Hugging Face's logo

jiaxin-wen
/
gemma-3-4b-pt-summarize-default-v3-seed0-ckpt471

PyTorch
gemma3
Model card Files
xet
Community
jiaxin-wen commited on
Commit
11f475e
·
verified ·
1 Parent(s): 26f0d01

Upload summarize-default-v3/seed-0/checkpoint-471

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. config.json +99 -0
  3. generation_config.json +13 -0
  4. pytorch_model-00001-of-00002.bin +3 -0
  5. pytorch_model-00002-of-00002.bin +3 -0
  6. pytorch_model.bin.index.json +892 -0
  7. special_tokens_map.json +33 -0
  8. tokenizer.json +3 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +0 -0
  11. trainer_state.json +3355 -0
  12. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": 1,
9
+ "image_token_index": 262144,
10
+ "initializer_range": 0.02,
11
+ "mm_tokens_per_image": 256,
12
+ "model_type": "gemma3",
13
+ "pad_token_id": 0,
14
+ "text_config": {
15
+ "_sliding_window_pattern": 6,
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "attn_logit_softcapping": null,
19
+ "cache_implementation": "hybrid",
20
+ "final_logit_softcapping": null,
21
+ "head_dim": 256,
22
+ "hidden_activation": "gelu_pytorch_tanh",
23
+ "hidden_size": 2560,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 10240,
26
+ "layer_types": [
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "full_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention"
61
+ ],
62
+ "max_position_embeddings": 131072,
63
+ "model_type": "gemma3_text",
64
+ "num_attention_heads": 8,
65
+ "num_hidden_layers": 34,
66
+ "num_key_value_heads": 4,
67
+ "query_pre_attn_scalar": 256,
68
+ "rms_norm_eps": 1e-06,
69
+ "rope_local_base_freq": 10000.0,
70
+ "rope_scaling": {
71
+ "factor": 8.0,
72
+ "rope_type": "linear"
73
+ },
74
+ "rope_theta": 1000000.0,
75
+ "sliding_window": 1024,
76
+ "torch_dtype": "bfloat16",
77
+ "use_cache": true,
78
+ "vocab_size": 262208
79
+ },
80
+ "torch_dtype": "bfloat16",
81
+ "transformers_version": "4.54.1",
82
+ "unsloth_fixed": true,
83
+ "unsloth_version": "2025.7.11",
84
+ "vision_config": {
85
+ "attention_dropout": 0.0,
86
+ "hidden_act": "gelu_pytorch_tanh",
87
+ "hidden_size": 1152,
88
+ "image_size": 896,
89
+ "intermediate_size": 4304,
90
+ "layer_norm_eps": 1e-06,
91
+ "model_type": "siglip_vision_model",
92
+ "num_attention_heads": 16,
93
+ "num_channels": 3,
94
+ "num_hidden_layers": 27,
95
+ "patch_size": 14,
96
+ "torch_dtype": "bfloat16",
97
+ "vision_use_head": false
98
+ }
99
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.54.1"
13
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf57e8eec62f016f0485f04482c04192a35d8c1d5ce08445a7227b2523ab882
3
+ size 4961401164
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b173a349dde0ef0e28b0b397e074a44e1b067cd2190262c15388747ae95a813
3
+ size 3639086221
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,892 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4300079472,
4
+ "total_size": 8600158944
5
+ },
6
+ "weight_map": {
7
+ "language_model.lm_head.weight": "pytorch_model-00001-of-00002.bin",
8
+ "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
9
+ "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
10
+ "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
14
+ "language_model.model.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "language_model.model.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
16
+ "language_model.model.layers.0.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
17
+ "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "language_model.model.layers.0.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
20
+ "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
23
+ "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "language_model.model.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
28
+ "language_model.model.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
29
+ "language_model.model.layers.1.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "language_model.model.layers.1.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
+ "language_model.model.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
41
+ "language_model.model.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
42
+ "language_model.model.layers.10.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "language_model.model.layers.10.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
46
+ "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "language_model.model.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
+ "language_model.model.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
55
+ "language_model.model.layers.11.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
56
+ "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "language_model.model.layers.11.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
62
+ "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "language_model.model.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
67
+ "language_model.model.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
68
+ "language_model.model.layers.12.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "language_model.model.layers.12.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
72
+ "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "language_model.model.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "language_model.model.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "language_model.model.layers.13.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
82
+ "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "language_model.model.layers.13.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
88
+ "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
89
+ "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
90
+ "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
92
+ "language_model.model.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
93
+ "language_model.model.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
94
+ "language_model.model.layers.14.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
95
+ "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "language_model.model.layers.14.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
98
+ "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
101
+ "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
102
+ "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
103
+ "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
104
+ "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
105
+ "language_model.model.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
106
+ "language_model.model.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
107
+ "language_model.model.layers.15.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
108
+ "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
109
+ "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
110
+ "language_model.model.layers.15.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
111
+ "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
112
+ "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
113
+ "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
114
+ "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
115
+ "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
116
+ "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
117
+ "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
118
+ "language_model.model.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
119
+ "language_model.model.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
120
+ "language_model.model.layers.16.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
121
+ "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
122
+ "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
123
+ "language_model.model.layers.16.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
124
+ "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
125
+ "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
126
+ "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
127
+ "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
128
+ "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
129
+ "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
130
+ "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
131
+ "language_model.model.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
132
+ "language_model.model.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
133
+ "language_model.model.layers.17.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
134
+ "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
135
+ "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "language_model.model.layers.17.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
137
+ "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
138
+ "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
140
+ "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
141
+ "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
142
+ "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
143
+ "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
144
+ "language_model.model.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
145
+ "language_model.model.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
146
+ "language_model.model.layers.18.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
147
+ "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
148
+ "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
149
+ "language_model.model.layers.18.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
150
+ "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
151
+ "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
152
+ "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
153
+ "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
156
+ "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
157
+ "language_model.model.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
158
+ "language_model.model.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
159
+ "language_model.model.layers.19.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
160
+ "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
162
+ "language_model.model.layers.19.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
163
+ "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
165
+ "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
166
+ "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
170
+ "language_model.model.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
+ "language_model.model.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
172
+ "language_model.model.layers.2.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
173
+ "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
174
+ "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "language_model.model.layers.2.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
176
+ "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
177
+ "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
179
+ "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
180
+ "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
181
+ "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
182
+ "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
183
+ "language_model.model.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
184
+ "language_model.model.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
185
+ "language_model.model.layers.20.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
186
+ "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
188
+ "language_model.model.layers.20.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
190
+ "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
191
+ "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
192
+ "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
193
+ "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
196
+ "language_model.model.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
197
+ "language_model.model.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
198
+ "language_model.model.layers.21.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
199
+ "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
200
+ "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
201
+ "language_model.model.layers.21.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
202
+ "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
203
+ "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
204
+ "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
205
+ "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
206
+ "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
207
+ "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
208
+ "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
209
+ "language_model.model.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
210
+ "language_model.model.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
211
+ "language_model.model.layers.22.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
212
+ "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
213
+ "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
214
+ "language_model.model.layers.22.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
215
+ "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
216
+ "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
217
+ "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
218
+ "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
219
+ "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
220
+ "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
221
+ "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
222
+ "language_model.model.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
223
+ "language_model.model.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
224
+ "language_model.model.layers.23.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
226
+ "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
227
+ "language_model.model.layers.23.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
228
+ "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
229
+ "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
230
+ "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
231
+ "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
232
+ "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
233
+ "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
234
+ "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
235
+ "language_model.model.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
236
+ "language_model.model.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
237
+ "language_model.model.layers.24.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
238
+ "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
239
+ "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
240
+ "language_model.model.layers.24.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
241
+ "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
242
+ "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
243
+ "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
244
+ "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
245
+ "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
246
+ "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
247
+ "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
248
+ "language_model.model.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
249
+ "language_model.model.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
250
+ "language_model.model.layers.25.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
251
+ "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
252
+ "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
253
+ "language_model.model.layers.25.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
254
+ "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
255
+ "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
256
+ "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
257
+ "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
258
+ "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
259
+ "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
260
+ "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
261
+ "language_model.model.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
262
+ "language_model.model.layers.26.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
263
+ "language_model.model.layers.26.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
264
+ "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
265
+ "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
266
+ "language_model.model.layers.26.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
267
+ "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
268
+ "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
269
+ "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
270
+ "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
271
+ "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
272
+ "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
273
+ "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
274
+ "language_model.model.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
275
+ "language_model.model.layers.27.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
276
+ "language_model.model.layers.27.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
277
+ "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
278
+ "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
279
+ "language_model.model.layers.27.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
280
+ "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
281
+ "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
282
+ "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
283
+ "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
284
+ "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
285
+ "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
286
+ "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
287
+ "language_model.model.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
288
+ "language_model.model.layers.28.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
289
+ "language_model.model.layers.28.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
290
+ "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
291
+ "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
292
+ "language_model.model.layers.28.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
293
+ "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
294
+ "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
295
+ "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
296
+ "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
297
+ "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
298
+ "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
299
+ "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
300
+ "language_model.model.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
301
+ "language_model.model.layers.29.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
302
+ "language_model.model.layers.29.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
303
+ "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
304
+ "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
305
+ "language_model.model.layers.29.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
306
+ "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
307
+ "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
308
+ "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
310
+ "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
312
+ "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
313
+ "language_model.model.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
314
+ "language_model.model.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
315
+ "language_model.model.layers.3.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
316
+ "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
317
+ "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
318
+ "language_model.model.layers.3.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
320
+ "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
321
+ "language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
322
+ "language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
323
+ "language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
324
+ "language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
325
+ "language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
326
+ "language_model.model.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
327
+ "language_model.model.layers.30.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
328
+ "language_model.model.layers.30.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
329
+ "language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
330
+ "language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
331
+ "language_model.model.layers.30.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
332
+ "language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
333
+ "language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
334
+ "language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
335
+ "language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
336
+ "language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
337
+ "language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
338
+ "language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
339
+ "language_model.model.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
340
+ "language_model.model.layers.31.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
341
+ "language_model.model.layers.31.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
342
+ "language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
343
+ "language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
344
+ "language_model.model.layers.31.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
345
+ "language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
346
+ "language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
347
+ "language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
348
+ "language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
349
+ "language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
350
+ "language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
351
+ "language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
352
+ "language_model.model.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
353
+ "language_model.model.layers.32.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
354
+ "language_model.model.layers.32.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
355
+ "language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
356
+ "language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
357
+ "language_model.model.layers.32.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
358
+ "language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
359
+ "language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
360
+ "language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
361
+ "language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
362
+ "language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
363
+ "language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
364
+ "language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
365
+ "language_model.model.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
366
+ "language_model.model.layers.33.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00002.bin",
367
+ "language_model.model.layers.33.self_attn.k_norm.weight": "pytorch_model-00002-of-00002.bin",
368
+ "language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
369
+ "language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
370
+ "language_model.model.layers.33.self_attn.q_norm.weight": "pytorch_model-00002-of-00002.bin",
371
+ "language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
372
+ "language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
373
+ "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
374
+ "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
375
+ "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
376
+ "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
377
+ "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
378
+ "language_model.model.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
379
+ "language_model.model.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
380
+ "language_model.model.layers.4.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
381
+ "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
382
+ "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
383
+ "language_model.model.layers.4.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
384
+ "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
385
+ "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
386
+ "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
387
+ "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
388
+ "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
389
+ "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
390
+ "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
391
+ "language_model.model.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
392
+ "language_model.model.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
393
+ "language_model.model.layers.5.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
394
+ "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
395
+ "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
396
+ "language_model.model.layers.5.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
397
+ "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
398
+ "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
399
+ "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
400
+ "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
401
+ "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
402
+ "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
403
+ "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
404
+ "language_model.model.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
405
+ "language_model.model.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
406
+ "language_model.model.layers.6.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
407
+ "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
408
+ "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
409
+ "language_model.model.layers.6.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
410
+ "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
411
+ "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
412
+ "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
413
+ "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
414
+ "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
415
+ "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
416
+ "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
417
+ "language_model.model.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
418
+ "language_model.model.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
419
+ "language_model.model.layers.7.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
420
+ "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
421
+ "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
422
+ "language_model.model.layers.7.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
423
+ "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
424
+ "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
425
+ "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
426
+ "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
427
+ "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
428
+ "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
429
+ "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
430
+ "language_model.model.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
431
+ "language_model.model.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
432
+ "language_model.model.layers.8.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
433
+ "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
434
+ "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
435
+ "language_model.model.layers.8.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
436
+ "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
437
+ "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
438
+ "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
439
+ "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
440
+ "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
441
+ "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
442
+ "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
443
+ "language_model.model.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
444
+ "language_model.model.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00001-of-00002.bin",
445
+ "language_model.model.layers.9.self_attn.k_norm.weight": "pytorch_model-00001-of-00002.bin",
446
+ "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
447
+ "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
448
+ "language_model.model.layers.9.self_attn.q_norm.weight": "pytorch_model-00001-of-00002.bin",
449
+ "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
450
+ "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
451
+ "language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
452
+ "multi_modal_projector.mm_input_projection_weight": "pytorch_model-00001-of-00002.bin",
453
+ "multi_modal_projector.mm_soft_emb_norm.weight": "pytorch_model-00001-of-00002.bin",
454
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin",
455
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
456
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
457
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
458
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
459
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
460
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
461
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
462
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
463
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
464
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
465
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
466
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
467
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
468
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
469
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
470
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
471
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
472
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
473
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
474
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
475
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
476
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
477
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
478
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
479
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
480
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
481
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
482
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
483
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
484
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
485
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
486
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
487
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
488
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
489
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
490
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
491
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
492
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
493
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
494
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
495
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
496
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
497
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
498
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
499
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
500
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
501
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
502
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
503
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
504
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
505
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
506
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
507
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
508
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
509
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
510
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
511
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
512
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
513
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
514
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
515
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
516
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
517
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
518
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
519
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
520
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
521
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
522
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
523
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
524
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
525
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
526
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
527
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
528
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
529
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
530
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
531
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
532
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
533
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
534
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
535
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
536
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
537
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
538
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
539
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
540
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
541
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
542
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
543
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
544
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
545
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
546
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
547
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
548
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
549
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
550
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
551
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
552
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
553
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
554
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
555
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
556
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
557
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
558
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
559
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
560
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
561
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
562
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
563
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
564
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
565
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
566
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
567
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
568
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
569
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
570
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
571
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
572
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
573
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
574
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
575
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
576
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
577
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
578
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
579
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
580
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
581
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
582
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
583
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
584
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
585
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
586
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
587
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
588
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
589
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
590
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
591
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
592
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
593
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
594
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
595
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
596
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
597
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
598
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
599
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
600
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
601
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
602
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
603
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
604
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
605
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
606
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
607
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
608
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
609
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
610
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
611
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
612
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
613
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
614
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
615
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
616
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
617
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
618
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
619
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
620
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
621
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
622
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
623
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
624
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
625
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
626
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
627
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
628
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
629
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
630
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
631
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
632
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
633
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
634
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
635
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
636
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
637
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
638
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
639
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
640
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
641
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
642
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
643
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
644
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
645
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
646
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
647
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
648
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
649
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
650
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
651
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
652
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
653
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
654
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
655
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
656
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
657
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
658
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
659
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
660
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
661
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
662
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
663
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
664
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
665
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
666
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
667
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
668
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
669
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
670
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
671
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
672
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
673
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
674
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
675
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
676
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
677
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
678
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
679
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
680
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
681
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
682
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
683
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
684
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
685
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
686
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
687
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
688
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
689
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
690
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
691
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
692
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
693
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
694
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
695
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
696
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
697
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
698
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
699
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
700
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
701
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
702
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
703
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
704
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
705
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
706
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
707
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
708
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
709
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
710
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
711
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
712
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
713
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
714
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
715
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
716
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
717
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
718
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
719
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
720
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
721
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
722
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
723
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
724
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
725
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
726
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
727
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
728
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
729
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
730
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
731
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
732
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
733
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
734
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
735
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
736
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
737
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
738
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
739
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
740
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
741
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
742
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
743
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
744
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
745
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
746
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
747
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
748
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
749
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
750
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
751
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
752
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
753
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
754
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
755
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
756
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
757
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
758
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
759
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
760
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
761
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
762
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
763
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
764
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
765
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
766
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
767
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
768
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
769
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
770
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
771
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
772
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
773
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
774
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
775
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
776
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
777
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
778
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
779
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
780
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
781
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
782
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
783
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
784
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
785
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
786
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
787
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
788
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
789
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
790
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
791
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
792
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
793
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
794
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
795
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
796
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
797
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
798
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
799
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
800
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
801
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
802
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
803
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
804
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
805
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
806
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
807
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
808
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
809
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
810
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
811
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
812
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
813
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
814
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
815
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
816
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
817
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
818
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
819
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
820
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
821
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
822
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
823
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
824
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
825
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
826
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
827
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
828
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
829
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
830
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
831
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
832
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
833
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
834
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
835
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
836
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
837
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
838
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
839
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
840
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
841
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
842
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
843
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
844
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
845
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
846
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
847
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
848
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
849
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
850
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
851
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
852
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
853
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
854
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
855
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
856
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
857
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
858
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
859
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
860
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
861
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
862
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
863
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
864
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
865
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
866
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
867
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
868
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
869
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
870
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
871
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
872
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
873
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
874
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
875
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
876
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
877
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
878
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
879
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
880
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
881
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
882
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
883
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
884
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
885
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
886
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
887
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
888
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
889
+ "vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
890
+ "vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
891
+ }
892
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a872e3bb510a751b26bd65f61aad05f948c9cf78fe4f787aebd197b393cc4081
3
+ size 33384667
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,3355 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 471,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.006369426751592357,
14
+ "grad_norm": 7.28125,
15
+ "learning_rate": 1e-05,
16
+ "loss": 2.4644,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.012738853503184714,
21
+ "grad_norm": 4.09375,
22
+ "learning_rate": 9.987261146496817e-06,
23
+ "loss": 2.2701,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.01910828025477707,
28
+ "grad_norm": 4.09375,
29
+ "learning_rate": 9.97452229299363e-06,
30
+ "loss": 2.333,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.025477707006369428,
35
+ "grad_norm": 3.515625,
36
+ "learning_rate": 9.961783439490446e-06,
37
+ "loss": 2.2616,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.03184713375796178,
42
+ "grad_norm": 3.390625,
43
+ "learning_rate": 9.949044585987262e-06,
44
+ "loss": 2.2408,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.03821656050955414,
49
+ "grad_norm": 3.828125,
50
+ "learning_rate": 9.936305732484078e-06,
51
+ "loss": 2.1906,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.044585987261146494,
56
+ "grad_norm": 4.96875,
57
+ "learning_rate": 9.923566878980892e-06,
58
+ "loss": 2.1708,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.050955414012738856,
63
+ "grad_norm": 4.28125,
64
+ "learning_rate": 9.910828025477707e-06,
65
+ "loss": 2.1055,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.05732484076433121,
70
+ "grad_norm": 4.71875,
71
+ "learning_rate": 9.898089171974523e-06,
72
+ "loss": 2.0758,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.06369426751592357,
77
+ "grad_norm": 4.1875,
78
+ "learning_rate": 9.885350318471339e-06,
79
+ "loss": 2.1453,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.07006369426751592,
84
+ "grad_norm": 3.46875,
85
+ "learning_rate": 9.872611464968153e-06,
86
+ "loss": 2.096,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.07643312101910828,
91
+ "grad_norm": 3.921875,
92
+ "learning_rate": 9.859872611464969e-06,
93
+ "loss": 2.1073,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.08280254777070063,
98
+ "grad_norm": 3.625,
99
+ "learning_rate": 9.847133757961784e-06,
100
+ "loss": 1.9877,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.08917197452229299,
105
+ "grad_norm": 5.15625,
106
+ "learning_rate": 9.8343949044586e-06,
107
+ "loss": 1.9904,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.09554140127388536,
112
+ "grad_norm": 5.25,
113
+ "learning_rate": 9.821656050955414e-06,
114
+ "loss": 2.0577,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.10191082802547771,
119
+ "grad_norm": 5.15625,
120
+ "learning_rate": 9.80891719745223e-06,
121
+ "loss": 2.005,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.10828025477707007,
126
+ "grad_norm": 4.375,
127
+ "learning_rate": 9.796178343949046e-06,
128
+ "loss": 1.9762,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.11464968152866242,
133
+ "grad_norm": 3.109375,
134
+ "learning_rate": 9.783439490445861e-06,
135
+ "loss": 2.0466,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.12101910828025478,
140
+ "grad_norm": 3.40625,
141
+ "learning_rate": 9.770700636942675e-06,
142
+ "loss": 2.0005,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.12738853503184713,
147
+ "grad_norm": 3.15625,
148
+ "learning_rate": 9.757961783439491e-06,
149
+ "loss": 2.0017,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.1337579617834395,
154
+ "grad_norm": 3.1875,
155
+ "learning_rate": 9.745222929936307e-06,
156
+ "loss": 2.029,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.14012738853503184,
161
+ "grad_norm": 3.15625,
162
+ "learning_rate": 9.732484076433122e-06,
163
+ "loss": 2.0261,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.1464968152866242,
168
+ "grad_norm": 3.421875,
169
+ "learning_rate": 9.719745222929937e-06,
170
+ "loss": 1.9504,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.15286624203821655,
175
+ "grad_norm": 3.265625,
176
+ "learning_rate": 9.707006369426752e-06,
177
+ "loss": 1.8378,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.1592356687898089,
182
+ "grad_norm": 3.046875,
183
+ "learning_rate": 9.694267515923568e-06,
184
+ "loss": 2.0114,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.16560509554140126,
189
+ "grad_norm": 3.03125,
190
+ "learning_rate": 9.681528662420384e-06,
191
+ "loss": 1.8339,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.17197452229299362,
196
+ "grad_norm": 3.40625,
197
+ "learning_rate": 9.668789808917198e-06,
198
+ "loss": 1.8907,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.17834394904458598,
203
+ "grad_norm": 3.328125,
204
+ "learning_rate": 9.656050955414013e-06,
205
+ "loss": 2.0329,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.18471337579617833,
210
+ "grad_norm": 3.359375,
211
+ "learning_rate": 9.64331210191083e-06,
212
+ "loss": 2.035,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.1910828025477707,
217
+ "grad_norm": 3.328125,
218
+ "learning_rate": 9.630573248407645e-06,
219
+ "loss": 2.0496,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.19745222929936307,
224
+ "grad_norm": 3.328125,
225
+ "learning_rate": 9.617834394904459e-06,
226
+ "loss": 1.9156,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.20382165605095542,
231
+ "grad_norm": 3.171875,
232
+ "learning_rate": 9.605095541401275e-06,
233
+ "loss": 1.7854,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.21019108280254778,
238
+ "grad_norm": 3.0625,
239
+ "learning_rate": 9.59235668789809e-06,
240
+ "loss": 1.9023,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.21656050955414013,
245
+ "grad_norm": 3.25,
246
+ "learning_rate": 9.579617834394906e-06,
247
+ "loss": 1.7827,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.2229299363057325,
252
+ "grad_norm": 3.1875,
253
+ "learning_rate": 9.56687898089172e-06,
254
+ "loss": 1.7565,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.22929936305732485,
259
+ "grad_norm": 3.046875,
260
+ "learning_rate": 9.554140127388536e-06,
261
+ "loss": 1.7709,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.2356687898089172,
266
+ "grad_norm": 3.234375,
267
+ "learning_rate": 9.541401273885352e-06,
268
+ "loss": 1.7737,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.24203821656050956,
273
+ "grad_norm": 3.765625,
274
+ "learning_rate": 9.528662420382167e-06,
275
+ "loss": 1.9197,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.2484076433121019,
280
+ "grad_norm": 3.359375,
281
+ "learning_rate": 9.515923566878981e-06,
282
+ "loss": 1.7437,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.25477707006369427,
287
+ "grad_norm": 4.75,
288
+ "learning_rate": 9.503184713375797e-06,
289
+ "loss": 1.7678,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.2611464968152866,
294
+ "grad_norm": 3.8125,
295
+ "learning_rate": 9.490445859872613e-06,
296
+ "loss": 1.8269,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.267515923566879,
301
+ "grad_norm": 10.9375,
302
+ "learning_rate": 9.477707006369428e-06,
303
+ "loss": 1.7639,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.27388535031847133,
308
+ "grad_norm": 3.5,
309
+ "learning_rate": 9.464968152866242e-06,
310
+ "loss": 1.893,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.2802547770700637,
315
+ "grad_norm": 3.265625,
316
+ "learning_rate": 9.452229299363058e-06,
317
+ "loss": 1.8033,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.28662420382165604,
322
+ "grad_norm": 3.625,
323
+ "learning_rate": 9.439490445859874e-06,
324
+ "loss": 1.6997,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.2929936305732484,
329
+ "grad_norm": 6.25,
330
+ "learning_rate": 9.426751592356688e-06,
331
+ "loss": 1.6561,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.29936305732484075,
336
+ "grad_norm": 3.359375,
337
+ "learning_rate": 9.414012738853504e-06,
338
+ "loss": 1.8291,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.3057324840764331,
343
+ "grad_norm": 4.34375,
344
+ "learning_rate": 9.40127388535032e-06,
345
+ "loss": 1.5057,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.31210191082802546,
350
+ "grad_norm": 4.40625,
351
+ "learning_rate": 9.388535031847135e-06,
352
+ "loss": 1.6756,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.3184713375796178,
357
+ "grad_norm": 4.09375,
358
+ "learning_rate": 9.375796178343949e-06,
359
+ "loss": 1.9471,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.3248407643312102,
364
+ "grad_norm": 3.53125,
365
+ "learning_rate": 9.363057324840765e-06,
366
+ "loss": 1.7311,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.33121019108280253,
371
+ "grad_norm": 3.515625,
372
+ "learning_rate": 9.35031847133758e-06,
373
+ "loss": 1.8262,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.3375796178343949,
378
+ "grad_norm": 5.71875,
379
+ "learning_rate": 9.337579617834396e-06,
380
+ "loss": 1.6343,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.34394904458598724,
385
+ "grad_norm": 4.53125,
386
+ "learning_rate": 9.32484076433121e-06,
387
+ "loss": 1.9391,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.3503184713375796,
392
+ "grad_norm": 4.8125,
393
+ "learning_rate": 9.312101910828026e-06,
394
+ "loss": 1.5763,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.35668789808917195,
399
+ "grad_norm": 3.296875,
400
+ "learning_rate": 9.299363057324842e-06,
401
+ "loss": 1.8256,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.3630573248407643,
406
+ "grad_norm": 3.90625,
407
+ "learning_rate": 9.286624203821658e-06,
408
+ "loss": 1.7978,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.36942675159235666,
413
+ "grad_norm": 3.4375,
414
+ "learning_rate": 9.273885350318472e-06,
415
+ "loss": 1.7385,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.37579617834394907,
420
+ "grad_norm": 4.0625,
421
+ "learning_rate": 9.261146496815287e-06,
422
+ "loss": 1.698,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.3821656050955414,
427
+ "grad_norm": 4.53125,
428
+ "learning_rate": 9.248407643312103e-06,
429
+ "loss": 1.7681,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.3885350318471338,
434
+ "grad_norm": 3.515625,
435
+ "learning_rate": 9.235668789808919e-06,
436
+ "loss": 1.5631,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.39490445859872614,
441
+ "grad_norm": 3.59375,
442
+ "learning_rate": 9.222929936305733e-06,
443
+ "loss": 1.8493,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.4012738853503185,
448
+ "grad_norm": 4.15625,
449
+ "learning_rate": 9.210191082802548e-06,
450
+ "loss": 1.7196,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.40764331210191085,
455
+ "grad_norm": 4.28125,
456
+ "learning_rate": 9.197452229299364e-06,
457
+ "loss": 1.5831,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.4140127388535032,
462
+ "grad_norm": 3.515625,
463
+ "learning_rate": 9.18471337579618e-06,
464
+ "loss": 1.6632,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.42038216560509556,
469
+ "grad_norm": 5.21875,
470
+ "learning_rate": 9.171974522292994e-06,
471
+ "loss": 1.5367,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.4267515923566879,
476
+ "grad_norm": 3.296875,
477
+ "learning_rate": 9.15923566878981e-06,
478
+ "loss": 1.7637,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.43312101910828027,
483
+ "grad_norm": 3.46875,
484
+ "learning_rate": 9.146496815286625e-06,
485
+ "loss": 1.4526,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.4394904458598726,
490
+ "grad_norm": 3.265625,
491
+ "learning_rate": 9.133757961783441e-06,
492
+ "loss": 1.6055,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.445859872611465,
497
+ "grad_norm": 3.53125,
498
+ "learning_rate": 9.121019108280255e-06,
499
+ "loss": 1.5293,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.45222929936305734,
504
+ "grad_norm": 3.234375,
505
+ "learning_rate": 9.10828025477707e-06,
506
+ "loss": 1.6286,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.4585987261146497,
511
+ "grad_norm": 3.46875,
512
+ "learning_rate": 9.095541401273887e-06,
513
+ "loss": 1.5673,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.46496815286624205,
518
+ "grad_norm": 3.4375,
519
+ "learning_rate": 9.082802547770702e-06,
520
+ "loss": 1.803,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.4713375796178344,
525
+ "grad_norm": 3.265625,
526
+ "learning_rate": 9.070063694267516e-06,
527
+ "loss": 1.5751,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.47770700636942676,
532
+ "grad_norm": 3.15625,
533
+ "learning_rate": 9.057324840764332e-06,
534
+ "loss": 1.5779,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.4840764331210191,
539
+ "grad_norm": 3.328125,
540
+ "learning_rate": 9.044585987261148e-06,
541
+ "loss": 1.6361,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.49044585987261147,
546
+ "grad_norm": 3.546875,
547
+ "learning_rate": 9.031847133757963e-06,
548
+ "loss": 1.557,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.4968152866242038,
553
+ "grad_norm": 3.3125,
554
+ "learning_rate": 9.019108280254777e-06,
555
+ "loss": 1.533,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.5031847133757962,
560
+ "grad_norm": 3.3125,
561
+ "learning_rate": 9.006369426751593e-06,
562
+ "loss": 1.9026,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.5095541401273885,
567
+ "grad_norm": 3.796875,
568
+ "learning_rate": 8.993630573248409e-06,
569
+ "loss": 1.5346,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.5159235668789809,
574
+ "grad_norm": 3.625,
575
+ "learning_rate": 8.980891719745225e-06,
576
+ "loss": 1.5926,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.5222929936305732,
581
+ "grad_norm": 3.421875,
582
+ "learning_rate": 8.968152866242039e-06,
583
+ "loss": 1.427,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.5286624203821656,
588
+ "grad_norm": 3.84375,
589
+ "learning_rate": 8.955414012738854e-06,
590
+ "loss": 1.8507,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.535031847133758,
595
+ "grad_norm": 3.15625,
596
+ "learning_rate": 8.94267515923567e-06,
597
+ "loss": 1.5766,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.5414012738853503,
602
+ "grad_norm": 3.171875,
603
+ "learning_rate": 8.929936305732486e-06,
604
+ "loss": 1.568,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.5477707006369427,
609
+ "grad_norm": 3.0625,
610
+ "learning_rate": 8.9171974522293e-06,
611
+ "loss": 1.7016,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.554140127388535,
616
+ "grad_norm": 3.40625,
617
+ "learning_rate": 8.904458598726116e-06,
618
+ "loss": 1.4861,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.5605095541401274,
623
+ "grad_norm": 3.359375,
624
+ "learning_rate": 8.891719745222931e-06,
625
+ "loss": 1.9244,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.5668789808917197,
630
+ "grad_norm": 3.078125,
631
+ "learning_rate": 8.878980891719747e-06,
632
+ "loss": 1.717,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.5732484076433121,
637
+ "grad_norm": 3.21875,
638
+ "learning_rate": 8.866242038216561e-06,
639
+ "loss": 1.6252,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.5796178343949044,
644
+ "grad_norm": 3.15625,
645
+ "learning_rate": 8.853503184713377e-06,
646
+ "loss": 1.5911,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.5859872611464968,
651
+ "grad_norm": 3.109375,
652
+ "learning_rate": 8.840764331210193e-06,
653
+ "loss": 1.4699,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.5923566878980892,
658
+ "grad_norm": 3.015625,
659
+ "learning_rate": 8.828025477707007e-06,
660
+ "loss": 1.6128,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.5987261146496815,
665
+ "grad_norm": 3.109375,
666
+ "learning_rate": 8.815286624203822e-06,
667
+ "loss": 1.2511,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.6050955414012739,
672
+ "grad_norm": 2.953125,
673
+ "learning_rate": 8.802547770700638e-06,
674
+ "loss": 1.3584,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.6114649681528662,
679
+ "grad_norm": 3.109375,
680
+ "learning_rate": 8.789808917197454e-06,
681
+ "loss": 1.4619,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.6178343949044586,
686
+ "grad_norm": 3.28125,
687
+ "learning_rate": 8.777070063694268e-06,
688
+ "loss": 1.4293,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.6242038216560509,
693
+ "grad_norm": 3.203125,
694
+ "learning_rate": 8.764331210191083e-06,
695
+ "loss": 1.5964,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.6305732484076433,
700
+ "grad_norm": 3.1875,
701
+ "learning_rate": 8.7515923566879e-06,
702
+ "loss": 1.6662,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.6369426751592356,
707
+ "grad_norm": 3.078125,
708
+ "learning_rate": 8.738853503184715e-06,
709
+ "loss": 1.4293,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.643312101910828,
714
+ "grad_norm": 3.390625,
715
+ "learning_rate": 8.726114649681529e-06,
716
+ "loss": 1.3474,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.6496815286624203,
721
+ "grad_norm": 2.953125,
722
+ "learning_rate": 8.713375796178345e-06,
723
+ "loss": 1.3867,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.6560509554140127,
728
+ "grad_norm": 3.328125,
729
+ "learning_rate": 8.70063694267516e-06,
730
+ "loss": 1.3772,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.6624203821656051,
735
+ "grad_norm": 3.015625,
736
+ "learning_rate": 8.687898089171976e-06,
737
+ "loss": 1.3609,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.6687898089171974,
742
+ "grad_norm": 3.453125,
743
+ "learning_rate": 8.67515923566879e-06,
744
+ "loss": 1.3219,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.6751592356687898,
749
+ "grad_norm": 3.015625,
750
+ "learning_rate": 8.662420382165606e-06,
751
+ "loss": 1.3503,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.6815286624203821,
756
+ "grad_norm": 3.09375,
757
+ "learning_rate": 8.649681528662422e-06,
758
+ "loss": 1.4379,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.6878980891719745,
763
+ "grad_norm": 3.65625,
764
+ "learning_rate": 8.636942675159237e-06,
765
+ "loss": 1.3036,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.6942675159235668,
770
+ "grad_norm": 3.390625,
771
+ "learning_rate": 8.624203821656051e-06,
772
+ "loss": 1.6116,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.7006369426751592,
777
+ "grad_norm": 3.21875,
778
+ "learning_rate": 8.611464968152867e-06,
779
+ "loss": 1.5167,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.7070063694267515,
784
+ "grad_norm": 3.203125,
785
+ "learning_rate": 8.598726114649683e-06,
786
+ "loss": 1.492,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.7133757961783439,
791
+ "grad_norm": 3.5,
792
+ "learning_rate": 8.585987261146498e-06,
793
+ "loss": 1.3769,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.7197452229299363,
798
+ "grad_norm": 3.25,
799
+ "learning_rate": 8.573248407643312e-06,
800
+ "loss": 1.4816,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.7261146496815286,
805
+ "grad_norm": 3.640625,
806
+ "learning_rate": 8.560509554140128e-06,
807
+ "loss": 1.5312,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.732484076433121,
812
+ "grad_norm": 3.53125,
813
+ "learning_rate": 8.547770700636944e-06,
814
+ "loss": 1.5366,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.7388535031847133,
819
+ "grad_norm": 3.015625,
820
+ "learning_rate": 8.53503184713376e-06,
821
+ "loss": 1.4656,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.7452229299363057,
826
+ "grad_norm": 2.84375,
827
+ "learning_rate": 8.522292993630574e-06,
828
+ "loss": 1.2655,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.7515923566878981,
833
+ "grad_norm": 3.1875,
834
+ "learning_rate": 8.50955414012739e-06,
835
+ "loss": 1.1561,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.7579617834394905,
840
+ "grad_norm": 3.203125,
841
+ "learning_rate": 8.496815286624205e-06,
842
+ "loss": 1.6108,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.7643312101910829,
847
+ "grad_norm": 3.390625,
848
+ "learning_rate": 8.484076433121021e-06,
849
+ "loss": 1.6502,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.7707006369426752,
854
+ "grad_norm": 5.84375,
855
+ "learning_rate": 8.471337579617835e-06,
856
+ "loss": 1.4259,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.7770700636942676,
861
+ "grad_norm": 3.28125,
862
+ "learning_rate": 8.45859872611465e-06,
863
+ "loss": 1.4768,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.7834394904458599,
868
+ "grad_norm": 3.15625,
869
+ "learning_rate": 8.445859872611466e-06,
870
+ "loss": 1.2934,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.7898089171974523,
875
+ "grad_norm": 3.34375,
876
+ "learning_rate": 8.433121019108282e-06,
877
+ "loss": 1.3926,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.7961783439490446,
882
+ "grad_norm": 3.03125,
883
+ "learning_rate": 8.420382165605096e-06,
884
+ "loss": 1.2003,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.802547770700637,
889
+ "grad_norm": 3.4375,
890
+ "learning_rate": 8.407643312101912e-06,
891
+ "loss": 1.1424,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.8089171974522293,
896
+ "grad_norm": 4.375,
897
+ "learning_rate": 8.394904458598728e-06,
898
+ "loss": 1.4789,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.8152866242038217,
903
+ "grad_norm": 3.625,
904
+ "learning_rate": 8.382165605095543e-06,
905
+ "loss": 1.7105,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.821656050955414,
910
+ "grad_norm": 3.34375,
911
+ "learning_rate": 8.369426751592357e-06,
912
+ "loss": 1.4726,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.8280254777070064,
917
+ "grad_norm": 3.5,
918
+ "learning_rate": 8.356687898089173e-06,
919
+ "loss": 1.271,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.8343949044585988,
924
+ "grad_norm": 3.546875,
925
+ "learning_rate": 8.343949044585989e-06,
926
+ "loss": 1.6827,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.8407643312101911,
931
+ "grad_norm": 3.3125,
932
+ "learning_rate": 8.331210191082804e-06,
933
+ "loss": 1.648,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.8471337579617835,
938
+ "grad_norm": 3.75,
939
+ "learning_rate": 8.318471337579618e-06,
940
+ "loss": 1.6786,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.8535031847133758,
945
+ "grad_norm": 3.65625,
946
+ "learning_rate": 8.305732484076434e-06,
947
+ "loss": 1.5643,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.8598726114649682,
952
+ "grad_norm": 3.828125,
953
+ "learning_rate": 8.29299363057325e-06,
954
+ "loss": 1.21,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.8662420382165605,
959
+ "grad_norm": 3.28125,
960
+ "learning_rate": 8.280254777070064e-06,
961
+ "loss": 1.5831,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.8726114649681529,
966
+ "grad_norm": 3.84375,
967
+ "learning_rate": 8.26751592356688e-06,
968
+ "loss": 1.5313,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.8789808917197452,
973
+ "grad_norm": 3.34375,
974
+ "learning_rate": 8.254777070063695e-06,
975
+ "loss": 1.4343,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.8853503184713376,
980
+ "grad_norm": 3.171875,
981
+ "learning_rate": 8.242038216560511e-06,
982
+ "loss": 1.2434,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.89171974522293,
987
+ "grad_norm": 3.75,
988
+ "learning_rate": 8.229299363057325e-06,
989
+ "loss": 1.249,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.8980891719745223,
994
+ "grad_norm": 3.328125,
995
+ "learning_rate": 8.21656050955414e-06,
996
+ "loss": 1.4488,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.9044585987261147,
1001
+ "grad_norm": 3.5,
1002
+ "learning_rate": 8.203821656050957e-06,
1003
+ "loss": 1.1975,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.910828025477707,
1008
+ "grad_norm": 3.5,
1009
+ "learning_rate": 8.191082802547772e-06,
1010
+ "loss": 1.6313,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.9171974522292994,
1015
+ "grad_norm": 3.4375,
1016
+ "learning_rate": 8.178343949044586e-06,
1017
+ "loss": 1.4878,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.9235668789808917,
1022
+ "grad_norm": 3.671875,
1023
+ "learning_rate": 8.165605095541402e-06,
1024
+ "loss": 1.6604,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.9299363057324841,
1029
+ "grad_norm": 3.625,
1030
+ "learning_rate": 8.152866242038218e-06,
1031
+ "loss": 1.4641,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.9363057324840764,
1036
+ "grad_norm": 3.546875,
1037
+ "learning_rate": 8.140127388535033e-06,
1038
+ "loss": 1.354,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.9426751592356688,
1043
+ "grad_norm": 3.578125,
1044
+ "learning_rate": 8.127388535031848e-06,
1045
+ "loss": 1.5926,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.9490445859872612,
1050
+ "grad_norm": 3.703125,
1051
+ "learning_rate": 8.114649681528663e-06,
1052
+ "loss": 1.5102,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.9554140127388535,
1057
+ "grad_norm": 3.421875,
1058
+ "learning_rate": 8.101910828025479e-06,
1059
+ "loss": 1.2165,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.9617834394904459,
1064
+ "grad_norm": 3.59375,
1065
+ "learning_rate": 8.089171974522295e-06,
1066
+ "loss": 1.474,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.9681528662420382,
1071
+ "grad_norm": 3.21875,
1072
+ "learning_rate": 8.076433121019109e-06,
1073
+ "loss": 1.3689,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.9745222929936306,
1078
+ "grad_norm": 2.90625,
1079
+ "learning_rate": 8.063694267515924e-06,
1080
+ "loss": 1.1301,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.9808917197452229,
1085
+ "grad_norm": 3.28125,
1086
+ "learning_rate": 8.05095541401274e-06,
1087
+ "loss": 1.3381,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.9872611464968153,
1092
+ "grad_norm": 3.5625,
1093
+ "learning_rate": 8.038216560509556e-06,
1094
+ "loss": 1.5356,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.9936305732484076,
1099
+ "grad_norm": 3.09375,
1100
+ "learning_rate": 8.02547770700637e-06,
1101
+ "loss": 1.2435,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 1.0,
1106
+ "grad_norm": 7.28125,
1107
+ "learning_rate": 8.012738853503186e-06,
1108
+ "loss": 1.7792,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 1.0,
1113
+ "eval_loss": 2.2599050998687744,
1114
+ "eval_runtime": 9.69,
1115
+ "eval_samples_per_second": 103.199,
1116
+ "eval_steps_per_second": 3.302,
1117
+ "step": 157
1118
+ },
1119
+ {
1120
+ "epoch": 1.0063694267515924,
1121
+ "grad_norm": 4.5,
1122
+ "learning_rate": 8.000000000000001e-06,
1123
+ "loss": 1.1506,
1124
+ "step": 158
1125
+ },
1126
+ {
1127
+ "epoch": 1.0127388535031847,
1128
+ "grad_norm": 3.234375,
1129
+ "learning_rate": 7.987261146496817e-06,
1130
+ "loss": 1.1858,
1131
+ "step": 159
1132
+ },
1133
+ {
1134
+ "epoch": 1.019108280254777,
1135
+ "grad_norm": 3.375,
1136
+ "learning_rate": 7.974522292993631e-06,
1137
+ "loss": 1.3049,
1138
+ "step": 160
1139
+ },
1140
+ {
1141
+ "epoch": 1.0254777070063694,
1142
+ "grad_norm": 3.46875,
1143
+ "learning_rate": 7.961783439490447e-06,
1144
+ "loss": 1.4405,
1145
+ "step": 161
1146
+ },
1147
+ {
1148
+ "epoch": 1.0318471337579618,
1149
+ "grad_norm": 4.3125,
1150
+ "learning_rate": 7.949044585987263e-06,
1151
+ "loss": 1.2883,
1152
+ "step": 162
1153
+ },
1154
+ {
1155
+ "epoch": 1.0382165605095541,
1156
+ "grad_norm": 3.390625,
1157
+ "learning_rate": 7.936305732484078e-06,
1158
+ "loss": 1.3032,
1159
+ "step": 163
1160
+ },
1161
+ {
1162
+ "epoch": 1.0445859872611465,
1163
+ "grad_norm": 3.578125,
1164
+ "learning_rate": 7.923566878980892e-06,
1165
+ "loss": 1.1127,
1166
+ "step": 164
1167
+ },
1168
+ {
1169
+ "epoch": 1.0509554140127388,
1170
+ "grad_norm": 3.75,
1171
+ "learning_rate": 7.910828025477708e-06,
1172
+ "loss": 1.456,
1173
+ "step": 165
1174
+ },
1175
+ {
1176
+ "epoch": 1.0573248407643312,
1177
+ "grad_norm": 3.953125,
1178
+ "learning_rate": 7.898089171974524e-06,
1179
+ "loss": 1.4393,
1180
+ "step": 166
1181
+ },
1182
+ {
1183
+ "epoch": 1.0636942675159236,
1184
+ "grad_norm": 3.578125,
1185
+ "learning_rate": 7.88535031847134e-06,
1186
+ "loss": 1.2993,
1187
+ "step": 167
1188
+ },
1189
+ {
1190
+ "epoch": 1.070063694267516,
1191
+ "grad_norm": 5.1875,
1192
+ "learning_rate": 7.872611464968153e-06,
1193
+ "loss": 1.1857,
1194
+ "step": 168
1195
+ },
1196
+ {
1197
+ "epoch": 1.0764331210191083,
1198
+ "grad_norm": 3.84375,
1199
+ "learning_rate": 7.85987261146497e-06,
1200
+ "loss": 1.4245,
1201
+ "step": 169
1202
+ },
1203
+ {
1204
+ "epoch": 1.0828025477707006,
1205
+ "grad_norm": 10.9375,
1206
+ "learning_rate": 7.847133757961785e-06,
1207
+ "loss": 1.4932,
1208
+ "step": 170
1209
+ },
1210
+ {
1211
+ "epoch": 1.089171974522293,
1212
+ "grad_norm": 4.15625,
1213
+ "learning_rate": 7.8343949044586e-06,
1214
+ "loss": 1.3369,
1215
+ "step": 171
1216
+ },
1217
+ {
1218
+ "epoch": 1.0955414012738853,
1219
+ "grad_norm": 3.890625,
1220
+ "learning_rate": 7.821656050955415e-06,
1221
+ "loss": 1.2068,
1222
+ "step": 172
1223
+ },
1224
+ {
1225
+ "epoch": 1.1019108280254777,
1226
+ "grad_norm": 3.921875,
1227
+ "learning_rate": 7.80891719745223e-06,
1228
+ "loss": 1.2368,
1229
+ "step": 173
1230
+ },
1231
+ {
1232
+ "epoch": 1.10828025477707,
1233
+ "grad_norm": 3.9375,
1234
+ "learning_rate": 7.796178343949046e-06,
1235
+ "loss": 1.3056,
1236
+ "step": 174
1237
+ },
1238
+ {
1239
+ "epoch": 1.1146496815286624,
1240
+ "grad_norm": 3.625,
1241
+ "learning_rate": 7.783439490445862e-06,
1242
+ "loss": 1.3238,
1243
+ "step": 175
1244
+ },
1245
+ {
1246
+ "epoch": 1.1210191082802548,
1247
+ "grad_norm": 4.3125,
1248
+ "learning_rate": 7.770700636942676e-06,
1249
+ "loss": 1.083,
1250
+ "step": 176
1251
+ },
1252
+ {
1253
+ "epoch": 1.127388535031847,
1254
+ "grad_norm": 4.40625,
1255
+ "learning_rate": 7.757961783439492e-06,
1256
+ "loss": 1.3215,
1257
+ "step": 177
1258
+ },
1259
+ {
1260
+ "epoch": 1.1337579617834395,
1261
+ "grad_norm": 6.4375,
1262
+ "learning_rate": 7.745222929936307e-06,
1263
+ "loss": 1.2644,
1264
+ "step": 178
1265
+ },
1266
+ {
1267
+ "epoch": 1.1401273885350318,
1268
+ "grad_norm": 6.46875,
1269
+ "learning_rate": 7.732484076433121e-06,
1270
+ "loss": 1.2775,
1271
+ "step": 179
1272
+ },
1273
+ {
1274
+ "epoch": 1.1464968152866242,
1275
+ "grad_norm": 5.1875,
1276
+ "learning_rate": 7.719745222929937e-06,
1277
+ "loss": 1.383,
1278
+ "step": 180
1279
+ },
1280
+ {
1281
+ "epoch": 1.1528662420382165,
1282
+ "grad_norm": 3.953125,
1283
+ "learning_rate": 7.707006369426753e-06,
1284
+ "loss": 1.4251,
1285
+ "step": 181
1286
+ },
1287
+ {
1288
+ "epoch": 1.1592356687898089,
1289
+ "grad_norm": 4.53125,
1290
+ "learning_rate": 7.694267515923568e-06,
1291
+ "loss": 1.1072,
1292
+ "step": 182
1293
+ },
1294
+ {
1295
+ "epoch": 1.1656050955414012,
1296
+ "grad_norm": 3.8125,
1297
+ "learning_rate": 7.681528662420383e-06,
1298
+ "loss": 1.3237,
1299
+ "step": 183
1300
+ },
1301
+ {
1302
+ "epoch": 1.1719745222929936,
1303
+ "grad_norm": 4.5,
1304
+ "learning_rate": 7.668789808917198e-06,
1305
+ "loss": 1.3913,
1306
+ "step": 184
1307
+ },
1308
+ {
1309
+ "epoch": 1.178343949044586,
1310
+ "grad_norm": 4.3125,
1311
+ "learning_rate": 7.656050955414014e-06,
1312
+ "loss": 1.2478,
1313
+ "step": 185
1314
+ },
1315
+ {
1316
+ "epoch": 1.1847133757961783,
1317
+ "grad_norm": 3.828125,
1318
+ "learning_rate": 7.64331210191083e-06,
1319
+ "loss": 1.441,
1320
+ "step": 186
1321
+ },
1322
+ {
1323
+ "epoch": 1.1910828025477707,
1324
+ "grad_norm": 6.5625,
1325
+ "learning_rate": 7.630573248407644e-06,
1326
+ "loss": 1.2952,
1327
+ "step": 187
1328
+ },
1329
+ {
1330
+ "epoch": 1.197452229299363,
1331
+ "grad_norm": 4.78125,
1332
+ "learning_rate": 7.6178343949044594e-06,
1333
+ "loss": 1.4144,
1334
+ "step": 188
1335
+ },
1336
+ {
1337
+ "epoch": 1.2038216560509554,
1338
+ "grad_norm": 5.34375,
1339
+ "learning_rate": 7.605095541401275e-06,
1340
+ "loss": 1.5017,
1341
+ "step": 189
1342
+ },
1343
+ {
1344
+ "epoch": 1.2101910828025477,
1345
+ "grad_norm": 4.34375,
1346
+ "learning_rate": 7.59235668789809e-06,
1347
+ "loss": 0.8401,
1348
+ "step": 190
1349
+ },
1350
+ {
1351
+ "epoch": 1.21656050955414,
1352
+ "grad_norm": 3.765625,
1353
+ "learning_rate": 7.579617834394906e-06,
1354
+ "loss": 1.1177,
1355
+ "step": 191
1356
+ },
1357
+ {
1358
+ "epoch": 1.2229299363057324,
1359
+ "grad_norm": 4.8125,
1360
+ "learning_rate": 7.566878980891721e-06,
1361
+ "loss": 1.3994,
1362
+ "step": 192
1363
+ },
1364
+ {
1365
+ "epoch": 1.2292993630573248,
1366
+ "grad_norm": 3.296875,
1367
+ "learning_rate": 7.554140127388536e-06,
1368
+ "loss": 0.8772,
1369
+ "step": 193
1370
+ },
1371
+ {
1372
+ "epoch": 1.2356687898089171,
1373
+ "grad_norm": 3.71875,
1374
+ "learning_rate": 7.541401273885351e-06,
1375
+ "loss": 1.0378,
1376
+ "step": 194
1377
+ },
1378
+ {
1379
+ "epoch": 1.2420382165605095,
1380
+ "grad_norm": 4.0,
1381
+ "learning_rate": 7.528662420382167e-06,
1382
+ "loss": 1.3615,
1383
+ "step": 195
1384
+ },
1385
+ {
1386
+ "epoch": 1.2484076433121019,
1387
+ "grad_norm": 3.9375,
1388
+ "learning_rate": 7.515923566878982e-06,
1389
+ "loss": 1.2462,
1390
+ "step": 196
1391
+ },
1392
+ {
1393
+ "epoch": 1.2547770700636942,
1394
+ "grad_norm": 4.25,
1395
+ "learning_rate": 7.5031847133757975e-06,
1396
+ "loss": 1.3453,
1397
+ "step": 197
1398
+ },
1399
+ {
1400
+ "epoch": 1.2611464968152866,
1401
+ "grad_norm": 4.34375,
1402
+ "learning_rate": 7.4904458598726116e-06,
1403
+ "loss": 1.2121,
1404
+ "step": 198
1405
+ },
1406
+ {
1407
+ "epoch": 1.267515923566879,
1408
+ "grad_norm": 3.984375,
1409
+ "learning_rate": 7.4777070063694264e-06,
1410
+ "loss": 1.3042,
1411
+ "step": 199
1412
+ },
1413
+ {
1414
+ "epoch": 1.2738853503184713,
1415
+ "grad_norm": 4.03125,
1416
+ "learning_rate": 7.464968152866242e-06,
1417
+ "loss": 1.2796,
1418
+ "step": 200
1419
+ },
1420
+ {
1421
+ "epoch": 1.2802547770700636,
1422
+ "grad_norm": 4.1875,
1423
+ "learning_rate": 7.452229299363057e-06,
1424
+ "loss": 1.3834,
1425
+ "step": 201
1426
+ },
1427
+ {
1428
+ "epoch": 1.286624203821656,
1429
+ "grad_norm": 4.9375,
1430
+ "learning_rate": 7.439490445859873e-06,
1431
+ "loss": 1.1585,
1432
+ "step": 202
1433
+ },
1434
+ {
1435
+ "epoch": 1.2929936305732483,
1436
+ "grad_norm": 4.59375,
1437
+ "learning_rate": 7.426751592356688e-06,
1438
+ "loss": 1.4038,
1439
+ "step": 203
1440
+ },
1441
+ {
1442
+ "epoch": 1.2993630573248407,
1443
+ "grad_norm": 3.84375,
1444
+ "learning_rate": 7.414012738853503e-06,
1445
+ "loss": 1.2507,
1446
+ "step": 204
1447
+ },
1448
+ {
1449
+ "epoch": 1.305732484076433,
1450
+ "grad_norm": 4.375,
1451
+ "learning_rate": 7.401273885350318e-06,
1452
+ "loss": 1.4411,
1453
+ "step": 205
1454
+ },
1455
+ {
1456
+ "epoch": 1.3121019108280254,
1457
+ "grad_norm": 4.0625,
1458
+ "learning_rate": 7.388535031847134e-06,
1459
+ "loss": 1.3703,
1460
+ "step": 206
1461
+ },
1462
+ {
1463
+ "epoch": 1.3184713375796178,
1464
+ "grad_norm": 3.859375,
1465
+ "learning_rate": 7.375796178343949e-06,
1466
+ "loss": 1.0656,
1467
+ "step": 207
1468
+ },
1469
+ {
1470
+ "epoch": 1.3248407643312101,
1471
+ "grad_norm": 3.765625,
1472
+ "learning_rate": 7.3630573248407645e-06,
1473
+ "loss": 1.0934,
1474
+ "step": 208
1475
+ },
1476
+ {
1477
+ "epoch": 1.3312101910828025,
1478
+ "grad_norm": 3.96875,
1479
+ "learning_rate": 7.350318471337579e-06,
1480
+ "loss": 1.2435,
1481
+ "step": 209
1482
+ },
1483
+ {
1484
+ "epoch": 1.3375796178343948,
1485
+ "grad_norm": 4.4375,
1486
+ "learning_rate": 7.337579617834395e-06,
1487
+ "loss": 1.5807,
1488
+ "step": 210
1489
+ },
1490
+ {
1491
+ "epoch": 1.3439490445859872,
1492
+ "grad_norm": 4.3125,
1493
+ "learning_rate": 7.32484076433121e-06,
1494
+ "loss": 1.2829,
1495
+ "step": 211
1496
+ },
1497
+ {
1498
+ "epoch": 1.3503184713375795,
1499
+ "grad_norm": 3.828125,
1500
+ "learning_rate": 7.312101910828026e-06,
1501
+ "loss": 1.2033,
1502
+ "step": 212
1503
+ },
1504
+ {
1505
+ "epoch": 1.356687898089172,
1506
+ "grad_norm": 3.953125,
1507
+ "learning_rate": 7.299363057324841e-06,
1508
+ "loss": 1.3174,
1509
+ "step": 213
1510
+ },
1511
+ {
1512
+ "epoch": 1.3630573248407643,
1513
+ "grad_norm": 3.609375,
1514
+ "learning_rate": 7.286624203821656e-06,
1515
+ "loss": 1.1424,
1516
+ "step": 214
1517
+ },
1518
+ {
1519
+ "epoch": 1.3694267515923566,
1520
+ "grad_norm": 3.59375,
1521
+ "learning_rate": 7.273885350318471e-06,
1522
+ "loss": 1.0503,
1523
+ "step": 215
1524
+ },
1525
+ {
1526
+ "epoch": 1.3757961783439492,
1527
+ "grad_norm": 3.515625,
1528
+ "learning_rate": 7.261146496815287e-06,
1529
+ "loss": 1.0615,
1530
+ "step": 216
1531
+ },
1532
+ {
1533
+ "epoch": 1.3821656050955413,
1534
+ "grad_norm": 4.0,
1535
+ "learning_rate": 7.248407643312102e-06,
1536
+ "loss": 1.1418,
1537
+ "step": 217
1538
+ },
1539
+ {
1540
+ "epoch": 1.388535031847134,
1541
+ "grad_norm": 4.375,
1542
+ "learning_rate": 7.2356687898089175e-06,
1543
+ "loss": 1.1493,
1544
+ "step": 218
1545
+ },
1546
+ {
1547
+ "epoch": 1.394904458598726,
1548
+ "grad_norm": 3.875,
1549
+ "learning_rate": 7.222929936305732e-06,
1550
+ "loss": 1.216,
1551
+ "step": 219
1552
+ },
1553
+ {
1554
+ "epoch": 1.4012738853503186,
1555
+ "grad_norm": 4.46875,
1556
+ "learning_rate": 7.210191082802548e-06,
1557
+ "loss": 1.3689,
1558
+ "step": 220
1559
+ },
1560
+ {
1561
+ "epoch": 1.4076433121019107,
1562
+ "grad_norm": 4.25,
1563
+ "learning_rate": 7.197452229299363e-06,
1564
+ "loss": 1.2668,
1565
+ "step": 221
1566
+ },
1567
+ {
1568
+ "epoch": 1.4140127388535033,
1569
+ "grad_norm": 4.03125,
1570
+ "learning_rate": 7.184713375796179e-06,
1571
+ "loss": 1.1461,
1572
+ "step": 222
1573
+ },
1574
+ {
1575
+ "epoch": 1.4203821656050954,
1576
+ "grad_norm": 4.3125,
1577
+ "learning_rate": 7.171974522292994e-06,
1578
+ "loss": 1.3251,
1579
+ "step": 223
1580
+ },
1581
+ {
1582
+ "epoch": 1.426751592356688,
1583
+ "grad_norm": 4.25,
1584
+ "learning_rate": 7.159235668789809e-06,
1585
+ "loss": 1.2247,
1586
+ "step": 224
1587
+ },
1588
+ {
1589
+ "epoch": 1.4331210191082802,
1590
+ "grad_norm": 4.21875,
1591
+ "learning_rate": 7.146496815286624e-06,
1592
+ "loss": 1.1493,
1593
+ "step": 225
1594
+ },
1595
+ {
1596
+ "epoch": 1.4394904458598727,
1597
+ "grad_norm": 4.0625,
1598
+ "learning_rate": 7.13375796178344e-06,
1599
+ "loss": 1.001,
1600
+ "step": 226
1601
+ },
1602
+ {
1603
+ "epoch": 1.4458598726114649,
1604
+ "grad_norm": 5.15625,
1605
+ "learning_rate": 7.121019108280255e-06,
1606
+ "loss": 1.2535,
1607
+ "step": 227
1608
+ },
1609
+ {
1610
+ "epoch": 1.4522292993630574,
1611
+ "grad_norm": 4.46875,
1612
+ "learning_rate": 7.1082802547770705e-06,
1613
+ "loss": 1.2611,
1614
+ "step": 228
1615
+ },
1616
+ {
1617
+ "epoch": 1.4585987261146496,
1618
+ "grad_norm": 4.46875,
1619
+ "learning_rate": 7.095541401273885e-06,
1620
+ "loss": 1.2477,
1621
+ "step": 229
1622
+ },
1623
+ {
1624
+ "epoch": 1.4649681528662422,
1625
+ "grad_norm": 3.8125,
1626
+ "learning_rate": 7.082802547770701e-06,
1627
+ "loss": 1.036,
1628
+ "step": 230
1629
+ },
1630
+ {
1631
+ "epoch": 1.4713375796178343,
1632
+ "grad_norm": 5.3125,
1633
+ "learning_rate": 7.070063694267516e-06,
1634
+ "loss": 1.1686,
1635
+ "step": 231
1636
+ },
1637
+ {
1638
+ "epoch": 1.4777070063694269,
1639
+ "grad_norm": 4.15625,
1640
+ "learning_rate": 7.057324840764332e-06,
1641
+ "loss": 0.9747,
1642
+ "step": 232
1643
+ },
1644
+ {
1645
+ "epoch": 1.484076433121019,
1646
+ "grad_norm": 4.625,
1647
+ "learning_rate": 7.0445859872611466e-06,
1648
+ "loss": 1.3628,
1649
+ "step": 233
1650
+ },
1651
+ {
1652
+ "epoch": 1.4904458598726116,
1653
+ "grad_norm": 4.625,
1654
+ "learning_rate": 7.031847133757962e-06,
1655
+ "loss": 1.1824,
1656
+ "step": 234
1657
+ },
1658
+ {
1659
+ "epoch": 1.4968152866242037,
1660
+ "grad_norm": 4.4375,
1661
+ "learning_rate": 7.019108280254777e-06,
1662
+ "loss": 1.3513,
1663
+ "step": 235
1664
+ },
1665
+ {
1666
+ "epoch": 1.5031847133757963,
1667
+ "grad_norm": 4.53125,
1668
+ "learning_rate": 7.006369426751593e-06,
1669
+ "loss": 1.1555,
1670
+ "step": 236
1671
+ },
1672
+ {
1673
+ "epoch": 1.5095541401273884,
1674
+ "grad_norm": 4.28125,
1675
+ "learning_rate": 6.993630573248408e-06,
1676
+ "loss": 1.19,
1677
+ "step": 237
1678
+ },
1679
+ {
1680
+ "epoch": 1.515923566878981,
1681
+ "grad_norm": 4.53125,
1682
+ "learning_rate": 6.9808917197452235e-06,
1683
+ "loss": 1.1311,
1684
+ "step": 238
1685
+ },
1686
+ {
1687
+ "epoch": 1.5222929936305731,
1688
+ "grad_norm": 5.125,
1689
+ "learning_rate": 6.968152866242038e-06,
1690
+ "loss": 1.1492,
1691
+ "step": 239
1692
+ },
1693
+ {
1694
+ "epoch": 1.5286624203821657,
1695
+ "grad_norm": 4.25,
1696
+ "learning_rate": 6.955414012738853e-06,
1697
+ "loss": 1.0331,
1698
+ "step": 240
1699
+ },
1700
+ {
1701
+ "epoch": 1.5350318471337578,
1702
+ "grad_norm": 4.53125,
1703
+ "learning_rate": 6.942675159235669e-06,
1704
+ "loss": 1.18,
1705
+ "step": 241
1706
+ },
1707
+ {
1708
+ "epoch": 1.5414012738853504,
1709
+ "grad_norm": 4.46875,
1710
+ "learning_rate": 6.929936305732484e-06,
1711
+ "loss": 1.2018,
1712
+ "step": 242
1713
+ },
1714
+ {
1715
+ "epoch": 1.5477707006369426,
1716
+ "grad_norm": 4.15625,
1717
+ "learning_rate": 6.9171974522292995e-06,
1718
+ "loss": 1.1482,
1719
+ "step": 243
1720
+ },
1721
+ {
1722
+ "epoch": 1.5541401273885351,
1723
+ "grad_norm": 4.15625,
1724
+ "learning_rate": 6.904458598726114e-06,
1725
+ "loss": 1.16,
1726
+ "step": 244
1727
+ },
1728
+ {
1729
+ "epoch": 1.5605095541401273,
1730
+ "grad_norm": 4.125,
1731
+ "learning_rate": 6.89171974522293e-06,
1732
+ "loss": 1.1973,
1733
+ "step": 245
1734
+ },
1735
+ {
1736
+ "epoch": 1.5668789808917198,
1737
+ "grad_norm": 5.0625,
1738
+ "learning_rate": 6.878980891719745e-06,
1739
+ "loss": 1.242,
1740
+ "step": 246
1741
+ },
1742
+ {
1743
+ "epoch": 1.573248407643312,
1744
+ "grad_norm": 4.84375,
1745
+ "learning_rate": 6.866242038216561e-06,
1746
+ "loss": 1.4425,
1747
+ "step": 247
1748
+ },
1749
+ {
1750
+ "epoch": 1.5796178343949046,
1751
+ "grad_norm": 4.09375,
1752
+ "learning_rate": 6.853503184713376e-06,
1753
+ "loss": 1.2239,
1754
+ "step": 248
1755
+ },
1756
+ {
1757
+ "epoch": 1.5859872611464967,
1758
+ "grad_norm": 4.3125,
1759
+ "learning_rate": 6.840764331210191e-06,
1760
+ "loss": 1.2579,
1761
+ "step": 249
1762
+ },
1763
+ {
1764
+ "epoch": 1.5923566878980893,
1765
+ "grad_norm": 5.03125,
1766
+ "learning_rate": 6.828025477707006e-06,
1767
+ "loss": 1.2273,
1768
+ "step": 250
1769
+ },
1770
+ {
1771
+ "epoch": 1.5987261146496814,
1772
+ "grad_norm": 4.65625,
1773
+ "learning_rate": 6.815286624203822e-06,
1774
+ "loss": 1.232,
1775
+ "step": 251
1776
+ },
1777
+ {
1778
+ "epoch": 1.605095541401274,
1779
+ "grad_norm": 4.25,
1780
+ "learning_rate": 6.802547770700637e-06,
1781
+ "loss": 1.093,
1782
+ "step": 252
1783
+ },
1784
+ {
1785
+ "epoch": 1.611464968152866,
1786
+ "grad_norm": 4.15625,
1787
+ "learning_rate": 6.7898089171974525e-06,
1788
+ "loss": 1.0387,
1789
+ "step": 253
1790
+ },
1791
+ {
1792
+ "epoch": 1.6178343949044587,
1793
+ "grad_norm": 4.875,
1794
+ "learning_rate": 6.777070063694267e-06,
1795
+ "loss": 1.3383,
1796
+ "step": 254
1797
+ },
1798
+ {
1799
+ "epoch": 1.6242038216560508,
1800
+ "grad_norm": 4.8125,
1801
+ "learning_rate": 6.764331210191083e-06,
1802
+ "loss": 1.1986,
1803
+ "step": 255
1804
+ },
1805
+ {
1806
+ "epoch": 1.6305732484076434,
1807
+ "grad_norm": 4.71875,
1808
+ "learning_rate": 6.751592356687898e-06,
1809
+ "loss": 1.3457,
1810
+ "step": 256
1811
+ },
1812
+ {
1813
+ "epoch": 1.6369426751592355,
1814
+ "grad_norm": 4.46875,
1815
+ "learning_rate": 6.738853503184714e-06,
1816
+ "loss": 1.0068,
1817
+ "step": 257
1818
+ },
1819
+ {
1820
+ "epoch": 1.643312101910828,
1821
+ "grad_norm": 4.75,
1822
+ "learning_rate": 6.726114649681529e-06,
1823
+ "loss": 1.337,
1824
+ "step": 258
1825
+ },
1826
+ {
1827
+ "epoch": 1.6496815286624202,
1828
+ "grad_norm": 5.34375,
1829
+ "learning_rate": 6.713375796178344e-06,
1830
+ "loss": 1.1661,
1831
+ "step": 259
1832
+ },
1833
+ {
1834
+ "epoch": 1.6560509554140128,
1835
+ "grad_norm": 4.40625,
1836
+ "learning_rate": 6.700636942675159e-06,
1837
+ "loss": 1.3514,
1838
+ "step": 260
1839
+ },
1840
+ {
1841
+ "epoch": 1.662420382165605,
1842
+ "grad_norm": 3.828125,
1843
+ "learning_rate": 6.687898089171975e-06,
1844
+ "loss": 0.9007,
1845
+ "step": 261
1846
+ },
1847
+ {
1848
+ "epoch": 1.6687898089171975,
1849
+ "grad_norm": 4.9375,
1850
+ "learning_rate": 6.67515923566879e-06,
1851
+ "loss": 1.2414,
1852
+ "step": 262
1853
+ },
1854
+ {
1855
+ "epoch": 1.6751592356687897,
1856
+ "grad_norm": 4.375,
1857
+ "learning_rate": 6.6624203821656055e-06,
1858
+ "loss": 1.0775,
1859
+ "step": 263
1860
+ },
1861
+ {
1862
+ "epoch": 1.6815286624203822,
1863
+ "grad_norm": 4.03125,
1864
+ "learning_rate": 6.64968152866242e-06,
1865
+ "loss": 0.9075,
1866
+ "step": 264
1867
+ },
1868
+ {
1869
+ "epoch": 1.6878980891719744,
1870
+ "grad_norm": 4.28125,
1871
+ "learning_rate": 6.636942675159236e-06,
1872
+ "loss": 1.0077,
1873
+ "step": 265
1874
+ },
1875
+ {
1876
+ "epoch": 1.694267515923567,
1877
+ "grad_norm": 4.9375,
1878
+ "learning_rate": 6.624203821656051e-06,
1879
+ "loss": 1.2201,
1880
+ "step": 266
1881
+ },
1882
+ {
1883
+ "epoch": 1.700636942675159,
1884
+ "grad_norm": 4.75,
1885
+ "learning_rate": 6.611464968152867e-06,
1886
+ "loss": 1.2891,
1887
+ "step": 267
1888
+ },
1889
+ {
1890
+ "epoch": 1.7070063694267517,
1891
+ "grad_norm": 4.28125,
1892
+ "learning_rate": 6.5987261146496816e-06,
1893
+ "loss": 1.0489,
1894
+ "step": 268
1895
+ },
1896
+ {
1897
+ "epoch": 1.7133757961783438,
1898
+ "grad_norm": 4.96875,
1899
+ "learning_rate": 6.585987261146497e-06,
1900
+ "loss": 1.2859,
1901
+ "step": 269
1902
+ },
1903
+ {
1904
+ "epoch": 1.7197452229299364,
1905
+ "grad_norm": 4.4375,
1906
+ "learning_rate": 6.573248407643312e-06,
1907
+ "loss": 1.0655,
1908
+ "step": 270
1909
+ },
1910
+ {
1911
+ "epoch": 1.7261146496815285,
1912
+ "grad_norm": 4.78125,
1913
+ "learning_rate": 6.560509554140128e-06,
1914
+ "loss": 1.2287,
1915
+ "step": 271
1916
+ },
1917
+ {
1918
+ "epoch": 1.732484076433121,
1919
+ "grad_norm": 4.34375,
1920
+ "learning_rate": 6.547770700636943e-06,
1921
+ "loss": 1.0643,
1922
+ "step": 272
1923
+ },
1924
+ {
1925
+ "epoch": 1.7388535031847132,
1926
+ "grad_norm": 5.15625,
1927
+ "learning_rate": 6.5350318471337585e-06,
1928
+ "loss": 1.3527,
1929
+ "step": 273
1930
+ },
1931
+ {
1932
+ "epoch": 1.7452229299363058,
1933
+ "grad_norm": 4.25,
1934
+ "learning_rate": 6.522292993630573e-06,
1935
+ "loss": 0.924,
1936
+ "step": 274
1937
+ },
1938
+ {
1939
+ "epoch": 1.7515923566878981,
1940
+ "grad_norm": 4.90625,
1941
+ "learning_rate": 6.509554140127389e-06,
1942
+ "loss": 1.1214,
1943
+ "step": 275
1944
+ },
1945
+ {
1946
+ "epoch": 1.7579617834394905,
1947
+ "grad_norm": 4.53125,
1948
+ "learning_rate": 6.496815286624204e-06,
1949
+ "loss": 1.1423,
1950
+ "step": 276
1951
+ },
1952
+ {
1953
+ "epoch": 1.7643312101910829,
1954
+ "grad_norm": 4.65625,
1955
+ "learning_rate": 6.48407643312102e-06,
1956
+ "loss": 1.1389,
1957
+ "step": 277
1958
+ },
1959
+ {
1960
+ "epoch": 1.7707006369426752,
1961
+ "grad_norm": 4.875,
1962
+ "learning_rate": 6.4713375796178345e-06,
1963
+ "loss": 1.1472,
1964
+ "step": 278
1965
+ },
1966
+ {
1967
+ "epoch": 1.7770700636942676,
1968
+ "grad_norm": 4.84375,
1969
+ "learning_rate": 6.45859872611465e-06,
1970
+ "loss": 1.1178,
1971
+ "step": 279
1972
+ },
1973
+ {
1974
+ "epoch": 1.78343949044586,
1975
+ "grad_norm": 4.46875,
1976
+ "learning_rate": 6.445859872611465e-06,
1977
+ "loss": 0.9769,
1978
+ "step": 280
1979
+ },
1980
+ {
1981
+ "epoch": 1.7898089171974523,
1982
+ "grad_norm": 4.9375,
1983
+ "learning_rate": 6.433121019108281e-06,
1984
+ "loss": 1.1464,
1985
+ "step": 281
1986
+ },
1987
+ {
1988
+ "epoch": 1.7961783439490446,
1989
+ "grad_norm": 4.46875,
1990
+ "learning_rate": 6.420382165605096e-06,
1991
+ "loss": 0.9458,
1992
+ "step": 282
1993
+ },
1994
+ {
1995
+ "epoch": 1.802547770700637,
1996
+ "grad_norm": 6.28125,
1997
+ "learning_rate": 6.407643312101911e-06,
1998
+ "loss": 1.2675,
1999
+ "step": 283
2000
+ },
2001
+ {
2002
+ "epoch": 1.8089171974522293,
2003
+ "grad_norm": 4.65625,
2004
+ "learning_rate": 6.394904458598726e-06,
2005
+ "loss": 1.0196,
2006
+ "step": 284
2007
+ },
2008
+ {
2009
+ "epoch": 1.8152866242038217,
2010
+ "grad_norm": 5.46875,
2011
+ "learning_rate": 6.382165605095541e-06,
2012
+ "loss": 1.1926,
2013
+ "step": 285
2014
+ },
2015
+ {
2016
+ "epoch": 1.821656050955414,
2017
+ "grad_norm": 4.65625,
2018
+ "learning_rate": 6.369426751592357e-06,
2019
+ "loss": 1.0087,
2020
+ "step": 286
2021
+ },
2022
+ {
2023
+ "epoch": 1.8280254777070064,
2024
+ "grad_norm": 5.03125,
2025
+ "learning_rate": 6.356687898089172e-06,
2026
+ "loss": 1.1128,
2027
+ "step": 287
2028
+ },
2029
+ {
2030
+ "epoch": 1.8343949044585988,
2031
+ "grad_norm": 5.09375,
2032
+ "learning_rate": 6.3439490445859875e-06,
2033
+ "loss": 1.4313,
2034
+ "step": 288
2035
+ },
2036
+ {
2037
+ "epoch": 1.8407643312101911,
2038
+ "grad_norm": 4.8125,
2039
+ "learning_rate": 6.331210191082802e-06,
2040
+ "loss": 1.0971,
2041
+ "step": 289
2042
+ },
2043
+ {
2044
+ "epoch": 1.8471337579617835,
2045
+ "grad_norm": 5.1875,
2046
+ "learning_rate": 6.318471337579618e-06,
2047
+ "loss": 1.0814,
2048
+ "step": 290
2049
+ },
2050
+ {
2051
+ "epoch": 1.8535031847133758,
2052
+ "grad_norm": 4.75,
2053
+ "learning_rate": 6.305732484076433e-06,
2054
+ "loss": 1.1713,
2055
+ "step": 291
2056
+ },
2057
+ {
2058
+ "epoch": 1.8598726114649682,
2059
+ "grad_norm": 4.40625,
2060
+ "learning_rate": 6.292993630573249e-06,
2061
+ "loss": 0.9948,
2062
+ "step": 292
2063
+ },
2064
+ {
2065
+ "epoch": 1.8662420382165605,
2066
+ "grad_norm": 5.25,
2067
+ "learning_rate": 6.280254777070064e-06,
2068
+ "loss": 1.0782,
2069
+ "step": 293
2070
+ },
2071
+ {
2072
+ "epoch": 1.872611464968153,
2073
+ "grad_norm": 5.125,
2074
+ "learning_rate": 6.267515923566879e-06,
2075
+ "loss": 1.1431,
2076
+ "step": 294
2077
+ },
2078
+ {
2079
+ "epoch": 1.8789808917197452,
2080
+ "grad_norm": 4.90625,
2081
+ "learning_rate": 6.254777070063694e-06,
2082
+ "loss": 0.8715,
2083
+ "step": 295
2084
+ },
2085
+ {
2086
+ "epoch": 1.8853503184713376,
2087
+ "grad_norm": 6.53125,
2088
+ "learning_rate": 6.24203821656051e-06,
2089
+ "loss": 1.0932,
2090
+ "step": 296
2091
+ },
2092
+ {
2093
+ "epoch": 1.89171974522293,
2094
+ "grad_norm": 5.1875,
2095
+ "learning_rate": 6.229299363057325e-06,
2096
+ "loss": 1.1361,
2097
+ "step": 297
2098
+ },
2099
+ {
2100
+ "epoch": 1.8980891719745223,
2101
+ "grad_norm": 4.5625,
2102
+ "learning_rate": 6.2165605095541405e-06,
2103
+ "loss": 0.9174,
2104
+ "step": 298
2105
+ },
2106
+ {
2107
+ "epoch": 1.9044585987261147,
2108
+ "grad_norm": 5.34375,
2109
+ "learning_rate": 6.203821656050955e-06,
2110
+ "loss": 1.1412,
2111
+ "step": 299
2112
+ },
2113
+ {
2114
+ "epoch": 1.910828025477707,
2115
+ "grad_norm": 5.21875,
2116
+ "learning_rate": 6.191082802547771e-06,
2117
+ "loss": 1.061,
2118
+ "step": 300
2119
+ },
2120
+ {
2121
+ "epoch": 1.9171974522292994,
2122
+ "grad_norm": 4.875,
2123
+ "learning_rate": 6.178343949044586e-06,
2124
+ "loss": 0.8711,
2125
+ "step": 301
2126
+ },
2127
+ {
2128
+ "epoch": 1.9235668789808917,
2129
+ "grad_norm": 5.15625,
2130
+ "learning_rate": 6.165605095541402e-06,
2131
+ "loss": 1.2286,
2132
+ "step": 302
2133
+ },
2134
+ {
2135
+ "epoch": 1.929936305732484,
2136
+ "grad_norm": 5.3125,
2137
+ "learning_rate": 6.1528662420382166e-06,
2138
+ "loss": 1.2596,
2139
+ "step": 303
2140
+ },
2141
+ {
2142
+ "epoch": 1.9363057324840764,
2143
+ "grad_norm": 4.875,
2144
+ "learning_rate": 6.140127388535032e-06,
2145
+ "loss": 0.9906,
2146
+ "step": 304
2147
+ },
2148
+ {
2149
+ "epoch": 1.9426751592356688,
2150
+ "grad_norm": 6.78125,
2151
+ "learning_rate": 6.127388535031847e-06,
2152
+ "loss": 1.2213,
2153
+ "step": 305
2154
+ },
2155
+ {
2156
+ "epoch": 1.9490445859872612,
2157
+ "grad_norm": 6.09375,
2158
+ "learning_rate": 6.114649681528663e-06,
2159
+ "loss": 1.0763,
2160
+ "step": 306
2161
+ },
2162
+ {
2163
+ "epoch": 1.9554140127388535,
2164
+ "grad_norm": 5.5,
2165
+ "learning_rate": 6.101910828025478e-06,
2166
+ "loss": 1.1975,
2167
+ "step": 307
2168
+ },
2169
+ {
2170
+ "epoch": 1.9617834394904459,
2171
+ "grad_norm": 5.09375,
2172
+ "learning_rate": 6.0891719745222935e-06,
2173
+ "loss": 1.0961,
2174
+ "step": 308
2175
+ },
2176
+ {
2177
+ "epoch": 1.9681528662420382,
2178
+ "grad_norm": 4.9375,
2179
+ "learning_rate": 6.076433121019108e-06,
2180
+ "loss": 0.9932,
2181
+ "step": 309
2182
+ },
2183
+ {
2184
+ "epoch": 1.9745222929936306,
2185
+ "grad_norm": 5.125,
2186
+ "learning_rate": 6.063694267515924e-06,
2187
+ "loss": 1.1388,
2188
+ "step": 310
2189
+ },
2190
+ {
2191
+ "epoch": 1.980891719745223,
2192
+ "grad_norm": 4.90625,
2193
+ "learning_rate": 6.050955414012739e-06,
2194
+ "loss": 0.9322,
2195
+ "step": 311
2196
+ },
2197
+ {
2198
+ "epoch": 1.9872611464968153,
2199
+ "grad_norm": 4.5625,
2200
+ "learning_rate": 6.038216560509555e-06,
2201
+ "loss": 0.9378,
2202
+ "step": 312
2203
+ },
2204
+ {
2205
+ "epoch": 1.9936305732484076,
2206
+ "grad_norm": 5.6875,
2207
+ "learning_rate": 6.0254777070063696e-06,
2208
+ "loss": 1.1822,
2209
+ "step": 313
2210
+ },
2211
+ {
2212
+ "epoch": 2.0,
2213
+ "grad_norm": 9.4375,
2214
+ "learning_rate": 6.012738853503185e-06,
2215
+ "loss": 0.973,
2216
+ "step": 314
2217
+ },
2218
+ {
2219
+ "epoch": 2.0,
2220
+ "eval_loss": 2.421236276626587,
2221
+ "eval_runtime": 9.7434,
2222
+ "eval_samples_per_second": 102.633,
2223
+ "eval_steps_per_second": 3.284,
2224
+ "step": 314
2225
+ },
2226
+ {
2227
+ "epoch": 2.0063694267515926,
2228
+ "grad_norm": 5.71875,
2229
+ "learning_rate": 6e-06,
2230
+ "loss": 1.132,
2231
+ "step": 315
2232
+ },
2233
+ {
2234
+ "epoch": 2.0127388535031847,
2235
+ "grad_norm": 5.875,
2236
+ "learning_rate": 5.987261146496816e-06,
2237
+ "loss": 1.1461,
2238
+ "step": 316
2239
+ },
2240
+ {
2241
+ "epoch": 2.0191082802547773,
2242
+ "grad_norm": 5.40625,
2243
+ "learning_rate": 5.974522292993631e-06,
2244
+ "loss": 0.9499,
2245
+ "step": 317
2246
+ },
2247
+ {
2248
+ "epoch": 2.0254777070063694,
2249
+ "grad_norm": 8.4375,
2250
+ "learning_rate": 5.9617834394904465e-06,
2251
+ "loss": 1.1719,
2252
+ "step": 318
2253
+ },
2254
+ {
2255
+ "epoch": 2.031847133757962,
2256
+ "grad_norm": 5.53125,
2257
+ "learning_rate": 5.949044585987261e-06,
2258
+ "loss": 0.9764,
2259
+ "step": 319
2260
+ },
2261
+ {
2262
+ "epoch": 2.038216560509554,
2263
+ "grad_norm": 5.71875,
2264
+ "learning_rate": 5.936305732484077e-06,
2265
+ "loss": 0.9386,
2266
+ "step": 320
2267
+ },
2268
+ {
2269
+ "epoch": 2.0445859872611467,
2270
+ "grad_norm": 5.625,
2271
+ "learning_rate": 5.923566878980892e-06,
2272
+ "loss": 0.9658,
2273
+ "step": 321
2274
+ },
2275
+ {
2276
+ "epoch": 2.050955414012739,
2277
+ "grad_norm": 6.5625,
2278
+ "learning_rate": 5.910828025477708e-06,
2279
+ "loss": 1.0306,
2280
+ "step": 322
2281
+ },
2282
+ {
2283
+ "epoch": 2.0573248407643314,
2284
+ "grad_norm": 5.65625,
2285
+ "learning_rate": 5.8980891719745225e-06,
2286
+ "loss": 0.8619,
2287
+ "step": 323
2288
+ },
2289
+ {
2290
+ "epoch": 2.0636942675159236,
2291
+ "grad_norm": 6.8125,
2292
+ "learning_rate": 5.885350318471338e-06,
2293
+ "loss": 1.0412,
2294
+ "step": 324
2295
+ },
2296
+ {
2297
+ "epoch": 2.070063694267516,
2298
+ "grad_norm": 6.375,
2299
+ "learning_rate": 5.872611464968153e-06,
2300
+ "loss": 1.1013,
2301
+ "step": 325
2302
+ },
2303
+ {
2304
+ "epoch": 2.0764331210191083,
2305
+ "grad_norm": 5.5625,
2306
+ "learning_rate": 5.859872611464969e-06,
2307
+ "loss": 0.8714,
2308
+ "step": 326
2309
+ },
2310
+ {
2311
+ "epoch": 2.082802547770701,
2312
+ "grad_norm": 6.71875,
2313
+ "learning_rate": 5.847133757961784e-06,
2314
+ "loss": 0.9839,
2315
+ "step": 327
2316
+ },
2317
+ {
2318
+ "epoch": 2.089171974522293,
2319
+ "grad_norm": 6.0,
2320
+ "learning_rate": 5.834394904458599e-06,
2321
+ "loss": 1.0009,
2322
+ "step": 328
2323
+ },
2324
+ {
2325
+ "epoch": 2.0955414012738856,
2326
+ "grad_norm": 5.8125,
2327
+ "learning_rate": 5.821656050955414e-06,
2328
+ "loss": 1.1039,
2329
+ "step": 329
2330
+ },
2331
+ {
2332
+ "epoch": 2.1019108280254777,
2333
+ "grad_norm": 5.21875,
2334
+ "learning_rate": 5.808917197452229e-06,
2335
+ "loss": 0.8139,
2336
+ "step": 330
2337
+ },
2338
+ {
2339
+ "epoch": 2.1082802547770703,
2340
+ "grad_norm": 5.28125,
2341
+ "learning_rate": 5.796178343949045e-06,
2342
+ "loss": 0.8953,
2343
+ "step": 331
2344
+ },
2345
+ {
2346
+ "epoch": 2.1146496815286624,
2347
+ "grad_norm": 6.8125,
2348
+ "learning_rate": 5.78343949044586e-06,
2349
+ "loss": 1.0324,
2350
+ "step": 332
2351
+ },
2352
+ {
2353
+ "epoch": 2.121019108280255,
2354
+ "grad_norm": 6.65625,
2355
+ "learning_rate": 5.7707006369426755e-06,
2356
+ "loss": 1.1492,
2357
+ "step": 333
2358
+ },
2359
+ {
2360
+ "epoch": 2.127388535031847,
2361
+ "grad_norm": 6.5,
2362
+ "learning_rate": 5.75796178343949e-06,
2363
+ "loss": 0.9653,
2364
+ "step": 334
2365
+ },
2366
+ {
2367
+ "epoch": 2.1337579617834397,
2368
+ "grad_norm": 5.96875,
2369
+ "learning_rate": 5.745222929936306e-06,
2370
+ "loss": 1.1312,
2371
+ "step": 335
2372
+ },
2373
+ {
2374
+ "epoch": 2.140127388535032,
2375
+ "grad_norm": 6.3125,
2376
+ "learning_rate": 5.732484076433121e-06,
2377
+ "loss": 1.1835,
2378
+ "step": 336
2379
+ },
2380
+ {
2381
+ "epoch": 2.1464968152866244,
2382
+ "grad_norm": 5.9375,
2383
+ "learning_rate": 5.719745222929937e-06,
2384
+ "loss": 1.1996,
2385
+ "step": 337
2386
+ },
2387
+ {
2388
+ "epoch": 2.1528662420382165,
2389
+ "grad_norm": 5.25,
2390
+ "learning_rate": 5.707006369426752e-06,
2391
+ "loss": 0.914,
2392
+ "step": 338
2393
+ },
2394
+ {
2395
+ "epoch": 2.159235668789809,
2396
+ "grad_norm": 6.25,
2397
+ "learning_rate": 5.694267515923567e-06,
2398
+ "loss": 1.022,
2399
+ "step": 339
2400
+ },
2401
+ {
2402
+ "epoch": 2.1656050955414012,
2403
+ "grad_norm": 5.65625,
2404
+ "learning_rate": 5.681528662420382e-06,
2405
+ "loss": 0.909,
2406
+ "step": 340
2407
+ },
2408
+ {
2409
+ "epoch": 2.171974522292994,
2410
+ "grad_norm": 5.3125,
2411
+ "learning_rate": 5.668789808917198e-06,
2412
+ "loss": 0.8324,
2413
+ "step": 341
2414
+ },
2415
+ {
2416
+ "epoch": 2.178343949044586,
2417
+ "grad_norm": 6.25,
2418
+ "learning_rate": 5.656050955414013e-06,
2419
+ "loss": 1.0246,
2420
+ "step": 342
2421
+ },
2422
+ {
2423
+ "epoch": 2.1847133757961785,
2424
+ "grad_norm": 5.0625,
2425
+ "learning_rate": 5.6433121019108285e-06,
2426
+ "loss": 0.8863,
2427
+ "step": 343
2428
+ },
2429
+ {
2430
+ "epoch": 2.1910828025477707,
2431
+ "grad_norm": 5.96875,
2432
+ "learning_rate": 5.630573248407643e-06,
2433
+ "loss": 0.9843,
2434
+ "step": 344
2435
+ },
2436
+ {
2437
+ "epoch": 2.1974522292993632,
2438
+ "grad_norm": 6.0625,
2439
+ "learning_rate": 5.617834394904459e-06,
2440
+ "loss": 0.9555,
2441
+ "step": 345
2442
+ },
2443
+ {
2444
+ "epoch": 2.2038216560509554,
2445
+ "grad_norm": 7.625,
2446
+ "learning_rate": 5.605095541401274e-06,
2447
+ "loss": 1.186,
2448
+ "step": 346
2449
+ },
2450
+ {
2451
+ "epoch": 2.210191082802548,
2452
+ "grad_norm": 5.875,
2453
+ "learning_rate": 5.59235668789809e-06,
2454
+ "loss": 1.0346,
2455
+ "step": 347
2456
+ },
2457
+ {
2458
+ "epoch": 2.21656050955414,
2459
+ "grad_norm": 5.4375,
2460
+ "learning_rate": 5.5796178343949046e-06,
2461
+ "loss": 0.9445,
2462
+ "step": 348
2463
+ },
2464
+ {
2465
+ "epoch": 2.2229299363057327,
2466
+ "grad_norm": 5.90625,
2467
+ "learning_rate": 5.56687898089172e-06,
2468
+ "loss": 0.9323,
2469
+ "step": 349
2470
+ },
2471
+ {
2472
+ "epoch": 2.229299363057325,
2473
+ "grad_norm": 6.46875,
2474
+ "learning_rate": 5.554140127388535e-06,
2475
+ "loss": 1.0115,
2476
+ "step": 350
2477
+ },
2478
+ {
2479
+ "epoch": 2.2356687898089174,
2480
+ "grad_norm": 6.375,
2481
+ "learning_rate": 5.541401273885351e-06,
2482
+ "loss": 0.859,
2483
+ "step": 351
2484
+ },
2485
+ {
2486
+ "epoch": 2.2420382165605095,
2487
+ "grad_norm": 6.03125,
2488
+ "learning_rate": 5.528662420382166e-06,
2489
+ "loss": 0.9925,
2490
+ "step": 352
2491
+ },
2492
+ {
2493
+ "epoch": 2.248407643312102,
2494
+ "grad_norm": 6.09375,
2495
+ "learning_rate": 5.5159235668789815e-06,
2496
+ "loss": 0.8639,
2497
+ "step": 353
2498
+ },
2499
+ {
2500
+ "epoch": 2.254777070063694,
2501
+ "grad_norm": 5.84375,
2502
+ "learning_rate": 5.503184713375796e-06,
2503
+ "loss": 0.9184,
2504
+ "step": 354
2505
+ },
2506
+ {
2507
+ "epoch": 2.261146496815287,
2508
+ "grad_norm": 6.5,
2509
+ "learning_rate": 5.490445859872612e-06,
2510
+ "loss": 1.03,
2511
+ "step": 355
2512
+ },
2513
+ {
2514
+ "epoch": 2.267515923566879,
2515
+ "grad_norm": 6.875,
2516
+ "learning_rate": 5.477707006369427e-06,
2517
+ "loss": 0.9746,
2518
+ "step": 356
2519
+ },
2520
+ {
2521
+ "epoch": 2.2738853503184715,
2522
+ "grad_norm": 6.25,
2523
+ "learning_rate": 5.464968152866243e-06,
2524
+ "loss": 1.0797,
2525
+ "step": 357
2526
+ },
2527
+ {
2528
+ "epoch": 2.2802547770700636,
2529
+ "grad_norm": 6.9375,
2530
+ "learning_rate": 5.4522292993630575e-06,
2531
+ "loss": 1.0282,
2532
+ "step": 358
2533
+ },
2534
+ {
2535
+ "epoch": 2.286624203821656,
2536
+ "grad_norm": 6.625,
2537
+ "learning_rate": 5.439490445859873e-06,
2538
+ "loss": 0.9307,
2539
+ "step": 359
2540
+ },
2541
+ {
2542
+ "epoch": 2.2929936305732483,
2543
+ "grad_norm": 5.6875,
2544
+ "learning_rate": 5.426751592356688e-06,
2545
+ "loss": 0.7967,
2546
+ "step": 360
2547
+ },
2548
+ {
2549
+ "epoch": 2.299363057324841,
2550
+ "grad_norm": 6.34375,
2551
+ "learning_rate": 5.414012738853504e-06,
2552
+ "loss": 1.0261,
2553
+ "step": 361
2554
+ },
2555
+ {
2556
+ "epoch": 2.305732484076433,
2557
+ "grad_norm": 5.625,
2558
+ "learning_rate": 5.401273885350319e-06,
2559
+ "loss": 1.1388,
2560
+ "step": 362
2561
+ },
2562
+ {
2563
+ "epoch": 2.3121019108280256,
2564
+ "grad_norm": 6.75,
2565
+ "learning_rate": 5.3885350318471345e-06,
2566
+ "loss": 1.081,
2567
+ "step": 363
2568
+ },
2569
+ {
2570
+ "epoch": 2.3184713375796178,
2571
+ "grad_norm": 5.375,
2572
+ "learning_rate": 5.375796178343949e-06,
2573
+ "loss": 0.8119,
2574
+ "step": 364
2575
+ },
2576
+ {
2577
+ "epoch": 2.3248407643312103,
2578
+ "grad_norm": 7.03125,
2579
+ "learning_rate": 5.363057324840765e-06,
2580
+ "loss": 0.9998,
2581
+ "step": 365
2582
+ },
2583
+ {
2584
+ "epoch": 2.3312101910828025,
2585
+ "grad_norm": 6.21875,
2586
+ "learning_rate": 5.35031847133758e-06,
2587
+ "loss": 1.0374,
2588
+ "step": 366
2589
+ },
2590
+ {
2591
+ "epoch": 2.337579617834395,
2592
+ "grad_norm": 6.125,
2593
+ "learning_rate": 5.337579617834396e-06,
2594
+ "loss": 0.9565,
2595
+ "step": 367
2596
+ },
2597
+ {
2598
+ "epoch": 2.343949044585987,
2599
+ "grad_norm": 6.0,
2600
+ "learning_rate": 5.3248407643312105e-06,
2601
+ "loss": 0.8843,
2602
+ "step": 368
2603
+ },
2604
+ {
2605
+ "epoch": 2.3503184713375798,
2606
+ "grad_norm": 5.75,
2607
+ "learning_rate": 5.312101910828026e-06,
2608
+ "loss": 0.8977,
2609
+ "step": 369
2610
+ },
2611
+ {
2612
+ "epoch": 2.356687898089172,
2613
+ "grad_norm": 5.9375,
2614
+ "learning_rate": 5.299363057324841e-06,
2615
+ "loss": 0.7443,
2616
+ "step": 370
2617
+ },
2618
+ {
2619
+ "epoch": 2.3630573248407645,
2620
+ "grad_norm": 6.15625,
2621
+ "learning_rate": 5.286624203821657e-06,
2622
+ "loss": 0.929,
2623
+ "step": 371
2624
+ },
2625
+ {
2626
+ "epoch": 2.3694267515923566,
2627
+ "grad_norm": 6.4375,
2628
+ "learning_rate": 5.273885350318472e-06,
2629
+ "loss": 0.9128,
2630
+ "step": 372
2631
+ },
2632
+ {
2633
+ "epoch": 2.375796178343949,
2634
+ "grad_norm": 6.0,
2635
+ "learning_rate": 5.261146496815287e-06,
2636
+ "loss": 0.8324,
2637
+ "step": 373
2638
+ },
2639
+ {
2640
+ "epoch": 2.3821656050955413,
2641
+ "grad_norm": 6.5,
2642
+ "learning_rate": 5.248407643312102e-06,
2643
+ "loss": 0.9828,
2644
+ "step": 374
2645
+ },
2646
+ {
2647
+ "epoch": 2.388535031847134,
2648
+ "grad_norm": 5.34375,
2649
+ "learning_rate": 5.235668789808917e-06,
2650
+ "loss": 0.7971,
2651
+ "step": 375
2652
+ },
2653
+ {
2654
+ "epoch": 2.394904458598726,
2655
+ "grad_norm": 6.71875,
2656
+ "learning_rate": 5.222929936305733e-06,
2657
+ "loss": 0.9408,
2658
+ "step": 376
2659
+ },
2660
+ {
2661
+ "epoch": 2.4012738853503186,
2662
+ "grad_norm": 5.875,
2663
+ "learning_rate": 5.210191082802548e-06,
2664
+ "loss": 0.8721,
2665
+ "step": 377
2666
+ },
2667
+ {
2668
+ "epoch": 2.4076433121019107,
2669
+ "grad_norm": 7.46875,
2670
+ "learning_rate": 5.1974522292993635e-06,
2671
+ "loss": 0.9568,
2672
+ "step": 378
2673
+ },
2674
+ {
2675
+ "epoch": 2.4140127388535033,
2676
+ "grad_norm": 7.78125,
2677
+ "learning_rate": 5.184713375796178e-06,
2678
+ "loss": 0.8417,
2679
+ "step": 379
2680
+ },
2681
+ {
2682
+ "epoch": 2.4203821656050954,
2683
+ "grad_norm": 6.0625,
2684
+ "learning_rate": 5.171974522292994e-06,
2685
+ "loss": 0.8513,
2686
+ "step": 380
2687
+ },
2688
+ {
2689
+ "epoch": 2.426751592356688,
2690
+ "grad_norm": 6.46875,
2691
+ "learning_rate": 5.159235668789809e-06,
2692
+ "loss": 1.1876,
2693
+ "step": 381
2694
+ },
2695
+ {
2696
+ "epoch": 2.43312101910828,
2697
+ "grad_norm": 6.3125,
2698
+ "learning_rate": 5.146496815286625e-06,
2699
+ "loss": 0.955,
2700
+ "step": 382
2701
+ },
2702
+ {
2703
+ "epoch": 2.4394904458598727,
2704
+ "grad_norm": 7.25,
2705
+ "learning_rate": 5.1337579617834396e-06,
2706
+ "loss": 0.9901,
2707
+ "step": 383
2708
+ },
2709
+ {
2710
+ "epoch": 2.445859872611465,
2711
+ "grad_norm": 6.09375,
2712
+ "learning_rate": 5.121019108280255e-06,
2713
+ "loss": 0.8645,
2714
+ "step": 384
2715
+ },
2716
+ {
2717
+ "epoch": 2.4522292993630574,
2718
+ "grad_norm": 7.5625,
2719
+ "learning_rate": 5.10828025477707e-06,
2720
+ "loss": 0.9549,
2721
+ "step": 385
2722
+ },
2723
+ {
2724
+ "epoch": 2.4585987261146496,
2725
+ "grad_norm": 6.1875,
2726
+ "learning_rate": 5.095541401273886e-06,
2727
+ "loss": 0.6233,
2728
+ "step": 386
2729
+ },
2730
+ {
2731
+ "epoch": 2.464968152866242,
2732
+ "grad_norm": 7.03125,
2733
+ "learning_rate": 5.082802547770701e-06,
2734
+ "loss": 0.9194,
2735
+ "step": 387
2736
+ },
2737
+ {
2738
+ "epoch": 2.4713375796178343,
2739
+ "grad_norm": 5.65625,
2740
+ "learning_rate": 5.0700636942675165e-06,
2741
+ "loss": 0.7292,
2742
+ "step": 388
2743
+ },
2744
+ {
2745
+ "epoch": 2.477707006369427,
2746
+ "grad_norm": 6.3125,
2747
+ "learning_rate": 5.057324840764331e-06,
2748
+ "loss": 0.9139,
2749
+ "step": 389
2750
+ },
2751
+ {
2752
+ "epoch": 2.484076433121019,
2753
+ "grad_norm": 7.3125,
2754
+ "learning_rate": 5.044585987261147e-06,
2755
+ "loss": 0.948,
2756
+ "step": 390
2757
+ },
2758
+ {
2759
+ "epoch": 2.4904458598726116,
2760
+ "grad_norm": 6.125,
2761
+ "learning_rate": 5.031847133757962e-06,
2762
+ "loss": 0.8746,
2763
+ "step": 391
2764
+ },
2765
+ {
2766
+ "epoch": 2.4968152866242037,
2767
+ "grad_norm": 6.59375,
2768
+ "learning_rate": 5.019108280254778e-06,
2769
+ "loss": 1.0893,
2770
+ "step": 392
2771
+ },
2772
+ {
2773
+ "epoch": 2.5031847133757963,
2774
+ "grad_norm": 6.0625,
2775
+ "learning_rate": 5.0063694267515925e-06,
2776
+ "loss": 0.9454,
2777
+ "step": 393
2778
+ },
2779
+ {
2780
+ "epoch": 2.5095541401273884,
2781
+ "grad_norm": 6.59375,
2782
+ "learning_rate": 4.993630573248408e-06,
2783
+ "loss": 1.0809,
2784
+ "step": 394
2785
+ },
2786
+ {
2787
+ "epoch": 2.515923566878981,
2788
+ "grad_norm": 6.90625,
2789
+ "learning_rate": 4.980891719745223e-06,
2790
+ "loss": 0.9386,
2791
+ "step": 395
2792
+ },
2793
+ {
2794
+ "epoch": 2.522292993630573,
2795
+ "grad_norm": 6.65625,
2796
+ "learning_rate": 4.968152866242039e-06,
2797
+ "loss": 0.9684,
2798
+ "step": 396
2799
+ },
2800
+ {
2801
+ "epoch": 2.5286624203821657,
2802
+ "grad_norm": 5.875,
2803
+ "learning_rate": 4.955414012738854e-06,
2804
+ "loss": 0.9721,
2805
+ "step": 397
2806
+ },
2807
+ {
2808
+ "epoch": 2.535031847133758,
2809
+ "grad_norm": 5.59375,
2810
+ "learning_rate": 4.9426751592356695e-06,
2811
+ "loss": 0.8638,
2812
+ "step": 398
2813
+ },
2814
+ {
2815
+ "epoch": 2.5414012738853504,
2816
+ "grad_norm": 6.5,
2817
+ "learning_rate": 4.929936305732484e-06,
2818
+ "loss": 0.9406,
2819
+ "step": 399
2820
+ },
2821
+ {
2822
+ "epoch": 2.5477707006369426,
2823
+ "grad_norm": 7.78125,
2824
+ "learning_rate": 4.9171974522293e-06,
2825
+ "loss": 0.9228,
2826
+ "step": 400
2827
+ },
2828
+ {
2829
+ "epoch": 2.554140127388535,
2830
+ "grad_norm": 7.4375,
2831
+ "learning_rate": 4.904458598726115e-06,
2832
+ "loss": 0.9641,
2833
+ "step": 401
2834
+ },
2835
+ {
2836
+ "epoch": 2.5605095541401273,
2837
+ "grad_norm": 6.15625,
2838
+ "learning_rate": 4.891719745222931e-06,
2839
+ "loss": 0.9077,
2840
+ "step": 402
2841
+ },
2842
+ {
2843
+ "epoch": 2.56687898089172,
2844
+ "grad_norm": 7.84375,
2845
+ "learning_rate": 4.8789808917197455e-06,
2846
+ "loss": 1.0531,
2847
+ "step": 403
2848
+ },
2849
+ {
2850
+ "epoch": 2.573248407643312,
2851
+ "grad_norm": 5.6875,
2852
+ "learning_rate": 4.866242038216561e-06,
2853
+ "loss": 0.9298,
2854
+ "step": 404
2855
+ },
2856
+ {
2857
+ "epoch": 2.5796178343949046,
2858
+ "grad_norm": 7.875,
2859
+ "learning_rate": 4.853503184713376e-06,
2860
+ "loss": 0.9839,
2861
+ "step": 405
2862
+ },
2863
+ {
2864
+ "epoch": 2.5859872611464967,
2865
+ "grad_norm": 7.25,
2866
+ "learning_rate": 4.840764331210192e-06,
2867
+ "loss": 1.076,
2868
+ "step": 406
2869
+ },
2870
+ {
2871
+ "epoch": 2.5923566878980893,
2872
+ "grad_norm": 6.4375,
2873
+ "learning_rate": 4.828025477707007e-06,
2874
+ "loss": 0.833,
2875
+ "step": 407
2876
+ },
2877
+ {
2878
+ "epoch": 2.5987261146496814,
2879
+ "grad_norm": 7.0625,
2880
+ "learning_rate": 4.8152866242038224e-06,
2881
+ "loss": 0.8417,
2882
+ "step": 408
2883
+ },
2884
+ {
2885
+ "epoch": 2.605095541401274,
2886
+ "grad_norm": 7.34375,
2887
+ "learning_rate": 4.802547770700637e-06,
2888
+ "loss": 1.0205,
2889
+ "step": 409
2890
+ },
2891
+ {
2892
+ "epoch": 2.611464968152866,
2893
+ "grad_norm": 6.9375,
2894
+ "learning_rate": 4.789808917197453e-06,
2895
+ "loss": 1.1493,
2896
+ "step": 410
2897
+ },
2898
+ {
2899
+ "epoch": 2.6178343949044587,
2900
+ "grad_norm": 8.0625,
2901
+ "learning_rate": 4.777070063694268e-06,
2902
+ "loss": 1.0063,
2903
+ "step": 411
2904
+ },
2905
+ {
2906
+ "epoch": 2.624203821656051,
2907
+ "grad_norm": 6.15625,
2908
+ "learning_rate": 4.764331210191084e-06,
2909
+ "loss": 0.778,
2910
+ "step": 412
2911
+ },
2912
+ {
2913
+ "epoch": 2.6305732484076434,
2914
+ "grad_norm": 6.375,
2915
+ "learning_rate": 4.7515923566878985e-06,
2916
+ "loss": 0.9035,
2917
+ "step": 413
2918
+ },
2919
+ {
2920
+ "epoch": 2.6369426751592355,
2921
+ "grad_norm": 7.9375,
2922
+ "learning_rate": 4.738853503184714e-06,
2923
+ "loss": 1.0745,
2924
+ "step": 414
2925
+ },
2926
+ {
2927
+ "epoch": 2.643312101910828,
2928
+ "grad_norm": 6.90625,
2929
+ "learning_rate": 4.726114649681529e-06,
2930
+ "loss": 0.8936,
2931
+ "step": 415
2932
+ },
2933
+ {
2934
+ "epoch": 2.6496815286624202,
2935
+ "grad_norm": 6.65625,
2936
+ "learning_rate": 4.713375796178344e-06,
2937
+ "loss": 0.9239,
2938
+ "step": 416
2939
+ },
2940
+ {
2941
+ "epoch": 2.656050955414013,
2942
+ "grad_norm": 7.1875,
2943
+ "learning_rate": 4.70063694267516e-06,
2944
+ "loss": 0.9792,
2945
+ "step": 417
2946
+ },
2947
+ {
2948
+ "epoch": 2.662420382165605,
2949
+ "grad_norm": 7.28125,
2950
+ "learning_rate": 4.6878980891719746e-06,
2951
+ "loss": 1.0535,
2952
+ "step": 418
2953
+ },
2954
+ {
2955
+ "epoch": 2.6687898089171975,
2956
+ "grad_norm": 6.71875,
2957
+ "learning_rate": 4.67515923566879e-06,
2958
+ "loss": 0.964,
2959
+ "step": 419
2960
+ },
2961
+ {
2962
+ "epoch": 2.6751592356687897,
2963
+ "grad_norm": 6.65625,
2964
+ "learning_rate": 4.662420382165605e-06,
2965
+ "loss": 0.8068,
2966
+ "step": 420
2967
+ },
2968
+ {
2969
+ "epoch": 2.6815286624203822,
2970
+ "grad_norm": 6.4375,
2971
+ "learning_rate": 4.649681528662421e-06,
2972
+ "loss": 0.7538,
2973
+ "step": 421
2974
+ },
2975
+ {
2976
+ "epoch": 2.6878980891719744,
2977
+ "grad_norm": 6.78125,
2978
+ "learning_rate": 4.636942675159236e-06,
2979
+ "loss": 0.9142,
2980
+ "step": 422
2981
+ },
2982
+ {
2983
+ "epoch": 2.694267515923567,
2984
+ "grad_norm": 6.625,
2985
+ "learning_rate": 4.6242038216560515e-06,
2986
+ "loss": 0.9294,
2987
+ "step": 423
2988
+ },
2989
+ {
2990
+ "epoch": 2.700636942675159,
2991
+ "grad_norm": 7.46875,
2992
+ "learning_rate": 4.611464968152866e-06,
2993
+ "loss": 0.9485,
2994
+ "step": 424
2995
+ },
2996
+ {
2997
+ "epoch": 2.7070063694267517,
2998
+ "grad_norm": 6.96875,
2999
+ "learning_rate": 4.598726114649682e-06,
3000
+ "loss": 1.0795,
3001
+ "step": 425
3002
+ },
3003
+ {
3004
+ "epoch": 2.713375796178344,
3005
+ "grad_norm": 6.65625,
3006
+ "learning_rate": 4.585987261146497e-06,
3007
+ "loss": 0.9952,
3008
+ "step": 426
3009
+ },
3010
+ {
3011
+ "epoch": 2.7197452229299364,
3012
+ "grad_norm": 7.34375,
3013
+ "learning_rate": 4.573248407643313e-06,
3014
+ "loss": 0.7474,
3015
+ "step": 427
3016
+ },
3017
+ {
3018
+ "epoch": 2.7261146496815285,
3019
+ "grad_norm": 7.1875,
3020
+ "learning_rate": 4.5605095541401276e-06,
3021
+ "loss": 0.8563,
3022
+ "step": 428
3023
+ },
3024
+ {
3025
+ "epoch": 2.732484076433121,
3026
+ "grad_norm": 6.65625,
3027
+ "learning_rate": 4.547770700636943e-06,
3028
+ "loss": 0.8809,
3029
+ "step": 429
3030
+ },
3031
+ {
3032
+ "epoch": 2.738853503184713,
3033
+ "grad_norm": 7.5625,
3034
+ "learning_rate": 4.535031847133758e-06,
3035
+ "loss": 0.9303,
3036
+ "step": 430
3037
+ },
3038
+ {
3039
+ "epoch": 2.745222929936306,
3040
+ "grad_norm": 7.28125,
3041
+ "learning_rate": 4.522292993630574e-06,
3042
+ "loss": 0.9433,
3043
+ "step": 431
3044
+ },
3045
+ {
3046
+ "epoch": 2.7515923566878984,
3047
+ "grad_norm": 7.78125,
3048
+ "learning_rate": 4.509554140127389e-06,
3049
+ "loss": 0.9392,
3050
+ "step": 432
3051
+ },
3052
+ {
3053
+ "epoch": 2.7579617834394905,
3054
+ "grad_norm": 6.9375,
3055
+ "learning_rate": 4.4968152866242045e-06,
3056
+ "loss": 0.9037,
3057
+ "step": 433
3058
+ },
3059
+ {
3060
+ "epoch": 2.7643312101910826,
3061
+ "grad_norm": 6.4375,
3062
+ "learning_rate": 4.484076433121019e-06,
3063
+ "loss": 0.758,
3064
+ "step": 434
3065
+ },
3066
+ {
3067
+ "epoch": 2.770700636942675,
3068
+ "grad_norm": 6.75,
3069
+ "learning_rate": 4.471337579617835e-06,
3070
+ "loss": 0.9663,
3071
+ "step": 435
3072
+ },
3073
+ {
3074
+ "epoch": 2.777070063694268,
3075
+ "grad_norm": 6.5,
3076
+ "learning_rate": 4.45859872611465e-06,
3077
+ "loss": 0.8865,
3078
+ "step": 436
3079
+ },
3080
+ {
3081
+ "epoch": 2.78343949044586,
3082
+ "grad_norm": 7.3125,
3083
+ "learning_rate": 4.445859872611466e-06,
3084
+ "loss": 0.9469,
3085
+ "step": 437
3086
+ },
3087
+ {
3088
+ "epoch": 2.789808917197452,
3089
+ "grad_norm": 7.6875,
3090
+ "learning_rate": 4.4331210191082805e-06,
3091
+ "loss": 1.0765,
3092
+ "step": 438
3093
+ },
3094
+ {
3095
+ "epoch": 2.7961783439490446,
3096
+ "grad_norm": 7.0625,
3097
+ "learning_rate": 4.420382165605096e-06,
3098
+ "loss": 0.8473,
3099
+ "step": 439
3100
+ },
3101
+ {
3102
+ "epoch": 2.802547770700637,
3103
+ "grad_norm": 6.28125,
3104
+ "learning_rate": 4.407643312101911e-06,
3105
+ "loss": 0.7556,
3106
+ "step": 440
3107
+ },
3108
+ {
3109
+ "epoch": 2.8089171974522293,
3110
+ "grad_norm": 6.65625,
3111
+ "learning_rate": 4.394904458598727e-06,
3112
+ "loss": 0.8978,
3113
+ "step": 441
3114
+ },
3115
+ {
3116
+ "epoch": 2.8152866242038215,
3117
+ "grad_norm": 7.59375,
3118
+ "learning_rate": 4.382165605095542e-06,
3119
+ "loss": 0.9394,
3120
+ "step": 442
3121
+ },
3122
+ {
3123
+ "epoch": 2.821656050955414,
3124
+ "grad_norm": 7.4375,
3125
+ "learning_rate": 4.3694267515923574e-06,
3126
+ "loss": 0.8886,
3127
+ "step": 443
3128
+ },
3129
+ {
3130
+ "epoch": 2.8280254777070066,
3131
+ "grad_norm": 8.4375,
3132
+ "learning_rate": 4.356687898089172e-06,
3133
+ "loss": 1.0954,
3134
+ "step": 444
3135
+ },
3136
+ {
3137
+ "epoch": 2.8343949044585988,
3138
+ "grad_norm": 7.71875,
3139
+ "learning_rate": 4.343949044585988e-06,
3140
+ "loss": 1.0049,
3141
+ "step": 445
3142
+ },
3143
+ {
3144
+ "epoch": 2.840764331210191,
3145
+ "grad_norm": 6.40625,
3146
+ "learning_rate": 4.331210191082803e-06,
3147
+ "loss": 0.7752,
3148
+ "step": 446
3149
+ },
3150
+ {
3151
+ "epoch": 2.8471337579617835,
3152
+ "grad_norm": 6.53125,
3153
+ "learning_rate": 4.318471337579619e-06,
3154
+ "loss": 0.7596,
3155
+ "step": 447
3156
+ },
3157
+ {
3158
+ "epoch": 2.853503184713376,
3159
+ "grad_norm": 6.875,
3160
+ "learning_rate": 4.3057324840764335e-06,
3161
+ "loss": 0.8002,
3162
+ "step": 448
3163
+ },
3164
+ {
3165
+ "epoch": 2.859872611464968,
3166
+ "grad_norm": 6.96875,
3167
+ "learning_rate": 4.292993630573249e-06,
3168
+ "loss": 0.8646,
3169
+ "step": 449
3170
+ },
3171
+ {
3172
+ "epoch": 2.8662420382165603,
3173
+ "grad_norm": 7.28125,
3174
+ "learning_rate": 4.280254777070064e-06,
3175
+ "loss": 0.9357,
3176
+ "step": 450
3177
+ },
3178
+ {
3179
+ "epoch": 2.872611464968153,
3180
+ "grad_norm": 6.875,
3181
+ "learning_rate": 4.26751592356688e-06,
3182
+ "loss": 0.8684,
3183
+ "step": 451
3184
+ },
3185
+ {
3186
+ "epoch": 2.8789808917197455,
3187
+ "grad_norm": 6.65625,
3188
+ "learning_rate": 4.254777070063695e-06,
3189
+ "loss": 0.8736,
3190
+ "step": 452
3191
+ },
3192
+ {
3193
+ "epoch": 2.8853503184713376,
3194
+ "grad_norm": 7.46875,
3195
+ "learning_rate": 4.2420382165605104e-06,
3196
+ "loss": 0.9671,
3197
+ "step": 453
3198
+ },
3199
+ {
3200
+ "epoch": 2.8917197452229297,
3201
+ "grad_norm": 8.875,
3202
+ "learning_rate": 4.229299363057325e-06,
3203
+ "loss": 1.1431,
3204
+ "step": 454
3205
+ },
3206
+ {
3207
+ "epoch": 2.8980891719745223,
3208
+ "grad_norm": 7.78125,
3209
+ "learning_rate": 4.216560509554141e-06,
3210
+ "loss": 0.8168,
3211
+ "step": 455
3212
+ },
3213
+ {
3214
+ "epoch": 2.904458598726115,
3215
+ "grad_norm": 7.375,
3216
+ "learning_rate": 4.203821656050956e-06,
3217
+ "loss": 0.7295,
3218
+ "step": 456
3219
+ },
3220
+ {
3221
+ "epoch": 2.910828025477707,
3222
+ "grad_norm": 6.6875,
3223
+ "learning_rate": 4.191082802547772e-06,
3224
+ "loss": 0.953,
3225
+ "step": 457
3226
+ },
3227
+ {
3228
+ "epoch": 2.917197452229299,
3229
+ "grad_norm": 6.59375,
3230
+ "learning_rate": 4.1783439490445865e-06,
3231
+ "loss": 0.8707,
3232
+ "step": 458
3233
+ },
3234
+ {
3235
+ "epoch": 2.9235668789808917,
3236
+ "grad_norm": 8.125,
3237
+ "learning_rate": 4.165605095541402e-06,
3238
+ "loss": 0.9631,
3239
+ "step": 459
3240
+ },
3241
+ {
3242
+ "epoch": 2.9299363057324843,
3243
+ "grad_norm": 7.15625,
3244
+ "learning_rate": 4.152866242038217e-06,
3245
+ "loss": 0.7732,
3246
+ "step": 460
3247
+ },
3248
+ {
3249
+ "epoch": 2.9363057324840764,
3250
+ "grad_norm": 7.4375,
3251
+ "learning_rate": 4.140127388535032e-06,
3252
+ "loss": 0.821,
3253
+ "step": 461
3254
+ },
3255
+ {
3256
+ "epoch": 2.9426751592356686,
3257
+ "grad_norm": 8.1875,
3258
+ "learning_rate": 4.127388535031848e-06,
3259
+ "loss": 0.9762,
3260
+ "step": 462
3261
+ },
3262
+ {
3263
+ "epoch": 2.949044585987261,
3264
+ "grad_norm": 6.96875,
3265
+ "learning_rate": 4.1146496815286626e-06,
3266
+ "loss": 0.8504,
3267
+ "step": 463
3268
+ },
3269
+ {
3270
+ "epoch": 2.9554140127388537,
3271
+ "grad_norm": 10.5625,
3272
+ "learning_rate": 4.101910828025478e-06,
3273
+ "loss": 0.7531,
3274
+ "step": 464
3275
+ },
3276
+ {
3277
+ "epoch": 2.961783439490446,
3278
+ "grad_norm": 8.0,
3279
+ "learning_rate": 4.089171974522293e-06,
3280
+ "loss": 0.9035,
3281
+ "step": 465
3282
+ },
3283
+ {
3284
+ "epoch": 2.968152866242038,
3285
+ "grad_norm": 8.75,
3286
+ "learning_rate": 4.076433121019109e-06,
3287
+ "loss": 0.7513,
3288
+ "step": 466
3289
+ },
3290
+ {
3291
+ "epoch": 2.9745222929936306,
3292
+ "grad_norm": 6.90625,
3293
+ "learning_rate": 4.063694267515924e-06,
3294
+ "loss": 0.9019,
3295
+ "step": 467
3296
+ },
3297
+ {
3298
+ "epoch": 2.980891719745223,
3299
+ "grad_norm": 7.1875,
3300
+ "learning_rate": 4.0509554140127395e-06,
3301
+ "loss": 0.8663,
3302
+ "step": 468
3303
+ },
3304
+ {
3305
+ "epoch": 2.9872611464968153,
3306
+ "grad_norm": 8.875,
3307
+ "learning_rate": 4.038216560509554e-06,
3308
+ "loss": 1.0418,
3309
+ "step": 469
3310
+ },
3311
+ {
3312
+ "epoch": 2.9936305732484074,
3313
+ "grad_norm": 6.09375,
3314
+ "learning_rate": 4.02547770700637e-06,
3315
+ "loss": 0.7108,
3316
+ "step": 470
3317
+ },
3318
+ {
3319
+ "epoch": 3.0,
3320
+ "grad_norm": 16.5,
3321
+ "learning_rate": 4.012738853503185e-06,
3322
+ "loss": 1.1715,
3323
+ "step": 471
3324
+ },
3325
+ {
3326
+ "epoch": 3.0,
3327
+ "eval_loss": 2.601672410964966,
3328
+ "eval_runtime": 9.0903,
3329
+ "eval_samples_per_second": 110.007,
3330
+ "eval_steps_per_second": 3.52,
3331
+ "step": 471
3332
+ }
3333
+ ],
3334
+ "logging_steps": 1,
3335
+ "max_steps": 785,
3336
+ "num_input_tokens_seen": 0,
3337
+ "num_train_epochs": 5,
3338
+ "save_steps": 500,
3339
+ "stateful_callbacks": {
3340
+ "TrainerControl": {
3341
+ "args": {
3342
+ "should_epoch_stop": false,
3343
+ "should_evaluate": false,
3344
+ "should_log": false,
3345
+ "should_save": true,
3346
+ "should_training_stop": false
3347
+ },
3348
+ "attributes": {}
3349
+ }
3350
+ },
3351
+ "total_flos": 1.8409890814656e+17,
3352
+ "train_batch_size": 32,
3353
+ "trial_name": null,
3354
+ "trial_params": null
3355
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798e5e8b163bf71167b5725b99779ad06d51f459438a623a4a0d8883ebe179cd
3
+ size 5816