,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0010376134889753567,
|
| 34 |
+
"grad_norm": 1.1146177053451538,
|
| 35 |
+
"learning_rate": 6.400000000000001e-05,
|
| 36 |
+
"loss": 0.1826,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0012970168612191958,
|
| 41 |
+
"grad_norm": 0.8707008957862854,
|
| 42 |
+
"learning_rate": 8e-05,
|
| 43 |
+
"loss": 0.1341,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0015564202334630351,
|
| 48 |
+
"grad_norm": 1.7411352396011353,
|
| 49 |
+
"learning_rate": 9.6e-05,
|
| 50 |
+
"loss": 0.1144,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0018158236057068742,
|
| 55 |
+
"grad_norm": 0.9691908955574036,
|
| 56 |
+
"learning_rate": 0.00011200000000000001,
|
| 57 |
+
"loss": 0.0831,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0020752269779507134,
|
| 62 |
+
"grad_norm": 1.0398532152175903,
|
| 63 |
+
"learning_rate": 0.00012800000000000002,
|
| 64 |
+
"loss": 0.0801,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0023346303501945525,
|
| 69 |
+
"grad_norm": 0.5252112746238708,
|
| 70 |
+
"learning_rate": 0.000144,
|
| 71 |
+
"loss": 0.081,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0025940337224383916,
|
| 76 |
+
"grad_norm": 0.6552278995513916,
|
| 77 |
+
"learning_rate": 0.00016,
|
| 78 |
+
"loss": 0.0821,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0028534370946822307,
|
| 83 |
+
"grad_norm": 0.6302046775817871,
|
| 84 |
+
"learning_rate": 0.00017600000000000002,
|
| 85 |
+
"loss": 0.0749,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0031128404669260703,
|
| 90 |
+
"grad_norm": 0.7439587712287903,
|
| 91 |
+
"learning_rate": 0.000192,
|
| 92 |
+
"loss": 0.0647,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0033722438391699094,
|
| 97 |
+
"grad_norm": 6.8584771156311035,
|
| 98 |
+
"learning_rate": 0.0001999978128380225,
|
| 99 |
+
"loss": 0.0726,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0036316472114137485,
|
| 104 |
+
"grad_norm": 2.014613389968872,
|
| 105 |
+
"learning_rate": 0.0001999803161162393,
|
| 106 |
+
"loss": 0.0936,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0038910505836575876,
|
| 111 |
+
"grad_norm": 1.3758050203323364,
|
| 112 |
+
"learning_rate": 0.00019994532573409262,
|
| 113 |
+
"loss": 0.1089,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004150453955901427,
|
| 118 |
+
"grad_norm": 1.3027769327163696,
|
| 119 |
+
"learning_rate": 0.00019989284781388617,
|
| 120 |
+
"loss": 0.0772,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.004409857328145266,
|
| 125 |
+
"grad_norm": 1.021938443183899,
|
| 126 |
+
"learning_rate": 0.00019982289153773646,
|
| 127 |
+
"loss": 0.0695,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.004669260700389105,
|
| 132 |
+
"grad_norm": 0.8069638609886169,
|
| 133 |
+
"learning_rate": 0.00019973546914596623,
|
| 134 |
+
"loss": 0.0624,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.004928664072632944,
|
| 139 |
+
"grad_norm": 0.5198134779930115,
|
| 140 |
+
"learning_rate": 0.00019963059593496268,
|
| 141 |
+
"loss": 0.0481,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.005188067444876783,
|
| 146 |
+
"grad_norm": 0.39965012669563293,
|
| 147 |
+
"learning_rate": 0.00019950829025450114,
|
| 148 |
+
"loss": 0.0493,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005447470817120622,
|
| 153 |
+
"grad_norm": 0.8152652978897095,
|
| 154 |
+
"learning_rate": 0.0001993685735045343,
|
| 155 |
+
"loss": 0.0477,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.005706874189364461,
|
| 160 |
+
"grad_norm": 0.7083427309989929,
|
| 161 |
+
"learning_rate": 0.0001992114701314478,
|
| 162 |
+
"loss": 0.0501,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0059662775616083005,
|
| 167 |
+
"grad_norm": 0.690096914768219,
|
| 168 |
+
"learning_rate": 0.000199037007623783,
|
| 169 |
+
"loss": 0.0509,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0062256809338521405,
|
| 174 |
+
"grad_norm": 0.871699869632721,
|
| 175 |
+
"learning_rate": 0.00019884521650742715,
|
| 176 |
+
"loss": 0.0464,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.00648508430609598,
|
| 181 |
+
"grad_norm": 0.6445639133453369,
|
| 182 |
+
"learning_rate": 0.00019863613034027224,
|
| 183 |
+
"loss": 0.0462,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.006744487678339819,
|
| 188 |
+
"grad_norm": 0.4920782148838043,
|
| 189 |
+
"learning_rate": 0.0001984097857063434,
|
| 190 |
+
"loss": 0.0425,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.007003891050583658,
|
| 195 |
+
"grad_norm": 0.8624788522720337,
|
| 196 |
+
"learning_rate": 0.0001981662222093976,
|
| 197 |
+
"loss": 0.0471,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007263294422827497,
|
| 202 |
+
"grad_norm": 0.5704030990600586,
|
| 203 |
+
"learning_rate": 0.00019790548246599447,
|
| 204 |
+
"loss": 0.0571,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.007522697795071336,
|
| 209 |
+
"grad_norm": 0.569247841835022,
|
| 210 |
+
"learning_rate": 0.00019762761209803927,
|
| 211 |
+
"loss": 0.0531,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.007782101167315175,
|
| 216 |
+
"grad_norm": 0.7414583563804626,
|
| 217 |
+
"learning_rate": 0.0001973326597248006,
|
| 218 |
+
"loss": 0.0455,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008041504539559013,
|
| 223 |
+
"grad_norm": 0.42905348539352417,
|
| 224 |
+
"learning_rate": 0.00019702067695440332,
|
| 225 |
+
"loss": 0.0542,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008300907911802853,
|
| 230 |
+
"grad_norm": 0.6132651567459106,
|
| 231 |
+
"learning_rate": 0.00019669171837479873,
|
| 232 |
+
"loss": 0.0439,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.008560311284046693,
|
| 237 |
+
"grad_norm": 0.44733384251594543,
|
| 238 |
+
"learning_rate": 0.00019634584154421317,
|
| 239 |
+
"loss": 0.0429,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.008819714656290532,
|
| 244 |
+
"grad_norm": 0.516659677028656,
|
| 245 |
+
"learning_rate": 0.00019598310698107702,
|
| 246 |
+
"loss": 0.0407,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.009079118028534372,
|
| 251 |
+
"grad_norm": 0.2340136468410492,
|
| 252 |
+
"learning_rate": 0.00019560357815343577,
|
| 253 |
+
"loss": 0.036,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.00933852140077821,
|
| 258 |
+
"grad_norm": 0.6629723906517029,
|
| 259 |
+
"learning_rate": 0.00019520732146784491,
|
| 260 |
+
"loss": 0.041,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.00959792477302205,
|
| 265 |
+
"grad_norm": 0.3777199387550354,
|
| 266 |
+
"learning_rate": 0.0001947944062577507,
|
| 267 |
+
"loss": 0.0414,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.009857328145265888,
|
| 272 |
+
"grad_norm": 0.44298338890075684,
|
| 273 |
+
"learning_rate": 0.00019436490477135878,
|
| 274 |
+
"loss": 0.0371,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.010116731517509728,
|
| 279 |
+
"grad_norm": 0.4530090093612671,
|
| 280 |
+
"learning_rate": 0.00019391889215899299,
|
| 281 |
+
"loss": 0.037,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.010376134889753566,
|
| 286 |
+
"grad_norm": 0.36142367124557495,
|
| 287 |
+
"learning_rate": 0.0001934564464599461,
|
| 288 |
+
"loss": 0.0387,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.010635538261997406,
|
| 293 |
+
"grad_norm": 0.36559927463531494,
|
| 294 |
+
"learning_rate": 0.00019297764858882514,
|
| 295 |
+
"loss": 0.0386,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.010894941634241245,
|
| 300 |
+
"grad_norm": 0.47660204768180847,
|
| 301 |
+
"learning_rate": 0.00019248258232139388,
|
| 302 |
+
"loss": 0.0316,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.011154345006485085,
|
| 307 |
+
"grad_norm": 0.2614981234073639,
|
| 308 |
+
"learning_rate": 0.00019197133427991436,
|
| 309 |
+
"loss": 0.0417,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011413748378728923,
|
| 314 |
+
"grad_norm": 0.44811561703681946,
|
| 315 |
+
"learning_rate": 0.00019144399391799043,
|
| 316 |
+
"loss": 0.036,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.011673151750972763,
|
| 321 |
+
"grad_norm": 0.4213508367538452,
|
| 322 |
+
"learning_rate": 0.00019090065350491626,
|
| 323 |
+
"loss": 0.0399,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.011932555123216601,
|
| 328 |
+
"grad_norm": 0.29146406054496765,
|
| 329 |
+
"learning_rate": 0.0001903414081095315,
|
| 330 |
+
"loss": 0.0376,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.012191958495460441,
|
| 335 |
+
"grad_norm": 0.2714293897151947,
|
| 336 |
+
"learning_rate": 0.00018976635558358722,
|
| 337 |
+
"loss": 0.0362,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012451361867704281,
|
| 342 |
+
"grad_norm": 0.3767367899417877,
|
| 343 |
+
"learning_rate": 0.00018917559654462474,
|
| 344 |
+
"loss": 0.0364,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01271076523994812,
|
| 349 |
+
"grad_norm": 0.36578992009162903,
|
| 350 |
+
"learning_rate": 0.00018856923435837022,
|
| 351 |
+
"loss": 0.0327,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.01297016861219196,
|
| 356 |
+
"grad_norm": 0.32976096868515015,
|
| 357 |
+
"learning_rate": 0.0001879473751206489,
|
| 358 |
+
"loss": 0.04,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.013229571984435798,
|
| 363 |
+
"grad_norm": 0.4037308990955353,
|
| 364 |
+
"learning_rate": 0.00018731012763882133,
|
| 365 |
+
"loss": 0.0365,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.013488975356679637,
|
| 370 |
+
"grad_norm": 0.3599701225757599,
|
| 371 |
+
"learning_rate": 0.00018665760341274505,
|
| 372 |
+
"loss": 0.0337,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.013748378728923476,
|
| 377 |
+
"grad_norm": 0.6167535185813904,
|
| 378 |
+
"learning_rate": 0.00018598991661526572,
|
| 379 |
+
"loss": 0.0384,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.014007782101167316,
|
| 384 |
+
"grad_norm": 0.44012153148651123,
|
| 385 |
+
"learning_rate": 0.00018530718407223974,
|
| 386 |
+
"loss": 0.0291,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.014267185473411154,
|
| 391 |
+
"grad_norm": 0.5593993663787842,
|
| 392 |
+
"learning_rate": 0.00018460952524209355,
|
| 393 |
+
"loss": 0.0328,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.014526588845654994,
|
| 398 |
+
"grad_norm": 0.3970232307910919,
|
| 399 |
+
"learning_rate": 0.00018389706219492147,
|
| 400 |
+
"loss": 0.0282,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.014785992217898832,
|
| 405 |
+
"grad_norm": 0.2354394942522049,
|
| 406 |
+
"learning_rate": 0.00018316991959112716,
|
| 407 |
+
"loss": 0.0317,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.015045395590142672,
|
| 412 |
+
"grad_norm": 0.35121485590934753,
|
| 413 |
+
"learning_rate": 0.00018242822465961176,
|
| 414 |
+
"loss": 0.0328,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.01530479896238651,
|
| 419 |
+
"grad_norm": 0.4026910066604614,
|
| 420 |
+
"learning_rate": 0.00018167210717551224,
|
| 421 |
+
"loss": 0.0346,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.01556420233463035,
|
| 426 |
+
"grad_norm": 0.36058488488197327,
|
| 427 |
+
"learning_rate": 0.00018090169943749476,
|
| 428 |
+
"loss": 0.0356,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.01582360570687419,
|
| 433 |
+
"grad_norm": 0.43329063057899475,
|
| 434 |
+
"learning_rate": 0.00018011713624460608,
|
| 435 |
+
"loss": 0.039,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.016083009079118027,
|
| 440 |
+
"grad_norm": 0.5267623662948608,
|
| 441 |
+
"learning_rate": 0.00017931855487268782,
|
| 442 |
+
"loss": 0.034,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.01634241245136187,
|
| 447 |
+
"grad_norm": 0.4230927526950836,
|
| 448 |
+
"learning_rate": 0.0001785060950503568,
|
| 449 |
+
"loss": 0.031,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.016601815823605707,
|
| 454 |
+
"grad_norm": 0.3721458613872528,
|
| 455 |
+
"learning_rate": 0.00017767989893455698,
|
| 456 |
+
"loss": 0.0306,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.016861219195849545,
|
| 461 |
+
"grad_norm": 0.4158923029899597,
|
| 462 |
+
"learning_rate": 0.00017684011108568592,
|
| 463 |
+
"loss": 0.0343,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.017120622568093387,
|
| 468 |
+
"grad_norm": 0.42805808782577515,
|
| 469 |
+
"learning_rate": 0.00017598687844230088,
|
| 470 |
+
"loss": 0.0348,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.017380025940337225,
|
| 475 |
+
"grad_norm": 0.2532889246940613,
|
| 476 |
+
"learning_rate": 0.00017512035029540885,
|
| 477 |
+
"loss": 0.0348,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.017639429312581063,
|
| 482 |
+
"grad_norm": 0.33485907316207886,
|
| 483 |
+
"learning_rate": 0.000174240678262345,
|
| 484 |
+
"loss": 0.0382,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.0178988326848249,
|
| 489 |
+
"grad_norm": 0.33811262249946594,
|
| 490 |
+
"learning_rate": 0.000173348016260244,
|
| 491 |
+
"loss": 0.0321,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.018158236057068743,
|
| 496 |
+
"grad_norm": 0.5319349765777588,
|
| 497 |
+
"learning_rate": 0.00017244252047910892,
|
| 498 |
+
"loss": 0.0369,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.01841763942931258,
|
| 503 |
+
"grad_norm": 0.1967012882232666,
|
| 504 |
+
"learning_rate": 0.00017152434935448256,
|
| 505 |
+
"loss": 0.0392,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.01867704280155642,
|
| 510 |
+
"grad_norm": 0.491212397813797,
|
| 511 |
+
"learning_rate": 0.0001705936635397259,
|
| 512 |
+
"loss": 0.034,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.018936446173800258,
|
| 517 |
+
"grad_norm": 0.3200204074382782,
|
| 518 |
+
"learning_rate": 0.00016965062587790823,
|
| 519 |
+
"loss": 0.0349,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.0191958495460441,
|
| 524 |
+
"grad_norm": 0.29090484976768494,
|
| 525 |
+
"learning_rate": 0.00016869540137331445,
|
| 526 |
+
"loss": 0.0302,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.019455252918287938,
|
| 531 |
+
"grad_norm": 0.4633236825466156,
|
| 532 |
+
"learning_rate": 0.00016772815716257412,
|
| 533 |
+
"loss": 0.0305,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.019714656290531776,
|
| 538 |
+
"grad_norm": 0.6030534505844116,
|
| 539 |
+
"learning_rate": 0.00016674906248541726,
|
| 540 |
+
"loss": 0.0331,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.019974059662775615,
|
| 545 |
+
"grad_norm": 0.28692400455474854,
|
| 546 |
+
"learning_rate": 0.00016575828865506245,
|
| 547 |
+
"loss": 0.0319,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.020233463035019456,
|
| 552 |
+
"grad_norm": 0.3799605667591095,
|
| 553 |
+
"learning_rate": 0.0001647560090282419,
|
| 554 |
+
"loss": 0.0316,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.020492866407263294,
|
| 559 |
+
"grad_norm": 0.529679536819458,
|
| 560 |
+
"learning_rate": 0.000163742398974869,
|
| 561 |
+
"loss": 0.0317,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.020752269779507133,
|
| 566 |
+
"grad_norm": 0.328056275844574,
|
| 567 |
+
"learning_rate": 0.0001627176358473537,
|
| 568 |
+
"loss": 0.0332,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.021011673151750974,
|
| 573 |
+
"grad_norm": 0.3303374648094177,
|
| 574 |
+
"learning_rate": 0.0001616818989495711,
|
| 575 |
+
"loss": 0.0323,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.021271076523994813,
|
| 580 |
+
"grad_norm": 0.23507635295391083,
|
| 581 |
+
"learning_rate": 0.00016063536950548826,
|
| 582 |
+
"loss": 0.0338,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.02153047989623865,
|
| 587 |
+
"grad_norm": 0.3870477080345154,
|
| 588 |
+
"learning_rate": 0.0001595782306274553,
|
| 589 |
+
"loss": 0.0326,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.02178988326848249,
|
| 594 |
+
"grad_norm": 0.37890198826789856,
|
| 595 |
+
"learning_rate": 0.00015851066728416618,
|
| 596 |
+
"loss": 0.0309,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.02204928664072633,
|
| 601 |
+
"grad_norm": 0.48460447788238525,
|
| 602 |
+
"learning_rate": 0.00015743286626829437,
|
| 603 |
+
"loss": 0.0351,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.02230869001297017,
|
| 608 |
+
"grad_norm": 0.38216733932495117,
|
| 609 |
+
"learning_rate": 0.00015634501616380967,
|
| 610 |
+
"loss": 0.0331,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.022568093385214007,
|
| 615 |
+
"grad_norm": 0.31668373942375183,
|
| 616 |
+
"learning_rate": 0.00015524730731298134,
|
| 617 |
+
"loss": 0.0306,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.022827496757457846,
|
| 622 |
+
"grad_norm": 0.5256275534629822,
|
| 623 |
+
"learning_rate": 0.0001541399317830738,
|
| 624 |
+
"loss": 0.0307,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.023086900129701687,
|
| 629 |
+
"grad_norm": 0.2295175939798355,
|
| 630 |
+
"learning_rate": 0.0001530230833327405,
|
| 631 |
+
"loss": 0.0297,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.023346303501945526,
|
| 636 |
+
"grad_norm": 0.35704338550567627,
|
| 637 |
+
"learning_rate": 0.00015189695737812152,
|
| 638 |
+
"loss": 0.0358,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.023605706874189364,
|
| 643 |
+
"grad_norm": 0.31458932161331177,
|
| 644 |
+
"learning_rate": 0.0001507617509586517,
|
| 645 |
+
"loss": 0.0278,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.023865110246433202,
|
| 650 |
+
"grad_norm": 0.47554951906204224,
|
| 651 |
+
"learning_rate": 0.00014961766270258422,
|
| 652 |
+
"loss": 0.0332,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.024124513618677044,
|
| 657 |
+
"grad_norm": 0.29959654808044434,
|
| 658 |
+
"learning_rate": 0.00014846489279223652,
|
| 659 |
+
"loss": 0.0268,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.024383916990920882,
|
| 664 |
+
"grad_norm": 0.31856444478034973,
|
| 665 |
+
"learning_rate": 0.0001473036429289641,
|
| 666 |
+
"loss": 0.028,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.02464332036316472,
|
| 671 |
+
"grad_norm": 0.23568253219127655,
|
| 672 |
+
"learning_rate": 0.0001461341162978688,
|
| 673 |
+
"loss": 0.0339,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.024902723735408562,
|
| 678 |
+
"grad_norm": 0.4032520055770874,
|
| 679 |
+
"learning_rate": 0.00014495651753224705,
|
| 680 |
+
"loss": 0.0291,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.0251621271076524,
|
| 685 |
+
"grad_norm": 0.36155375838279724,
|
| 686 |
+
"learning_rate": 0.00014377105267778518,
|
| 687 |
+
"loss": 0.0261,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.02542153047989624,
|
| 692 |
+
"grad_norm": 0.2985226511955261,
|
| 693 |
+
"learning_rate": 0.00014257792915650728,
|
| 694 |
+
"loss": 0.03,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.025680933852140077,
|
| 699 |
+
"grad_norm": 0.3420771658420563,
|
| 700 |
+
"learning_rate": 0.00014137735573048233,
|
| 701 |
+
"loss": 0.0318,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.02594033722438392,
|
| 706 |
+
"grad_norm": 0.19557547569274902,
|
| 707 |
+
"learning_rate": 0.00014016954246529696,
|
| 708 |
+
"loss": 0.0287,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.026199740596627757,
|
| 713 |
+
"grad_norm": 0.2249382734298706,
|
| 714 |
+
"learning_rate": 0.00013895470069330004,
|
| 715 |
+
"loss": 0.0258,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.026459143968871595,
|
| 720 |
+
"grad_norm": 0.5154671669006348,
|
| 721 |
+
"learning_rate": 0.00013773304297662559,
|
| 722 |
+
"loss": 0.0339,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.026718547341115433,
|
| 727 |
+
"grad_norm": 0.3469725251197815,
|
| 728 |
+
"learning_rate": 0.00013650478307000057,
|
| 729 |
+
"loss": 0.032,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.026977950713359275,
|
| 734 |
+
"grad_norm": 0.34428727626800537,
|
| 735 |
+
"learning_rate": 0.00013527013588334415,
|
| 736 |
+
"loss": 0.0317,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.027237354085603113,
|
| 741 |
+
"grad_norm": 0.2862760126590729,
|
| 742 |
+
"learning_rate": 0.00013402931744416433,
|
| 743 |
+
"loss": 0.03,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.02749675745784695,
|
| 748 |
+
"grad_norm": 0.5235270261764526,
|
| 749 |
+
"learning_rate": 0.00013278254485975976,
|
| 750 |
+
"loss": 0.0368,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.02775616083009079,
|
| 755 |
+
"grad_norm": 0.2167377918958664,
|
| 756 |
+
"learning_rate": 0.00013153003627923218,
|
| 757 |
+
"loss": 0.0306,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.02801556420233463,
|
| 762 |
+
"grad_norm": 0.29817643761634827,
|
| 763 |
+
"learning_rate": 0.00013027201085531634,
|
| 764 |
+
"loss": 0.0301,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.02827496757457847,
|
| 769 |
+
"grad_norm": 0.29515424370765686,
|
| 770 |
+
"learning_rate": 0.00012900868870603503,
|
| 771 |
+
"loss": 0.0249,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.028534370946822308,
|
| 776 |
+
"grad_norm": 0.3012550473213196,
|
| 777 |
+
"learning_rate": 0.00012774029087618446,
|
| 778 |
+
"loss": 0.0264,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.028793774319066146,
|
| 783 |
+
"grad_norm": 0.31644681096076965,
|
| 784 |
+
"learning_rate": 0.00012646703929865817,
|
| 785 |
+
"loss": 0.0316,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.029053177691309988,
|
| 790 |
+
"grad_norm": 0.37952420115470886,
|
| 791 |
+
"learning_rate": 0.00012518915675561483,
|
| 792 |
+
"loss": 0.0296,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.029312581063553826,
|
| 797 |
+
"grad_norm": 0.2594399154186249,
|
| 798 |
+
"learning_rate": 0.00012390686683949798,
|
| 799 |
+
"loss": 0.0321,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.029571984435797664,
|
| 804 |
+
"grad_norm": 0.34381750226020813,
|
| 805 |
+
"learning_rate": 0.00012262039391391404,
|
| 806 |
+
"loss": 0.0305,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.029831387808041506,
|
| 811 |
+
"grad_norm": 0.2528727948665619,
|
| 812 |
+
"learning_rate": 0.0001213299630743747,
|
| 813 |
+
"loss": 0.0303,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.030090791180285344,
|
| 818 |
+
"grad_norm": 0.32746660709381104,
|
| 819 |
+
"learning_rate": 0.00012003580010891213,
|
| 820 |
+
"loss": 0.0309,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.030350194552529183,
|
| 825 |
+
"grad_norm": 0.46516871452331543,
|
| 826 |
+
"learning_rate": 0.00011873813145857249,
|
| 827 |
+
"loss": 0.0288,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.03060959792477302,
|
| 832 |
+
"grad_norm": 0.21779906749725342,
|
| 833 |
+
"learning_rate": 0.00011743718417779517,
|
| 834 |
+
"loss": 0.0268,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.030869001297016863,
|
| 839 |
+
"grad_norm": 0.2870500087738037,
|
| 840 |
+
"learning_rate": 0.00011613318589468511,
|
| 841 |
+
"loss": 0.0284,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.0311284046692607,
|
| 846 |
+
"grad_norm": 0.223075732588768,
|
| 847 |
+
"learning_rate": 0.0001148263647711842,
|
| 848 |
+
"loss": 0.0283,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.03138780804150454,
|
| 853 |
+
"grad_norm": 0.3081727921962738,
|
| 854 |
+
"learning_rate": 0.0001135169494631497,
|
| 855 |
+
"loss": 0.0319,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.03164721141374838,
|
| 860 |
+
"grad_norm": 0.48067420721054077,
|
| 861 |
+
"learning_rate": 0.00011220516908034601,
|
| 862 |
+
"loss": 0.0286,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.031906614785992216,
|
| 867 |
+
"grad_norm": 0.34588056802749634,
|
| 868 |
+
"learning_rate": 0.00011089125314635726,
|
| 869 |
+
"loss": 0.0287,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.032166018158236054,
|
| 874 |
+
"grad_norm": 0.3428352475166321,
|
| 875 |
+
"learning_rate": 0.00010957543155842702,
|
| 876 |
+
"loss": 0.025,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.0324254215304799,
|
| 881 |
+
"grad_norm": 0.4223664700984955,
|
| 882 |
+
"learning_rate": 0.00010825793454723325,
|
| 883 |
+
"loss": 0.0304,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.03268482490272374,
|
| 888 |
+
"grad_norm": 0.21455545723438263,
|
| 889 |
+
"learning_rate": 0.00010693899263660441,
|
| 890 |
+
"loss": 0.0265,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.032944228274967575,
|
| 895 |
+
"grad_norm": 0.2936132252216339,
|
| 896 |
+
"learning_rate": 0.00010561883660318455,
|
| 897 |
+
"loss": 0.0298,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.033203631647211414,
|
| 902 |
+
"grad_norm": 0.3222610056400299,
|
| 903 |
+
"learning_rate": 0.00010429769743605407,
|
| 904 |
+
"loss": 0.0333,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.03346303501945525,
|
| 909 |
+
"grad_norm": 0.42949262261390686,
|
| 910 |
+
"learning_rate": 0.00010297580629631325,
|
| 911 |
+
"loss": 0.0336,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.03372243839169909,
|
| 916 |
+
"grad_norm": 0.3103349208831787,
|
| 917 |
+
"learning_rate": 0.00010165339447663587,
|
| 918 |
+
"loss": 0.0327,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.03398184176394293,
|
| 923 |
+
"grad_norm": 0.3449970483779907,
|
| 924 |
+
"learning_rate": 0.00010033069336079952,
|
| 925 |
+
"loss": 0.0293,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.034241245136186774,
|
| 930 |
+
"grad_norm": 0.3841015100479126,
|
| 931 |
+
"learning_rate": 9.900793438320037e-05,
|
| 932 |
+
"loss": 0.0305,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.03450064850843061,
|
| 937 |
+
"grad_norm": 0.3848475515842438,
|
| 938 |
+
"learning_rate": 9.768534898835862e-05,
|
| 939 |
+
"loss": 0.026,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.03476005188067445,
|
| 944 |
+
"grad_norm": 0.43429145216941833,
|
| 945 |
+
"learning_rate": 9.636316859042259e-05,
|
| 946 |
+
"loss": 0.0294,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.03501945525291829,
|
| 951 |
+
"grad_norm": 0.2181561291217804,
|
| 952 |
+
"learning_rate": 9.504162453267777e-05,
|
| 953 |
+
"loss": 0.0275,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.03527885862516213,
|
| 958 |
+
"grad_norm": 0.4230787754058838,
|
| 959 |
+
"learning_rate": 9.372094804706867e-05,
|
| 960 |
+
"loss": 0.0273,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.035538261997405965,
|
| 965 |
+
"grad_norm": 0.273333340883255,
|
| 966 |
+
"learning_rate": 9.24013702137397e-05,
|
| 967 |
+
"loss": 0.0246,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.0357976653696498,
|
| 972 |
+
"grad_norm": 0.21888947486877441,
|
| 973 |
+
"learning_rate": 9.108312192060298e-05,
|
| 974 |
+
"loss": 0.0223,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.03605706874189364,
|
| 979 |
+
"grad_norm": 0.22308865189552307,
|
| 980 |
+
"learning_rate": 8.97664338229395e-05,
|
| 981 |
+
"loss": 0.0249,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.03631647211413749,
|
| 986 |
+
"grad_norm": 0.2270708829164505,
|
| 987 |
+
"learning_rate": 8.845153630304139e-05,
|
| 988 |
+
"loss": 0.0272,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.036575875486381325,
|
| 993 |
+
"grad_norm": 0.3046322166919708,
|
| 994 |
+
"learning_rate": 8.713865942990141e-05,
|
| 995 |
+
"loss": 0.0225,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.03683527885862516,
|
| 1000 |
+
"grad_norm": 0.31552374362945557,
|
| 1001 |
+
"learning_rate": 8.582803291895758e-05,
|
| 1002 |
+
"loss": 0.0302,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.037094682230869,
|
| 1007 |
+
"grad_norm": 0.46200478076934814,
|
| 1008 |
+
"learning_rate": 8.451988609189987e-05,
|
| 1009 |
+
"loss": 0.0272,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.03735408560311284,
|
| 1014 |
+
"grad_norm": 0.22868406772613525,
|
| 1015 |
+
"learning_rate": 8.321444783654524e-05,
|
| 1016 |
+
"loss": 0.0267,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.03761348897535668,
|
| 1021 |
+
"grad_norm": 0.23030489683151245,
|
| 1022 |
+
"learning_rate": 8.191194656678904e-05,
|
| 1023 |
+
"loss": 0.0287,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.037872892347600516,
|
| 1028 |
+
"grad_norm": 0.19943729043006897,
|
| 1029 |
+
"learning_rate": 8.061261018263919e-05,
|
| 1030 |
+
"loss": 0.0249,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.03813229571984436,
|
| 1035 |
+
"grad_norm": 0.3236585557460785,
|
| 1036 |
+
"learning_rate": 7.931666603034033e-05,
|
| 1037 |
+
"loss": 0.0261,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.0383916990920882,
|
| 1042 |
+
"grad_norm": 0.27057945728302,
|
| 1043 |
+
"learning_rate": 7.80243408625947e-05,
|
| 1044 |
+
"loss": 0.0313,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.03865110246433204,
|
| 1049 |
+
"grad_norm": 0.40263959765434265,
|
| 1050 |
+
"learning_rate": 7.673586079888698e-05,
|
| 1051 |
+
"loss": 0.0255,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.038910505836575876,
|
| 1056 |
+
"grad_norm": 0.36453911662101746,
|
| 1057 |
+
"learning_rate": 7.54514512859201e-05,
|
| 1058 |
+
"loss": 0.0306,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.039169909208819714,
|
| 1063 |
+
"grad_norm": 0.2801981270313263,
|
| 1064 |
+
"learning_rate": 7.417133705816837e-05,
|
| 1065 |
+
"loss": 0.0272,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.03942931258106355,
|
| 1070 |
+
"grad_norm": 0.2771183252334595,
|
| 1071 |
+
"learning_rate": 7.289574209855559e-05,
|
| 1072 |
+
"loss": 0.0252,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.03968871595330739,
|
| 1077 |
+
"grad_norm": 0.1658083200454712,
|
| 1078 |
+
"learning_rate": 7.16248895992645e-05,
|
| 1079 |
+
"loss": 0.0278,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.03994811932555123,
|
| 1084 |
+
"grad_norm": 0.19812481105327606,
|
| 1085 |
+
"learning_rate": 7.035900192268464e-05,
|
| 1086 |
+
"loss": 0.028,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.040207522697795074,
|
| 1091 |
+
"grad_norm": 0.2751558721065521,
|
| 1092 |
+
"learning_rate": 6.909830056250527e-05,
|
| 1093 |
+
"loss": 0.0293,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.04046692607003891,
|
| 1098 |
+
"grad_norm": 0.24725764989852905,
|
| 1099 |
+
"learning_rate": 6.784300610496048e-05,
|
| 1100 |
+
"loss": 0.0245,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.04072632944228275,
|
| 1105 |
+
"grad_norm": 0.6854105591773987,
|
| 1106 |
+
"learning_rate": 6.65933381902329e-05,
|
| 1107 |
+
"loss": 0.0278,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.04098573281452659,
|
| 1112 |
+
"grad_norm": 0.19634288549423218,
|
| 1113 |
+
"learning_rate": 6.534951547402322e-05,
|
| 1114 |
+
"loss": 0.0251,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.04124513618677043,
|
| 1119 |
+
"grad_norm": 0.21054495871067047,
|
| 1120 |
+
"learning_rate": 6.411175558929152e-05,
|
| 1121 |
+
"loss": 0.0263,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.041504539559014265,
|
| 1126 |
+
"grad_norm": 0.2615554630756378,
|
| 1127 |
+
"learning_rate": 6.28802751081779e-05,
|
| 1128 |
+
"loss": 0.0268,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.041763942931258104,
|
| 1133 |
+
"grad_norm": 0.23431521654129028,
|
| 1134 |
+
"learning_rate": 6.165528950410884e-05,
|
| 1135 |
+
"loss": 0.0272,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.04202334630350195,
|
| 1140 |
+
"grad_norm": 0.14299079775810242,
|
| 1141 |
+
"learning_rate": 6.0437013114095195e-05,
|
| 1142 |
+
"loss": 0.0206,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.04228274967574579,
|
| 1147 |
+
"grad_norm": 0.32186359167099,
|
| 1148 |
+
"learning_rate": 5.922565910122967e-05,
|
| 1149 |
+
"loss": 0.0257,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.042542153047989625,
|
| 1154 |
+
"grad_norm": 0.3568614423274994,
|
| 1155 |
+
"learning_rate": 5.8021439417389444e-05,
|
| 1156 |
+
"loss": 0.0263,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.042801556420233464,
|
| 1161 |
+
"grad_norm": 0.2789517045021057,
|
| 1162 |
+
"learning_rate": 5.6824564766150726e-05,
|
| 1163 |
+
"loss": 0.0273,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.0430609597924773,
|
| 1168 |
+
"grad_norm": 0.23182226717472076,
|
| 1169 |
+
"learning_rate": 5.563524456592163e-05,
|
| 1170 |
+
"loss": 0.0216,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.04332036316472114,
|
| 1175 |
+
"grad_norm": 0.20413507521152496,
|
| 1176 |
+
"learning_rate": 5.4453686913300074e-05,
|
| 1177 |
+
"loss": 0.0281,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.04357976653696498,
|
| 1182 |
+
"grad_norm": 0.21678327023983002,
|
| 1183 |
+
"learning_rate": 5.328009854666303e-05,
|
| 1184 |
+
"loss": 0.0258,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.04383916990920882,
|
| 1189 |
+
"grad_norm": 0.25063127279281616,
|
| 1190 |
+
"learning_rate": 5.2114684809993044e-05,
|
| 1191 |
+
"loss": 0.0265,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.04409857328145266,
|
| 1196 |
+
"grad_norm": 0.17453815042972565,
|
| 1197 |
+
"learning_rate": 5.095764961694922e-05,
|
| 1198 |
+
"loss": 0.0256,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.0443579766536965,
|
| 1203 |
+
"grad_norm": 0.22323985397815704,
|
| 1204 |
+
"learning_rate": 4.980919541518796e-05,
|
| 1205 |
+
"loss": 0.025,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.04461738002594034,
|
| 1210 |
+
"grad_norm": 0.2994442880153656,
|
| 1211 |
+
"learning_rate": 4.866952315094088e-05,
|
| 1212 |
+
"loss": 0.0266,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.04487678339818418,
|
| 1217 |
+
"grad_norm": 0.27734553813934326,
|
| 1218 |
+
"learning_rate": 4.753883223385467e-05,
|
| 1219 |
+
"loss": 0.0247,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.045136186770428015,
|
| 1224 |
+
"grad_norm": 0.18703316152095795,
|
| 1225 |
+
"learning_rate": 4.6417320502100316e-05,
|
| 1226 |
+
"loss": 0.0232,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.04539559014267185,
|
| 1231 |
+
"grad_norm": 0.271628201007843,
|
| 1232 |
+
"learning_rate": 4.530518418775733e-05,
|
| 1233 |
+
"loss": 0.0275,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.04565499351491569,
|
| 1238 |
+
"grad_norm": 0.26739704608917236,
|
| 1239 |
+
"learning_rate": 4.4202617882478405e-05,
|
| 1240 |
+
"loss": 0.0273,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.045914396887159536,
|
| 1245 |
+
"grad_norm": 0.2327081710100174,
|
| 1246 |
+
"learning_rate": 4.310981450344189e-05,
|
| 1247 |
+
"loss": 0.0244,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.046173800259403375,
|
| 1252 |
+
"grad_norm": 0.23359940946102142,
|
| 1253 |
+
"learning_rate": 4.2026965259596666e-05,
|
| 1254 |
+
"loss": 0.0266,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.04643320363164721,
|
| 1259 |
+
"grad_norm": 0.1780378818511963,
|
| 1260 |
+
"learning_rate": 4.0954259618206295e-05,
|
| 1261 |
+
"loss": 0.0275,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.04669260700389105,
|
| 1266 |
+
"grad_norm": 0.14094606041908264,
|
| 1267 |
+
"learning_rate": 3.9891885271697496e-05,
|
| 1268 |
+
"loss": 0.0224,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.04695201037613489,
|
| 1273 |
+
"grad_norm": 0.21397313475608826,
|
| 1274 |
+
"learning_rate": 3.884002810481958e-05,
|
| 1275 |
+
"loss": 0.0262,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.04721141374837873,
|
| 1280 |
+
"grad_norm": 0.18339146673679352,
|
| 1281 |
+
"learning_rate": 3.779887216211995e-05,
|
| 1282 |
+
"loss": 0.0227,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.047470817120622566,
|
| 1287 |
+
"grad_norm": 0.3625165522098541,
|
| 1288 |
+
"learning_rate": 3.676859961574162e-05,
|
| 1289 |
+
"loss": 0.0261,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.047730220492866404,
|
| 1294 |
+
"grad_norm": 0.24323268234729767,
|
| 1295 |
+
"learning_rate": 3.574939073354838e-05,
|
| 1296 |
+
"loss": 0.0263,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.04798962386511025,
|
| 1301 |
+
"grad_norm": 0.16706861555576324,
|
| 1302 |
+
"learning_rate": 3.4741423847583134e-05,
|
| 1303 |
+
"loss": 0.0236,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.04824902723735409,
|
| 1308 |
+
"grad_norm": 0.25477734208106995,
|
| 1309 |
+
"learning_rate": 3.3744875322865034e-05,
|
| 1310 |
+
"loss": 0.0265,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.048508430609597926,
|
| 1315 |
+
"grad_norm": 0.23444534838199615,
|
| 1316 |
+
"learning_rate": 3.275991952653054e-05,
|
| 1317 |
+
"loss": 0.0255,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.048767833981841764,
|
| 1322 |
+
"grad_norm": 0.13936041295528412,
|
| 1323 |
+
"learning_rate": 3.178672879732435e-05,
|
| 1324 |
+
"loss": 0.0247,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.0490272373540856,
|
| 1329 |
+
"grad_norm": 0.27730414271354675,
|
| 1330 |
+
"learning_rate": 3.0825473415445074e-05,
|
| 1331 |
+
"loss": 0.0211,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.04928664072632944,
|
| 1336 |
+
"grad_norm": 0.44268760085105896,
|
| 1337 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 1338 |
+
"loss": 0.0293,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.04954604409857328,
|
| 1343 |
+
"grad_norm": 0.2908082902431488,
|
| 1344 |
+
"learning_rate": 2.8939439343332086e-05,
|
| 1345 |
+
"loss": 0.0283,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.049805447470817124,
|
| 1350 |
+
"grad_norm": 0.20642030239105225,
|
| 1351 |
+
"learning_rate": 2.8014990654450325e-05,
|
| 1352 |
+
"loss": 0.0237,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.05006485084306096,
|
| 1357 |
+
"grad_norm": 0.23467542231082916,
|
| 1358 |
+
"learning_rate": 2.7103137257858868e-05,
|
| 1359 |
+
"loss": 0.0257,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.0503242542153048,
|
| 1364 |
+
"grad_norm": 0.30216318368911743,
|
| 1365 |
+
"learning_rate": 2.6204038701499056e-05,
|
| 1366 |
+
"loss": 0.023,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.05058365758754864,
|
| 1371 |
+
"grad_norm": 0.2494220733642578,
|
| 1372 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 1373 |
+
"loss": 0.0248,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.05084306095979248,
|
| 1378 |
+
"grad_norm": 0.3801492154598236,
|
| 1379 |
+
"learning_rate": 2.4444733115075823e-05,
|
| 1380 |
+
"loss": 0.0208,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.051102464332036315,
|
| 1385 |
+
"grad_norm": 0.18340712785720825,
|
| 1386 |
+
"learning_rate": 2.3584833912548888e-05,
|
| 1387 |
+
"loss": 0.0265,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.051361867704280154,
|
| 1392 |
+
"grad_norm": 0.20898978412151337,
|
| 1393 |
+
"learning_rate": 2.2738305151465645e-05,
|
| 1394 |
+
"loss": 0.0242,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.05162127107652399,
|
| 1399 |
+
"grad_norm": 0.2393597811460495,
|
| 1400 |
+
"learning_rate": 2.190529494984782e-05,
|
| 1401 |
+
"loss": 0.0223,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.05188067444876784,
|
| 1406 |
+
"grad_norm": 0.16330353915691376,
|
| 1407 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 1408 |
+
"loss": 0.0207,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
}
|
| 1411 |
+
],
|
| 1412 |
+
"logging_steps": 10,
|
| 1413 |
+
"max_steps": 2500,
|
| 1414 |
+
"num_input_tokens_seen": 0,
|
| 1415 |
+
"num_train_epochs": 1,
|
| 1416 |
+
"save_steps": 500,
|
| 1417 |
+
"stateful_callbacks": {
|
| 1418 |
+
"TrainerControl": {
|
| 1419 |
+
"args": {
|
| 1420 |
+
"should_epoch_stop": false,
|
| 1421 |
+
"should_evaluate": false,
|
| 1422 |
+
"should_log": false,
|
| 1423 |
+
"should_save": true,
|
| 1424 |
+
"should_training_stop": false
|
| 1425 |
+
},
|
| 1426 |
+
"attributes": {}
|
| 1427 |
+
}
|
| 1428 |
+
},
|
| 1429 |
+
"total_flos": 2.62919912685568e+17,
|
| 1430 |
+
"train_batch_size": 32,
|
| 1431 |
+
"trial_name": null,
|
| 1432 |
+
"trial_params": null
|
| 1433 |
+
}
|
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/adleboy/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
|
| 3 |
+
"action_dim": 32,
|
| 4 |
+
"action_head_cfg": {
|
| 5 |
+
"action_dim": 32,
|
| 6 |
+
"action_horizon": 16,
|
| 7 |
+
"add_pos_embed": true,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"dropout": 0.2,
|
| 11 |
+
"final_dropout": true,
|
| 12 |
+
"interleave_self_attention": true,
|
| 13 |
+
"norm_type": "ada_norm",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_layers": 16,
|
| 16 |
+
"output_dim": 1024,
|
| 17 |
+
"positional_embeddings": null
|
| 18 |
+
},
|
| 19 |
+
"freeze_decode_layer": false,
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"load_pretrained_det_decode_layer_path": null,
|
| 23 |
+
"max_action_dim": 32,
|
| 24 |
+
"max_state_dim": 64,
|
| 25 |
+
"model_dtype": "float32",
|
| 26 |
+
"noise_beta_alpha": 1.5,
|
| 27 |
+
"noise_beta_beta": 1.0,
|
| 28 |
+
"noise_s": 0.999,
|
| 29 |
+
"num_inference_timesteps": 16,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true
|
| 33 |
+
},
|
| 34 |
+
"action_horizon": 16,
|
| 35 |
+
"architectures": [
|
| 36 |
+
"GR00T_N1"
|
| 37 |
+
],
|
| 38 |
+
"attn_implementation": null,
|
| 39 |
+
"backbone_cfg": {
|
| 40 |
+
"allow_reshape_visual": true,
|
| 41 |
+
"load_pretrained_det_eagle_path": null,
|
| 42 |
+
"model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 43 |
+
"processor_cfg": {
|
| 44 |
+
"max_input_tiles": 1,
|
| 45 |
+
"model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 46 |
+
"model_spec": {
|
| 47 |
+
"num_image_token": 64,
|
| 48 |
+
"template": "qwen2-chat"
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"projector_dim": 2048,
|
| 52 |
+
"remove_llm": false,
|
| 53 |
+
"reproject_vision": false,
|
| 54 |
+
"scale_image_resolution": 1,
|
| 55 |
+
"select_layer": 12,
|
| 56 |
+
"tune_llm": false,
|
| 57 |
+
"tune_visual": true
|
| 58 |
+
},
|
| 59 |
+
"compute_dtype": "bfloat16",
|
| 60 |
+
"hidden_size": 1536,
|
| 61 |
+
"model_dtype": "float32",
|
| 62 |
+
"model_type": "gr00t_n1",
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.45.2"
|
| 65 |
+
}
|
checkpoint-2500/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"single_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
122.080078125,
|
| 8 |
+
198.193359375,
|
| 9 |
+
182.28515625,
|
| 10 |
+
114.43359375,
|
| 11 |
+
262.177734375
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-95.9765625,
|
| 15 |
+
-179.912109375,
|
| 16 |
+
-258.486328125,
|
| 17 |
+
-100.01953125,
|
| 18 |
+
-179.912109375
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
9.608419418334961,
|
| 22 |
+
114.65914154052734,
|
| 23 |
+
102.69532775878906,
|
| 24 |
+
63.54849624633789,
|
| 25 |
+
-3.96468186378479
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
30.130109786987305,
|
| 29 |
+
52.885677337646484,
|
| 30 |
+
68.62229919433594,
|
| 31 |
+
26.573131561279297,
|
| 32 |
+
62.51667785644531
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-55.1953125,
|
| 36 |
+
12.196582031250038,
|
| 37 |
+
-228.779296875,
|
| 38 |
+
-40.78125,
|
| 39 |
+
-152.40234375
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
87.626953125,
|
| 43 |
+
192.041015625,
|
| 44 |
+
179.47265625,
|
| 45 |
+
108.28125,
|
| 46 |
+
155.0390625
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
105.29850769042969
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
-2.7297544479370117
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
11.653524398803711
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
17.93401336669922
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
-1.4121800661087036
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
93.88059997558594
|
| 67 |
+
]
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"action": {
|
| 71 |
+
"single_arm": {
|
| 72 |
+
"max": [
|
| 73 |
+
123.046875,
|
| 74 |
+
202.763671875,
|
| 75 |
+
190.458984375,
|
| 76 |
+
117.0703125,
|
| 77 |
+
267.802734375
|
| 78 |
+
],
|
| 79 |
+
"min": [
|
| 80 |
+
-97.646484375,
|
| 81 |
+
-179.912109375,
|
| 82 |
+
-269.6484375,
|
| 83 |
+
-102.65625,
|
| 84 |
+
-270.0
|
| 85 |
+
],
|
| 86 |
+
"mean": [
|
| 87 |
+
9.716768264770508,
|
| 88 |
+
117.07723999023438,
|
| 89 |
+
101.3852767944336,
|
| 90 |
+
63.94012451171875,
|
| 91 |
+
-4.292983531951904
|
| 92 |
+
],
|
| 93 |
+
"std": [
|
| 94 |
+
30.517000198364258,
|
| 95 |
+
52.163082122802734,
|
| 96 |
+
69.69375610351562,
|
| 97 |
+
26.988319396972656,
|
| 98 |
+
63.348819732666016
|
| 99 |
+
],
|
| 100 |
+
"q01": [
|
| 101 |
+
-55.8984375,
|
| 102 |
+
16.435546875,
|
| 103 |
+
-230.888671875,
|
| 104 |
+
-41.66015625,
|
| 105 |
+
-153.896484375
|
| 106 |
+
],
|
| 107 |
+
"q99": [
|
| 108 |
+
88.505859375,
|
| 109 |
+
195.64453125,
|
| 110 |
+
182.900390625,
|
| 111 |
+
109.599609375,
|
| 112 |
+
155.7421875
|
| 113 |
+
]
|
| 114 |
+
},
|
| 115 |
+
"gripper": {
|
| 116 |
+
"max": [
|
| 117 |
+
109.84339904785156
|
| 118 |
+
],
|
| 119 |
+
"min": [
|
| 120 |
+
-7.955596446990967
|
| 121 |
+
],
|
| 122 |
+
"mean": [
|
| 123 |
+
9.987146377563477
|
| 124 |
+
],
|
| 125 |
+
"std": [
|
| 126 |
+
18.02056121826172
|
| 127 |
+
],
|
| 128 |
+
"q01": [
|
| 129 |
+
-2.5742573738098145
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
96.20721435546875
|
| 133 |
+
]
|
| 134 |
+
}
|
| 135 |
+
}
|
| 136 |
+
},
|
| 137 |
+
"modalities": {
|
| 138 |
+
"video": {
|
| 139 |
+
"images0": {
|
| 140 |
+
"resolution": [
|
| 141 |
+
320,
|
| 142 |
+
240
|
| 143 |
+
],
|
| 144 |
+
"channels": 3,
|
| 145 |
+
"fps": 30.0
|
| 146 |
+
},
|
| 147 |
+
"images1": {
|
| 148 |
+
"resolution": [
|
| 149 |
+
320,
|
| 150 |
+
240
|
| 151 |
+
],
|
| 152 |
+
"channels": 3,
|
| 153 |
+
"fps": 30.0
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"state": {
|
| 157 |
+
"single_arm": {
|
| 158 |
+
"absolute": true,
|
| 159 |
+
"rotation_type": null,
|
| 160 |
+
"shape": [
|
| 161 |
+
5
|
| 162 |
+
],
|
| 163 |
+
"continuous": true
|
| 164 |
+
},
|
| 165 |
+
"gripper": {
|
| 166 |
+
"absolute": true,
|
| 167 |
+
"rotation_type": null,
|
| 168 |
+
"shape": [
|
| 169 |
+
1
|
| 170 |
+
],
|
| 171 |
+
"continuous": true
|
| 172 |
+
}
|
| 173 |
+
},
|
| 174 |
+
"action": {
|
| 175 |
+
"single_arm": {
|
| 176 |
+
"absolute": true,
|
| 177 |
+
"rotation_type": null,
|
| 178 |
+
"shape": [
|
| 179 |
+
5
|
| 180 |
+
],
|
| 181 |
+
"continuous": true
|
| 182 |
+
},
|
| 183 |
+
"gripper": {
|
| 184 |
+
"absolute": true,
|
| 185 |
+
"rotation_type": null,
|
| 186 |
+
"shape": [
|
| 187 |
+
1
|
| 188 |
+
],
|
| 189 |
+
"continuous": true
|
| 190 |
+
}
|
| 191 |
+
}
|
| 192 |
+
},
|
| 193 |
+
"embodiment_tag": "new_embodiment"
|
| 194 |
+
}
|
| 195 |
+
}
|
checkpoint-2500/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:227c9d13d75a47f45e577a85a99b0f3d5c39fdb424d9d062e8bc4da10cd10a27
|
| 3 |
+
size 4938446392
|
checkpoint-2500/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77ad3508a87586dda5b15ae92c4e62e0fa0566d6c35912adf6a4914257417b2c
|
| 3 |
+
size 3821736024
|
checkpoint-2500/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,809 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8760067008
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 7 |
+
"action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 8 |
+
"action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 9 |
+
"action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 10 |
+
"action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
|
| 11 |
+
"action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
|
| 12 |
+
"action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
|
| 13 |
+
"action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
|
| 14 |
+
"action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
|
| 15 |
+
"action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
|
| 16 |
+
"action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
|
| 17 |
+
"action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
|
| 18 |
+
"action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
|
| 19 |
+
"action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
|
| 20 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
|
| 21 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
|
| 23 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 25 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 26 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 27 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 29 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 30 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 31 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 32 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 33 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 35 |
+
"action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 37 |
+
"action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 38 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 39 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 41 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 43 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 44 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 45 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 46 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 47 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 49 |
+
"action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 50 |
+
"action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 51 |
+
"action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 53 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 56 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 57 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 59 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 60 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 61 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 63 |
+
"action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 65 |
+
"action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 66 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 67 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 68 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 69 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 70 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 71 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 73 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 74 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 75 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 77 |
+
"action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 78 |
+
"action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 79 |
+
"action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 81 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 83 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 85 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 87 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 89 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 92 |
+
"action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 93 |
+
"action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 95 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 97 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 99 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 101 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 103 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 105 |
+
"action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 107 |
+
"action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 109 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 111 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 113 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 115 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 117 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 119 |
+
"action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 121 |
+
"action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 123 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 125 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 127 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 129 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 131 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 133 |
+
"action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 135 |
+
"action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 137 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 139 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 141 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 143 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 145 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 147 |
+
"action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 149 |
+
"action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 151 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 153 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 155 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 157 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 159 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 161 |
+
"action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 165 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 167 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 171 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 177 |
+
"action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 179 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 189 |
+
"action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 191 |
+
"action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 195 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 201 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 203 |
+
"action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 215 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 219 |
+
"action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 225 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 227 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 237 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 239 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 243 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 250 |
+
"action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 251 |
+
"action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 252 |
+
"action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 253 |
+
"backbone.linear.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"backbone.linear.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
|
| 370 |
+
"backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 381 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 655 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 715 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 727 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 739 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 751 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 763 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 775 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 787 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 799 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
| 808 |
+
}
|
| 809 |
+
}
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99c0450faf5f91453bfb94516e496e2c1f41940321792d7ca8d8837917468300
|
| 3 |
+
size 10272357262
|
checkpoint-2500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ea5b2cd970379342d8d01b06c011b2ddab0e310abf6710f323b55e4c59f206f
|
| 3 |
+
size 14512
|
checkpoint-2500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e12b1b3703db27dc227ebd80ba2bd130750fa35f6f7f9e1bb1a07cd50d717a4
|
| 3 |
+
size 14512
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b204b20cdc92a140e2e21e015bdaa04af008c00e0bde30e59edf0f23817a338
|
| 3 |
+
size 1064
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,1783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0648508430609598,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00025940337224383917,
|
| 13 |
+
"grad_norm": 13.49365234375,
|
| 14 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 15 |
+
"loss": 1.5584,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0005188067444876783,
|
| 20 |
+
"grad_norm": 2.6006040573120117,
|
| 21 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 22 |
+
"loss": 0.7111,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0007782101167315176,
|
| 27 |
+
"grad_norm": 4.435553073883057,
|
| 28 |
+
"learning_rate": 4.8e-05,
|
| 29 |
+
"loss": 0.3076,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0010376134889753567,
|
| 34 |
+
"grad_norm": 1.1146177053451538,
|
| 35 |
+
"learning_rate": 6.400000000000001e-05,
|
| 36 |
+
"loss": 0.1826,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0012970168612191958,
|
| 41 |
+
"grad_norm": 0.8707008957862854,
|
| 42 |
+
"learning_rate": 8e-05,
|
| 43 |
+
"loss": 0.1341,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0015564202334630351,
|
| 48 |
+
"grad_norm": 1.7411352396011353,
|
| 49 |
+
"learning_rate": 9.6e-05,
|
| 50 |
+
"loss": 0.1144,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0018158236057068742,
|
| 55 |
+
"grad_norm": 0.9691908955574036,
|
| 56 |
+
"learning_rate": 0.00011200000000000001,
|
| 57 |
+
"loss": 0.0831,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0020752269779507134,
|
| 62 |
+
"grad_norm": 1.0398532152175903,
|
| 63 |
+
"learning_rate": 0.00012800000000000002,
|
| 64 |
+
"loss": 0.0801,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0023346303501945525,
|
| 69 |
+
"grad_norm": 0.5252112746238708,
|
| 70 |
+
"learning_rate": 0.000144,
|
| 71 |
+
"loss": 0.081,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0025940337224383916,
|
| 76 |
+
"grad_norm": 0.6552278995513916,
|
| 77 |
+
"learning_rate": 0.00016,
|
| 78 |
+
"loss": 0.0821,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0028534370946822307,
|
| 83 |
+
"grad_norm": 0.6302046775817871,
|
| 84 |
+
"learning_rate": 0.00017600000000000002,
|
| 85 |
+
"loss": 0.0749,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0031128404669260703,
|
| 90 |
+
"grad_norm": 0.7439587712287903,
|
| 91 |
+
"learning_rate": 0.000192,
|
| 92 |
+
"loss": 0.0647,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0033722438391699094,
|
| 97 |
+
"grad_norm": 6.8584771156311035,
|
| 98 |
+
"learning_rate": 0.0001999978128380225,
|
| 99 |
+
"loss": 0.0726,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0036316472114137485,
|
| 104 |
+
"grad_norm": 2.014613389968872,
|
| 105 |
+
"learning_rate": 0.0001999803161162393,
|
| 106 |
+
"loss": 0.0936,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0038910505836575876,
|
| 111 |
+
"grad_norm": 1.3758050203323364,
|
| 112 |
+
"learning_rate": 0.00019994532573409262,
|
| 113 |
+
"loss": 0.1089,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004150453955901427,
|
| 118 |
+
"grad_norm": 1.3027769327163696,
|
| 119 |
+
"learning_rate": 0.00019989284781388617,
|
| 120 |
+
"loss": 0.0772,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.004409857328145266,
|
| 125 |
+
"grad_norm": 1.021938443183899,
|
| 126 |
+
"learning_rate": 0.00019982289153773646,
|
| 127 |
+
"loss": 0.0695,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.004669260700389105,
|
| 132 |
+
"grad_norm": 0.8069638609886169,
|
| 133 |
+
"learning_rate": 0.00019973546914596623,
|
| 134 |
+
"loss": 0.0624,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.004928664072632944,
|
| 139 |
+
"grad_norm": 0.5198134779930115,
|
| 140 |
+
"learning_rate": 0.00019963059593496268,
|
| 141 |
+
"loss": 0.0481,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.005188067444876783,
|
| 146 |
+
"grad_norm": 0.39965012669563293,
|
| 147 |
+
"learning_rate": 0.00019950829025450114,
|
| 148 |
+
"loss": 0.0493,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005447470817120622,
|
| 153 |
+
"grad_norm": 0.8152652978897095,
|
| 154 |
+
"learning_rate": 0.0001993685735045343,
|
| 155 |
+
"loss": 0.0477,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.005706874189364461,
|
| 160 |
+
"grad_norm": 0.7083427309989929,
|
| 161 |
+
"learning_rate": 0.0001992114701314478,
|
| 162 |
+
"loss": 0.0501,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0059662775616083005,
|
| 167 |
+
"grad_norm": 0.690096914768219,
|
| 168 |
+
"learning_rate": 0.000199037007623783,
|
| 169 |
+
"loss": 0.0509,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0062256809338521405,
|
| 174 |
+
"grad_norm": 0.871699869632721,
|
| 175 |
+
"learning_rate": 0.00019884521650742715,
|
| 176 |
+
"loss": 0.0464,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.00648508430609598,
|
| 181 |
+
"grad_norm": 0.6445639133453369,
|
| 182 |
+
"learning_rate": 0.00019863613034027224,
|
| 183 |
+
"loss": 0.0462,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.006744487678339819,
|
| 188 |
+
"grad_norm": 0.4920782148838043,
|
| 189 |
+
"learning_rate": 0.0001984097857063434,
|
| 190 |
+
"loss": 0.0425,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.007003891050583658,
|
| 195 |
+
"grad_norm": 0.8624788522720337,
|
| 196 |
+
"learning_rate": 0.0001981662222093976,
|
| 197 |
+
"loss": 0.0471,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007263294422827497,
|
| 202 |
+
"grad_norm": 0.5704030990600586,
|
| 203 |
+
"learning_rate": 0.00019790548246599447,
|
| 204 |
+
"loss": 0.0571,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.007522697795071336,
|
| 209 |
+
"grad_norm": 0.569247841835022,
|
| 210 |
+
"learning_rate": 0.00019762761209803927,
|
| 211 |
+
"loss": 0.0531,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.007782101167315175,
|
| 216 |
+
"grad_norm": 0.7414583563804626,
|
| 217 |
+
"learning_rate": 0.0001973326597248006,
|
| 218 |
+
"loss": 0.0455,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008041504539559013,
|
| 223 |
+
"grad_norm": 0.42905348539352417,
|
| 224 |
+
"learning_rate": 0.00019702067695440332,
|
| 225 |
+
"loss": 0.0542,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008300907911802853,
|
| 230 |
+
"grad_norm": 0.6132651567459106,
|
| 231 |
+
"learning_rate": 0.00019669171837479873,
|
| 232 |
+
"loss": 0.0439,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.008560311284046693,
|
| 237 |
+
"grad_norm": 0.44733384251594543,
|
| 238 |
+
"learning_rate": 0.00019634584154421317,
|
| 239 |
+
"loss": 0.0429,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.008819714656290532,
|
| 244 |
+
"grad_norm": 0.516659677028656,
|
| 245 |
+
"learning_rate": 0.00019598310698107702,
|
| 246 |
+
"loss": 0.0407,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.009079118028534372,
|
| 251 |
+
"grad_norm": 0.2340136468410492,
|
| 252 |
+
"learning_rate": 0.00019560357815343577,
|
| 253 |
+
"loss": 0.036,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.00933852140077821,
|
| 258 |
+
"grad_norm": 0.6629723906517029,
|
| 259 |
+
"learning_rate": 0.00019520732146784491,
|
| 260 |
+
"loss": 0.041,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.00959792477302205,
|
| 265 |
+
"grad_norm": 0.3777199387550354,
|
| 266 |
+
"learning_rate": 0.0001947944062577507,
|
| 267 |
+
"loss": 0.0414,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.009857328145265888,
|
| 272 |
+
"grad_norm": 0.44298338890075684,
|
| 273 |
+
"learning_rate": 0.00019436490477135878,
|
| 274 |
+
"loss": 0.0371,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.010116731517509728,
|
| 279 |
+
"grad_norm": 0.4530090093612671,
|
| 280 |
+
"learning_rate": 0.00019391889215899299,
|
| 281 |
+
"loss": 0.037,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.010376134889753566,
|
| 286 |
+
"grad_norm": 0.36142367124557495,
|
| 287 |
+
"learning_rate": 0.0001934564464599461,
|
| 288 |
+
"loss": 0.0387,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.010635538261997406,
|
| 293 |
+
"grad_norm": 0.36559927463531494,
|
| 294 |
+
"learning_rate": 0.00019297764858882514,
|
| 295 |
+
"loss": 0.0386,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.010894941634241245,
|
| 300 |
+
"grad_norm": 0.47660204768180847,
|
| 301 |
+
"learning_rate": 0.00019248258232139388,
|
| 302 |
+
"loss": 0.0316,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.011154345006485085,
|
| 307 |
+
"grad_norm": 0.2614981234073639,
|
| 308 |
+
"learning_rate": 0.00019197133427991436,
|
| 309 |
+
"loss": 0.0417,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011413748378728923,
|
| 314 |
+
"grad_norm": 0.44811561703681946,
|
| 315 |
+
"learning_rate": 0.00019144399391799043,
|
| 316 |
+
"loss": 0.036,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.011673151750972763,
|
| 321 |
+
"grad_norm": 0.4213508367538452,
|
| 322 |
+
"learning_rate": 0.00019090065350491626,
|
| 323 |
+
"loss": 0.0399,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.011932555123216601,
|
| 328 |
+
"grad_norm": 0.29146406054496765,
|
| 329 |
+
"learning_rate": 0.0001903414081095315,
|
| 330 |
+
"loss": 0.0376,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.012191958495460441,
|
| 335 |
+
"grad_norm": 0.2714293897151947,
|
| 336 |
+
"learning_rate": 0.00018976635558358722,
|
| 337 |
+
"loss": 0.0362,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012451361867704281,
|
| 342 |
+
"grad_norm": 0.3767367899417877,
|
| 343 |
+
"learning_rate": 0.00018917559654462474,
|
| 344 |
+
"loss": 0.0364,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01271076523994812,
|
| 349 |
+
"grad_norm": 0.36578992009162903,
|
| 350 |
+
"learning_rate": 0.00018856923435837022,
|
| 351 |
+
"loss": 0.0327,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.01297016861219196,
|
| 356 |
+
"grad_norm": 0.32976096868515015,
|
| 357 |
+
"learning_rate": 0.0001879473751206489,
|
| 358 |
+
"loss": 0.04,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.013229571984435798,
|
| 363 |
+
"grad_norm": 0.4037308990955353,
|
| 364 |
+
"learning_rate": 0.00018731012763882133,
|
| 365 |
+
"loss": 0.0365,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.013488975356679637,
|
| 370 |
+
"grad_norm": 0.3599701225757599,
|
| 371 |
+
"learning_rate": 0.00018665760341274505,
|
| 372 |
+
"loss": 0.0337,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.013748378728923476,
|
| 377 |
+
"grad_norm": 0.6167535185813904,
|
| 378 |
+
"learning_rate": 0.00018598991661526572,
|
| 379 |
+
"loss": 0.0384,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.014007782101167316,
|
| 384 |
+
"grad_norm": 0.44012153148651123,
|
| 385 |
+
"learning_rate": 0.00018530718407223974,
|
| 386 |
+
"loss": 0.0291,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.014267185473411154,
|
| 391 |
+
"grad_norm": 0.5593993663787842,
|
| 392 |
+
"learning_rate": 0.00018460952524209355,
|
| 393 |
+
"loss": 0.0328,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.014526588845654994,
|
| 398 |
+
"grad_norm": 0.3970232307910919,
|
| 399 |
+
"learning_rate": 0.00018389706219492147,
|
| 400 |
+
"loss": 0.0282,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.014785992217898832,
|
| 405 |
+
"grad_norm": 0.2354394942522049,
|
| 406 |
+
"learning_rate": 0.00018316991959112716,
|
| 407 |
+
"loss": 0.0317,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.015045395590142672,
|
| 412 |
+
"grad_norm": 0.35121485590934753,
|
| 413 |
+
"learning_rate": 0.00018242822465961176,
|
| 414 |
+
"loss": 0.0328,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.01530479896238651,
|
| 419 |
+
"grad_norm": 0.4026910066604614,
|
| 420 |
+
"learning_rate": 0.00018167210717551224,
|
| 421 |
+
"loss": 0.0346,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.01556420233463035,
|
| 426 |
+
"grad_norm": 0.36058488488197327,
|
| 427 |
+
"learning_rate": 0.00018090169943749476,
|
| 428 |
+
"loss": 0.0356,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.01582360570687419,
|
| 433 |
+
"grad_norm": 0.43329063057899475,
|
| 434 |
+
"learning_rate": 0.00018011713624460608,
|
| 435 |
+
"loss": 0.039,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.016083009079118027,
|
| 440 |
+
"grad_norm": 0.5267623662948608,
|
| 441 |
+
"learning_rate": 0.00017931855487268782,
|
| 442 |
+
"loss": 0.034,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.01634241245136187,
|
| 447 |
+
"grad_norm": 0.4230927526950836,
|
| 448 |
+
"learning_rate": 0.0001785060950503568,
|
| 449 |
+
"loss": 0.031,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.016601815823605707,
|
| 454 |
+
"grad_norm": 0.3721458613872528,
|
| 455 |
+
"learning_rate": 0.00017767989893455698,
|
| 456 |
+
"loss": 0.0306,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.016861219195849545,
|
| 461 |
+
"grad_norm": 0.4158923029899597,
|
| 462 |
+
"learning_rate": 0.00017684011108568592,
|
| 463 |
+
"loss": 0.0343,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.017120622568093387,
|
| 468 |
+
"grad_norm": 0.42805808782577515,
|
| 469 |
+
"learning_rate": 0.00017598687844230088,
|
| 470 |
+
"loss": 0.0348,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.017380025940337225,
|
| 475 |
+
"grad_norm": 0.2532889246940613,
|
| 476 |
+
"learning_rate": 0.00017512035029540885,
|
| 477 |
+
"loss": 0.0348,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.017639429312581063,
|
| 482 |
+
"grad_norm": 0.33485907316207886,
|
| 483 |
+
"learning_rate": 0.000174240678262345,
|
| 484 |
+
"loss": 0.0382,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.0178988326848249,
|
| 489 |
+
"grad_norm": 0.33811262249946594,
|
| 490 |
+
"learning_rate": 0.000173348016260244,
|
| 491 |
+
"loss": 0.0321,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.018158236057068743,
|
| 496 |
+
"grad_norm": 0.5319349765777588,
|
| 497 |
+
"learning_rate": 0.00017244252047910892,
|
| 498 |
+
"loss": 0.0369,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.01841763942931258,
|
| 503 |
+
"grad_norm": 0.1967012882232666,
|
| 504 |
+
"learning_rate": 0.00017152434935448256,
|
| 505 |
+
"loss": 0.0392,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.01867704280155642,
|
| 510 |
+
"grad_norm": 0.491212397813797,
|
| 511 |
+
"learning_rate": 0.0001705936635397259,
|
| 512 |
+
"loss": 0.034,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.018936446173800258,
|
| 517 |
+
"grad_norm": 0.3200204074382782,
|
| 518 |
+
"learning_rate": 0.00016965062587790823,
|
| 519 |
+
"loss": 0.0349,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.0191958495460441,
|
| 524 |
+
"grad_norm": 0.29090484976768494,
|
| 525 |
+
"learning_rate": 0.00016869540137331445,
|
| 526 |
+
"loss": 0.0302,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.019455252918287938,
|
| 531 |
+
"grad_norm": 0.4633236825466156,
|
| 532 |
+
"learning_rate": 0.00016772815716257412,
|
| 533 |
+
"loss": 0.0305,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.019714656290531776,
|
| 538 |
+
"grad_norm": 0.6030534505844116,
|
| 539 |
+
"learning_rate": 0.00016674906248541726,
|
| 540 |
+
"loss": 0.0331,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.019974059662775615,
|
| 545 |
+
"grad_norm": 0.28692400455474854,
|
| 546 |
+
"learning_rate": 0.00016575828865506245,
|
| 547 |
+
"loss": 0.0319,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.020233463035019456,
|
| 552 |
+
"grad_norm": 0.3799605667591095,
|
| 553 |
+
"learning_rate": 0.0001647560090282419,
|
| 554 |
+
"loss": 0.0316,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.020492866407263294,
|
| 559 |
+
"grad_norm": 0.529679536819458,
|
| 560 |
+
"learning_rate": 0.000163742398974869,
|
| 561 |
+
"loss": 0.0317,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.020752269779507133,
|
| 566 |
+
"grad_norm": 0.328056275844574,
|
| 567 |
+
"learning_rate": 0.0001627176358473537,
|
| 568 |
+
"loss": 0.0332,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.021011673151750974,
|
| 573 |
+
"grad_norm": 0.3303374648094177,
|
| 574 |
+
"learning_rate": 0.0001616818989495711,
|
| 575 |
+
"loss": 0.0323,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.021271076523994813,
|
| 580 |
+
"grad_norm": 0.23507635295391083,
|
| 581 |
+
"learning_rate": 0.00016063536950548826,
|
| 582 |
+
"loss": 0.0338,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.02153047989623865,
|
| 587 |
+
"grad_norm": 0.3870477080345154,
|
| 588 |
+
"learning_rate": 0.0001595782306274553,
|
| 589 |
+
"loss": 0.0326,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.02178988326848249,
|
| 594 |
+
"grad_norm": 0.37890198826789856,
|
| 595 |
+
"learning_rate": 0.00015851066728416618,
|
| 596 |
+
"loss": 0.0309,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.02204928664072633,
|
| 601 |
+
"grad_norm": 0.48460447788238525,
|
| 602 |
+
"learning_rate": 0.00015743286626829437,
|
| 603 |
+
"loss": 0.0351,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.02230869001297017,
|
| 608 |
+
"grad_norm": 0.38216733932495117,
|
| 609 |
+
"learning_rate": 0.00015634501616380967,
|
| 610 |
+
"loss": 0.0331,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.022568093385214007,
|
| 615 |
+
"grad_norm": 0.31668373942375183,
|
| 616 |
+
"learning_rate": 0.00015524730731298134,
|
| 617 |
+
"loss": 0.0306,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.022827496757457846,
|
| 622 |
+
"grad_norm": 0.5256275534629822,
|
| 623 |
+
"learning_rate": 0.0001541399317830738,
|
| 624 |
+
"loss": 0.0307,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.023086900129701687,
|
| 629 |
+
"grad_norm": 0.2295175939798355,
|
| 630 |
+
"learning_rate": 0.0001530230833327405,
|
| 631 |
+
"loss": 0.0297,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.023346303501945526,
|
| 636 |
+
"grad_norm": 0.35704338550567627,
|
| 637 |
+
"learning_rate": 0.00015189695737812152,
|
| 638 |
+
"loss": 0.0358,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.023605706874189364,
|
| 643 |
+
"grad_norm": 0.31458932161331177,
|
| 644 |
+
"learning_rate": 0.0001507617509586517,
|
| 645 |
+
"loss": 0.0278,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.023865110246433202,
|
| 650 |
+
"grad_norm": 0.47554951906204224,
|
| 651 |
+
"learning_rate": 0.00014961766270258422,
|
| 652 |
+
"loss": 0.0332,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.024124513618677044,
|
| 657 |
+
"grad_norm": 0.29959654808044434,
|
| 658 |
+
"learning_rate": 0.00014846489279223652,
|
| 659 |
+
"loss": 0.0268,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.024383916990920882,
|
| 664 |
+
"grad_norm": 0.31856444478034973,
|
| 665 |
+
"learning_rate": 0.0001473036429289641,
|
| 666 |
+
"loss": 0.028,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.02464332036316472,
|
| 671 |
+
"grad_norm": 0.23568253219127655,
|
| 672 |
+
"learning_rate": 0.0001461341162978688,
|
| 673 |
+
"loss": 0.0339,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.024902723735408562,
|
| 678 |
+
"grad_norm": 0.4032520055770874,
|
| 679 |
+
"learning_rate": 0.00014495651753224705,
|
| 680 |
+
"loss": 0.0291,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.0251621271076524,
|
| 685 |
+
"grad_norm": 0.36155375838279724,
|
| 686 |
+
"learning_rate": 0.00014377105267778518,
|
| 687 |
+
"loss": 0.0261,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.02542153047989624,
|
| 692 |
+
"grad_norm": 0.2985226511955261,
|
| 693 |
+
"learning_rate": 0.00014257792915650728,
|
| 694 |
+
"loss": 0.03,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.025680933852140077,
|
| 699 |
+
"grad_norm": 0.3420771658420563,
|
| 700 |
+
"learning_rate": 0.00014137735573048233,
|
| 701 |
+
"loss": 0.0318,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.02594033722438392,
|
| 706 |
+
"grad_norm": 0.19557547569274902,
|
| 707 |
+
"learning_rate": 0.00014016954246529696,
|
| 708 |
+
"loss": 0.0287,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.026199740596627757,
|
| 713 |
+
"grad_norm": 0.2249382734298706,
|
| 714 |
+
"learning_rate": 0.00013895470069330004,
|
| 715 |
+
"loss": 0.0258,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.026459143968871595,
|
| 720 |
+
"grad_norm": 0.5154671669006348,
|
| 721 |
+
"learning_rate": 0.00013773304297662559,
|
| 722 |
+
"loss": 0.0339,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.026718547341115433,
|
| 727 |
+
"grad_norm": 0.3469725251197815,
|
| 728 |
+
"learning_rate": 0.00013650478307000057,
|
| 729 |
+
"loss": 0.032,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.026977950713359275,
|
| 734 |
+
"grad_norm": 0.34428727626800537,
|
| 735 |
+
"learning_rate": 0.00013527013588334415,
|
| 736 |
+
"loss": 0.0317,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.027237354085603113,
|
| 741 |
+
"grad_norm": 0.2862760126590729,
|
| 742 |
+
"learning_rate": 0.00013402931744416433,
|
| 743 |
+
"loss": 0.03,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.02749675745784695,
|
| 748 |
+
"grad_norm": 0.5235270261764526,
|
| 749 |
+
"learning_rate": 0.00013278254485975976,
|
| 750 |
+
"loss": 0.0368,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.02775616083009079,
|
| 755 |
+
"grad_norm": 0.2167377918958664,
|
| 756 |
+
"learning_rate": 0.00013153003627923218,
|
| 757 |
+
"loss": 0.0306,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.02801556420233463,
|
| 762 |
+
"grad_norm": 0.29817643761634827,
|
| 763 |
+
"learning_rate": 0.00013027201085531634,
|
| 764 |
+
"loss": 0.0301,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.02827496757457847,
|
| 769 |
+
"grad_norm": 0.29515424370765686,
|
| 770 |
+
"learning_rate": 0.00012900868870603503,
|
| 771 |
+
"loss": 0.0249,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.028534370946822308,
|
| 776 |
+
"grad_norm": 0.3012550473213196,
|
| 777 |
+
"learning_rate": 0.00012774029087618446,
|
| 778 |
+
"loss": 0.0264,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.028793774319066146,
|
| 783 |
+
"grad_norm": 0.31644681096076965,
|
| 784 |
+
"learning_rate": 0.00012646703929865817,
|
| 785 |
+
"loss": 0.0316,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.029053177691309988,
|
| 790 |
+
"grad_norm": 0.37952420115470886,
|
| 791 |
+
"learning_rate": 0.00012518915675561483,
|
| 792 |
+
"loss": 0.0296,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.029312581063553826,
|
| 797 |
+
"grad_norm": 0.2594399154186249,
|
| 798 |
+
"learning_rate": 0.00012390686683949798,
|
| 799 |
+
"loss": 0.0321,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.029571984435797664,
|
| 804 |
+
"grad_norm": 0.34381750226020813,
|
| 805 |
+
"learning_rate": 0.00012262039391391404,
|
| 806 |
+
"loss": 0.0305,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.029831387808041506,
|
| 811 |
+
"grad_norm": 0.2528727948665619,
|
| 812 |
+
"learning_rate": 0.0001213299630743747,
|
| 813 |
+
"loss": 0.0303,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.030090791180285344,
|
| 818 |
+
"grad_norm": 0.32746660709381104,
|
| 819 |
+
"learning_rate": 0.00012003580010891213,
|
| 820 |
+
"loss": 0.0309,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.030350194552529183,
|
| 825 |
+
"grad_norm": 0.46516871452331543,
|
| 826 |
+
"learning_rate": 0.00011873813145857249,
|
| 827 |
+
"loss": 0.0288,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.03060959792477302,
|
| 832 |
+
"grad_norm": 0.21779906749725342,
|
| 833 |
+
"learning_rate": 0.00011743718417779517,
|
| 834 |
+
"loss": 0.0268,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.030869001297016863,
|
| 839 |
+
"grad_norm": 0.2870500087738037,
|
| 840 |
+
"learning_rate": 0.00011613318589468511,
|
| 841 |
+
"loss": 0.0284,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.0311284046692607,
|
| 846 |
+
"grad_norm": 0.223075732588768,
|
| 847 |
+
"learning_rate": 0.0001148263647711842,
|
| 848 |
+
"loss": 0.0283,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.03138780804150454,
|
| 853 |
+
"grad_norm": 0.3081727921962738,
|
| 854 |
+
"learning_rate": 0.0001135169494631497,
|
| 855 |
+
"loss": 0.0319,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.03164721141374838,
|
| 860 |
+
"grad_norm": 0.48067420721054077,
|
| 861 |
+
"learning_rate": 0.00011220516908034601,
|
| 862 |
+
"loss": 0.0286,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.031906614785992216,
|
| 867 |
+
"grad_norm": 0.34588056802749634,
|
| 868 |
+
"learning_rate": 0.00011089125314635726,
|
| 869 |
+
"loss": 0.0287,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.032166018158236054,
|
| 874 |
+
"grad_norm": 0.3428352475166321,
|
| 875 |
+
"learning_rate": 0.00010957543155842702,
|
| 876 |
+
"loss": 0.025,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.0324254215304799,
|
| 881 |
+
"grad_norm": 0.4223664700984955,
|
| 882 |
+
"learning_rate": 0.00010825793454723325,
|
| 883 |
+
"loss": 0.0304,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.03268482490272374,
|
| 888 |
+
"grad_norm": 0.21455545723438263,
|
| 889 |
+
"learning_rate": 0.00010693899263660441,
|
| 890 |
+
"loss": 0.0265,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.032944228274967575,
|
| 895 |
+
"grad_norm": 0.2936132252216339,
|
| 896 |
+
"learning_rate": 0.00010561883660318455,
|
| 897 |
+
"loss": 0.0298,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.033203631647211414,
|
| 902 |
+
"grad_norm": 0.3222610056400299,
|
| 903 |
+
"learning_rate": 0.00010429769743605407,
|
| 904 |
+
"loss": 0.0333,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.03346303501945525,
|
| 909 |
+
"grad_norm": 0.42949262261390686,
|
| 910 |
+
"learning_rate": 0.00010297580629631325,
|
| 911 |
+
"loss": 0.0336,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.03372243839169909,
|
| 916 |
+
"grad_norm": 0.3103349208831787,
|
| 917 |
+
"learning_rate": 0.00010165339447663587,
|
| 918 |
+
"loss": 0.0327,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.03398184176394293,
|
| 923 |
+
"grad_norm": 0.3449970483779907,
|
| 924 |
+
"learning_rate": 0.00010033069336079952,
|
| 925 |
+
"loss": 0.0293,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.034241245136186774,
|
| 930 |
+
"grad_norm": 0.3841015100479126,
|
| 931 |
+
"learning_rate": 9.900793438320037e-05,
|
| 932 |
+
"loss": 0.0305,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.03450064850843061,
|
| 937 |
+
"grad_norm": 0.3848475515842438,
|
| 938 |
+
"learning_rate": 9.768534898835862e-05,
|
| 939 |
+
"loss": 0.026,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.03476005188067445,
|
| 944 |
+
"grad_norm": 0.43429145216941833,
|
| 945 |
+
"learning_rate": 9.636316859042259e-05,
|
| 946 |
+
"loss": 0.0294,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.03501945525291829,
|
| 951 |
+
"grad_norm": 0.2181561291217804,
|
| 952 |
+
"learning_rate": 9.504162453267777e-05,
|
| 953 |
+
"loss": 0.0275,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.03527885862516213,
|
| 958 |
+
"grad_norm": 0.4230787754058838,
|
| 959 |
+
"learning_rate": 9.372094804706867e-05,
|
| 960 |
+
"loss": 0.0273,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.035538261997405965,
|
| 965 |
+
"grad_norm": 0.273333340883255,
|
| 966 |
+
"learning_rate": 9.24013702137397e-05,
|
| 967 |
+
"loss": 0.0246,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.0357976653696498,
|
| 972 |
+
"grad_norm": 0.21888947486877441,
|
| 973 |
+
"learning_rate": 9.108312192060298e-05,
|
| 974 |
+
"loss": 0.0223,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.03605706874189364,
|
| 979 |
+
"grad_norm": 0.22308865189552307,
|
| 980 |
+
"learning_rate": 8.97664338229395e-05,
|
| 981 |
+
"loss": 0.0249,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.03631647211413749,
|
| 986 |
+
"grad_norm": 0.2270708829164505,
|
| 987 |
+
"learning_rate": 8.845153630304139e-05,
|
| 988 |
+
"loss": 0.0272,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.036575875486381325,
|
| 993 |
+
"grad_norm": 0.3046322166919708,
|
| 994 |
+
"learning_rate": 8.713865942990141e-05,
|
| 995 |
+
"loss": 0.0225,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.03683527885862516,
|
| 1000 |
+
"grad_norm": 0.31552374362945557,
|
| 1001 |
+
"learning_rate": 8.582803291895758e-05,
|
| 1002 |
+
"loss": 0.0302,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.037094682230869,
|
| 1007 |
+
"grad_norm": 0.46200478076934814,
|
| 1008 |
+
"learning_rate": 8.451988609189987e-05,
|
| 1009 |
+
"loss": 0.0272,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.03735408560311284,
|
| 1014 |
+
"grad_norm": 0.22868406772613525,
|
| 1015 |
+
"learning_rate": 8.321444783654524e-05,
|
| 1016 |
+
"loss": 0.0267,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.03761348897535668,
|
| 1021 |
+
"grad_norm": 0.23030489683151245,
|
| 1022 |
+
"learning_rate": 8.191194656678904e-05,
|
| 1023 |
+
"loss": 0.0287,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.037872892347600516,
|
| 1028 |
+
"grad_norm": 0.19943729043006897,
|
| 1029 |
+
"learning_rate": 8.061261018263919e-05,
|
| 1030 |
+
"loss": 0.0249,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.03813229571984436,
|
| 1035 |
+
"grad_norm": 0.3236585557460785,
|
| 1036 |
+
"learning_rate": 7.931666603034033e-05,
|
| 1037 |
+
"loss": 0.0261,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.0383916990920882,
|
| 1042 |
+
"grad_norm": 0.27057945728302,
|
| 1043 |
+
"learning_rate": 7.80243408625947e-05,
|
| 1044 |
+
"loss": 0.0313,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.03865110246433204,
|
| 1049 |
+
"grad_norm": 0.40263959765434265,
|
| 1050 |
+
"learning_rate": 7.673586079888698e-05,
|
| 1051 |
+
"loss": 0.0255,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.038910505836575876,
|
| 1056 |
+
"grad_norm": 0.36453911662101746,
|
| 1057 |
+
"learning_rate": 7.54514512859201e-05,
|
| 1058 |
+
"loss": 0.0306,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.039169909208819714,
|
| 1063 |
+
"grad_norm": 0.2801981270313263,
|
| 1064 |
+
"learning_rate": 7.417133705816837e-05,
|
| 1065 |
+
"loss": 0.0272,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.03942931258106355,
|
| 1070 |
+
"grad_norm": 0.2771183252334595,
|
| 1071 |
+
"learning_rate": 7.289574209855559e-05,
|
| 1072 |
+
"loss": 0.0252,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.03968871595330739,
|
| 1077 |
+
"grad_norm": 0.1658083200454712,
|
| 1078 |
+
"learning_rate": 7.16248895992645e-05,
|
| 1079 |
+
"loss": 0.0278,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.03994811932555123,
|
| 1084 |
+
"grad_norm": 0.19812481105327606,
|
| 1085 |
+
"learning_rate": 7.035900192268464e-05,
|
| 1086 |
+
"loss": 0.028,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.040207522697795074,
|
| 1091 |
+
"grad_norm": 0.2751558721065521,
|
| 1092 |
+
"learning_rate": 6.909830056250527e-05,
|
| 1093 |
+
"loss": 0.0293,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.04046692607003891,
|
| 1098 |
+
"grad_norm": 0.24725764989852905,
|
| 1099 |
+
"learning_rate": 6.784300610496048e-05,
|
| 1100 |
+
"loss": 0.0245,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.04072632944228275,
|
| 1105 |
+
"grad_norm": 0.6854105591773987,
|
| 1106 |
+
"learning_rate": 6.65933381902329e-05,
|
| 1107 |
+
"loss": 0.0278,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.04098573281452659,
|
| 1112 |
+
"grad_norm": 0.19634288549423218,
|
| 1113 |
+
"learning_rate": 6.534951547402322e-05,
|
| 1114 |
+
"loss": 0.0251,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.04124513618677043,
|
| 1119 |
+
"grad_norm": 0.21054495871067047,
|
| 1120 |
+
"learning_rate": 6.411175558929152e-05,
|
| 1121 |
+
"loss": 0.0263,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.041504539559014265,
|
| 1126 |
+
"grad_norm": 0.2615554630756378,
|
| 1127 |
+
"learning_rate": 6.28802751081779e-05,
|
| 1128 |
+
"loss": 0.0268,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.041763942931258104,
|
| 1133 |
+
"grad_norm": 0.23431521654129028,
|
| 1134 |
+
"learning_rate": 6.165528950410884e-05,
|
| 1135 |
+
"loss": 0.0272,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.04202334630350195,
|
| 1140 |
+
"grad_norm": 0.14299079775810242,
|
| 1141 |
+
"learning_rate": 6.0437013114095195e-05,
|
| 1142 |
+
"loss": 0.0206,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.04228274967574579,
|
| 1147 |
+
"grad_norm": 0.32186359167099,
|
| 1148 |
+
"learning_rate": 5.922565910122967e-05,
|
| 1149 |
+
"loss": 0.0257,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.042542153047989625,
|
| 1154 |
+
"grad_norm": 0.3568614423274994,
|
| 1155 |
+
"learning_rate": 5.8021439417389444e-05,
|
| 1156 |
+
"loss": 0.0263,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.042801556420233464,
|
| 1161 |
+
"grad_norm": 0.2789517045021057,
|
| 1162 |
+
"learning_rate": 5.6824564766150726e-05,
|
| 1163 |
+
"loss": 0.0273,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.0430609597924773,
|
| 1168 |
+
"grad_norm": 0.23182226717472076,
|
| 1169 |
+
"learning_rate": 5.563524456592163e-05,
|
| 1170 |
+
"loss": 0.0216,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.04332036316472114,
|
| 1175 |
+
"grad_norm": 0.20413507521152496,
|
| 1176 |
+
"learning_rate": 5.4453686913300074e-05,
|
| 1177 |
+
"loss": 0.0281,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.04357976653696498,
|
| 1182 |
+
"grad_norm": 0.21678327023983002,
|
| 1183 |
+
"learning_rate": 5.328009854666303e-05,
|
| 1184 |
+
"loss": 0.0258,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.04383916990920882,
|
| 1189 |
+
"grad_norm": 0.25063127279281616,
|
| 1190 |
+
"learning_rate": 5.2114684809993044e-05,
|
| 1191 |
+
"loss": 0.0265,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.04409857328145266,
|
| 1196 |
+
"grad_norm": 0.17453815042972565,
|
| 1197 |
+
"learning_rate": 5.095764961694922e-05,
|
| 1198 |
+
"loss": 0.0256,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.0443579766536965,
|
| 1203 |
+
"grad_norm": 0.22323985397815704,
|
| 1204 |
+
"learning_rate": 4.980919541518796e-05,
|
| 1205 |
+
"loss": 0.025,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.04461738002594034,
|
| 1210 |
+
"grad_norm": 0.2994442880153656,
|
| 1211 |
+
"learning_rate": 4.866952315094088e-05,
|
| 1212 |
+
"loss": 0.0266,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.04487678339818418,
|
| 1217 |
+
"grad_norm": 0.27734553813934326,
|
| 1218 |
+
"learning_rate": 4.753883223385467e-05,
|
| 1219 |
+
"loss": 0.0247,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.045136186770428015,
|
| 1224 |
+
"grad_norm": 0.18703316152095795,
|
| 1225 |
+
"learning_rate": 4.6417320502100316e-05,
|
| 1226 |
+
"loss": 0.0232,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.04539559014267185,
|
| 1231 |
+
"grad_norm": 0.271628201007843,
|
| 1232 |
+
"learning_rate": 4.530518418775733e-05,
|
| 1233 |
+
"loss": 0.0275,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.04565499351491569,
|
| 1238 |
+
"grad_norm": 0.26739704608917236,
|
| 1239 |
+
"learning_rate": 4.4202617882478405e-05,
|
| 1240 |
+
"loss": 0.0273,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.045914396887159536,
|
| 1245 |
+
"grad_norm": 0.2327081710100174,
|
| 1246 |
+
"learning_rate": 4.310981450344189e-05,
|
| 1247 |
+
"loss": 0.0244,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.046173800259403375,
|
| 1252 |
+
"grad_norm": 0.23359940946102142,
|
| 1253 |
+
"learning_rate": 4.2026965259596666e-05,
|
| 1254 |
+
"loss": 0.0266,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.04643320363164721,
|
| 1259 |
+
"grad_norm": 0.1780378818511963,
|
| 1260 |
+
"learning_rate": 4.0954259618206295e-05,
|
| 1261 |
+
"loss": 0.0275,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.04669260700389105,
|
| 1266 |
+
"grad_norm": 0.14094606041908264,
|
| 1267 |
+
"learning_rate": 3.9891885271697496e-05,
|
| 1268 |
+
"loss": 0.0224,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.04695201037613489,
|
| 1273 |
+
"grad_norm": 0.21397313475608826,
|
| 1274 |
+
"learning_rate": 3.884002810481958e-05,
|
| 1275 |
+
"loss": 0.0262,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.04721141374837873,
|
| 1280 |
+
"grad_norm": 0.18339146673679352,
|
| 1281 |
+
"learning_rate": 3.779887216211995e-05,
|
| 1282 |
+
"loss": 0.0227,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.047470817120622566,
|
| 1287 |
+
"grad_norm": 0.3625165522098541,
|
| 1288 |
+
"learning_rate": 3.676859961574162e-05,
|
| 1289 |
+
"loss": 0.0261,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.047730220492866404,
|
| 1294 |
+
"grad_norm": 0.24323268234729767,
|
| 1295 |
+
"learning_rate": 3.574939073354838e-05,
|
| 1296 |
+
"loss": 0.0263,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.04798962386511025,
|
| 1301 |
+
"grad_norm": 0.16706861555576324,
|
| 1302 |
+
"learning_rate": 3.4741423847583134e-05,
|
| 1303 |
+
"loss": 0.0236,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.04824902723735409,
|
| 1308 |
+
"grad_norm": 0.25477734208106995,
|
| 1309 |
+
"learning_rate": 3.3744875322865034e-05,
|
| 1310 |
+
"loss": 0.0265,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.048508430609597926,
|
| 1315 |
+
"grad_norm": 0.23444534838199615,
|
| 1316 |
+
"learning_rate": 3.275991952653054e-05,
|
| 1317 |
+
"loss": 0.0255,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.048767833981841764,
|
| 1322 |
+
"grad_norm": 0.13936041295528412,
|
| 1323 |
+
"learning_rate": 3.178672879732435e-05,
|
| 1324 |
+
"loss": 0.0247,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.0490272373540856,
|
| 1329 |
+
"grad_norm": 0.27730414271354675,
|
| 1330 |
+
"learning_rate": 3.0825473415445074e-05,
|
| 1331 |
+
"loss": 0.0211,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.04928664072632944,
|
| 1336 |
+
"grad_norm": 0.44268760085105896,
|
| 1337 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 1338 |
+
"loss": 0.0293,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.04954604409857328,
|
| 1343 |
+
"grad_norm": 0.2908082902431488,
|
| 1344 |
+
"learning_rate": 2.8939439343332086e-05,
|
| 1345 |
+
"loss": 0.0283,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.049805447470817124,
|
| 1350 |
+
"grad_norm": 0.20642030239105225,
|
| 1351 |
+
"learning_rate": 2.8014990654450325e-05,
|
| 1352 |
+
"loss": 0.0237,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.05006485084306096,
|
| 1357 |
+
"grad_norm": 0.23467542231082916,
|
| 1358 |
+
"learning_rate": 2.7103137257858868e-05,
|
| 1359 |
+
"loss": 0.0257,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.0503242542153048,
|
| 1364 |
+
"grad_norm": 0.30216318368911743,
|
| 1365 |
+
"learning_rate": 2.6204038701499056e-05,
|
| 1366 |
+
"loss": 0.023,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.05058365758754864,
|
| 1371 |
+
"grad_norm": 0.2494220733642578,
|
| 1372 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 1373 |
+
"loss": 0.0248,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.05084306095979248,
|
| 1378 |
+
"grad_norm": 0.3801492154598236,
|
| 1379 |
+
"learning_rate": 2.4444733115075823e-05,
|
| 1380 |
+
"loss": 0.0208,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.051102464332036315,
|
| 1385 |
+
"grad_norm": 0.18340712785720825,
|
| 1386 |
+
"learning_rate": 2.3584833912548888e-05,
|
| 1387 |
+
"loss": 0.0265,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.051361867704280154,
|
| 1392 |
+
"grad_norm": 0.20898978412151337,
|
| 1393 |
+
"learning_rate": 2.2738305151465645e-05,
|
| 1394 |
+
"loss": 0.0242,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.05162127107652399,
|
| 1399 |
+
"grad_norm": 0.2393597811460495,
|
| 1400 |
+
"learning_rate": 2.190529494984782e-05,
|
| 1401 |
+
"loss": 0.0223,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.05188067444876784,
|
| 1406 |
+
"grad_norm": 0.16330353915691376,
|
| 1407 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 1408 |
+
"loss": 0.0207,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.052140077821011675,
|
| 1413 |
+
"grad_norm": 0.2321455329656601,
|
| 1414 |
+
"learning_rate": 2.0280410844810428e-05,
|
| 1415 |
+
"loss": 0.0208,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.052399481193255514,
|
| 1420 |
+
"grad_norm": 0.1408013105392456,
|
| 1421 |
+
"learning_rate": 1.9488821249060297e-05,
|
| 1422 |
+
"loss": 0.0248,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.05265888456549935,
|
| 1427 |
+
"grad_norm": 0.38080984354019165,
|
| 1428 |
+
"learning_rate": 1.871131877836879e-05,
|
| 1429 |
+
"loss": 0.0286,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.05291828793774319,
|
| 1434 |
+
"grad_norm": 0.17722366750240326,
|
| 1435 |
+
"learning_rate": 1.7948039473155554e-05,
|
| 1436 |
+
"loss": 0.0283,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.05317769130998703,
|
| 1441 |
+
"grad_norm": 0.2016279697418213,
|
| 1442 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 1443 |
+
"loss": 0.0258,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.053437094682230867,
|
| 1448 |
+
"grad_norm": 0.24826838076114655,
|
| 1449 |
+
"learning_rate": 1.646468205426377e-05,
|
| 1450 |
+
"loss": 0.0233,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.053696498054474705,
|
| 1455 |
+
"grad_norm": 0.21984995901584625,
|
| 1456 |
+
"learning_rate": 1.5744863485182537e-05,
|
| 1457 |
+
"loss": 0.0234,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.05395590142671855,
|
| 1462 |
+
"grad_norm": 0.16736479103565216,
|
| 1463 |
+
"learning_rate": 1.5039787125361326e-05,
|
| 1464 |
+
"loss": 0.0229,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.05421530479896239,
|
| 1469 |
+
"grad_norm": 0.1707315593957901,
|
| 1470 |
+
"learning_rate": 1.4349576342747462e-05,
|
| 1471 |
+
"loss": 0.02,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.054474708171206226,
|
| 1476 |
+
"grad_norm": 0.20376580953598022,
|
| 1477 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 1478 |
+
"loss": 0.0193,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.054734111543450065,
|
| 1483 |
+
"grad_norm": 0.18196424841880798,
|
| 1484 |
+
"learning_rate": 1.3014231954572287e-05,
|
| 1485 |
+
"loss": 0.0201,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.0549935149156939,
|
| 1490 |
+
"grad_norm": 0.2857169806957245,
|
| 1491 |
+
"learning_rate": 1.2369331995613665e-05,
|
| 1492 |
+
"loss": 0.0222,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.05525291828793774,
|
| 1497 |
+
"grad_norm": 0.23490458726882935,
|
| 1498 |
+
"learning_rate": 1.173976486618631e-05,
|
| 1499 |
+
"loss": 0.0224,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.05551232166018158,
|
| 1504 |
+
"grad_norm": 0.2817946672439575,
|
| 1505 |
+
"learning_rate": 1.1125640722308628e-05,
|
| 1506 |
+
"loss": 0.0227,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.055771725032425425,
|
| 1511 |
+
"grad_norm": 0.2497781217098236,
|
| 1512 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 1513 |
+
"loss": 0.0216,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.05603112840466926,
|
| 1518 |
+
"grad_norm": 0.2638106048107147,
|
| 1519 |
+
"learning_rate": 9.944148486097793e-06,
|
| 1520 |
+
"loss": 0.0236,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.0562905317769131,
|
| 1525 |
+
"grad_norm": 0.11962006986141205,
|
| 1526 |
+
"learning_rate": 9.376987120695545e-06,
|
| 1527 |
+
"loss": 0.0187,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.05654993514915694,
|
| 1532 |
+
"grad_norm": 0.3043888211250305,
|
| 1533 |
+
"learning_rate": 8.825682158533554e-06,
|
| 1534 |
+
"loss": 0.0254,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.05680933852140078,
|
| 1539 |
+
"grad_norm": 0.18844349682331085,
|
| 1540 |
+
"learning_rate": 8.290330062017016e-06,
|
| 1541 |
+
"loss": 0.0214,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.057068741893644616,
|
| 1546 |
+
"grad_norm": 0.320204496383667,
|
| 1547 |
+
"learning_rate": 7.771024502261526e-06,
|
| 1548 |
+
"loss": 0.0239,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.057328145265888454,
|
| 1553 |
+
"grad_norm": 0.16253778338432312,
|
| 1554 |
+
"learning_rate": 7.267856342703461e-06,
|
| 1555 |
+
"loss": 0.0207,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.05758754863813229,
|
| 1560 |
+
"grad_norm": 0.1236085444688797,
|
| 1561 |
+
"learning_rate": 6.780913623201346e-06,
|
| 1562 |
+
"loss": 0.0194,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.05784695201037614,
|
| 1567 |
+
"grad_norm": 0.17225727438926697,
|
| 1568 |
+
"learning_rate": 6.310281544631546e-06,
|
| 1569 |
+
"loss": 0.0229,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.058106355382619976,
|
| 1574 |
+
"grad_norm": 0.15956400334835052,
|
| 1575 |
+
"learning_rate": 5.856042453980526e-06,
|
| 1576 |
+
"loss": 0.0213,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.058365758754863814,
|
| 1581 |
+
"grad_norm": 0.14553219079971313,
|
| 1582 |
+
"learning_rate": 5.418275829936537e-06,
|
| 1583 |
+
"loss": 0.0267,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.05862516212710765,
|
| 1588 |
+
"grad_norm": 0.1686364859342575,
|
| 1589 |
+
"learning_rate": 4.997058268983135e-06,
|
| 1590 |
+
"loss": 0.0218,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.05888456549935149,
|
| 1595 |
+
"grad_norm": 0.2441764622926712,
|
| 1596 |
+
"learning_rate": 4.592463471997022e-06,
|
| 1597 |
+
"loss": 0.0232,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.05914396887159533,
|
| 1602 |
+
"grad_norm": 0.3006925880908966,
|
| 1603 |
+
"learning_rate": 4.204562231352516e-06,
|
| 1604 |
+
"loss": 0.027,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.05940337224383917,
|
| 1609 |
+
"grad_norm": 0.23077550530433655,
|
| 1610 |
+
"learning_rate": 3.83342241853496e-06,
|
| 1611 |
+
"loss": 0.0232,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.05966277561608301,
|
| 1616 |
+
"grad_norm": 0.32399365305900574,
|
| 1617 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 1618 |
+
"loss": 0.0211,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.05992217898832685,
|
| 1623 |
+
"grad_norm": 0.2478347271680832,
|
| 1624 |
+
"learning_rate": 3.1416838871368924e-06,
|
| 1625 |
+
"loss": 0.027,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.06018158236057069,
|
| 1630 |
+
"grad_norm": 0.17069502174854279,
|
| 1631 |
+
"learning_rate": 2.821206202769899e-06,
|
| 1632 |
+
"loss": 0.023,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.06044098573281453,
|
| 1637 |
+
"grad_norm": 0.1713675558567047,
|
| 1638 |
+
"learning_rate": 2.5177319934794e-06,
|
| 1639 |
+
"loss": 0.0275,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.060700389105058365,
|
| 1644 |
+
"grad_norm": 0.13431312143802643,
|
| 1645 |
+
"learning_rate": 2.2313143584648423e-06,
|
| 1646 |
+
"loss": 0.0209,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.0609597924773022,
|
| 1651 |
+
"grad_norm": 0.20045480132102966,
|
| 1652 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 1653 |
+
"loss": 0.026,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.06121919584954604,
|
| 1658 |
+
"grad_norm": 0.1736753284931183,
|
| 1659 |
+
"learning_rate": 1.7098462772596302e-06,
|
| 1660 |
+
"loss": 0.0224,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.06147859922178988,
|
| 1665 |
+
"grad_norm": 0.20570042729377747,
|
| 1666 |
+
"learning_rate": 1.4748870728839347e-06,
|
| 1667 |
+
"loss": 0.0213,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.061738002594033725,
|
| 1672 |
+
"grad_norm": 0.15525294840335846,
|
| 1673 |
+
"learning_rate": 1.2571669104494256e-06,
|
| 1674 |
+
"loss": 0.0215,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.06199740596627756,
|
| 1679 |
+
"grad_norm": 0.16905346512794495,
|
| 1680 |
+
"learning_rate": 1.0567238846803996e-06,
|
| 1681 |
+
"loss": 0.0231,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.0622568093385214,
|
| 1686 |
+
"grad_norm": 0.18170209228992462,
|
| 1687 |
+
"learning_rate": 8.735930673024806e-07,
|
| 1688 |
+
"loss": 0.0233,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.06251621271076524,
|
| 1693 |
+
"grad_norm": 0.19480860233306885,
|
| 1694 |
+
"learning_rate": 7.078065009060941e-07,
|
| 1695 |
+
"loss": 0.0215,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.06277561608300908,
|
| 1700 |
+
"grad_norm": 0.1651337891817093,
|
| 1701 |
+
"learning_rate": 5.593931933399854e-07,
|
| 1702 |
+
"loss": 0.0224,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.06303501945525292,
|
| 1707 |
+
"grad_norm": 0.1658225804567337,
|
| 1708 |
+
"learning_rate": 4.2837911263562404e-07,
|
| 1709 |
+
"loss": 0.024,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.06329442282749675,
|
| 1714 |
+
"grad_norm": 0.2529785633087158,
|
| 1715 |
+
"learning_rate": 3.1478718246357173e-07,
|
| 1716 |
+
"loss": 0.0275,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.06355382619974059,
|
| 1721 |
+
"grad_norm": 0.14123444259166718,
|
| 1722 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 1723 |
+
"loss": 0.0212,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.06381322957198443,
|
| 1728 |
+
"grad_norm": 0.14571131765842438,
|
| 1729 |
+
"learning_rate": 1.3994622306173765e-07,
|
| 1730 |
+
"loss": 0.0225,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.06407263294422827,
|
| 1735 |
+
"grad_norm": 0.20619624853134155,
|
| 1736 |
+
"learning_rate": 7.872778593728258e-08,
|
| 1737 |
+
"loss": 0.0214,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.06433203631647211,
|
| 1742 |
+
"grad_norm": 0.19361430406570435,
|
| 1743 |
+
"learning_rate": 3.499267820307184e-08,
|
| 1744 |
+
"loss": 0.0233,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.06459143968871596,
|
| 1749 |
+
"grad_norm": 0.20903588831424713,
|
| 1750 |
+
"learning_rate": 8.748552236603757e-09,
|
| 1751 |
+
"loss": 0.0234,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.0648508430609598,
|
| 1756 |
+
"grad_norm": 0.17228850722312927,
|
| 1757 |
+
"learning_rate": 0.0,
|
| 1758 |
+
"loss": 0.0261,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
}
|
| 1761 |
+
],
|
| 1762 |
+
"logging_steps": 10,
|
| 1763 |
+
"max_steps": 2500,
|
| 1764 |
+
"num_input_tokens_seen": 0,
|
| 1765 |
+
"num_train_epochs": 1,
|
| 1766 |
+
"save_steps": 500,
|
| 1767 |
+
"stateful_callbacks": {
|
| 1768 |
+
"TrainerControl": {
|
| 1769 |
+
"args": {
|
| 1770 |
+
"should_epoch_stop": false,
|
| 1771 |
+
"should_evaluate": false,
|
| 1772 |
+
"should_log": false,
|
| 1773 |
+
"should_save": true,
|
| 1774 |
+
"should_training_stop": true
|
| 1775 |
+
},
|
| 1776 |
+
"attributes": {}
|
| 1777 |
+
}
|
| 1778 |
+
},
|
| 1779 |
+
"total_flos": 3.2864989085696e+17,
|
| 1780 |
+
"train_batch_size": 32,
|
| 1781 |
+
"trial_name": null,
|
| 1782 |
+
"trial_params": null
|
| 1783 |
+
}
|
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/adleboy/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
|
| 3 |
+
"action_dim": 32,
|
| 4 |
+
"action_head_cfg": {
|
| 5 |
+
"action_dim": 32,
|
| 6 |
+
"action_horizon": 16,
|
| 7 |
+
"add_pos_embed": true,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"dropout": 0.2,
|
| 11 |
+
"final_dropout": true,
|
| 12 |
+
"interleave_self_attention": true,
|
| 13 |
+
"norm_type": "ada_norm",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_layers": 16,
|
| 16 |
+
"output_dim": 1024,
|
| 17 |
+
"positional_embeddings": null
|
| 18 |
+
},
|
| 19 |
+
"freeze_decode_layer": false,
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"load_pretrained_det_decode_layer_path": null,
|
| 23 |
+
"max_action_dim": 32,
|
| 24 |
+
"max_state_dim": 64,
|
| 25 |
+
"model_dtype": "float32",
|
| 26 |
+
"noise_beta_alpha": 1.5,
|
| 27 |
+
"noise_beta_beta": 1.0,
|
| 28 |
+
"noise_s": 0.999,
|
| 29 |
+
"num_inference_timesteps": 16,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true
|
| 33 |
+
},
|
| 34 |
+
"action_horizon": 16,
|
| 35 |
+
"architectures": [
|
| 36 |
+
"GR00T_N1"
|
| 37 |
+
],
|
| 38 |
+
"attn_implementation": null,
|
| 39 |
+
"backbone_cfg": {
|
| 40 |
+
"allow_reshape_visual": true,
|
| 41 |
+
"load_pretrained_det_eagle_path": null,
|
| 42 |
+
"model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 43 |
+
"processor_cfg": {
|
| 44 |
+
"max_input_tiles": 1,
|
| 45 |
+
"model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
|
| 46 |
+
"model_spec": {
|
| 47 |
+
"num_image_token": 64,
|
| 48 |
+
"template": "qwen2-chat"
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"projector_dim": 2048,
|
| 52 |
+
"remove_llm": false,
|
| 53 |
+
"reproject_vision": false,
|
| 54 |
+
"scale_image_resolution": 1,
|
| 55 |
+
"select_layer": 12,
|
| 56 |
+
"tune_llm": false,
|
| 57 |
+
"tune_visual": true
|
| 58 |
+
},
|
| 59 |
+
"compute_dtype": "bfloat16",
|
| 60 |
+
"hidden_size": 1536,
|
| 61 |
+
"model_dtype": "float32",
|
| 62 |
+
"model_type": "gr00t_n1",
|
| 63 |
+
"torch_dtype": "float32",
|
| 64 |
+
"transformers_version": "4.45.2"
|
| 65 |
+
}
|
checkpoint-500/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"single_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
122.080078125,
|
| 8 |
+
198.193359375,
|
| 9 |
+
182.28515625,
|
| 10 |
+
114.43359375,
|
| 11 |
+
262.177734375
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-95.9765625,
|
| 15 |
+
-179.912109375,
|
| 16 |
+
-258.486328125,
|
| 17 |
+
-100.01953125,
|
| 18 |
+
-179.912109375
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
9.608419418334961,
|
| 22 |
+
114.65914154052734,
|
| 23 |
+
102.69532775878906,
|
| 24 |
+
63.54849624633789,
|
| 25 |
+
-3.96468186378479
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
30.130109786987305,
|
| 29 |
+
52.885677337646484,
|
| 30 |
+
68.62229919433594,
|
| 31 |
+
26.573131561279297,
|
| 32 |
+
62.51667785644531
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-55.1953125,
|
| 36 |
+
12.196582031250038,
|
| 37 |
+
-228.779296875,
|
| 38 |
+
-40.78125,
|
| 39 |
+
-152.40234375
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
87.626953125,
|
| 43 |
+
192.041015625,
|
| 44 |
+
179.47265625,
|
| 45 |
+
108.28125,
|
| 46 |
+
155.0390625
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
105.29850769042969
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
-2.7297544479370117
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
11.653524398803711
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
17.93401336669922
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
-1.4121800661087036
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
93.88059997558594
|
| 67 |
+
]
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"action": {
|
| 71 |
+
"single_arm": {
|
| 72 |
+
"max": [
|
| 73 |
+
123.046875,
|
| 74 |
+
202.763671875,
|
| 75 |
+
190.458984375,
|
| 76 |
+
117.0703125,
|
| 77 |
+
267.802734375
|
| 78 |
+
],
|
| 79 |
+
"min": [
|
| 80 |
+
-97.646484375,
|
| 81 |
+
-179.912109375,
|
| 82 |
+
-269.6484375,
|
| 83 |
+
-102.65625,
|
| 84 |
+
-270.0
|
| 85 |
+
],
|
| 86 |
+
"mean": [
|
| 87 |
+
9.716768264770508,
|
| 88 |
+
117.07723999023438,
|
| 89 |
+
101.3852767944336,
|
| 90 |
+
63.94012451171875,
|
| 91 |
+
-4.292983531951904
|
| 92 |
+
],
|
| 93 |
+
"std": [
|
| 94 |
+
30.517000198364258,
|
| 95 |
+
52.163082122802734,
|
| 96 |
+
69.69375610351562,
|
| 97 |
+
26.988319396972656,
|
| 98 |
+
63.348819732666016
|
| 99 |
+
],
|
| 100 |
+
"q01": [
|
| 101 |
+
-55.8984375,
|
| 102 |
+
16.435546875,
|
| 103 |
+
-230.888671875,
|
| 104 |
+
-41.66015625,
|
| 105 |
+
-153.896484375
|
| 106 |
+
],
|
| 107 |
+
"q99": [
|
| 108 |
+
88.505859375,
|
| 109 |
+
195.64453125,
|
| 110 |
+
182.900390625,
|
| 111 |
+
109.599609375,
|
| 112 |
+
155.7421875
|
| 113 |
+
]
|
| 114 |
+
},
|
| 115 |
+
"gripper": {
|
| 116 |
+
"max": [
|
| 117 |
+
109.84339904785156
|
| 118 |
+
],
|
| 119 |
+
"min": [
|
| 120 |
+
-7.955596446990967
|
| 121 |
+
],
|
| 122 |
+
"mean": [
|
| 123 |
+
9.987146377563477
|
| 124 |
+
],
|
| 125 |
+
"std": [
|
| 126 |
+
18.02056121826172
|
| 127 |
+
],
|
| 128 |
+
"q01": [
|
| 129 |
+
-2.5742573738098145
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
96.20721435546875
|
| 133 |
+
]
|
| 134 |
+
}
|
| 135 |
+
}
|
| 136 |
+
},
|
| 137 |
+
"modalities": {
|
| 138 |
+
"video": {
|
| 139 |
+
"images0": {
|
| 140 |
+
"resolution": [
|
| 141 |
+
320,
|
| 142 |
+
240
|
| 143 |
+
],
|
| 144 |
+
"channels": 3,
|
| 145 |
+
"fps": 30.0
|
| 146 |
+
},
|
| 147 |
+
"images1": {
|
| 148 |
+
"resolution": [
|
| 149 |
+
320,
|
| 150 |
+
240
|
| 151 |
+
],
|
| 152 |
+
"channels": 3,
|
| 153 |
+
"fps": 30.0
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"state": {
|
| 157 |
+
"single_arm": {
|
| 158 |
+
"absolute": true,
|
| 159 |
+
"rotation_type": null,
|
| 160 |
+
"shape": [
|
| 161 |
+
5
|
| 162 |
+
],
|
| 163 |
+
"continuous": true
|
| 164 |
+
},
|
| 165 |
+
"gripper": {
|
| 166 |
+
"absolute": true,
|
| 167 |
+
"rotation_type": null,
|
| 168 |
+
"shape": [
|
| 169 |
+
1
|
| 170 |
+
],
|
| 171 |
+
"continuous": true
|
| 172 |
+
}
|
| 173 |
+
},
|
| 174 |
+
"action": {
|
| 175 |
+
"single_arm": {
|
| 176 |
+
"absolute": true,
|
| 177 |
+
"rotation_type": null,
|
| 178 |
+
"shape": [
|
| 179 |
+
5
|
| 180 |
+
],
|
| 181 |
+
"continuous": true
|
| 182 |
+
},
|
| 183 |
+
"gripper": {
|
| 184 |
+
"absolute": true,
|
| 185 |
+
"rotation_type": null,
|
| 186 |
+
"shape": [
|
| 187 |
+
1
|
| 188 |
+
],
|
| 189 |
+
"continuous": true
|
| 190 |
+
}
|
| 191 |
+
}
|
| 192 |
+
},
|
| 193 |
+
"embodiment_tag": "new_embodiment"
|
| 194 |
+
}
|
| 195 |
+
}
|
checkpoint-500/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:876131bbccf9da0427fb352e58eb5a30e9ccb84799950389871b6d9aa41dc85d
|
| 3 |
+
size 4938446392
|
checkpoint-500/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:234a7262245752938ee295c24b845100a9a4f22df98b2a717b012e09c6e77bd2
|
| 3 |
+
size 3821736024
|
checkpoint-500/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,809 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 8760067008
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 7 |
+
"action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 8 |
+
"action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 9 |
+
"action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 10 |
+
"action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
|
| 11 |
+
"action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
|
| 12 |
+
"action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
|
| 13 |
+
"action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
|
| 14 |
+
"action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
|
| 15 |
+
"action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
|
| 16 |
+
"action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
|
| 17 |
+
"action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
|
| 18 |
+
"action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
|
| 19 |
+
"action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
|
| 20 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
|
| 21 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
|
| 22 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
|
| 23 |
+
"action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
|
| 24 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 25 |
+
"action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 26 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 27 |
+
"action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 29 |
+
"action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 30 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 31 |
+
"action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 32 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 33 |
+
"action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 35 |
+
"action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 37 |
+
"action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 38 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 39 |
+
"action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 41 |
+
"action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 43 |
+
"action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 44 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 45 |
+
"action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 46 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 47 |
+
"action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 49 |
+
"action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 50 |
+
"action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 51 |
+
"action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 53 |
+
"action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 55 |
+
"action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 56 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 57 |
+
"action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 59 |
+
"action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 60 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 61 |
+
"action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 63 |
+
"action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 65 |
+
"action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 66 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 67 |
+
"action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 68 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 69 |
+
"action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 70 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 71 |
+
"action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 73 |
+
"action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 74 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 75 |
+
"action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 77 |
+
"action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 78 |
+
"action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 79 |
+
"action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 81 |
+
"action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 83 |
+
"action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 85 |
+
"action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 87 |
+
"action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 89 |
+
"action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 91 |
+
"action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 92 |
+
"action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 93 |
+
"action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 95 |
+
"action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 97 |
+
"action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 99 |
+
"action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 101 |
+
"action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 103 |
+
"action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 105 |
+
"action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 107 |
+
"action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 109 |
+
"action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 111 |
+
"action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 113 |
+
"action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 115 |
+
"action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 117 |
+
"action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 119 |
+
"action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 121 |
+
"action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 123 |
+
"action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 125 |
+
"action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 127 |
+
"action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 129 |
+
"action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 131 |
+
"action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 133 |
+
"action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 135 |
+
"action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 137 |
+
"action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 139 |
+
"action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 141 |
+
"action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 143 |
+
"action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 145 |
+
"action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 147 |
+
"action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 149 |
+
"action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 151 |
+
"action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 153 |
+
"action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 155 |
+
"action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 157 |
+
"action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 159 |
+
"action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 161 |
+
"action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 163 |
+
"action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 165 |
+
"action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 167 |
+
"action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 171 |
+
"action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 173 |
+
"action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 175 |
+
"action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 177 |
+
"action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 179 |
+
"action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 183 |
+
"action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 187 |
+
"action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 189 |
+
"action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 191 |
+
"action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 195 |
+
"action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 197 |
+
"action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 201 |
+
"action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 203 |
+
"action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 207 |
+
"action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 209 |
+
"action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 211 |
+
"action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 215 |
+
"action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 219 |
+
"action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 221 |
+
"action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 223 |
+
"action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 225 |
+
"action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 227 |
+
"action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 231 |
+
"action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 233 |
+
"action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
|
| 235 |
+
"action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
|
| 237 |
+
"action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
|
| 239 |
+
"action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
|
| 243 |
+
"action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
|
| 245 |
+
"action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
|
| 247 |
+
"action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
|
| 250 |
+
"action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
|
| 251 |
+
"action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
|
| 252 |
+
"action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
|
| 253 |
+
"backbone.linear.bias": "model-00002-of-00002.safetensors",
|
| 254 |
+
"backbone.linear.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
|
| 370 |
+
"backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 381 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 393 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 395 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 399 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 403 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 655 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 715 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 727 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 739 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 751 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 763 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 775 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 787 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 799 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
| 808 |
+
}
|
| 809 |
+
}
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bd12710d398c3bb7ddd60d44530f78bb8f464b9c000de8dcb9faac5e4875941
|
| 3 |
+
size 10272357262
|
checkpoint-500/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3e48d6d3ef33f7d09024662fcc18bef6a631322727a80f1992c34ed9f2ddcde
|
| 3 |
+
size 14512
|
checkpoint-500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaaad7be2fc045747f23eeb0573399ccbe0657cd494a52daf23552b353b0b120
|
| 3 |
+
size 14512
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:869f30213a64fa0bf2df67a562f11845a1ac9ff11f06397142f7ec66319cba38
|
| 3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.01297016861219196,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00025940337224383917,
|
| 13 |
+
"grad_norm": 13.49365234375,
|
| 14 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 15 |
+
"loss": 1.5584,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0005188067444876783,
|
| 20 |
+
"grad_norm": 2.6006040573120117,
|
| 21 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 22 |
+
"loss": 0.7111,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0007782101167315176,
|
| 27 |
+
"grad_norm": 4.435553073883057,
|
| 28 |
+
"learning_rate": 4.8e-05,
|
| 29 |
+
"loss": 0.3076,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0010376134889753567,
|
| 34 |
+
"grad_norm": 1.1146177053451538,
|
| 35 |
+
"learning_rate": 6.400000000000001e-05,
|
| 36 |
+
"loss": 0.1826,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0012970168612191958,
|
| 41 |
+
"grad_norm": 0.8707008957862854,
|
| 42 |
+
"learning_rate": 8e-05,
|
| 43 |
+
"loss": 0.1341,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0015564202334630351,
|
| 48 |
+
"grad_norm": 1.7411352396011353,
|
| 49 |
+
"learning_rate": 9.6e-05,
|
| 50 |
+
"loss": 0.1144,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0018158236057068742,
|
| 55 |
+
"grad_norm": 0.9691908955574036,
|
| 56 |
+
"learning_rate": 0.00011200000000000001,
|
| 57 |
+
"loss": 0.0831,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0020752269779507134,
|
| 62 |
+
"grad_norm": 1.0398532152175903,
|
| 63 |
+
"learning_rate": 0.00012800000000000002,
|
| 64 |
+
"loss": 0.0801,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0023346303501945525,
|
| 69 |
+
"grad_norm": 0.5252112746238708,
|
| 70 |
+
"learning_rate": 0.000144,
|
| 71 |
+
"loss": 0.081,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0025940337224383916,
|
| 76 |
+
"grad_norm": 0.6552278995513916,
|
| 77 |
+
"learning_rate": 0.00016,
|
| 78 |
+
"loss": 0.0821,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0028534370946822307,
|
| 83 |
+
"grad_norm": 0.6302046775817871,
|
| 84 |
+
"learning_rate": 0.00017600000000000002,
|
| 85 |
+
"loss": 0.0749,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0031128404669260703,
|
| 90 |
+
"grad_norm": 0.7439587712287903,
|
| 91 |
+
"learning_rate": 0.000192,
|
| 92 |
+
"loss": 0.0647,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0033722438391699094,
|
| 97 |
+
"grad_norm": 6.8584771156311035,
|
| 98 |
+
"learning_rate": 0.0001999978128380225,
|
| 99 |
+
"loss": 0.0726,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0036316472114137485,
|
| 104 |
+
"grad_norm": 2.014613389968872,
|
| 105 |
+
"learning_rate": 0.0001999803161162393,
|
| 106 |
+
"loss": 0.0936,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0038910505836575876,
|
| 111 |
+
"grad_norm": 1.3758050203323364,
|
| 112 |
+
"learning_rate": 0.00019994532573409262,
|
| 113 |
+
"loss": 0.1089,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.004150453955901427,
|
| 118 |
+
"grad_norm": 1.3027769327163696,
|
| 119 |
+
"learning_rate": 0.00019989284781388617,
|
| 120 |
+
"loss": 0.0772,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.004409857328145266,
|
| 125 |
+
"grad_norm": 1.021938443183899,
|
| 126 |
+
"learning_rate": 0.00019982289153773646,
|
| 127 |
+
"loss": 0.0695,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.004669260700389105,
|
| 132 |
+
"grad_norm": 0.8069638609886169,
|
| 133 |
+
"learning_rate": 0.00019973546914596623,
|
| 134 |
+
"loss": 0.0624,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.004928664072632944,
|
| 139 |
+
"grad_norm": 0.5198134779930115,
|
| 140 |
+
"learning_rate": 0.00019963059593496268,
|
| 141 |
+
"loss": 0.0481,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.005188067444876783,
|
| 146 |
+
"grad_norm": 0.39965012669563293,
|
| 147 |
+
"learning_rate": 0.00019950829025450114,
|
| 148 |
+
"loss": 0.0493,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.005447470817120622,
|
| 153 |
+
"grad_norm": 0.8152652978897095,
|
| 154 |
+
"learning_rate": 0.0001993685735045343,
|
| 155 |
+
"loss": 0.0477,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.005706874189364461,
|
| 160 |
+
"grad_norm": 0.7083427309989929,
|
| 161 |
+
"learning_rate": 0.0001992114701314478,
|
| 162 |
+
"loss": 0.0501,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0059662775616083005,
|
| 167 |
+
"grad_norm": 0.690096914768219,
|
| 168 |
+
"learning_rate": 0.000199037007623783,
|
| 169 |
+
"loss": 0.0509,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0062256809338521405,
|
| 174 |
+
"grad_norm": 0.871699869632721,
|
| 175 |
+
"learning_rate": 0.00019884521650742715,
|
| 176 |
+
"loss": 0.0464,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.00648508430609598,
|
| 181 |
+
"grad_norm": 0.6445639133453369,
|
| 182 |
+
"learning_rate": 0.00019863613034027224,
|
| 183 |
+
"loss": 0.0462,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.006744487678339819,
|
| 188 |
+
"grad_norm": 0.4920782148838043,
|
| 189 |
+
"learning_rate": 0.0001984097857063434,
|
| 190 |
+
"loss": 0.0425,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.007003891050583658,
|
| 195 |
+
"grad_norm": 0.8624788522720337,
|
| 196 |
+
"learning_rate": 0.0001981662222093976,
|
| 197 |
+
"loss": 0.0471,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.007263294422827497,
|
| 202 |
+
"grad_norm": 0.5704030990600586,
|
| 203 |
+
"learning_rate": 0.00019790548246599447,
|
| 204 |
+
"loss": 0.0571,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.007522697795071336,
|
| 209 |
+
"grad_norm": 0.569247841835022,
|
| 210 |
+
"learning_rate": 0.00019762761209803927,
|
| 211 |
+
"loss": 0.0531,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.007782101167315175,
|
| 216 |
+
"grad_norm": 0.7414583563804626,
|
| 217 |
+
"learning_rate": 0.0001973326597248006,
|
| 218 |
+
"loss": 0.0455,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.008041504539559013,
|
| 223 |
+
"grad_norm": 0.42905348539352417,
|
| 224 |
+
"learning_rate": 0.00019702067695440332,
|
| 225 |
+
"loss": 0.0542,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.008300907911802853,
|
| 230 |
+
"grad_norm": 0.6132651567459106,
|
| 231 |
+
"learning_rate": 0.00019669171837479873,
|
| 232 |
+
"loss": 0.0439,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.008560311284046693,
|
| 237 |
+
"grad_norm": 0.44733384251594543,
|
| 238 |
+
"learning_rate": 0.00019634584154421317,
|
| 239 |
+
"loss": 0.0429,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.008819714656290532,
|
| 244 |
+
"grad_norm": 0.516659677028656,
|
| 245 |
+
"learning_rate": 0.00019598310698107702,
|
| 246 |
+
"loss": 0.0407,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.009079118028534372,
|
| 251 |
+
"grad_norm": 0.2340136468410492,
|
| 252 |
+
"learning_rate": 0.00019560357815343577,
|
| 253 |
+
"loss": 0.036,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.00933852140077821,
|
| 258 |
+
"grad_norm": 0.6629723906517029,
|
| 259 |
+
"learning_rate": 0.00019520732146784491,
|
| 260 |
+
"loss": 0.041,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.00959792477302205,
|
| 265 |
+
"grad_norm": 0.3777199387550354,
|
| 266 |
+
"learning_rate": 0.0001947944062577507,
|
| 267 |
+
"loss": 0.0414,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.009857328145265888,
|
| 272 |
+
"grad_norm": 0.44298338890075684,
|
| 273 |
+
"learning_rate": 0.00019436490477135878,
|
| 274 |
+
"loss": 0.0371,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.010116731517509728,
|
| 279 |
+
"grad_norm": 0.4530090093612671,
|
| 280 |
+
"learning_rate": 0.00019391889215899299,
|
| 281 |
+
"loss": 0.037,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.010376134889753566,
|
| 286 |
+
"grad_norm": 0.36142367124557495,
|
| 287 |
+
"learning_rate": 0.0001934564464599461,
|
| 288 |
+
"loss": 0.0387,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.010635538261997406,
|
| 293 |
+
"grad_norm": 0.36559927463531494,
|
| 294 |
+
"learning_rate": 0.00019297764858882514,
|
| 295 |
+
"loss": 0.0386,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.010894941634241245,
|
| 300 |
+
"grad_norm": 0.47660204768180847,
|
| 301 |
+
"learning_rate": 0.00019248258232139388,
|
| 302 |
+
"loss": 0.0316,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.011154345006485085,
|
| 307 |
+
"grad_norm": 0.2614981234073639,
|
| 308 |
+
"learning_rate": 0.00019197133427991436,
|
| 309 |
+
"loss": 0.0417,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.011413748378728923,
|
| 314 |
+
"grad_norm": 0.44811561703681946,
|
| 315 |
+
"learning_rate": 0.00019144399391799043,
|
| 316 |
+
"loss": 0.036,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.011673151750972763,
|
| 321 |
+
"grad_norm": 0.4213508367538452,
|
| 322 |
+
"learning_rate": 0.00019090065350491626,
|
| 323 |
+
"loss": 0.0399,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.011932555123216601,
|
| 328 |
+
"grad_norm": 0.29146406054496765,
|
| 329 |
+
"learning_rate": 0.0001903414081095315,
|
| 330 |
+
"loss": 0.0376,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.012191958495460441,
|
| 335 |
+
"grad_norm": 0.2714293897151947,
|
| 336 |
+
"learning_rate": 0.00018976635558358722,
|
| 337 |
+
"loss": 0.0362,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.012451361867704281,
|
| 342 |
+
"grad_norm": 0.3767367899417877,
|
| 343 |
+
"learning_rate": 0.00018917559654462474,
|
| 344 |
+
"loss": 0.0364,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.01271076523994812,
|
| 349 |
+
"grad_norm": 0.36578992009162903,
|
| 350 |
+
"learning_rate": 0.00018856923435837022,
|
| 351 |
+
"loss": 0.0327,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.01297016861219196,
|
| 356 |
+
"grad_norm": 0.32976096868515015,
|
| 357 |
+
"learning_rate": 0.0001879473751206489,
|
| 358 |
+
"loss": 0.04,
|
| 359 |
+
"step": 500
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 10,
|
| 363 |
+
"max_steps": 2500,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 1,
|
| 366 |
+
"save_steps": 500,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": false
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 6.5729978171392e+16,
|
| 380 |
+
"train_batch_size": 32,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|