Hugging Face's logo

CocoRoF
/
POLAR-G3-4b-Commerce_Law-sft

Safetensors
gemma3
Model card Files
xet
 Community
CocoRoF commited on
Commit
7c96822
·
verified ·
1 Parent(s): 0e1c5ac

Upload content from checkpoint-320

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. config.json +64 -0
  3. generation_config.json +13 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +890 -0
  7. optimizer.pt +3 -0
  8. scheduler.pt +3 -0
  9. special_tokens_map.json +33 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +0 -0
  12. trainer_state.json +2594 -0
  13. 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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "eoi_token_index": 256000,
7
+ "eos_token_id": [
8
+ 1,
9
+ 106
10
+ ],
11
+ "id2label": {},
12
+ "image_token_index": 262144,
13
+ "initializer_range": 0.02,
14
+ "label2id": {},
15
+ "mm_tokens_per_image": 256,
16
+ "model_type": "gemma3",
17
+ "text_config": {
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "attn_logit_softcapping": null,
21
+ "cache_implementation": "hybrid",
22
+ "final_logit_softcapping": null,
23
+ "head_dim": 256,
24
+ "hidden_activation": "gelu_pytorch_tanh",
25
+ "hidden_size": 2560,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 10240,
28
+ "max_position_embeddings": 131072,
29
+ "model_type": "gemma3_text",
30
+ "num_attention_heads": 8,
31
+ "num_hidden_layers": 34,
32
+ "num_key_value_heads": 4,
33
+ "query_pre_attn_scalar": 256,
34
+ "rms_norm_eps": 1e-06,
35
+ "rope_local_base_freq": 10000.0,
36
+ "rope_scaling": {
37
+ "factor": 8.0,
38
+ "rope_type": "linear"
39
+ },
40
+ "rope_theta": 1000000.0,
41
+ "sliding_window": 1024,
42
+ "sliding_window_pattern": 6,
43
+ "torch_dtype": "bfloat16",
44
+ "use_cache": true,
45
+ "vocab_size": 262208
46
+ },
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.51.0",
49
+ "vision_config": {
50
+ "attention_dropout": 0.0,
51
+ "hidden_act": "gelu_pytorch_tanh",
52
+ "hidden_size": 1152,
53
+ "image_size": 896,
54
+ "intermediate_size": 4304,
55
+ "layer_norm_eps": 1e-06,
56
+ "model_type": "siglip_vision_model",
57
+ "num_attention_heads": 16,
58
+ "num_channels": 3,
59
+ "num_hidden_layers": 27,
60
+ "patch_size": 14,
61
+ "torch_dtype": "bfloat16",
62
+ "vision_use_head": false
63
+ }
64
+ }
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": "4.51.0"
13
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ccb5a7035e39b4d6ff3e62888e49d8e8d22be89b7fbc17320e3c8c893e802d3
3
+ size 4961251752
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90cf4c40dfa2006871c9383b76d697d767169a818405cbd390a5d49d11a3a7a8
3
+ size 3639026128
model.safetensors.index.json ADDED
@@ -0,0 +1,890 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8600158944
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
15
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
18
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
28
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
29
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
30
+ "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
31
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
32
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
33
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
36
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
37
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
41
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
42
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
44
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
45
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
46
+ "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
48
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
49
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
50
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
51
+ "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
54
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
55
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
56
+ "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
57
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
58
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
59
+ "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
61
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
62
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
63
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
67
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
70
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
71
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
72
+ "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
74
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
75
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
76
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
77
+ "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
86
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
87
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
90
+ "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
91
+ "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
93
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
96
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
101
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
102
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
103
+ "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
106
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
107
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
108
+ "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
109
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
110
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
111
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
112
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
113
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
114
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
115
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
116
+ "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
118
+ "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
119
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
120
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
121
+ "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
122
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
123
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
124
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
125
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
126
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
127
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
128
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
132
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
133
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
134
+ "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
135
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
136
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
137
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
139
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
140
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
141
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
142
+ "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
145
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
146
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
147
+ "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
148
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
149
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
150
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
151
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
152
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
153
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
154
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
155
+ "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
158
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
159
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
160
+ "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
161
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
162
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
163
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
165
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
166
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
171
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
172
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
173
+ "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
174
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
175
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
176
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
177
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
178
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
179
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
180
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
181
+ "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
182
+ "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
184
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
187
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
188
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
189
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
191
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
192
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
193
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
194
+ "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
195
+ "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
197
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
198
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
199
+ "language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
200
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
201
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
202
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
203
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
204
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
205
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
206
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
208
+ "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
209
+ "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
210
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
211
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
212
+ "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
213
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
214
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
215
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
216
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
217
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
218
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
219
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
220
+ "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
221
+ "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
236
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
237
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
238
+ "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
239
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
240
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
241
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
242
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
243
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
244
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
245
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
246
+ "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
247
+ "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
249
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
250
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
251
+ "language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
252
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
253
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
254
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
255
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
256
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
257
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
258
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
259
+ "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
262
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
263
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
264
+ "language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
265
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
266
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
267
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
268
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
269
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
270
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
271
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
272
+ "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
275
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
276
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
277
+ "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
278
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
279
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
280
+ "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
281
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
282
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
283
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
284
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
285
+ "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
286
+ "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
287
+ "language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
288
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
289
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
290
+ "language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
291
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
292
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
293
+ "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
294
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
295
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
296
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
297
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
298
+ "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
301
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
302
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
304
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
306
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
307
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
308
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
309
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
310
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
311
+ "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
312
+ "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
314
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
315
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
316
+ "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
317
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
318
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
+ "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
320
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
321
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
322
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
323
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
324
+ "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
326
+ "language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
327
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
328
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
329
+ "language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
330
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
331
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
332
+ "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
334
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
335
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
336
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
337
+ "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
338
+ "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
339
+ "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
340
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
341
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
342
+ "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
343
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
344
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
345
+ "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
346
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
347
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
348
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
349
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
350
+ "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
351
+ "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
352
+ "language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
353
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
354
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
355
+ "language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
356
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
357
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
358
+ "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
359
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
360
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
361
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
362
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
363
+ "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
364
+ "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
365
+ "language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
366
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
367
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
368
+ "language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
369
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
370
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
371
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
378
+ "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
379
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
380
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
381
+ "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
382
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
383
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
384
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
385
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
386
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
387
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
388
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
389
+ "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
390
+ "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
391
+ "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
392
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
393
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
394
+ "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
395
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
396
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
397
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
399
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
400
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
401
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
402
+ "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
403
+ "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
405
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
406
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
407
+ "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
408
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
409
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
410
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
411
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
412
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
413
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
414
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
415
+ "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
418
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
419
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
420
+ "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
421
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
422
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
423
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
424
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
425
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
426
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
427
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
431
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
432
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
433
+ "language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
434
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
435
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
436
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
437
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
438
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
439
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
440
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
441
+ "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
442
+ "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
443
+ "language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
444
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
445
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
446
+ "language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
447
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
448
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
449
+ "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
450
+ "multi_modal_projector.mm_input_projection_weight": "model-00001-of-00002.safetensors",
451
+ "multi_modal_projector.mm_soft_emb_norm.weight": "model-00001-of-00002.safetensors",
452
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
453
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
454
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
455
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
689
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
690
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
691
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
692
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
693
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
694
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
695
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
696
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
697
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
698
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
699
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
700
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
701
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
702
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
703
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
704
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
705
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
706
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
707
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
708
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
709
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
710
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
711
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
712
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
713
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
714
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
715
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
716
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
717
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
718
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
719
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
720
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
721
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
722
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
723
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
724
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
725
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
726
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
727
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
728
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
729
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
730
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
731
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
732
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
733
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
734
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
735
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
736
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
737
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
738
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
739
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
740
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
741
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
742
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
743
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
744
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
745
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
746
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
747
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
748
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
749
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
750
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
751
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
752
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
753
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
754
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
755
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
756
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
757
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
758
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
759
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
760
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
761
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
762
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
763
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
764
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
765
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
766
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
767
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
768
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
769
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
770
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
771
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
772
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
773
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
774
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
775
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
776
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
777
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
778
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
779
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
780
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
781
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
782
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
783
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
784
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
785
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
786
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
787
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
788
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
789
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
790
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
791
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
792
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
793
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
794
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
795
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
796
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
797
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
798
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
799
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
800
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
801
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
802
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
803
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
804
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
805
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
806
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
807
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
808
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
809
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
810
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
811
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
812
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
813
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
814
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
815
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
816
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
817
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
818
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
819
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
820
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
821
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
822
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
823
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
824
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
825
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
826
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
827
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
828
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
829
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
830
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
831
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
832
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
833
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
834
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
835
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
836
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
837
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
838
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
839
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
840
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
841
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
842
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
843
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
844
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
845
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
846
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
847
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
848
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
849
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
850
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
851
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
852
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
853
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
854
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
855
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
856
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
857
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
858
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
859
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
860
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
861
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
862
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
863
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
864
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
865
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
866
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
867
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
868
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
869
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
870
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
871
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
872
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
873
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
874
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
875
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
876
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
877
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
878
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
879
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
880
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
881
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
882
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
883
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
884
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
885
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
886
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
887
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
888
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
889
+ }
890
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8381a213499166575e049232c9c96aabb2b14d85f92aa2d37cc2023d486ec710
3
+ size 15521442051
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4080383105c41fd955839a60c3413533684abc23df5fedd23f2777e562a6ce35
3
+ size 1465
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 sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,2594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 100.0,
7
+ "global_step": 320,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015625,
14
+ "grad_norm": 179.0,
15
+ "learning_rate": 0.0,
16
+ "loss": 5.2367,
17
+ "mean_token_accuracy": 0.43311607837677,
18
+ "step": 1
19
+ },
20
+ {
21
+ "epoch": 0.03125,
22
+ "grad_norm": 198.0,
23
+ "learning_rate": 3.75e-07,
24
+ "loss": 5.5486,
25
+ "mean_token_accuracy": 0.4108841121196747,
26
+ "step": 2
27
+ },
28
+ {
29
+ "epoch": 0.046875,
30
+ "grad_norm": 178.0,
31
+ "learning_rate": 7.5e-07,
32
+ "loss": 5.2141,
33
+ "mean_token_accuracy": 0.4345736503601074,
34
+ "step": 3
35
+ },
36
+ {
37
+ "epoch": 0.0625,
38
+ "grad_norm": 172.0,
39
+ "learning_rate": 1.125e-06,
40
+ "loss": 5.5836,
41
+ "mean_token_accuracy": 0.41250425577163696,
42
+ "step": 4
43
+ },
44
+ {
45
+ "epoch": 0.078125,
46
+ "grad_norm": 152.0,
47
+ "learning_rate": 1.5e-06,
48
+ "loss": 5.2296,
49
+ "mean_token_accuracy": 0.4149760901927948,
50
+ "step": 5
51
+ },
52
+ {
53
+ "epoch": 0.09375,
54
+ "grad_norm": 126.5,
55
+ "learning_rate": 1.875e-06,
56
+ "loss": 4.6572,
57
+ "mean_token_accuracy": 0.4508528411388397,
58
+ "step": 6
59
+ },
60
+ {
61
+ "epoch": 0.109375,
62
+ "grad_norm": 122.0,
63
+ "learning_rate": 2.25e-06,
64
+ "loss": 4.8441,
65
+ "mean_token_accuracy": 0.4253324270248413,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.125,
70
+ "grad_norm": 93.5,
71
+ "learning_rate": 2.6250000000000003e-06,
72
+ "loss": 4.3849,
73
+ "mean_token_accuracy": 0.4506120979785919,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.140625,
78
+ "grad_norm": 73.0,
79
+ "learning_rate": 3e-06,
80
+ "loss": 4.0401,
81
+ "mean_token_accuracy": 0.45889315009117126,
82
+ "step": 9
83
+ },
84
+ {
85
+ "epoch": 0.15625,
86
+ "grad_norm": 60.75,
87
+ "learning_rate": 2.9903846153846156e-06,
88
+ "loss": 3.8834,
89
+ "mean_token_accuracy": 0.47038498520851135,
90
+ "step": 10
91
+ },
92
+ {
93
+ "epoch": 0.171875,
94
+ "grad_norm": 50.5,
95
+ "learning_rate": 2.9807692307692307e-06,
96
+ "loss": 3.6623,
97
+ "mean_token_accuracy": 0.4854481816291809,
98
+ "step": 11
99
+ },
100
+ {
101
+ "epoch": 0.1875,
102
+ "grad_norm": 43.5,
103
+ "learning_rate": 2.9711538461538463e-06,
104
+ "loss": 3.4374,
105
+ "mean_token_accuracy": 0.4968532621860504,
106
+ "step": 12
107
+ },
108
+ {
109
+ "epoch": 0.203125,
110
+ "grad_norm": 45.5,
111
+ "learning_rate": 2.961538461538462e-06,
112
+ "loss": 3.2283,
113
+ "mean_token_accuracy": 0.513970673084259,
114
+ "step": 13
115
+ },
116
+ {
117
+ "epoch": 0.21875,
118
+ "grad_norm": 35.25,
119
+ "learning_rate": 2.951923076923077e-06,
120
+ "loss": 3.1423,
121
+ "mean_token_accuracy": 0.5192499160766602,
122
+ "step": 14
123
+ },
124
+ {
125
+ "epoch": 0.234375,
126
+ "grad_norm": 32.0,
127
+ "learning_rate": 2.942307692307692e-06,
128
+ "loss": 2.9815,
129
+ "mean_token_accuracy": 0.5281234383583069,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.25,
134
+ "grad_norm": 32.5,
135
+ "learning_rate": 2.9326923076923076e-06,
136
+ "loss": 2.863,
137
+ "mean_token_accuracy": 0.5459433197975159,
138
+ "step": 16
139
+ },
140
+ {
141
+ "epoch": 0.265625,
142
+ "grad_norm": 27.5,
143
+ "learning_rate": 2.923076923076923e-06,
144
+ "loss": 2.8314,
145
+ "mean_token_accuracy": 0.5349738597869873,
146
+ "step": 17
147
+ },
148
+ {
149
+ "epoch": 0.28125,
150
+ "grad_norm": 26.125,
151
+ "learning_rate": 2.9134615384615387e-06,
152
+ "loss": 2.7488,
153
+ "mean_token_accuracy": 0.5427058339118958,
154
+ "step": 18
155
+ },
156
+ {
157
+ "epoch": 0.296875,
158
+ "grad_norm": 23.625,
159
+ "learning_rate": 2.903846153846154e-06,
160
+ "loss": 2.6134,
161
+ "mean_token_accuracy": 0.5453544855117798,
162
+ "step": 19
163
+ },
164
+ {
165
+ "epoch": 0.3125,
166
+ "grad_norm": 23.75,
167
+ "learning_rate": 2.8942307692307693e-06,
168
+ "loss": 2.562,
169
+ "mean_token_accuracy": 0.5491897463798523,
170
+ "step": 20
171
+ },
172
+ {
173
+ "epoch": 0.328125,
174
+ "grad_norm": 22.625,
175
+ "learning_rate": 2.884615384615385e-06,
176
+ "loss": 2.4742,
177
+ "mean_token_accuracy": 0.5496063232421875,
178
+ "step": 21
179
+ },
180
+ {
181
+ "epoch": 0.34375,
182
+ "grad_norm": 21.875,
183
+ "learning_rate": 2.875e-06,
184
+ "loss": 2.3924,
185
+ "mean_token_accuracy": 0.5709417462348938,
186
+ "step": 22
187
+ },
188
+ {
189
+ "epoch": 0.359375,
190
+ "grad_norm": 22.625,
191
+ "learning_rate": 2.8653846153846155e-06,
192
+ "loss": 2.2842,
193
+ "mean_token_accuracy": 0.5809605717658997,
194
+ "step": 23
195
+ },
196
+ {
197
+ "epoch": 0.375,
198
+ "grad_norm": 21.125,
199
+ "learning_rate": 2.8557692307692307e-06,
200
+ "loss": 2.1831,
201
+ "mean_token_accuracy": 0.5968478918075562,
202
+ "step": 24
203
+ },
204
+ {
205
+ "epoch": 0.390625,
206
+ "grad_norm": 21.875,
207
+ "learning_rate": 2.846153846153846e-06,
208
+ "loss": 2.1536,
209
+ "mean_token_accuracy": 0.602466344833374,
210
+ "step": 25
211
+ },
212
+ {
213
+ "epoch": 0.40625,
214
+ "grad_norm": 21.5,
215
+ "learning_rate": 2.8365384615384613e-06,
216
+ "loss": 2.0267,
217
+ "mean_token_accuracy": 0.6342177987098694,
218
+ "step": 26
219
+ },
220
+ {
221
+ "epoch": 0.421875,
222
+ "grad_norm": 23.25,
223
+ "learning_rate": 2.826923076923077e-06,
224
+ "loss": 1.9421,
225
+ "mean_token_accuracy": 0.6432027220726013,
226
+ "step": 27
227
+ },
228
+ {
229
+ "epoch": 0.4375,
230
+ "grad_norm": 23.5,
231
+ "learning_rate": 2.8173076923076924e-06,
232
+ "loss": 1.9156,
233
+ "mean_token_accuracy": 0.6579385995864868,
234
+ "step": 28
235
+ },
236
+ {
237
+ "epoch": 0.453125,
238
+ "grad_norm": 24.125,
239
+ "learning_rate": 2.807692307692308e-06,
240
+ "loss": 1.8596,
241
+ "mean_token_accuracy": 0.6711886525154114,
242
+ "step": 29
243
+ },
244
+ {
245
+ "epoch": 0.46875,
246
+ "grad_norm": 21.5,
247
+ "learning_rate": 2.798076923076923e-06,
248
+ "loss": 1.7841,
249
+ "mean_token_accuracy": 0.6769159436225891,
250
+ "step": 30
251
+ },
252
+ {
253
+ "epoch": 0.484375,
254
+ "grad_norm": 19.25,
255
+ "learning_rate": 2.7884615384615386e-06,
256
+ "loss": 1.7306,
257
+ "mean_token_accuracy": 0.6835744976997375,
258
+ "step": 31
259
+ },
260
+ {
261
+ "epoch": 0.5,
262
+ "grad_norm": 19.375,
263
+ "learning_rate": 2.778846153846154e-06,
264
+ "loss": 1.6979,
265
+ "mean_token_accuracy": 0.6885009407997131,
266
+ "step": 32
267
+ },
268
+ {
269
+ "epoch": 0.515625,
270
+ "grad_norm": 19.625,
271
+ "learning_rate": 2.7692307692307693e-06,
272
+ "loss": 1.6705,
273
+ "mean_token_accuracy": 0.6899428963661194,
274
+ "step": 33
275
+ },
276
+ {
277
+ "epoch": 0.53125,
278
+ "grad_norm": 19.375,
279
+ "learning_rate": 2.7596153846153844e-06,
280
+ "loss": 1.5569,
281
+ "mean_token_accuracy": 0.7047604918479919,
282
+ "step": 34
283
+ },
284
+ {
285
+ "epoch": 0.546875,
286
+ "grad_norm": 25.25,
287
+ "learning_rate": 2.75e-06,
288
+ "loss": 1.5437,
289
+ "mean_token_accuracy": 0.7077205777168274,
290
+ "step": 35
291
+ },
292
+ {
293
+ "epoch": 0.5625,
294
+ "grad_norm": 18.0,
295
+ "learning_rate": 2.7403846153846155e-06,
296
+ "loss": 1.5079,
297
+ "mean_token_accuracy": 0.721455454826355,
298
+ "step": 36
299
+ },
300
+ {
301
+ "epoch": 0.578125,
302
+ "grad_norm": 16.125,
303
+ "learning_rate": 2.7307692307692306e-06,
304
+ "loss": 1.4751,
305
+ "mean_token_accuracy": 0.731259822845459,
306
+ "step": 37
307
+ },
308
+ {
309
+ "epoch": 0.59375,
310
+ "grad_norm": 13.875,
311
+ "learning_rate": 2.721153846153846e-06,
312
+ "loss": 1.4444,
313
+ "mean_token_accuracy": 0.721596896648407,
314
+ "step": 38
315
+ },
316
+ {
317
+ "epoch": 0.609375,
318
+ "grad_norm": 17.25,
319
+ "learning_rate": 2.7115384615384617e-06,
320
+ "loss": 1.4267,
321
+ "mean_token_accuracy": 0.7311121821403503,
322
+ "step": 39
323
+ },
324
+ {
325
+ "epoch": 0.625,
326
+ "grad_norm": 14.6875,
327
+ "learning_rate": 2.7019230769230772e-06,
328
+ "loss": 1.4606,
329
+ "mean_token_accuracy": 0.7229064106941223,
330
+ "step": 40
331
+ },
332
+ {
333
+ "epoch": 0.640625,
334
+ "grad_norm": 12.0625,
335
+ "learning_rate": 2.6923076923076923e-06,
336
+ "loss": 1.4415,
337
+ "mean_token_accuracy": 0.7228537201881409,
338
+ "step": 41
339
+ },
340
+ {
341
+ "epoch": 0.65625,
342
+ "grad_norm": 12.1875,
343
+ "learning_rate": 2.682692307692308e-06,
344
+ "loss": 1.3615,
345
+ "mean_token_accuracy": 0.7459965944290161,
346
+ "step": 42
347
+ },
348
+ {
349
+ "epoch": 0.671875,
350
+ "grad_norm": 12.0625,
351
+ "learning_rate": 2.6730769230769234e-06,
352
+ "loss": 1.3769,
353
+ "mean_token_accuracy": 0.7359253764152527,
354
+ "step": 43
355
+ },
356
+ {
357
+ "epoch": 0.6875,
358
+ "grad_norm": 12.0,
359
+ "learning_rate": 2.6634615384615385e-06,
360
+ "loss": 1.3322,
361
+ "mean_token_accuracy": 0.7482958436012268,
362
+ "step": 44
363
+ },
364
+ {
365
+ "epoch": 0.703125,
366
+ "grad_norm": 11.3125,
367
+ "learning_rate": 2.6538461538461537e-06,
368
+ "loss": 1.3471,
369
+ "mean_token_accuracy": 0.738798975944519,
370
+ "step": 45
371
+ },
372
+ {
373
+ "epoch": 0.71875,
374
+ "grad_norm": 12.8125,
375
+ "learning_rate": 2.644230769230769e-06,
376
+ "loss": 1.2892,
377
+ "mean_token_accuracy": 0.7512567043304443,
378
+ "step": 46
379
+ },
380
+ {
381
+ "epoch": 0.734375,
382
+ "grad_norm": 12.25,
383
+ "learning_rate": 2.6346153846153847e-06,
384
+ "loss": 1.2592,
385
+ "mean_token_accuracy": 0.7561485171318054,
386
+ "step": 47
387
+ },
388
+ {
389
+ "epoch": 0.75,
390
+ "grad_norm": 13.875,
391
+ "learning_rate": 2.6250000000000003e-06,
392
+ "loss": 1.289,
393
+ "mean_token_accuracy": 0.7504905462265015,
394
+ "step": 48
395
+ },
396
+ {
397
+ "epoch": 0.765625,
398
+ "grad_norm": 17.25,
399
+ "learning_rate": 2.6153846153846154e-06,
400
+ "loss": 1.2412,
401
+ "mean_token_accuracy": 0.7566288113594055,
402
+ "step": 49
403
+ },
404
+ {
405
+ "epoch": 0.78125,
406
+ "grad_norm": 24.375,
407
+ "learning_rate": 2.605769230769231e-06,
408
+ "loss": 1.2232,
409
+ "mean_token_accuracy": 0.7667444348335266,
410
+ "step": 50
411
+ },
412
+ {
413
+ "epoch": 0.796875,
414
+ "grad_norm": 34.25,
415
+ "learning_rate": 2.5961538461538465e-06,
416
+ "loss": 1.2176,
417
+ "mean_token_accuracy": 0.7597681879997253,
418
+ "step": 51
419
+ },
420
+ {
421
+ "epoch": 0.8125,
422
+ "grad_norm": 31.0,
423
+ "learning_rate": 2.5865384615384616e-06,
424
+ "loss": 1.2091,
425
+ "mean_token_accuracy": 0.7564249634742737,
426
+ "step": 52
427
+ },
428
+ {
429
+ "epoch": 0.828125,
430
+ "grad_norm": 9.4375,
431
+ "learning_rate": 2.5769230769230767e-06,
432
+ "loss": 1.1706,
433
+ "mean_token_accuracy": 0.7586262226104736,
434
+ "step": 53
435
+ },
436
+ {
437
+ "epoch": 0.84375,
438
+ "grad_norm": 9.3125,
439
+ "learning_rate": 2.5673076923076923e-06,
440
+ "loss": 1.2491,
441
+ "mean_token_accuracy": 0.7373932600021362,
442
+ "step": 54
443
+ },
444
+ {
445
+ "epoch": 0.859375,
446
+ "grad_norm": 8.8125,
447
+ "learning_rate": 2.557692307692308e-06,
448
+ "loss": 1.2008,
449
+ "mean_token_accuracy": 0.7576074004173279,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.875,
454
+ "grad_norm": 7.8125,
455
+ "learning_rate": 2.548076923076923e-06,
456
+ "loss": 1.1553,
457
+ "mean_token_accuracy": 0.7607351541519165,
458
+ "step": 56
459
+ },
460
+ {
461
+ "epoch": 0.890625,
462
+ "grad_norm": 7.875,
463
+ "learning_rate": 2.5384615384615385e-06,
464
+ "loss": 1.1896,
465
+ "mean_token_accuracy": 0.7548706531524658,
466
+ "step": 57
467
+ },
468
+ {
469
+ "epoch": 0.90625,
470
+ "grad_norm": 13.6875,
471
+ "learning_rate": 2.528846153846154e-06,
472
+ "loss": 1.156,
473
+ "mean_token_accuracy": 0.7589271664619446,
474
+ "step": 58
475
+ },
476
+ {
477
+ "epoch": 0.921875,
478
+ "grad_norm": 12.375,
479
+ "learning_rate": 2.5192307692307695e-06,
480
+ "loss": 1.1924,
481
+ "mean_token_accuracy": 0.7581174373626709,
482
+ "step": 59
483
+ },
484
+ {
485
+ "epoch": 0.9375,
486
+ "grad_norm": 8.875,
487
+ "learning_rate": 2.5096153846153847e-06,
488
+ "loss": 1.193,
489
+ "mean_token_accuracy": 0.7505763173103333,
490
+ "step": 60
491
+ },
492
+ {
493
+ "epoch": 0.953125,
494
+ "grad_norm": 7.53125,
495
+ "learning_rate": 2.5e-06,
496
+ "loss": 1.118,
497
+ "mean_token_accuracy": 0.7625401020050049,
498
+ "step": 61
499
+ },
500
+ {
501
+ "epoch": 0.96875,
502
+ "grad_norm": 7.03125,
503
+ "learning_rate": 2.4903846153846157e-06,
504
+ "loss": 1.1186,
505
+ "mean_token_accuracy": 0.7640949487686157,
506
+ "step": 62
507
+ },
508
+ {
509
+ "epoch": 0.984375,
510
+ "grad_norm": 6.9375,
511
+ "learning_rate": 2.480769230769231e-06,
512
+ "loss": 1.1178,
513
+ "mean_token_accuracy": 0.7689425945281982,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 1.0,
518
+ "grad_norm": 9.75,
519
+ "learning_rate": 2.471153846153846e-06,
520
+ "loss": 1.1485,
521
+ "mean_token_accuracy": 0.7646326422691345,
522
+ "step": 64
523
+ },
524
+ {
525
+ "epoch": 1.015625,
526
+ "grad_norm": 15.3125,
527
+ "learning_rate": 2.4615384615384615e-06,
528
+ "loss": 1.1362,
529
+ "mean_token_accuracy": 0.7596017122268677,
530
+ "step": 65
531
+ },
532
+ {
533
+ "epoch": 1.03125,
534
+ "grad_norm": 11.5625,
535
+ "learning_rate": 2.451923076923077e-06,
536
+ "loss": 1.1227,
537
+ "mean_token_accuracy": 0.7617481350898743,
538
+ "step": 66
539
+ },
540
+ {
541
+ "epoch": 1.046875,
542
+ "grad_norm": 29.125,
543
+ "learning_rate": 2.442307692307692e-06,
544
+ "loss": 1.0983,
545
+ "mean_token_accuracy": 0.7637330293655396,
546
+ "step": 67
547
+ },
548
+ {
549
+ "epoch": 1.0625,
550
+ "grad_norm": 11.0625,
551
+ "learning_rate": 2.4326923076923077e-06,
552
+ "loss": 1.1244,
553
+ "mean_token_accuracy": 0.75943922996521,
554
+ "step": 68
555
+ },
556
+ {
557
+ "epoch": 1.078125,
558
+ "grad_norm": 6.78125,
559
+ "learning_rate": 2.4230769230769233e-06,
560
+ "loss": 1.1029,
561
+ "mean_token_accuracy": 0.7678335309028625,
562
+ "step": 69
563
+ },
564
+ {
565
+ "epoch": 1.09375,
566
+ "grad_norm": 8.25,
567
+ "learning_rate": 2.413461538461539e-06,
568
+ "loss": 1.1107,
569
+ "mean_token_accuracy": 0.766456127166748,
570
+ "step": 70
571
+ },
572
+ {
573
+ "epoch": 1.109375,
574
+ "grad_norm": 6.5,
575
+ "learning_rate": 2.403846153846154e-06,
576
+ "loss": 1.0539,
577
+ "mean_token_accuracy": 0.7779717445373535,
578
+ "step": 71
579
+ },
580
+ {
581
+ "epoch": 1.125,
582
+ "grad_norm": 11.125,
583
+ "learning_rate": 2.3942307692307695e-06,
584
+ "loss": 1.1745,
585
+ "mean_token_accuracy": 0.7527372241020203,
586
+ "step": 72
587
+ },
588
+ {
589
+ "epoch": 1.140625,
590
+ "grad_norm": 6.65625,
591
+ "learning_rate": 2.3846153846153846e-06,
592
+ "loss": 1.1154,
593
+ "mean_token_accuracy": 0.7618581652641296,
594
+ "step": 73
595
+ },
596
+ {
597
+ "epoch": 1.15625,
598
+ "grad_norm": 6.65625,
599
+ "learning_rate": 2.375e-06,
600
+ "loss": 1.0716,
601
+ "mean_token_accuracy": 0.7723715305328369,
602
+ "step": 74
603
+ },
604
+ {
605
+ "epoch": 1.171875,
606
+ "grad_norm": 7.09375,
607
+ "learning_rate": 2.3653846153846152e-06,
608
+ "loss": 1.0951,
609
+ "mean_token_accuracy": 0.7622343897819519,
610
+ "step": 75
611
+ },
612
+ {
613
+ "epoch": 1.1875,
614
+ "grad_norm": 6.375,
615
+ "learning_rate": 2.355769230769231e-06,
616
+ "loss": 1.1046,
617
+ "mean_token_accuracy": 0.768226146697998,
618
+ "step": 76
619
+ },
620
+ {
621
+ "epoch": 1.203125,
622
+ "grad_norm": 8.0,
623
+ "learning_rate": 2.3461538461538463e-06,
624
+ "loss": 1.1724,
625
+ "mean_token_accuracy": 0.7464057803153992,
626
+ "step": 77
627
+ },
628
+ {
629
+ "epoch": 1.21875,
630
+ "grad_norm": 6.96875,
631
+ "learning_rate": 2.3365384615384615e-06,
632
+ "loss": 1.0518,
633
+ "mean_token_accuracy": 0.7725957036018372,
634
+ "step": 78
635
+ },
636
+ {
637
+ "epoch": 1.234375,
638
+ "grad_norm": 7.03125,
639
+ "learning_rate": 2.326923076923077e-06,
640
+ "loss": 1.0578,
641
+ "mean_token_accuracy": 0.7661430835723877,
642
+ "step": 79
643
+ },
644
+ {
645
+ "epoch": 1.25,
646
+ "grad_norm": 7.15625,
647
+ "learning_rate": 2.3173076923076925e-06,
648
+ "loss": 1.0921,
649
+ "mean_token_accuracy": 0.7706676125526428,
650
+ "step": 80
651
+ },
652
+ {
653
+ "epoch": 1.265625,
654
+ "grad_norm": 7.9375,
655
+ "learning_rate": 2.307692307692308e-06,
656
+ "loss": 1.0947,
657
+ "mean_token_accuracy": 0.7600434422492981,
658
+ "step": 81
659
+ },
660
+ {
661
+ "epoch": 1.28125,
662
+ "grad_norm": 6.28125,
663
+ "learning_rate": 2.298076923076923e-06,
664
+ "loss": 1.0152,
665
+ "mean_token_accuracy": 0.7791481614112854,
666
+ "step": 82
667
+ },
668
+ {
669
+ "epoch": 1.296875,
670
+ "grad_norm": 6.40625,
671
+ "learning_rate": 2.2884615384615383e-06,
672
+ "loss": 1.1093,
673
+ "mean_token_accuracy": 0.7621586918830872,
674
+ "step": 83
675
+ },
676
+ {
677
+ "epoch": 1.3125,
678
+ "grad_norm": 6.0625,
679
+ "learning_rate": 2.278846153846154e-06,
680
+ "loss": 1.0595,
681
+ "mean_token_accuracy": 0.7689430713653564,
682
+ "step": 84
683
+ },
684
+ {
685
+ "epoch": 1.328125,
686
+ "grad_norm": 25.625,
687
+ "learning_rate": 2.2692307692307694e-06,
688
+ "loss": 1.1264,
689
+ "mean_token_accuracy": 0.7479003667831421,
690
+ "step": 85
691
+ },
692
+ {
693
+ "epoch": 1.34375,
694
+ "grad_norm": 6.9375,
695
+ "learning_rate": 2.2596153846153845e-06,
696
+ "loss": 1.0278,
697
+ "mean_token_accuracy": 0.7810243964195251,
698
+ "step": 86
699
+ },
700
+ {
701
+ "epoch": 1.359375,
702
+ "grad_norm": 12.0,
703
+ "learning_rate": 2.25e-06,
704
+ "loss": 1.0898,
705
+ "mean_token_accuracy": 0.7608263492584229,
706
+ "step": 87
707
+ },
708
+ {
709
+ "epoch": 1.375,
710
+ "grad_norm": 6.96875,
711
+ "learning_rate": 2.2403846153846156e-06,
712
+ "loss": 1.0646,
713
+ "mean_token_accuracy": 0.7628912925720215,
714
+ "step": 88
715
+ },
716
+ {
717
+ "epoch": 1.390625,
718
+ "grad_norm": 6.3125,
719
+ "learning_rate": 2.2307692307692307e-06,
720
+ "loss": 1.1259,
721
+ "mean_token_accuracy": 0.747133195400238,
722
+ "step": 89
723
+ },
724
+ {
725
+ "epoch": 1.40625,
726
+ "grad_norm": 6.96875,
727
+ "learning_rate": 2.2211538461538463e-06,
728
+ "loss": 1.0527,
729
+ "mean_token_accuracy": 0.769545316696167,
730
+ "step": 90
731
+ },
732
+ {
733
+ "epoch": 1.421875,
734
+ "grad_norm": 6.78125,
735
+ "learning_rate": 2.211538461538462e-06,
736
+ "loss": 1.0857,
737
+ "mean_token_accuracy": 0.7563959956169128,
738
+ "step": 91
739
+ },
740
+ {
741
+ "epoch": 1.4375,
742
+ "grad_norm": 6.6875,
743
+ "learning_rate": 2.201923076923077e-06,
744
+ "loss": 1.0779,
745
+ "mean_token_accuracy": 0.7625620365142822,
746
+ "step": 92
747
+ },
748
+ {
749
+ "epoch": 1.453125,
750
+ "grad_norm": 11.0,
751
+ "learning_rate": 2.192307692307692e-06,
752
+ "loss": 1.0615,
753
+ "mean_token_accuracy": 0.7684396505355835,
754
+ "step": 93
755
+ },
756
+ {
757
+ "epoch": 1.46875,
758
+ "grad_norm": 7.53125,
759
+ "learning_rate": 2.1826923076923076e-06,
760
+ "loss": 1.0067,
761
+ "mean_token_accuracy": 0.773740291595459,
762
+ "step": 94
763
+ },
764
+ {
765
+ "epoch": 1.484375,
766
+ "grad_norm": 6.40625,
767
+ "learning_rate": 2.173076923076923e-06,
768
+ "loss": 1.0334,
769
+ "mean_token_accuracy": 0.7674839496612549,
770
+ "step": 95
771
+ },
772
+ {
773
+ "epoch": 1.5,
774
+ "grad_norm": 9.3125,
775
+ "learning_rate": 2.1634615384615387e-06,
776
+ "loss": 1.0772,
777
+ "mean_token_accuracy": 0.7548962235450745,
778
+ "step": 96
779
+ },
780
+ {
781
+ "epoch": 1.515625,
782
+ "grad_norm": 20.25,
783
+ "learning_rate": 2.1538461538461538e-06,
784
+ "loss": 1.0953,
785
+ "mean_token_accuracy": 0.7568336129188538,
786
+ "step": 97
787
+ },
788
+ {
789
+ "epoch": 1.53125,
790
+ "grad_norm": 6.84375,
791
+ "learning_rate": 2.1442307692307693e-06,
792
+ "loss": 1.0656,
793
+ "mean_token_accuracy": 0.7618821859359741,
794
+ "step": 98
795
+ },
796
+ {
797
+ "epoch": 1.546875,
798
+ "grad_norm": 6.96875,
799
+ "learning_rate": 2.134615384615385e-06,
800
+ "loss": 0.9638,
801
+ "mean_token_accuracy": 0.7852028608322144,
802
+ "step": 99
803
+ },
804
+ {
805
+ "epoch": 1.5625,
806
+ "grad_norm": 16.25,
807
+ "learning_rate": 2.125e-06,
808
+ "loss": 1.057,
809
+ "mean_token_accuracy": 0.7648255228996277,
810
+ "step": 100
811
+ },
812
+ {
813
+ "epoch": 1.578125,
814
+ "grad_norm": 6.59375,
815
+ "learning_rate": 2.1153846153846155e-06,
816
+ "loss": 1.0351,
817
+ "mean_token_accuracy": 0.7706173062324524,
818
+ "step": 101
819
+ },
820
+ {
821
+ "epoch": 1.59375,
822
+ "grad_norm": 19.375,
823
+ "learning_rate": 2.1057692307692306e-06,
824
+ "loss": 1.0262,
825
+ "mean_token_accuracy": 0.7676799297332764,
826
+ "step": 102
827
+ },
828
+ {
829
+ "epoch": 1.609375,
830
+ "grad_norm": 6.40625,
831
+ "learning_rate": 2.096153846153846e-06,
832
+ "loss": 0.9901,
833
+ "mean_token_accuracy": 0.7759581208229065,
834
+ "step": 103
835
+ },
836
+ {
837
+ "epoch": 1.625,
838
+ "grad_norm": 8.5,
839
+ "learning_rate": 2.0865384615384613e-06,
840
+ "loss": 0.9888,
841
+ "mean_token_accuracy": 0.7782798409461975,
842
+ "step": 104
843
+ },
844
+ {
845
+ "epoch": 1.640625,
846
+ "grad_norm": 6.90625,
847
+ "learning_rate": 2.076923076923077e-06,
848
+ "loss": 0.9912,
849
+ "mean_token_accuracy": 0.7795735001564026,
850
+ "step": 105
851
+ },
852
+ {
853
+ "epoch": 1.65625,
854
+ "grad_norm": 8.6875,
855
+ "learning_rate": 2.0673076923076924e-06,
856
+ "loss": 1.0046,
857
+ "mean_token_accuracy": 0.7750487923622131,
858
+ "step": 106
859
+ },
860
+ {
861
+ "epoch": 1.671875,
862
+ "grad_norm": 6.59375,
863
+ "learning_rate": 2.057692307692308e-06,
864
+ "loss": 1.0527,
865
+ "mean_token_accuracy": 0.7730545997619629,
866
+ "step": 107
867
+ },
868
+ {
869
+ "epoch": 1.6875,
870
+ "grad_norm": 7.0,
871
+ "learning_rate": 2.048076923076923e-06,
872
+ "loss": 0.9943,
873
+ "mean_token_accuracy": 0.7790677547454834,
874
+ "step": 108
875
+ },
876
+ {
877
+ "epoch": 1.703125,
878
+ "grad_norm": 52.25,
879
+ "learning_rate": 2.0384615384615386e-06,
880
+ "loss": 1.0243,
881
+ "mean_token_accuracy": 0.7736808657646179,
882
+ "step": 109
883
+ },
884
+ {
885
+ "epoch": 1.71875,
886
+ "grad_norm": 6.65625,
887
+ "learning_rate": 2.028846153846154e-06,
888
+ "loss": 0.9599,
889
+ "mean_token_accuracy": 0.7829864025115967,
890
+ "step": 110
891
+ },
892
+ {
893
+ "epoch": 1.734375,
894
+ "grad_norm": 6.875,
895
+ "learning_rate": 2.0192307692307692e-06,
896
+ "loss": 0.993,
897
+ "mean_token_accuracy": 0.784246563911438,
898
+ "step": 111
899
+ },
900
+ {
901
+ "epoch": 1.75,
902
+ "grad_norm": 15.9375,
903
+ "learning_rate": 2.0096153846153844e-06,
904
+ "loss": 1.0284,
905
+ "mean_token_accuracy": 0.7701562643051147,
906
+ "step": 112
907
+ },
908
+ {
909
+ "epoch": 1.765625,
910
+ "grad_norm": 11.25,
911
+ "learning_rate": 2e-06,
912
+ "loss": 1.0453,
913
+ "mean_token_accuracy": 0.765605092048645,
914
+ "step": 113
915
+ },
916
+ {
917
+ "epoch": 1.78125,
918
+ "grad_norm": 11.25,
919
+ "learning_rate": 1.9903846153846155e-06,
920
+ "loss": 0.9963,
921
+ "mean_token_accuracy": 0.7780460119247437,
922
+ "step": 114
923
+ },
924
+ {
925
+ "epoch": 1.796875,
926
+ "grad_norm": 7.8125,
927
+ "learning_rate": 1.9807692307692306e-06,
928
+ "loss": 1.0104,
929
+ "mean_token_accuracy": 0.7722231149673462,
930
+ "step": 115
931
+ },
932
+ {
933
+ "epoch": 1.8125,
934
+ "grad_norm": 7.46875,
935
+ "learning_rate": 1.971153846153846e-06,
936
+ "loss": 0.9977,
937
+ "mean_token_accuracy": 0.7763562798500061,
938
+ "step": 116
939
+ },
940
+ {
941
+ "epoch": 1.828125,
942
+ "grad_norm": 7.09375,
943
+ "learning_rate": 1.9615384615384617e-06,
944
+ "loss": 0.9994,
945
+ "mean_token_accuracy": 0.7727492451667786,
946
+ "step": 117
947
+ },
948
+ {
949
+ "epoch": 1.84375,
950
+ "grad_norm": 6.71875,
951
+ "learning_rate": 1.951923076923077e-06,
952
+ "loss": 0.9729,
953
+ "mean_token_accuracy": 0.7792785167694092,
954
+ "step": 118
955
+ },
956
+ {
957
+ "epoch": 1.859375,
958
+ "grad_norm": 10.25,
959
+ "learning_rate": 1.9423076923076923e-06,
960
+ "loss": 1.0092,
961
+ "mean_token_accuracy": 0.7684956789016724,
962
+ "step": 119
963
+ },
964
+ {
965
+ "epoch": 1.875,
966
+ "grad_norm": 7.53125,
967
+ "learning_rate": 1.932692307692308e-06,
968
+ "loss": 0.962,
969
+ "mean_token_accuracy": 0.7807108163833618,
970
+ "step": 120
971
+ },
972
+ {
973
+ "epoch": 1.890625,
974
+ "grad_norm": 7.0,
975
+ "learning_rate": 1.9230769230769234e-06,
976
+ "loss": 1.0035,
977
+ "mean_token_accuracy": 0.7749958634376526,
978
+ "step": 121
979
+ },
980
+ {
981
+ "epoch": 1.90625,
982
+ "grad_norm": 9.3125,
983
+ "learning_rate": 1.9134615384615385e-06,
984
+ "loss": 1.0121,
985
+ "mean_token_accuracy": 0.7693877816200256,
986
+ "step": 122
987
+ },
988
+ {
989
+ "epoch": 1.921875,
990
+ "grad_norm": 6.46875,
991
+ "learning_rate": 1.9038461538461538e-06,
992
+ "loss": 0.9797,
993
+ "mean_token_accuracy": 0.7859560251235962,
994
+ "step": 123
995
+ },
996
+ {
997
+ "epoch": 1.9375,
998
+ "grad_norm": 6.65625,
999
+ "learning_rate": 1.8942307692307692e-06,
1000
+ "loss": 0.9071,
1001
+ "mean_token_accuracy": 0.7927353978157043,
1002
+ "step": 124
1003
+ },
1004
+ {
1005
+ "epoch": 1.953125,
1006
+ "grad_norm": 6.5,
1007
+ "learning_rate": 1.8846153846153847e-06,
1008
+ "loss": 0.8898,
1009
+ "mean_token_accuracy": 0.7983871102333069,
1010
+ "step": 125
1011
+ },
1012
+ {
1013
+ "epoch": 1.96875,
1014
+ "grad_norm": 11.625,
1015
+ "learning_rate": 1.875e-06,
1016
+ "loss": 0.9509,
1017
+ "mean_token_accuracy": 0.7818240523338318,
1018
+ "step": 126
1019
+ },
1020
+ {
1021
+ "epoch": 1.984375,
1022
+ "grad_norm": 23.0,
1023
+ "learning_rate": 1.8653846153846154e-06,
1024
+ "loss": 0.9974,
1025
+ "mean_token_accuracy": 0.7754906415939331,
1026
+ "step": 127
1027
+ },
1028
+ {
1029
+ "epoch": 2.0,
1030
+ "grad_norm": 16.25,
1031
+ "learning_rate": 1.855769230769231e-06,
1032
+ "loss": 0.9983,
1033
+ "mean_token_accuracy": 0.7626262903213501,
1034
+ "step": 128
1035
+ },
1036
+ {
1037
+ "epoch": 2.015625,
1038
+ "grad_norm": 107.5,
1039
+ "learning_rate": 1.8461538461538462e-06,
1040
+ "loss": 0.981,
1041
+ "mean_token_accuracy": 0.7775020599365234,
1042
+ "step": 129
1043
+ },
1044
+ {
1045
+ "epoch": 2.03125,
1046
+ "grad_norm": 78.0,
1047
+ "learning_rate": 1.8365384615384618e-06,
1048
+ "loss": 1.0013,
1049
+ "mean_token_accuracy": 0.777273416519165,
1050
+ "step": 130
1051
+ },
1052
+ {
1053
+ "epoch": 2.046875,
1054
+ "grad_norm": 15.75,
1055
+ "learning_rate": 1.826923076923077e-06,
1056
+ "loss": 1.0124,
1057
+ "mean_token_accuracy": 0.7745746970176697,
1058
+ "step": 131
1059
+ },
1060
+ {
1061
+ "epoch": 2.0625,
1062
+ "grad_norm": 6.75,
1063
+ "learning_rate": 1.8173076923076922e-06,
1064
+ "loss": 1.0109,
1065
+ "mean_token_accuracy": 0.7626786828041077,
1066
+ "step": 132
1067
+ },
1068
+ {
1069
+ "epoch": 2.078125,
1070
+ "grad_norm": 10.75,
1071
+ "learning_rate": 1.8076923076923076e-06,
1072
+ "loss": 0.9854,
1073
+ "mean_token_accuracy": 0.7782512903213501,
1074
+ "step": 133
1075
+ },
1076
+ {
1077
+ "epoch": 2.09375,
1078
+ "grad_norm": 13.1875,
1079
+ "learning_rate": 1.7980769230769231e-06,
1080
+ "loss": 0.9558,
1081
+ "mean_token_accuracy": 0.7810325026512146,
1082
+ "step": 134
1083
+ },
1084
+ {
1085
+ "epoch": 2.109375,
1086
+ "grad_norm": 9.875,
1087
+ "learning_rate": 1.7884615384615384e-06,
1088
+ "loss": 0.9925,
1089
+ "mean_token_accuracy": 0.7802160978317261,
1090
+ "step": 135
1091
+ },
1092
+ {
1093
+ "epoch": 2.125,
1094
+ "grad_norm": 7.40625,
1095
+ "learning_rate": 1.778846153846154e-06,
1096
+ "loss": 0.9899,
1097
+ "mean_token_accuracy": 0.7759094834327698,
1098
+ "step": 136
1099
+ },
1100
+ {
1101
+ "epoch": 2.140625,
1102
+ "grad_norm": 6.28125,
1103
+ "learning_rate": 1.7692307692307693e-06,
1104
+ "loss": 0.9509,
1105
+ "mean_token_accuracy": 0.7890124917030334,
1106
+ "step": 137
1107
+ },
1108
+ {
1109
+ "epoch": 2.15625,
1110
+ "grad_norm": 8.1875,
1111
+ "learning_rate": 1.7596153846153846e-06,
1112
+ "loss": 0.9832,
1113
+ "mean_token_accuracy": 0.7752114534378052,
1114
+ "step": 138
1115
+ },
1116
+ {
1117
+ "epoch": 2.171875,
1118
+ "grad_norm": 6.25,
1119
+ "learning_rate": 1.7500000000000002e-06,
1120
+ "loss": 0.9225,
1121
+ "mean_token_accuracy": 0.7903473973274231,
1122
+ "step": 139
1123
+ },
1124
+ {
1125
+ "epoch": 2.1875,
1126
+ "grad_norm": 5.84375,
1127
+ "learning_rate": 1.7403846153846155e-06,
1128
+ "loss": 0.9476,
1129
+ "mean_token_accuracy": 0.7873295545578003,
1130
+ "step": 140
1131
+ },
1132
+ {
1133
+ "epoch": 2.203125,
1134
+ "grad_norm": 20.625,
1135
+ "learning_rate": 1.7307692307692306e-06,
1136
+ "loss": 1.0055,
1137
+ "mean_token_accuracy": 0.7686769962310791,
1138
+ "step": 141
1139
+ },
1140
+ {
1141
+ "epoch": 2.21875,
1142
+ "grad_norm": 26.625,
1143
+ "learning_rate": 1.7211538461538462e-06,
1144
+ "loss": 1.0145,
1145
+ "mean_token_accuracy": 0.7676523923873901,
1146
+ "step": 142
1147
+ },
1148
+ {
1149
+ "epoch": 2.234375,
1150
+ "grad_norm": 7.4375,
1151
+ "learning_rate": 1.7115384615384615e-06,
1152
+ "loss": 0.9358,
1153
+ "mean_token_accuracy": 0.7874542474746704,
1154
+ "step": 143
1155
+ },
1156
+ {
1157
+ "epoch": 2.25,
1158
+ "grad_norm": 23.875,
1159
+ "learning_rate": 1.7019230769230768e-06,
1160
+ "loss": 1.0153,
1161
+ "mean_token_accuracy": 0.768985390663147,
1162
+ "step": 144
1163
+ },
1164
+ {
1165
+ "epoch": 2.265625,
1166
+ "grad_norm": 6.625,
1167
+ "learning_rate": 1.6923076923076924e-06,
1168
+ "loss": 0.9844,
1169
+ "mean_token_accuracy": 0.7775037288665771,
1170
+ "step": 145
1171
+ },
1172
+ {
1173
+ "epoch": 2.28125,
1174
+ "grad_norm": 7.03125,
1175
+ "learning_rate": 1.6826923076923077e-06,
1176
+ "loss": 0.9851,
1177
+ "mean_token_accuracy": 0.7740368843078613,
1178
+ "step": 146
1179
+ },
1180
+ {
1181
+ "epoch": 2.296875,
1182
+ "grad_norm": 44.25,
1183
+ "learning_rate": 1.6730769230769232e-06,
1184
+ "loss": 0.9817,
1185
+ "mean_token_accuracy": 0.7741778492927551,
1186
+ "step": 147
1187
+ },
1188
+ {
1189
+ "epoch": 2.3125,
1190
+ "grad_norm": 13.3125,
1191
+ "learning_rate": 1.6634615384615386e-06,
1192
+ "loss": 0.9974,
1193
+ "mean_token_accuracy": 0.7730644941329956,
1194
+ "step": 148
1195
+ },
1196
+ {
1197
+ "epoch": 2.328125,
1198
+ "grad_norm": 5.625,
1199
+ "learning_rate": 1.653846153846154e-06,
1200
+ "loss": 0.927,
1201
+ "mean_token_accuracy": 0.7886461615562439,
1202
+ "step": 149
1203
+ },
1204
+ {
1205
+ "epoch": 2.34375,
1206
+ "grad_norm": 6.9375,
1207
+ "learning_rate": 1.6442307692307695e-06,
1208
+ "loss": 0.8944,
1209
+ "mean_token_accuracy": 0.795914888381958,
1210
+ "step": 150
1211
+ },
1212
+ {
1213
+ "epoch": 2.359375,
1214
+ "grad_norm": 8.625,
1215
+ "learning_rate": 1.6346153846153846e-06,
1216
+ "loss": 0.9641,
1217
+ "mean_token_accuracy": 0.7850483059883118,
1218
+ "step": 151
1219
+ },
1220
+ {
1221
+ "epoch": 2.375,
1222
+ "grad_norm": 61.25,
1223
+ "learning_rate": 1.625e-06,
1224
+ "loss": 0.9894,
1225
+ "mean_token_accuracy": 0.7669225335121155,
1226
+ "step": 152
1227
+ },
1228
+ {
1229
+ "epoch": 2.390625,
1230
+ "grad_norm": 13.9375,
1231
+ "learning_rate": 1.6153846153846154e-06,
1232
+ "loss": 0.9687,
1233
+ "mean_token_accuracy": 0.7841285467147827,
1234
+ "step": 153
1235
+ },
1236
+ {
1237
+ "epoch": 2.40625,
1238
+ "grad_norm": 25.375,
1239
+ "learning_rate": 1.6057692307692308e-06,
1240
+ "loss": 0.9431,
1241
+ "mean_token_accuracy": 0.7892006039619446,
1242
+ "step": 154
1243
+ },
1244
+ {
1245
+ "epoch": 2.421875,
1246
+ "grad_norm": 6.28125,
1247
+ "learning_rate": 1.596153846153846e-06,
1248
+ "loss": 0.9615,
1249
+ "mean_token_accuracy": 0.7802021503448486,
1250
+ "step": 155
1251
+ },
1252
+ {
1253
+ "epoch": 2.4375,
1254
+ "grad_norm": 9.4375,
1255
+ "learning_rate": 1.5865384615384616e-06,
1256
+ "loss": 0.912,
1257
+ "mean_token_accuracy": 0.7976588606834412,
1258
+ "step": 156
1259
+ },
1260
+ {
1261
+ "epoch": 2.453125,
1262
+ "grad_norm": 6.1875,
1263
+ "learning_rate": 1.576923076923077e-06,
1264
+ "loss": 0.944,
1265
+ "mean_token_accuracy": 0.7864833474159241,
1266
+ "step": 157
1267
+ },
1268
+ {
1269
+ "epoch": 2.46875,
1270
+ "grad_norm": 10.4375,
1271
+ "learning_rate": 1.5673076923076925e-06,
1272
+ "loss": 0.9251,
1273
+ "mean_token_accuracy": 0.7923402786254883,
1274
+ "step": 158
1275
+ },
1276
+ {
1277
+ "epoch": 2.484375,
1278
+ "grad_norm": 14.0625,
1279
+ "learning_rate": 1.5576923076923078e-06,
1280
+ "loss": 0.9495,
1281
+ "mean_token_accuracy": 0.7810263633728027,
1282
+ "step": 159
1283
+ },
1284
+ {
1285
+ "epoch": 2.5,
1286
+ "grad_norm": 27.75,
1287
+ "learning_rate": 1.5480769230769232e-06,
1288
+ "loss": 1.0118,
1289
+ "mean_token_accuracy": 0.7756314873695374,
1290
+ "step": 160
1291
+ },
1292
+ {
1293
+ "epoch": 2.515625,
1294
+ "grad_norm": 6.1875,
1295
+ "learning_rate": 1.5384615384615383e-06,
1296
+ "loss": 0.8795,
1297
+ "mean_token_accuracy": 0.8030520677566528,
1298
+ "step": 161
1299
+ },
1300
+ {
1301
+ "epoch": 2.53125,
1302
+ "grad_norm": 10.75,
1303
+ "learning_rate": 1.5288461538461538e-06,
1304
+ "loss": 0.993,
1305
+ "mean_token_accuracy": 0.7751861214637756,
1306
+ "step": 162
1307
+ },
1308
+ {
1309
+ "epoch": 2.546875,
1310
+ "grad_norm": 6.34375,
1311
+ "learning_rate": 1.5192307692307692e-06,
1312
+ "loss": 0.9337,
1313
+ "mean_token_accuracy": 0.7878151535987854,
1314
+ "step": 163
1315
+ },
1316
+ {
1317
+ "epoch": 2.5625,
1318
+ "grad_norm": 6.4375,
1319
+ "learning_rate": 1.5096153846153847e-06,
1320
+ "loss": 0.9229,
1321
+ "mean_token_accuracy": 0.7985841631889343,
1322
+ "step": 164
1323
+ },
1324
+ {
1325
+ "epoch": 2.578125,
1326
+ "grad_norm": 6.03125,
1327
+ "learning_rate": 1.5e-06,
1328
+ "loss": 0.9183,
1329
+ "mean_token_accuracy": 0.7949057221412659,
1330
+ "step": 165
1331
+ },
1332
+ {
1333
+ "epoch": 2.59375,
1334
+ "grad_norm": 8.1875,
1335
+ "learning_rate": 1.4903846153846154e-06,
1336
+ "loss": 0.9715,
1337
+ "mean_token_accuracy": 0.7781420946121216,
1338
+ "step": 166
1339
+ },
1340
+ {
1341
+ "epoch": 2.609375,
1342
+ "grad_norm": 5.90625,
1343
+ "learning_rate": 1.480769230769231e-06,
1344
+ "loss": 0.9473,
1345
+ "mean_token_accuracy": 0.7875062227249146,
1346
+ "step": 167
1347
+ },
1348
+ {
1349
+ "epoch": 2.625,
1350
+ "grad_norm": 5.75,
1351
+ "learning_rate": 1.471153846153846e-06,
1352
+ "loss": 0.9271,
1353
+ "mean_token_accuracy": 0.7928742170333862,
1354
+ "step": 168
1355
+ },
1356
+ {
1357
+ "epoch": 2.640625,
1358
+ "grad_norm": 13.25,
1359
+ "learning_rate": 1.4615384615384616e-06,
1360
+ "loss": 0.9739,
1361
+ "mean_token_accuracy": 0.7802754640579224,
1362
+ "step": 169
1363
+ },
1364
+ {
1365
+ "epoch": 2.65625,
1366
+ "grad_norm": 6.34375,
1367
+ "learning_rate": 1.451923076923077e-06,
1368
+ "loss": 0.9205,
1369
+ "mean_token_accuracy": 0.7956867218017578,
1370
+ "step": 170
1371
+ },
1372
+ {
1373
+ "epoch": 2.671875,
1374
+ "grad_norm": 20.125,
1375
+ "learning_rate": 1.4423076923076924e-06,
1376
+ "loss": 0.9228,
1377
+ "mean_token_accuracy": 0.7963763475418091,
1378
+ "step": 171
1379
+ },
1380
+ {
1381
+ "epoch": 2.6875,
1382
+ "grad_norm": 7.8125,
1383
+ "learning_rate": 1.4326923076923078e-06,
1384
+ "loss": 0.9705,
1385
+ "mean_token_accuracy": 0.7838233113288879,
1386
+ "step": 172
1387
+ },
1388
+ {
1389
+ "epoch": 2.703125,
1390
+ "grad_norm": 7.625,
1391
+ "learning_rate": 1.423076923076923e-06,
1392
+ "loss": 0.9856,
1393
+ "mean_token_accuracy": 0.777830958366394,
1394
+ "step": 173
1395
+ },
1396
+ {
1397
+ "epoch": 2.71875,
1398
+ "grad_norm": 5.90625,
1399
+ "learning_rate": 1.4134615384615384e-06,
1400
+ "loss": 0.9123,
1401
+ "mean_token_accuracy": 0.7965753674507141,
1402
+ "step": 174
1403
+ },
1404
+ {
1405
+ "epoch": 2.734375,
1406
+ "grad_norm": 6.59375,
1407
+ "learning_rate": 1.403846153846154e-06,
1408
+ "loss": 0.8977,
1409
+ "mean_token_accuracy": 0.7950465679168701,
1410
+ "step": 175
1411
+ },
1412
+ {
1413
+ "epoch": 2.75,
1414
+ "grad_norm": 5.96875,
1415
+ "learning_rate": 1.3942307692307693e-06,
1416
+ "loss": 0.9534,
1417
+ "mean_token_accuracy": 0.7896023392677307,
1418
+ "step": 176
1419
+ },
1420
+ {
1421
+ "epoch": 2.765625,
1422
+ "grad_norm": 51.5,
1423
+ "learning_rate": 1.3846153846153846e-06,
1424
+ "loss": 0.9886,
1425
+ "mean_token_accuracy": 0.7733170390129089,
1426
+ "step": 177
1427
+ },
1428
+ {
1429
+ "epoch": 2.78125,
1430
+ "grad_norm": 6.25,
1431
+ "learning_rate": 1.375e-06,
1432
+ "loss": 0.9304,
1433
+ "mean_token_accuracy": 0.7874513864517212,
1434
+ "step": 178
1435
+ },
1436
+ {
1437
+ "epoch": 2.796875,
1438
+ "grad_norm": 9.1875,
1439
+ "learning_rate": 1.3653846153846153e-06,
1440
+ "loss": 0.9909,
1441
+ "mean_token_accuracy": 0.7773162722587585,
1442
+ "step": 179
1443
+ },
1444
+ {
1445
+ "epoch": 2.8125,
1446
+ "grad_norm": 17.375,
1447
+ "learning_rate": 1.3557692307692308e-06,
1448
+ "loss": 0.9561,
1449
+ "mean_token_accuracy": 0.7817555665969849,
1450
+ "step": 180
1451
+ },
1452
+ {
1453
+ "epoch": 2.828125,
1454
+ "grad_norm": 6.15625,
1455
+ "learning_rate": 1.3461538461538462e-06,
1456
+ "loss": 0.9449,
1457
+ "mean_token_accuracy": 0.7880972623825073,
1458
+ "step": 181
1459
+ },
1460
+ {
1461
+ "epoch": 2.84375,
1462
+ "grad_norm": 6.375,
1463
+ "learning_rate": 1.3365384615384617e-06,
1464
+ "loss": 0.9588,
1465
+ "mean_token_accuracy": 0.7854828238487244,
1466
+ "step": 182
1467
+ },
1468
+ {
1469
+ "epoch": 2.859375,
1470
+ "grad_norm": 33.75,
1471
+ "learning_rate": 1.3269230769230768e-06,
1472
+ "loss": 0.9635,
1473
+ "mean_token_accuracy": 0.7801363468170166,
1474
+ "step": 183
1475
+ },
1476
+ {
1477
+ "epoch": 2.875,
1478
+ "grad_norm": 6.53125,
1479
+ "learning_rate": 1.3173076923076924e-06,
1480
+ "loss": 0.9914,
1481
+ "mean_token_accuracy": 0.7746433615684509,
1482
+ "step": 184
1483
+ },
1484
+ {
1485
+ "epoch": 2.890625,
1486
+ "grad_norm": 6.4375,
1487
+ "learning_rate": 1.3076923076923077e-06,
1488
+ "loss": 0.9492,
1489
+ "mean_token_accuracy": 0.7791839838027954,
1490
+ "step": 185
1491
+ },
1492
+ {
1493
+ "epoch": 2.90625,
1494
+ "grad_norm": 6.65625,
1495
+ "learning_rate": 1.2980769230769232e-06,
1496
+ "loss": 0.9667,
1497
+ "mean_token_accuracy": 0.7795350551605225,
1498
+ "step": 186
1499
+ },
1500
+ {
1501
+ "epoch": 2.921875,
1502
+ "grad_norm": 10.0625,
1503
+ "learning_rate": 1.2884615384615384e-06,
1504
+ "loss": 0.9588,
1505
+ "mean_token_accuracy": 0.7847999930381775,
1506
+ "step": 187
1507
+ },
1508
+ {
1509
+ "epoch": 2.9375,
1510
+ "grad_norm": 25.375,
1511
+ "learning_rate": 1.278846153846154e-06,
1512
+ "loss": 0.8759,
1513
+ "mean_token_accuracy": 0.8001649975776672,
1514
+ "step": 188
1515
+ },
1516
+ {
1517
+ "epoch": 2.953125,
1518
+ "grad_norm": 8.5625,
1519
+ "learning_rate": 1.2692307692307692e-06,
1520
+ "loss": 0.9675,
1521
+ "mean_token_accuracy": 0.7719402313232422,
1522
+ "step": 189
1523
+ },
1524
+ {
1525
+ "epoch": 2.96875,
1526
+ "grad_norm": 6.9375,
1527
+ "learning_rate": 1.2596153846153848e-06,
1528
+ "loss": 0.9304,
1529
+ "mean_token_accuracy": 0.7856206893920898,
1530
+ "step": 190
1531
+ },
1532
+ {
1533
+ "epoch": 2.984375,
1534
+ "grad_norm": 6.1875,
1535
+ "learning_rate": 1.25e-06,
1536
+ "loss": 0.9542,
1537
+ "mean_token_accuracy": 0.78487229347229,
1538
+ "step": 191
1539
+ },
1540
+ {
1541
+ "epoch": 3.0,
1542
+ "grad_norm": 10.8125,
1543
+ "learning_rate": 1.2403846153846154e-06,
1544
+ "loss": 0.9371,
1545
+ "mean_token_accuracy": 0.7693274617195129,
1546
+ "step": 192
1547
+ },
1548
+ {
1549
+ "epoch": 3.015625,
1550
+ "grad_norm": 6.25,
1551
+ "learning_rate": 1.2307692307692308e-06,
1552
+ "loss": 0.892,
1553
+ "mean_token_accuracy": 0.7988702654838562,
1554
+ "step": 193
1555
+ },
1556
+ {
1557
+ "epoch": 3.03125,
1558
+ "grad_norm": 18.375,
1559
+ "learning_rate": 1.221153846153846e-06,
1560
+ "loss": 0.9524,
1561
+ "mean_token_accuracy": 0.782721221446991,
1562
+ "step": 194
1563
+ },
1564
+ {
1565
+ "epoch": 3.046875,
1566
+ "grad_norm": 15.25,
1567
+ "learning_rate": 1.2115384615384616e-06,
1568
+ "loss": 0.9835,
1569
+ "mean_token_accuracy": 0.7716888189315796,
1570
+ "step": 195
1571
+ },
1572
+ {
1573
+ "epoch": 3.0625,
1574
+ "grad_norm": 6.03125,
1575
+ "learning_rate": 1.201923076923077e-06,
1576
+ "loss": 0.8871,
1577
+ "mean_token_accuracy": 0.8021034002304077,
1578
+ "step": 196
1579
+ },
1580
+ {
1581
+ "epoch": 3.078125,
1582
+ "grad_norm": 35.0,
1583
+ "learning_rate": 1.1923076923076923e-06,
1584
+ "loss": 0.9402,
1585
+ "mean_token_accuracy": 0.7832167744636536,
1586
+ "step": 197
1587
+ },
1588
+ {
1589
+ "epoch": 3.09375,
1590
+ "grad_norm": 8.75,
1591
+ "learning_rate": 1.1826923076923076e-06,
1592
+ "loss": 0.991,
1593
+ "mean_token_accuracy": 0.7750375866889954,
1594
+ "step": 198
1595
+ },
1596
+ {
1597
+ "epoch": 3.109375,
1598
+ "grad_norm": 20.25,
1599
+ "learning_rate": 1.1730769230769232e-06,
1600
+ "loss": 0.906,
1601
+ "mean_token_accuracy": 0.7941325902938843,
1602
+ "step": 199
1603
+ },
1604
+ {
1605
+ "epoch": 3.125,
1606
+ "grad_norm": 6.15625,
1607
+ "learning_rate": 1.1634615384615385e-06,
1608
+ "loss": 0.9131,
1609
+ "mean_token_accuracy": 0.7984575629234314,
1610
+ "step": 200
1611
+ },
1612
+ {
1613
+ "epoch": 3.140625,
1614
+ "grad_norm": 6.3125,
1615
+ "learning_rate": 1.153846153846154e-06,
1616
+ "loss": 0.823,
1617
+ "mean_token_accuracy": 0.8103417158126831,
1618
+ "step": 201
1619
+ },
1620
+ {
1621
+ "epoch": 3.15625,
1622
+ "grad_norm": 7.0,
1623
+ "learning_rate": 1.1442307692307692e-06,
1624
+ "loss": 0.9495,
1625
+ "mean_token_accuracy": 0.7842703461647034,
1626
+ "step": 202
1627
+ },
1628
+ {
1629
+ "epoch": 3.171875,
1630
+ "grad_norm": 7.4375,
1631
+ "learning_rate": 1.1346153846153847e-06,
1632
+ "loss": 0.9537,
1633
+ "mean_token_accuracy": 0.7833541035652161,
1634
+ "step": 203
1635
+ },
1636
+ {
1637
+ "epoch": 3.1875,
1638
+ "grad_norm": 8.8125,
1639
+ "learning_rate": 1.125e-06,
1640
+ "loss": 0.9689,
1641
+ "mean_token_accuracy": 0.7763713002204895,
1642
+ "step": 204
1643
+ },
1644
+ {
1645
+ "epoch": 3.203125,
1646
+ "grad_norm": 23.375,
1647
+ "learning_rate": 1.1153846153846154e-06,
1648
+ "loss": 0.9487,
1649
+ "mean_token_accuracy": 0.7811124920845032,
1650
+ "step": 205
1651
+ },
1652
+ {
1653
+ "epoch": 3.21875,
1654
+ "grad_norm": 6.0625,
1655
+ "learning_rate": 1.105769230769231e-06,
1656
+ "loss": 0.8658,
1657
+ "mean_token_accuracy": 0.8113903999328613,
1658
+ "step": 206
1659
+ },
1660
+ {
1661
+ "epoch": 3.234375,
1662
+ "grad_norm": 11.625,
1663
+ "learning_rate": 1.096153846153846e-06,
1664
+ "loss": 0.9577,
1665
+ "mean_token_accuracy": 0.7787481546401978,
1666
+ "step": 207
1667
+ },
1668
+ {
1669
+ "epoch": 3.25,
1670
+ "grad_norm": 6.4375,
1671
+ "learning_rate": 1.0865384615384616e-06,
1672
+ "loss": 0.9042,
1673
+ "mean_token_accuracy": 0.7923972010612488,
1674
+ "step": 208
1675
+ },
1676
+ {
1677
+ "epoch": 3.265625,
1678
+ "grad_norm": 6.6875,
1679
+ "learning_rate": 1.0769230769230769e-06,
1680
+ "loss": 0.9379,
1681
+ "mean_token_accuracy": 0.7835002541542053,
1682
+ "step": 209
1683
+ },
1684
+ {
1685
+ "epoch": 3.28125,
1686
+ "grad_norm": 5.9375,
1687
+ "learning_rate": 1.0673076923076924e-06,
1688
+ "loss": 0.9172,
1689
+ "mean_token_accuracy": 0.7931802868843079,
1690
+ "step": 210
1691
+ },
1692
+ {
1693
+ "epoch": 3.296875,
1694
+ "grad_norm": 7.875,
1695
+ "learning_rate": 1.0576923076923078e-06,
1696
+ "loss": 0.9593,
1697
+ "mean_token_accuracy": 0.7814356684684753,
1698
+ "step": 211
1699
+ },
1700
+ {
1701
+ "epoch": 3.3125,
1702
+ "grad_norm": 30.125,
1703
+ "learning_rate": 1.048076923076923e-06,
1704
+ "loss": 0.9164,
1705
+ "mean_token_accuracy": 0.7888871431350708,
1706
+ "step": 212
1707
+ },
1708
+ {
1709
+ "epoch": 3.328125,
1710
+ "grad_norm": 6.28125,
1711
+ "learning_rate": 1.0384615384615384e-06,
1712
+ "loss": 0.9056,
1713
+ "mean_token_accuracy": 0.7965211868286133,
1714
+ "step": 213
1715
+ },
1716
+ {
1717
+ "epoch": 3.34375,
1718
+ "grad_norm": 6.53125,
1719
+ "learning_rate": 1.028846153846154e-06,
1720
+ "loss": 0.948,
1721
+ "mean_token_accuracy": 0.7837017178535461,
1722
+ "step": 214
1723
+ },
1724
+ {
1725
+ "epoch": 3.359375,
1726
+ "grad_norm": 6.3125,
1727
+ "learning_rate": 1.0192307692307693e-06,
1728
+ "loss": 0.902,
1729
+ "mean_token_accuracy": 0.8006668090820312,
1730
+ "step": 215
1731
+ },
1732
+ {
1733
+ "epoch": 3.375,
1734
+ "grad_norm": 5.75,
1735
+ "learning_rate": 1.0096153846153846e-06,
1736
+ "loss": 0.8923,
1737
+ "mean_token_accuracy": 0.7972199320793152,
1738
+ "step": 216
1739
+ },
1740
+ {
1741
+ "epoch": 3.390625,
1742
+ "grad_norm": 6.1875,
1743
+ "learning_rate": 1e-06,
1744
+ "loss": 0.8828,
1745
+ "mean_token_accuracy": 0.8011194467544556,
1746
+ "step": 217
1747
+ },
1748
+ {
1749
+ "epoch": 3.40625,
1750
+ "grad_norm": 6.28125,
1751
+ "learning_rate": 9.903846153846153e-07,
1752
+ "loss": 0.8411,
1753
+ "mean_token_accuracy": 0.8033494353294373,
1754
+ "step": 218
1755
+ },
1756
+ {
1757
+ "epoch": 3.421875,
1758
+ "grad_norm": 33.75,
1759
+ "learning_rate": 9.807692307692308e-07,
1760
+ "loss": 0.916,
1761
+ "mean_token_accuracy": 0.7819077372550964,
1762
+ "step": 219
1763
+ },
1764
+ {
1765
+ "epoch": 3.4375,
1766
+ "grad_norm": 6.40625,
1767
+ "learning_rate": 9.711538461538462e-07,
1768
+ "loss": 0.9401,
1769
+ "mean_token_accuracy": 0.7851645946502686,
1770
+ "step": 220
1771
+ },
1772
+ {
1773
+ "epoch": 3.453125,
1774
+ "grad_norm": 6.15625,
1775
+ "learning_rate": 9.615384615384617e-07,
1776
+ "loss": 0.8603,
1777
+ "mean_token_accuracy": 0.8017836213111877,
1778
+ "step": 221
1779
+ },
1780
+ {
1781
+ "epoch": 3.46875,
1782
+ "grad_norm": 7.5,
1783
+ "learning_rate": 9.519230769230769e-07,
1784
+ "loss": 0.9541,
1785
+ "mean_token_accuracy": 0.7865185141563416,
1786
+ "step": 222
1787
+ },
1788
+ {
1789
+ "epoch": 3.484375,
1790
+ "grad_norm": 8.625,
1791
+ "learning_rate": 9.423076923076924e-07,
1792
+ "loss": 0.9576,
1793
+ "mean_token_accuracy": 0.774846613407135,
1794
+ "step": 223
1795
+ },
1796
+ {
1797
+ "epoch": 3.5,
1798
+ "grad_norm": 15.25,
1799
+ "learning_rate": 9.326923076923077e-07,
1800
+ "loss": 0.9012,
1801
+ "mean_token_accuracy": 0.7876802086830139,
1802
+ "step": 224
1803
+ },
1804
+ {
1805
+ "epoch": 3.515625,
1806
+ "grad_norm": 25.5,
1807
+ "learning_rate": 9.230769230769231e-07,
1808
+ "loss": 0.9489,
1809
+ "mean_token_accuracy": 0.7805652618408203,
1810
+ "step": 225
1811
+ },
1812
+ {
1813
+ "epoch": 3.53125,
1814
+ "grad_norm": 6.28125,
1815
+ "learning_rate": 9.134615384615385e-07,
1816
+ "loss": 0.874,
1817
+ "mean_token_accuracy": 0.7986671328544617,
1818
+ "step": 226
1819
+ },
1820
+ {
1821
+ "epoch": 3.546875,
1822
+ "grad_norm": 23.5,
1823
+ "learning_rate": 9.038461538461538e-07,
1824
+ "loss": 0.966,
1825
+ "mean_token_accuracy": 0.7745603322982788,
1826
+ "step": 227
1827
+ },
1828
+ {
1829
+ "epoch": 3.5625,
1830
+ "grad_norm": 6.46875,
1831
+ "learning_rate": 8.942307692307692e-07,
1832
+ "loss": 0.8936,
1833
+ "mean_token_accuracy": 0.7917812466621399,
1834
+ "step": 228
1835
+ },
1836
+ {
1837
+ "epoch": 3.578125,
1838
+ "grad_norm": 10.875,
1839
+ "learning_rate": 8.846153846153847e-07,
1840
+ "loss": 0.9755,
1841
+ "mean_token_accuracy": 0.7724282145500183,
1842
+ "step": 229
1843
+ },
1844
+ {
1845
+ "epoch": 3.59375,
1846
+ "grad_norm": 21.875,
1847
+ "learning_rate": 8.750000000000001e-07,
1848
+ "loss": 0.9574,
1849
+ "mean_token_accuracy": 0.7761261463165283,
1850
+ "step": 230
1851
+ },
1852
+ {
1853
+ "epoch": 3.609375,
1854
+ "grad_norm": 20.625,
1855
+ "learning_rate": 8.653846153846153e-07,
1856
+ "loss": 0.9784,
1857
+ "mean_token_accuracy": 0.7752029299736023,
1858
+ "step": 231
1859
+ },
1860
+ {
1861
+ "epoch": 3.625,
1862
+ "grad_norm": 6.25,
1863
+ "learning_rate": 8.557692307692308e-07,
1864
+ "loss": 0.8936,
1865
+ "mean_token_accuracy": 0.796856701374054,
1866
+ "step": 232
1867
+ },
1868
+ {
1869
+ "epoch": 3.640625,
1870
+ "grad_norm": 6.21875,
1871
+ "learning_rate": 8.461538461538462e-07,
1872
+ "loss": 0.9131,
1873
+ "mean_token_accuracy": 0.7863614559173584,
1874
+ "step": 233
1875
+ },
1876
+ {
1877
+ "epoch": 3.65625,
1878
+ "grad_norm": 5.9375,
1879
+ "learning_rate": 8.365384615384616e-07,
1880
+ "loss": 0.8746,
1881
+ "mean_token_accuracy": 0.7959774732589722,
1882
+ "step": 234
1883
+ },
1884
+ {
1885
+ "epoch": 3.671875,
1886
+ "grad_norm": 24.625,
1887
+ "learning_rate": 8.26923076923077e-07,
1888
+ "loss": 0.9224,
1889
+ "mean_token_accuracy": 0.7824280858039856,
1890
+ "step": 235
1891
+ },
1892
+ {
1893
+ "epoch": 3.6875,
1894
+ "grad_norm": 27.125,
1895
+ "learning_rate": 8.173076923076923e-07,
1896
+ "loss": 0.9327,
1897
+ "mean_token_accuracy": 0.7815178632736206,
1898
+ "step": 236
1899
+ },
1900
+ {
1901
+ "epoch": 3.703125,
1902
+ "grad_norm": 6.09375,
1903
+ "learning_rate": 8.076923076923077e-07,
1904
+ "loss": 0.9501,
1905
+ "mean_token_accuracy": 0.7856559157371521,
1906
+ "step": 237
1907
+ },
1908
+ {
1909
+ "epoch": 3.71875,
1910
+ "grad_norm": 20.25,
1911
+ "learning_rate": 7.98076923076923e-07,
1912
+ "loss": 0.8748,
1913
+ "mean_token_accuracy": 0.7932746410369873,
1914
+ "step": 238
1915
+ },
1916
+ {
1917
+ "epoch": 3.734375,
1918
+ "grad_norm": 6.625,
1919
+ "learning_rate": 7.884615384615385e-07,
1920
+ "loss": 0.9192,
1921
+ "mean_token_accuracy": 0.7865205407142639,
1922
+ "step": 239
1923
+ },
1924
+ {
1925
+ "epoch": 3.75,
1926
+ "grad_norm": 6.4375,
1927
+ "learning_rate": 7.788461538461539e-07,
1928
+ "loss": 0.9443,
1929
+ "mean_token_accuracy": 0.7778134346008301,
1930
+ "step": 240
1931
+ },
1932
+ {
1933
+ "epoch": 3.765625,
1934
+ "grad_norm": 6.0,
1935
+ "learning_rate": 7.692307692307691e-07,
1936
+ "loss": 0.9398,
1937
+ "mean_token_accuracy": 0.7858214974403381,
1938
+ "step": 241
1939
+ },
1940
+ {
1941
+ "epoch": 3.78125,
1942
+ "grad_norm": 5.9375,
1943
+ "learning_rate": 7.596153846153846e-07,
1944
+ "loss": 0.873,
1945
+ "mean_token_accuracy": 0.7989254593849182,
1946
+ "step": 242
1947
+ },
1948
+ {
1949
+ "epoch": 3.796875,
1950
+ "grad_norm": 6.21875,
1951
+ "learning_rate": 7.5e-07,
1952
+ "loss": 0.9991,
1953
+ "mean_token_accuracy": 0.7662928104400635,
1954
+ "step": 243
1955
+ },
1956
+ {
1957
+ "epoch": 3.8125,
1958
+ "grad_norm": 11.75,
1959
+ "learning_rate": 7.403846153846155e-07,
1960
+ "loss": 0.8945,
1961
+ "mean_token_accuracy": 0.7896128296852112,
1962
+ "step": 244
1963
+ },
1964
+ {
1965
+ "epoch": 3.828125,
1966
+ "grad_norm": 6.375,
1967
+ "learning_rate": 7.307692307692308e-07,
1968
+ "loss": 0.917,
1969
+ "mean_token_accuracy": 0.7882217764854431,
1970
+ "step": 245
1971
+ },
1972
+ {
1973
+ "epoch": 3.84375,
1974
+ "grad_norm": 6.28125,
1975
+ "learning_rate": 7.211538461538462e-07,
1976
+ "loss": 0.9661,
1977
+ "mean_token_accuracy": 0.7709052562713623,
1978
+ "step": 246
1979
+ },
1980
+ {
1981
+ "epoch": 3.859375,
1982
+ "grad_norm": 6.125,
1983
+ "learning_rate": 7.115384615384616e-07,
1984
+ "loss": 0.9326,
1985
+ "mean_token_accuracy": 0.7830464243888855,
1986
+ "step": 247
1987
+ },
1988
+ {
1989
+ "epoch": 3.875,
1990
+ "grad_norm": 8.5,
1991
+ "learning_rate": 7.01923076923077e-07,
1992
+ "loss": 0.9376,
1993
+ "mean_token_accuracy": 0.7810230255126953,
1994
+ "step": 248
1995
+ },
1996
+ {
1997
+ "epoch": 3.890625,
1998
+ "grad_norm": 14.0,
1999
+ "learning_rate": 6.923076923076923e-07,
2000
+ "loss": 0.9734,
2001
+ "mean_token_accuracy": 0.7753646373748779,
2002
+ "step": 249
2003
+ },
2004
+ {
2005
+ "epoch": 3.90625,
2006
+ "grad_norm": 12.8125,
2007
+ "learning_rate": 6.826923076923076e-07,
2008
+ "loss": 0.8922,
2009
+ "mean_token_accuracy": 0.7958292961120605,
2010
+ "step": 250
2011
+ },
2012
+ {
2013
+ "epoch": 3.921875,
2014
+ "grad_norm": 5.71875,
2015
+ "learning_rate": 6.730769230769231e-07,
2016
+ "loss": 0.9053,
2017
+ "mean_token_accuracy": 0.7927485704421997,
2018
+ "step": 251
2019
+ },
2020
+ {
2021
+ "epoch": 3.9375,
2022
+ "grad_norm": 6.21875,
2023
+ "learning_rate": 6.634615384615384e-07,
2024
+ "loss": 0.8707,
2025
+ "mean_token_accuracy": 0.8024818897247314,
2026
+ "step": 252
2027
+ },
2028
+ {
2029
+ "epoch": 3.953125,
2030
+ "grad_norm": 6.09375,
2031
+ "learning_rate": 6.538461538461538e-07,
2032
+ "loss": 0.8756,
2033
+ "mean_token_accuracy": 0.7953294515609741,
2034
+ "step": 253
2035
+ },
2036
+ {
2037
+ "epoch": 3.96875,
2038
+ "grad_norm": 16.75,
2039
+ "learning_rate": 6.442307692307692e-07,
2040
+ "loss": 0.9806,
2041
+ "mean_token_accuracy": 0.7700640559196472,
2042
+ "step": 254
2043
+ },
2044
+ {
2045
+ "epoch": 3.984375,
2046
+ "grad_norm": 6.15625,
2047
+ "learning_rate": 6.346153846153846e-07,
2048
+ "loss": 0.9052,
2049
+ "mean_token_accuracy": 0.7910767197608948,
2050
+ "step": 255
2051
+ },
2052
+ {
2053
+ "epoch": 4.0,
2054
+ "grad_norm": 6.1875,
2055
+ "learning_rate": 6.25e-07,
2056
+ "loss": 0.8756,
2057
+ "mean_token_accuracy": 0.7918968796730042,
2058
+ "step": 256
2059
+ },
2060
+ {
2061
+ "epoch": 4.015625,
2062
+ "grad_norm": 6.15625,
2063
+ "learning_rate": 6.153846153846154e-07,
2064
+ "loss": 0.8858,
2065
+ "mean_token_accuracy": 0.7959042191505432,
2066
+ "step": 257
2067
+ },
2068
+ {
2069
+ "epoch": 4.03125,
2070
+ "grad_norm": 6.8125,
2071
+ "learning_rate": 6.057692307692308e-07,
2072
+ "loss": 0.9302,
2073
+ "mean_token_accuracy": 0.7876441478729248,
2074
+ "step": 258
2075
+ },
2076
+ {
2077
+ "epoch": 4.046875,
2078
+ "grad_norm": 7.96875,
2079
+ "learning_rate": 5.961538461538461e-07,
2080
+ "loss": 0.9649,
2081
+ "mean_token_accuracy": 0.7740775346755981,
2082
+ "step": 259
2083
+ },
2084
+ {
2085
+ "epoch": 4.0625,
2086
+ "grad_norm": 19.125,
2087
+ "learning_rate": 5.865384615384616e-07,
2088
+ "loss": 0.9184,
2089
+ "mean_token_accuracy": 0.7818529605865479,
2090
+ "step": 260
2091
+ },
2092
+ {
2093
+ "epoch": 4.078125,
2094
+ "grad_norm": 11.375,
2095
+ "learning_rate": 5.76923076923077e-07,
2096
+ "loss": 0.912,
2097
+ "mean_token_accuracy": 0.7843265533447266,
2098
+ "step": 261
2099
+ },
2100
+ {
2101
+ "epoch": 4.09375,
2102
+ "grad_norm": 6.84375,
2103
+ "learning_rate": 5.673076923076923e-07,
2104
+ "loss": 0.9025,
2105
+ "mean_token_accuracy": 0.7933535575866699,
2106
+ "step": 262
2107
+ },
2108
+ {
2109
+ "epoch": 4.109375,
2110
+ "grad_norm": 6.1875,
2111
+ "learning_rate": 5.576923076923077e-07,
2112
+ "loss": 0.9127,
2113
+ "mean_token_accuracy": 0.7852448225021362,
2114
+ "step": 263
2115
+ },
2116
+ {
2117
+ "epoch": 4.125,
2118
+ "grad_norm": 6.03125,
2119
+ "learning_rate": 5.48076923076923e-07,
2120
+ "loss": 0.9111,
2121
+ "mean_token_accuracy": 0.7866109013557434,
2122
+ "step": 264
2123
+ },
2124
+ {
2125
+ "epoch": 4.140625,
2126
+ "grad_norm": 6.21875,
2127
+ "learning_rate": 5.384615384615384e-07,
2128
+ "loss": 0.892,
2129
+ "mean_token_accuracy": 0.7890470027923584,
2130
+ "step": 265
2131
+ },
2132
+ {
2133
+ "epoch": 4.15625,
2134
+ "grad_norm": 12.0625,
2135
+ "learning_rate": 5.288461538461539e-07,
2136
+ "loss": 0.8986,
2137
+ "mean_token_accuracy": 0.7962346076965332,
2138
+ "step": 266
2139
+ },
2140
+ {
2141
+ "epoch": 4.171875,
2142
+ "grad_norm": 29.0,
2143
+ "learning_rate": 5.192307692307692e-07,
2144
+ "loss": 0.9209,
2145
+ "mean_token_accuracy": 0.786607563495636,
2146
+ "step": 267
2147
+ },
2148
+ {
2149
+ "epoch": 4.1875,
2150
+ "grad_norm": 6.25,
2151
+ "learning_rate": 5.096153846153846e-07,
2152
+ "loss": 0.904,
2153
+ "mean_token_accuracy": 0.7876223921775818,
2154
+ "step": 268
2155
+ },
2156
+ {
2157
+ "epoch": 4.203125,
2158
+ "grad_norm": 7.96875,
2159
+ "learning_rate": 5e-07,
2160
+ "loss": 0.9383,
2161
+ "mean_token_accuracy": 0.7814289927482605,
2162
+ "step": 269
2163
+ },
2164
+ {
2165
+ "epoch": 4.21875,
2166
+ "grad_norm": 6.15625,
2167
+ "learning_rate": 4.903846153846154e-07,
2168
+ "loss": 0.9128,
2169
+ "mean_token_accuracy": 0.7915287613868713,
2170
+ "step": 270
2171
+ },
2172
+ {
2173
+ "epoch": 4.234375,
2174
+ "grad_norm": 6.78125,
2175
+ "learning_rate": 4.807692307692308e-07,
2176
+ "loss": 0.9481,
2177
+ "mean_token_accuracy": 0.7819157242774963,
2178
+ "step": 271
2179
+ },
2180
+ {
2181
+ "epoch": 4.25,
2182
+ "grad_norm": 6.25,
2183
+ "learning_rate": 4.711538461538462e-07,
2184
+ "loss": 0.8902,
2185
+ "mean_token_accuracy": 0.7958080768585205,
2186
+ "step": 272
2187
+ },
2188
+ {
2189
+ "epoch": 4.265625,
2190
+ "grad_norm": 7.65625,
2191
+ "learning_rate": 4.6153846153846156e-07,
2192
+ "loss": 0.977,
2193
+ "mean_token_accuracy": 0.7705891132354736,
2194
+ "step": 273
2195
+ },
2196
+ {
2197
+ "epoch": 4.28125,
2198
+ "grad_norm": 18.125,
2199
+ "learning_rate": 4.519230769230769e-07,
2200
+ "loss": 0.9237,
2201
+ "mean_token_accuracy": 0.7899967432022095,
2202
+ "step": 274
2203
+ },
2204
+ {
2205
+ "epoch": 4.296875,
2206
+ "grad_norm": 8.0,
2207
+ "learning_rate": 4.4230769230769233e-07,
2208
+ "loss": 0.8679,
2209
+ "mean_token_accuracy": 0.7969164252281189,
2210
+ "step": 275
2211
+ },
2212
+ {
2213
+ "epoch": 4.3125,
2214
+ "grad_norm": 6.03125,
2215
+ "learning_rate": 4.3269230769230766e-07,
2216
+ "loss": 0.8823,
2217
+ "mean_token_accuracy": 0.7964279651641846,
2218
+ "step": 276
2219
+ },
2220
+ {
2221
+ "epoch": 4.328125,
2222
+ "grad_norm": 9.6875,
2223
+ "learning_rate": 4.230769230769231e-07,
2224
+ "loss": 0.8829,
2225
+ "mean_token_accuracy": 0.7917771935462952,
2226
+ "step": 277
2227
+ },
2228
+ {
2229
+ "epoch": 4.34375,
2230
+ "grad_norm": 5.9375,
2231
+ "learning_rate": 4.134615384615385e-07,
2232
+ "loss": 0.8448,
2233
+ "mean_token_accuracy": 0.80218505859375,
2234
+ "step": 278
2235
+ },
2236
+ {
2237
+ "epoch": 4.359375,
2238
+ "grad_norm": 23.875,
2239
+ "learning_rate": 4.0384615384615386e-07,
2240
+ "loss": 0.9189,
2241
+ "mean_token_accuracy": 0.7808871865272522,
2242
+ "step": 279
2243
+ },
2244
+ {
2245
+ "epoch": 4.375,
2246
+ "grad_norm": 11.9375,
2247
+ "learning_rate": 3.9423076923076924e-07,
2248
+ "loss": 0.9288,
2249
+ "mean_token_accuracy": 0.7887097001075745,
2250
+ "step": 280
2251
+ },
2252
+ {
2253
+ "epoch": 4.390625,
2254
+ "grad_norm": 6.0625,
2255
+ "learning_rate": 3.846153846153846e-07,
2256
+ "loss": 0.9306,
2257
+ "mean_token_accuracy": 0.7884582877159119,
2258
+ "step": 281
2259
+ },
2260
+ {
2261
+ "epoch": 4.40625,
2262
+ "grad_norm": 6.40625,
2263
+ "learning_rate": 3.75e-07,
2264
+ "loss": 0.9234,
2265
+ "mean_token_accuracy": 0.7834262847900391,
2266
+ "step": 282
2267
+ },
2268
+ {
2269
+ "epoch": 4.421875,
2270
+ "grad_norm": 6.1875,
2271
+ "learning_rate": 3.653846153846154e-07,
2272
+ "loss": 0.8417,
2273
+ "mean_token_accuracy": 0.8057113885879517,
2274
+ "step": 283
2275
+ },
2276
+ {
2277
+ "epoch": 4.4375,
2278
+ "grad_norm": 6.59375,
2279
+ "learning_rate": 3.557692307692308e-07,
2280
+ "loss": 0.9138,
2281
+ "mean_token_accuracy": 0.7837575078010559,
2282
+ "step": 284
2283
+ },
2284
+ {
2285
+ "epoch": 4.453125,
2286
+ "grad_norm": 33.25,
2287
+ "learning_rate": 3.4615384615384616e-07,
2288
+ "loss": 0.8612,
2289
+ "mean_token_accuracy": 0.7957943081855774,
2290
+ "step": 285
2291
+ },
2292
+ {
2293
+ "epoch": 4.46875,
2294
+ "grad_norm": 5.71875,
2295
+ "learning_rate": 3.3653846153846154e-07,
2296
+ "loss": 0.8749,
2297
+ "mean_token_accuracy": 0.8011859059333801,
2298
+ "step": 286
2299
+ },
2300
+ {
2301
+ "epoch": 4.484375,
2302
+ "grad_norm": 6.5,
2303
+ "learning_rate": 3.269230769230769e-07,
2304
+ "loss": 0.8933,
2305
+ "mean_token_accuracy": 0.7931327819824219,
2306
+ "step": 287
2307
+ },
2308
+ {
2309
+ "epoch": 4.5,
2310
+ "grad_norm": 5.96875,
2311
+ "learning_rate": 3.173076923076923e-07,
2312
+ "loss": 0.873,
2313
+ "mean_token_accuracy": 0.799176812171936,
2314
+ "step": 288
2315
+ },
2316
+ {
2317
+ "epoch": 4.515625,
2318
+ "grad_norm": 29.25,
2319
+ "learning_rate": 3.076923076923077e-07,
2320
+ "loss": 0.9831,
2321
+ "mean_token_accuracy": 0.7707536816596985,
2322
+ "step": 289
2323
+ },
2324
+ {
2325
+ "epoch": 4.53125,
2326
+ "grad_norm": 13.0,
2327
+ "learning_rate": 2.980769230769231e-07,
2328
+ "loss": 0.9484,
2329
+ "mean_token_accuracy": 0.7785703539848328,
2330
+ "step": 290
2331
+ },
2332
+ {
2333
+ "epoch": 4.546875,
2334
+ "grad_norm": 6.875,
2335
+ "learning_rate": 2.884615384615385e-07,
2336
+ "loss": 0.9039,
2337
+ "mean_token_accuracy": 0.7895255088806152,
2338
+ "step": 291
2339
+ },
2340
+ {
2341
+ "epoch": 4.5625,
2342
+ "grad_norm": 6.625,
2343
+ "learning_rate": 2.7884615384615384e-07,
2344
+ "loss": 0.9063,
2345
+ "mean_token_accuracy": 0.7905294299125671,
2346
+ "step": 292
2347
+ },
2348
+ {
2349
+ "epoch": 4.578125,
2350
+ "grad_norm": 7.5,
2351
+ "learning_rate": 2.692307692307692e-07,
2352
+ "loss": 0.8963,
2353
+ "mean_token_accuracy": 0.7899447083473206,
2354
+ "step": 293
2355
+ },
2356
+ {
2357
+ "epoch": 4.59375,
2358
+ "grad_norm": 6.84375,
2359
+ "learning_rate": 2.596153846153846e-07,
2360
+ "loss": 0.94,
2361
+ "mean_token_accuracy": 0.7839446663856506,
2362
+ "step": 294
2363
+ },
2364
+ {
2365
+ "epoch": 4.609375,
2366
+ "grad_norm": 5.875,
2367
+ "learning_rate": 2.5e-07,
2368
+ "loss": 0.8796,
2369
+ "mean_token_accuracy": 0.7935015559196472,
2370
+ "step": 295
2371
+ },
2372
+ {
2373
+ "epoch": 4.625,
2374
+ "grad_norm": 10.125,
2375
+ "learning_rate": 2.403846153846154e-07,
2376
+ "loss": 0.8859,
2377
+ "mean_token_accuracy": 0.789797842502594,
2378
+ "step": 296
2379
+ },
2380
+ {
2381
+ "epoch": 4.640625,
2382
+ "grad_norm": 6.5,
2383
+ "learning_rate": 2.3076923076923078e-07,
2384
+ "loss": 0.9302,
2385
+ "mean_token_accuracy": 0.7839468121528625,
2386
+ "step": 297
2387
+ },
2388
+ {
2389
+ "epoch": 4.65625,
2390
+ "grad_norm": 6.28125,
2391
+ "learning_rate": 2.2115384615384616e-07,
2392
+ "loss": 0.9524,
2393
+ "mean_token_accuracy": 0.7737887501716614,
2394
+ "step": 298
2395
+ },
2396
+ {
2397
+ "epoch": 4.671875,
2398
+ "grad_norm": 8.125,
2399
+ "learning_rate": 2.1153846153846155e-07,
2400
+ "loss": 0.9181,
2401
+ "mean_token_accuracy": 0.7865311503410339,
2402
+ "step": 299
2403
+ },
2404
+ {
2405
+ "epoch": 4.6875,
2406
+ "grad_norm": 6.8125,
2407
+ "learning_rate": 2.0192307692307693e-07,
2408
+ "loss": 0.8934,
2409
+ "mean_token_accuracy": 0.789657473564148,
2410
+ "step": 300
2411
+ },
2412
+ {
2413
+ "epoch": 4.703125,
2414
+ "grad_norm": 6.4375,
2415
+ "learning_rate": 1.923076923076923e-07,
2416
+ "loss": 0.9065,
2417
+ "mean_token_accuracy": 0.789890468120575,
2418
+ "step": 301
2419
+ },
2420
+ {
2421
+ "epoch": 4.71875,
2422
+ "grad_norm": 6.0625,
2423
+ "learning_rate": 1.826923076923077e-07,
2424
+ "loss": 0.8889,
2425
+ "mean_token_accuracy": 0.7914140820503235,
2426
+ "step": 302
2427
+ },
2428
+ {
2429
+ "epoch": 4.734375,
2430
+ "grad_norm": 14.0,
2431
+ "learning_rate": 1.7307692307692308e-07,
2432
+ "loss": 0.9113,
2433
+ "mean_token_accuracy": 0.7846829891204834,
2434
+ "step": 303
2435
+ },
2436
+ {
2437
+ "epoch": 4.75,
2438
+ "grad_norm": 7.34375,
2439
+ "learning_rate": 1.6346153846153846e-07,
2440
+ "loss": 0.9374,
2441
+ "mean_token_accuracy": 0.7835116386413574,
2442
+ "step": 304
2443
+ },
2444
+ {
2445
+ "epoch": 4.765625,
2446
+ "grad_norm": 11.375,
2447
+ "learning_rate": 1.5384615384615385e-07,
2448
+ "loss": 0.8824,
2449
+ "mean_token_accuracy": 0.7850437760353088,
2450
+ "step": 305
2451
+ },
2452
+ {
2453
+ "epoch": 4.78125,
2454
+ "grad_norm": 7.1875,
2455
+ "learning_rate": 1.4423076923076925e-07,
2456
+ "loss": 0.9408,
2457
+ "mean_token_accuracy": 0.7855393886566162,
2458
+ "step": 306
2459
+ },
2460
+ {
2461
+ "epoch": 4.796875,
2462
+ "grad_norm": 8.3125,
2463
+ "learning_rate": 1.346153846153846e-07,
2464
+ "loss": 0.9047,
2465
+ "mean_token_accuracy": 0.7834271788597107,
2466
+ "step": 307
2467
+ },
2468
+ {
2469
+ "epoch": 4.8125,
2470
+ "grad_norm": 8.0625,
2471
+ "learning_rate": 1.25e-07,
2472
+ "loss": 0.9188,
2473
+ "mean_token_accuracy": 0.7803459167480469,
2474
+ "step": 308
2475
+ },
2476
+ {
2477
+ "epoch": 4.828125,
2478
+ "grad_norm": 20.25,
2479
+ "learning_rate": 1.1538461538461539e-07,
2480
+ "loss": 0.9627,
2481
+ "mean_token_accuracy": 0.7762289047241211,
2482
+ "step": 309
2483
+ },
2484
+ {
2485
+ "epoch": 4.84375,
2486
+ "grad_norm": 10.6875,
2487
+ "learning_rate": 1.0576923076923077e-07,
2488
+ "loss": 0.884,
2489
+ "mean_token_accuracy": 0.7895846962928772,
2490
+ "step": 310
2491
+ },
2492
+ {
2493
+ "epoch": 4.859375,
2494
+ "grad_norm": 6.53125,
2495
+ "learning_rate": 9.615384615384614e-08,
2496
+ "loss": 0.894,
2497
+ "mean_token_accuracy": 0.792397677898407,
2498
+ "step": 311
2499
+ },
2500
+ {
2501
+ "epoch": 4.875,
2502
+ "grad_norm": 10.6875,
2503
+ "learning_rate": 8.653846153846154e-08,
2504
+ "loss": 0.9112,
2505
+ "mean_token_accuracy": 0.786827564239502,
2506
+ "step": 312
2507
+ },
2508
+ {
2509
+ "epoch": 4.890625,
2510
+ "grad_norm": 6.6875,
2511
+ "learning_rate": 7.692307692307692e-08,
2512
+ "loss": 0.9368,
2513
+ "mean_token_accuracy": 0.7861944437026978,
2514
+ "step": 313
2515
+ },
2516
+ {
2517
+ "epoch": 4.90625,
2518
+ "grad_norm": 10.625,
2519
+ "learning_rate": 6.73076923076923e-08,
2520
+ "loss": 0.9033,
2521
+ "mean_token_accuracy": 0.7840073704719543,
2522
+ "step": 314
2523
+ },
2524
+ {
2525
+ "epoch": 4.921875,
2526
+ "grad_norm": 10.25,
2527
+ "learning_rate": 5.7692307692307695e-08,
2528
+ "loss": 0.8777,
2529
+ "mean_token_accuracy": 0.7938881516456604,
2530
+ "step": 315
2531
+ },
2532
+ {
2533
+ "epoch": 4.9375,
2534
+ "grad_norm": 6.5625,
2535
+ "learning_rate": 4.807692307692307e-08,
2536
+ "loss": 0.9133,
2537
+ "mean_token_accuracy": 0.7796001434326172,
2538
+ "step": 316
2539
+ },
2540
+ {
2541
+ "epoch": 4.953125,
2542
+ "grad_norm": 5.6875,
2543
+ "learning_rate": 3.846153846153846e-08,
2544
+ "loss": 0.8674,
2545
+ "mean_token_accuracy": 0.7963815927505493,
2546
+ "step": 317
2547
+ },
2548
+ {
2549
+ "epoch": 4.96875,
2550
+ "grad_norm": 5.96875,
2551
+ "learning_rate": 2.8846153846153848e-08,
2552
+ "loss": 0.8872,
2553
+ "mean_token_accuracy": 0.7956120371818542,
2554
+ "step": 318
2555
+ },
2556
+ {
2557
+ "epoch": 4.984375,
2558
+ "grad_norm": 35.0,
2559
+ "learning_rate": 1.923076923076923e-08,
2560
+ "loss": 0.9419,
2561
+ "mean_token_accuracy": 0.7827126979827881,
2562
+ "step": 319
2563
+ },
2564
+ {
2565
+ "epoch": 5.0,
2566
+ "grad_norm": 6.625,
2567
+ "learning_rate": 9.615384615384615e-09,
2568
+ "loss": 0.8891,
2569
+ "mean_token_accuracy": 0.7931276559829712,
2570
+ "step": 320
2571
+ }
2572
+ ],
2573
+ "logging_steps": 1.0,
2574
+ "max_steps": 320,
2575
+ "num_input_tokens_seen": 0,
2576
+ "num_train_epochs": 5,
2577
+ "save_steps": 25,
2578
+ "stateful_callbacks": {
2579
+ "TrainerControl": {
2580
+ "args": {
2581
+ "should_epoch_stop": false,
2582
+ "should_evaluate": false,
2583
+ "should_log": false,
2584
+ "should_save": true,
2585
+ "should_training_stop": true
2586
+ },
2587
+ "attributes": {}
2588
+ }
2589
+ },
2590
+ "total_flos": 5.299754052563763e+16,
2591
+ "train_batch_size": 4,
2592
+ "trial_name": null,
2593
+ "trial_params": null
2594
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98bd385032fabae84af47b70399a2a4db5904a252258915189882343cc98234
3
+ size 6033