Hugging Face's logo

GGmorello
/
so100-test-v3-groot-1000steps-20250606_151525

Safetensors
gr00t_n1
Model card Files
xet
Community
1
GGmorello commited on
Commit
ecf3092
·
verified ·
1 Parent(s): 33a5018

SO100 GR00T finetuning - 1000 steps - 20250606_151525

Browse files
Files changed (7) hide show
  1. config.json +65 -0
  2. experiment_cfg/metadata.json +195 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +809 -0
  6. trainer_state.json +742 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.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
+ }
experiment_cfg/metadata.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "new_embodiment": {
3
+ "statistics": {
4
+ "state": {
5
+ "single_arm": {
6
+ "max": [
7
+ 61.962890625,
8
+ 193.623046875,
9
+ 176.8359375,
10
+ 92.98828125,
11
+ 92.28515625
12
+ ],
13
+ "min": [
14
+ -58.7109375,
15
+ 25.927734375,
16
+ 17.578125,
17
+ -21.357421875,
18
+ -50.80078125
19
+ ],
20
+ "mean": [
21
+ 0.11941353976726532,
22
+ 142.74105834960938,
23
+ 135.23336791992188,
24
+ 50.59025192260742,
25
+ 11.910408973693848
26
+ ],
27
+ "std": [
28
+ 21.142391204833984,
29
+ 60.2663688659668,
30
+ 51.097373962402344,
31
+ 21.456897735595703,
32
+ 17.020837783813477
33
+ ],
34
+ "q01": [
35
+ -54.580078125,
36
+ 35.15625,
37
+ 29.436328124999996,
38
+ -10.634765625,
39
+ -4.306640625
40
+ ],
41
+ "q99": [
42
+ 53.96484375,
43
+ 193.623046875,
44
+ 176.572265625,
45
+ 80.595703125,
46
+ 83.49609375
47
+ ]
48
+ },
49
+ "gripper": {
50
+ "max": [
51
+ 43.93939208984375
52
+ ],
53
+ "min": [
54
+ 0.4208754301071167
55
+ ],
56
+ "mean": [
57
+ 8.039040565490723
58
+ ],
59
+ "std": [
60
+ 10.57606029510498
61
+ ],
62
+ "q01": [
63
+ 0.4208754301071167
64
+ ],
65
+ "q99": [
66
+ 34.09090805053711
67
+ ]
68
+ }
69
+ },
70
+ "action": {
71
+ "single_arm": {
72
+ "max": [
73
+ 62.314453125,
74
+ 198.6328125,
75
+ 186.50390625,
76
+ 93.251953125,
77
+ 92.4609375
78
+ ],
79
+ "min": [
80
+ -59.58984375,
81
+ 28.388671875,
82
+ 10.986328125,
83
+ -23.115234375,
84
+ -50.9765625
85
+ ],
86
+ "mean": [
87
+ 0.1032688245177269,
88
+ 147.1798858642578,
89
+ 136.07020568847656,
90
+ 50.089725494384766,
91
+ 12.036090850830078
92
+ ],
93
+ "std": [
94
+ 21.120389938354492,
95
+ 60.26120376586914,
96
+ 55.90507125854492,
97
+ 21.857622146606445,
98
+ 17.09563446044922
99
+ ],
100
+ "q01": [
101
+ -54.931640625,
102
+ 39.287109375,
103
+ 23.02734375,
104
+ -12.041015625,
105
+ -4.21875
106
+ ],
107
+ "q99": [
108
+ 54.404296875,
109
+ 198.45703125,
110
+ 186.240234375,
111
+ 80.33906250000015,
112
+ 83.408203125
113
+ ]
114
+ },
115
+ "gripper": {
116
+ "max": [
117
+ 44.4444465637207
118
+ ],
119
+ "min": [
120
+ -0.35273367166519165
121
+ ],
122
+ "mean": [
123
+ 5.195815563201904
124
+ ],
125
+ "std": [
126
+ 10.435248374938965
127
+ ],
128
+ "q01": [
129
+ -0.26455026865005493
130
+ ],
131
+ "q99": [
132
+ 34.39153289794922
133
+ ]
134
+ }
135
+ }
136
+ },
137
+ "modalities": {
138
+ "video": {
139
+ "top": {
140
+ "resolution": [
141
+ 640,
142
+ 480
143
+ ],
144
+ "channels": 3,
145
+ "fps": 30.0
146
+ },
147
+ "wrist_left": {
148
+ "resolution": [
149
+ 640,
150
+ 480
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
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d547656b359403240ba555d6fa87a30f1d413e4a2ae00e3c4ebae336fab8d4db
3
+ size 4938446392
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08eaac4657bb8b441423efcf20f22a7ec502b599290c588d2e4ebd7d5f1daed6
3
+ size 3821736024
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
+ }
trainer_state.json ADDED
@@ -0,0 +1,742 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2680246582685607,
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": 0.002680246582685607,
13
+ "grad_norm": 8.250123023986816,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.6027,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.005360493165371214,
20
+ "grad_norm": 8.169787406921387,
21
+ "learning_rate": 4e-05,
22
+ "loss": 0.526,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.008040739748056821,
27
+ "grad_norm": 3.18163800239563,
28
+ "learning_rate": 6e-05,
29
+ "loss": 0.3044,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.010720986330742428,
34
+ "grad_norm": 1.0450339317321777,
35
+ "learning_rate": 8e-05,
36
+ "loss": 0.1667,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.013401232913428035,
41
+ "grad_norm": 2.213252067565918,
42
+ "learning_rate": 0.0001,
43
+ "loss": 0.1464,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.016081479496113642,
48
+ "grad_norm": 1.4973703622817993,
49
+ "learning_rate": 9.997266286704631e-05,
50
+ "loss": 0.1422,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.01876172607879925,
55
+ "grad_norm": 1.0988550186157227,
56
+ "learning_rate": 9.989068136093873e-05,
57
+ "loss": 0.1073,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.021441972661484857,
62
+ "grad_norm": 0.9315886497497559,
63
+ "learning_rate": 9.975414512725057e-05,
64
+ "loss": 0.1027,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.024122219244170465,
69
+ "grad_norm": 0.47680798172950745,
70
+ "learning_rate": 9.956320346634876e-05,
71
+ "loss": 0.0897,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.02680246582685607,
76
+ "grad_norm": 0.9933809638023376,
77
+ "learning_rate": 9.931806517013612e-05,
78
+ "loss": 0.086,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.02948271240954168,
83
+ "grad_norm": 1.217789888381958,
84
+ "learning_rate": 9.901899829374047e-05,
85
+ "loss": 0.0896,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.032162958992227285,
90
+ "grad_norm": 0.8621407747268677,
91
+ "learning_rate": 9.86663298624003e-05,
92
+ "loss": 0.0763,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.03484320557491289,
97
+ "grad_norm": 0.7449028491973877,
98
+ "learning_rate": 9.826044551386744e-05,
99
+ "loss": 0.0616,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.0375234521575985,
104
+ "grad_norm": 0.7699333429336548,
105
+ "learning_rate": 9.780178907671789e-05,
106
+ "loss": 0.0719,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.04020369874028411,
111
+ "grad_norm": 1.2004507780075073,
112
+ "learning_rate": 9.729086208503174e-05,
113
+ "loss": 0.0722,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.04288394532296971,
118
+ "grad_norm": 0.5228219032287598,
119
+ "learning_rate": 9.672822322997305e-05,
120
+ "loss": 0.0669,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.04556419190565532,
125
+ "grad_norm": 0.6181493401527405,
126
+ "learning_rate": 9.611448774886924e-05,
127
+ "loss": 0.0518,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.04824443848834093,
132
+ "grad_norm": 0.8244765400886536,
133
+ "learning_rate": 9.545032675245813e-05,
134
+ "loss": 0.0517,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.050924685071026536,
139
+ "grad_norm": 0.465935617685318,
140
+ "learning_rate": 9.473646649103818e-05,
141
+ "loss": 0.0629,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.05360493165371214,
146
+ "grad_norm": 0.7628882527351379,
147
+ "learning_rate": 9.397368756032445e-05,
148
+ "loss": 0.067,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.05628517823639775,
153
+ "grad_norm": 0.5569078922271729,
154
+ "learning_rate": 9.316282404787871e-05,
155
+ "loss": 0.0529,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.05896542481908336,
160
+ "grad_norm": 0.9355059266090393,
161
+ "learning_rate": 9.230476262104677e-05,
162
+ "loss": 0.0629,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.061645671401768964,
167
+ "grad_norm": 0.9668640494346619,
168
+ "learning_rate": 9.140044155740101e-05,
169
+ "loss": 0.0547,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.06432591798445457,
174
+ "grad_norm": 0.8556283712387085,
175
+ "learning_rate": 9.045084971874738e-05,
176
+ "loss": 0.0513,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.06700616456714018,
181
+ "grad_norm": 0.6625803112983704,
182
+ "learning_rate": 8.945702546981969e-05,
183
+ "loss": 0.0534,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.06968641114982578,
188
+ "grad_norm": 0.5024917125701904,
189
+ "learning_rate": 8.842005554284296e-05,
190
+ "loss": 0.0488,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.07236665773251139,
195
+ "grad_norm": 0.5751430988311768,
196
+ "learning_rate": 8.73410738492077e-05,
197
+ "loss": 0.0435,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.075046904315197,
202
+ "grad_norm": 0.6379340887069702,
203
+ "learning_rate": 8.622126023955446e-05,
204
+ "loss": 0.0522,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.07772715089788261,
209
+ "grad_norm": 0.7763623595237732,
210
+ "learning_rate": 8.506183921362443e-05,
211
+ "loss": 0.0453,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.08040739748056822,
216
+ "grad_norm": 0.3686479926109314,
217
+ "learning_rate": 8.386407858128706e-05,
218
+ "loss": 0.0471,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.08308764406325382,
223
+ "grad_norm": 0.6437963843345642,
224
+ "learning_rate": 8.262928807620843e-05,
225
+ "loss": 0.0517,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.08576789064593943,
230
+ "grad_norm": 0.778682291507721,
231
+ "learning_rate": 8.135881792367686e-05,
232
+ "loss": 0.0489,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.08844813722862503,
237
+ "grad_norm": 0.8759865760803223,
238
+ "learning_rate": 8.005405736415126e-05,
239
+ "loss": 0.0554,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.09112838381131064,
244
+ "grad_norm": 1.0058921575546265,
245
+ "learning_rate": 7.871643313414718e-05,
246
+ "loss": 0.0455,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.09380863039399624,
251
+ "grad_norm": 0.6325032711029053,
252
+ "learning_rate": 7.734740790612136e-05,
253
+ "loss": 0.0492,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.09648887697668186,
258
+ "grad_norm": 0.7008940577507019,
259
+ "learning_rate": 7.594847868906076e-05,
260
+ "loss": 0.0467,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.09916912355936747,
265
+ "grad_norm": 0.506203293800354,
266
+ "learning_rate": 7.452117519152542e-05,
267
+ "loss": 0.0416,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.10184937014205307,
272
+ "grad_norm": 1.2564700841903687,
273
+ "learning_rate": 7.30670581489344e-05,
274
+ "loss": 0.0453,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.10452961672473868,
279
+ "grad_norm": 0.734930694103241,
280
+ "learning_rate": 7.158771761692464e-05,
281
+ "loss": 0.0409,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.10720986330742428,
286
+ "grad_norm": 2.210068464279175,
287
+ "learning_rate": 7.008477123264848e-05,
288
+ "loss": 0.0396,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.10989010989010989,
293
+ "grad_norm": 0.4128628671169281,
294
+ "learning_rate": 6.855986244591104e-05,
295
+ "loss": 0.0408,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.1125703564727955,
300
+ "grad_norm": 0.689657986164093,
301
+ "learning_rate": 6.701465872208216e-05,
302
+ "loss": 0.042,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.1152506030554811,
307
+ "grad_norm": 0.4255755543708801,
308
+ "learning_rate": 6.545084971874738e-05,
309
+ "loss": 0.0397,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.11793084963816672,
314
+ "grad_norm": 0.5444298386573792,
315
+ "learning_rate": 6.387014543809223e-05,
316
+ "loss": 0.0398,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.12061109622085232,
321
+ "grad_norm": 0.9493265151977539,
322
+ "learning_rate": 6.227427435703997e-05,
323
+ "loss": 0.0413,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.12329134280353793,
328
+ "grad_norm": 0.7940002679824829,
329
+ "learning_rate": 6.066498153718735e-05,
330
+ "loss": 0.0349,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.12597158938622352,
335
+ "grad_norm": 0.36994078755378723,
336
+ "learning_rate": 5.90440267166055e-05,
337
+ "loss": 0.0355,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.12865183596890914,
342
+ "grad_norm": 0.45527538657188416,
343
+ "learning_rate": 5.74131823855921e-05,
344
+ "loss": 0.0288,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.13133208255159476,
349
+ "grad_norm": 0.39583277702331543,
350
+ "learning_rate": 5.577423184847932e-05,
351
+ "loss": 0.035,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.13401232913428035,
356
+ "grad_norm": 0.6096331477165222,
357
+ "learning_rate": 5.4128967273616625e-05,
358
+ "loss": 0.0299,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.13669257571696597,
363
+ "grad_norm": 0.463346928358078,
364
+ "learning_rate": 5.247918773366112e-05,
365
+ "loss": 0.0311,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.13937282229965156,
370
+ "grad_norm": 0.3993473947048187,
371
+ "learning_rate": 5.0826697238317935e-05,
372
+ "loss": 0.0248,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.14205306888233718,
377
+ "grad_norm": 0.4366605877876282,
378
+ "learning_rate": 4.917330276168208e-05,
379
+ "loss": 0.0317,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.14473331546502277,
384
+ "grad_norm": 0.4238353967666626,
385
+ "learning_rate": 4.7520812266338885e-05,
386
+ "loss": 0.035,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.1474135620477084,
391
+ "grad_norm": 0.5067757368087769,
392
+ "learning_rate": 4.5871032726383386e-05,
393
+ "loss": 0.0358,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.150093808630394,
398
+ "grad_norm": 0.297085165977478,
399
+ "learning_rate": 4.4225768151520694e-05,
400
+ "loss": 0.0298,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.1527740552130796,
405
+ "grad_norm": 0.7078633308410645,
406
+ "learning_rate": 4.2586817614407895e-05,
407
+ "loss": 0.0451,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.15545430179576522,
412
+ "grad_norm": 0.4920105040073395,
413
+ "learning_rate": 4.095597328339452e-05,
414
+ "loss": 0.0385,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.1581345483784508,
419
+ "grad_norm": 0.4603646993637085,
420
+ "learning_rate": 3.933501846281267e-05,
421
+ "loss": 0.0308,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.16081479496113643,
426
+ "grad_norm": 0.4976177513599396,
427
+ "learning_rate": 3.772572564296005e-05,
428
+ "loss": 0.0298,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.16349504154382202,
433
+ "grad_norm": 0.5399843454360962,
434
+ "learning_rate": 3.612985456190778e-05,
435
+ "loss": 0.0349,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.16617528812650764,
440
+ "grad_norm": 0.5437161326408386,
441
+ "learning_rate": 3.4549150281252636e-05,
442
+ "loss": 0.0307,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.16885553470919323,
447
+ "grad_norm": 0.34628498554229736,
448
+ "learning_rate": 3.298534127791785e-05,
449
+ "loss": 0.0311,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.17153578129187885,
454
+ "grad_norm": 0.39712560176849365,
455
+ "learning_rate": 3.144013755408895e-05,
456
+ "loss": 0.0288,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.17421602787456447,
461
+ "grad_norm": 0.471830815076828,
462
+ "learning_rate": 2.991522876735154e-05,
463
+ "loss": 0.024,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.17689627445725006,
468
+ "grad_norm": 0.4147932827472687,
469
+ "learning_rate": 2.8412282383075363e-05,
470
+ "loss": 0.0332,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.17957652103993568,
475
+ "grad_norm": 0.43954959511756897,
476
+ "learning_rate": 2.693294185106562e-05,
477
+ "loss": 0.0192,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.18225676762262127,
482
+ "grad_norm": 0.35023635625839233,
483
+ "learning_rate": 2.547882480847461e-05,
484
+ "loss": 0.0349,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.1849370142053069,
489
+ "grad_norm": 0.45557934045791626,
490
+ "learning_rate": 2.405152131093926e-05,
491
+ "loss": 0.0215,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.18761726078799248,
496
+ "grad_norm": 0.5371317863464355,
497
+ "learning_rate": 2.2652592093878666e-05,
498
+ "loss": 0.0323,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.1902975073706781,
503
+ "grad_norm": 0.38529205322265625,
504
+ "learning_rate": 2.128356686585282e-05,
505
+ "loss": 0.0262,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.19297775395336372,
510
+ "grad_norm": 0.3064388930797577,
511
+ "learning_rate": 1.9945942635848748e-05,
512
+ "loss": 0.0239,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.19565800053604931,
517
+ "grad_norm": 0.3981006443500519,
518
+ "learning_rate": 1.8641182076323148e-05,
519
+ "loss": 0.0319,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.19833824711873493,
524
+ "grad_norm": 0.2789249122142792,
525
+ "learning_rate": 1.7370711923791567e-05,
526
+ "loss": 0.0188,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.20101849370142053,
531
+ "grad_norm": 0.3047102391719818,
532
+ "learning_rate": 1.6135921418712956e-05,
533
+ "loss": 0.0256,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.20369874028410614,
538
+ "grad_norm": 0.29851242899894714,
539
+ "learning_rate": 1.4938160786375572e-05,
540
+ "loss": 0.0251,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.20637898686679174,
545
+ "grad_norm": 0.3336225152015686,
546
+ "learning_rate": 1.3778739760445552e-05,
547
+ "loss": 0.0253,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.20905923344947736,
552
+ "grad_norm": 0.2149994969367981,
553
+ "learning_rate": 1.2658926150792322e-05,
554
+ "loss": 0.029,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.21173948003216295,
559
+ "grad_norm": 0.28521740436553955,
560
+ "learning_rate": 1.157994445715706e-05,
561
+ "loss": 0.0168,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.21441972661484857,
566
+ "grad_norm": 0.4623824656009674,
567
+ "learning_rate": 1.0542974530180327e-05,
568
+ "loss": 0.0247,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.21709997319753419,
573
+ "grad_norm": 0.13243989646434784,
574
+ "learning_rate": 9.549150281252633e-06,
575
+ "loss": 0.0214,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.21978021978021978,
580
+ "grad_norm": 0.3828597962856293,
581
+ "learning_rate": 8.599558442598998e-06,
582
+ "loss": 0.0352,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.2224604663629054,
587
+ "grad_norm": 0.4629635512828827,
588
+ "learning_rate": 7.695237378953223e-06,
589
+ "loss": 0.0255,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.225140712945591,
594
+ "grad_norm": 0.250387579202652,
595
+ "learning_rate": 6.837175952121306e-06,
596
+ "loss": 0.0209,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.2278209595282766,
601
+ "grad_norm": 0.29020366072654724,
602
+ "learning_rate": 6.026312439675552e-06,
603
+ "loss": 0.0201,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.2305012061109622,
608
+ "grad_norm": 0.4371938705444336,
609
+ "learning_rate": 5.263533508961827e-06,
610
+ "loss": 0.028,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.23318145269364782,
615
+ "grad_norm": 0.24014584720134735,
616
+ "learning_rate": 4.549673247541875e-06,
617
+ "loss": 0.0207,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.23586169927633344,
622
+ "grad_norm": 0.5081115961074829,
623
+ "learning_rate": 3.885512251130763e-06,
624
+ "loss": 0.0248,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.23854194585901903,
629
+ "grad_norm": 0.21056871116161346,
630
+ "learning_rate": 3.271776770026963e-06,
631
+ "loss": 0.0237,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.24122219244170465,
636
+ "grad_norm": 0.2332233041524887,
637
+ "learning_rate": 2.7091379149682685e-06,
638
+ "loss": 0.023,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.24390243902439024,
643
+ "grad_norm": 0.4083575904369354,
644
+ "learning_rate": 2.1982109232821178e-06,
645
+ "loss": 0.0194,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.24658268560707586,
650
+ "grad_norm": 0.3951759338378906,
651
+ "learning_rate": 1.7395544861325718e-06,
652
+ "loss": 0.0334,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.24926293218976145,
657
+ "grad_norm": 0.39557790756225586,
658
+ "learning_rate": 1.333670137599713e-06,
659
+ "loss": 0.0354,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.25194317877244704,
664
+ "grad_norm": 0.361500084400177,
665
+ "learning_rate": 9.810017062595322e-07,
666
+ "loss": 0.0233,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.25462342535513266,
671
+ "grad_norm": 0.2627847194671631,
672
+ "learning_rate": 6.819348298638839e-07,
673
+ "loss": 0.0162,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.2573036719378183,
678
+ "grad_norm": 0.38893792033195496,
679
+ "learning_rate": 4.367965336512403e-07,
680
+ "loss": 0.0237,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.2599839185205039,
685
+ "grad_norm": 0.37608370184898376,
686
+ "learning_rate": 2.458548727494292e-07,
687
+ "loss": 0.0269,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.2626641651031895,
692
+ "grad_norm": 0.24754008650779724,
693
+ "learning_rate": 1.0931863906127327e-07,
694
+ "loss": 0.0234,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.2653444116858751,
699
+ "grad_norm": 0.36760881543159485,
700
+ "learning_rate": 2.7337132953697554e-08,
701
+ "loss": 0.0199,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.2680246582685607,
706
+ "grad_norm": 0.4145486652851105,
707
+ "learning_rate": 0.0,
708
+ "loss": 0.0208,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.2680246582685607,
713
+ "step": 1000,
714
+ "total_flos": 3.50693465472e+16,
715
+ "train_loss": 0.06646776857972145,
716
+ "train_runtime": 651.1011,
717
+ "train_samples_per_second": 24.574,
718
+ "train_steps_per_second": 1.536
719
+ }
720
+ ],
721
+ "logging_steps": 10,
722
+ "max_steps": 1000,
723
+ "num_input_tokens_seen": 0,
724
+ "num_train_epochs": 1,
725
+ "save_steps": 500,
726
+ "stateful_callbacks": {
727
+ "TrainerControl": {
728
+ "args": {
729
+ "should_epoch_stop": false,
730
+ "should_evaluate": false,
731
+ "should_log": false,
732
+ "should_save": true,
733
+ "should_training_stop": true
734
+ },
735
+ "attributes": {}
736
+ }
737
+ },
738
+ "total_flos": 3.50693465472e+16,
739
+ "train_batch_size": 16,
740
+ "trial_name": null,
741
+ "trial_params": null
742
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0835c6aa34b20b70832fdd2b06f0c2502b3a64feb20b2855c73ece818d9f07e
3
+ size 5304