Hugging Face's logo

WhiteDandelion
/
gemma3-checkpoint-300

Safetensors
gemma3
Model card Files
xet
 Community
WhiteDandelion commited on
Commit
d3602f0
·
verified ·
1 Parent(s): cd7b1ca

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. chat_template.json +3 -0
  4. config.json +63 -0
  5. generation_config.json +11 -0
  6. model-00001-of-00002.safetensors +3 -0
  7. model-00002-of-00002.safetensors +3 -0
  8. model.safetensors.index.json +890 -0
  9. optimizer.pt +3 -0
  10. preprocessor_config.json +29 -0
  11. processor_config.json +4 -0
  12. rng_state.pth +3 -0
  13. scheduler.pt +3 -0
  14. special_tokens_map.json +33 -0
  15. tokenizer.json +3 -0
  16. tokenizer.model +3 -0
  17. tokenizer_config.json +0 -0
  18. trainer_state.json +2134 -0
  19. 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
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
3
+ }
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": 106,
9
+ "image_token_index": 262144,
10
+ "initializer_range": 0.02,
11
+ "mm_tokens_per_image": 256,
12
+ "model_type": "gemma3",
13
+ "pad_token_id": 0,
14
+ "text_config": {
15
+ "attention_bias": false,
16
+ "attention_dropout": 0.0,
17
+ "attn_logit_softcapping": 0,
18
+ "cache_implementation": "hybrid",
19
+ "final_logit_softcapping": 0,
20
+ "head_dim": 256,
21
+ "hidden_activation": "gelu_pytorch_tanh",
22
+ "hidden_size": 2560,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 10240,
25
+ "max_position_embeddings": 131072,
26
+ "model_type": "gemma3_text",
27
+ "num_attention_heads": 8,
28
+ "num_hidden_layers": 34,
29
+ "num_key_value_heads": 4,
30
+ "query_pre_attn_scalar": 256,
31
+ "rms_norm_eps": 1e-06,
32
+ "rope_local_base_freq": 10000.0,
33
+ "rope_scaling": {
34
+ "factor": 8.0,
35
+ "rope_type": "linear"
36
+ },
37
+ "rope_theta": 1000000.0,
38
+ "sliding_window": 1024,
39
+ "sliding_window_pattern": 6,
40
+ "torch_dtype": "bfloat16",
41
+ "use_cache": false,
42
+ "vocab_size": 262208
43
+ },
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.50.3",
46
+ "unsloth_fixed": true,
47
+ "unsloth_version": "2025.3.19",
48
+ "vision_config": {
49
+ "attention_dropout": 0.0,
50
+ "hidden_act": "gelu_pytorch_tanh",
51
+ "hidden_size": 1152,
52
+ "image_size": 896,
53
+ "intermediate_size": 4304,
54
+ "layer_norm_eps": 1e-06,
55
+ "model_type": "siglip_vision_model",
56
+ "num_attention_heads": 16,
57
+ "num_channels": 3,
58
+ "num_hidden_layers": 27,
59
+ "patch_size": 14,
60
+ "torch_dtype": "bfloat16",
61
+ "vision_use_head": false
62
+ }
63
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "transformers_version": "4.50.3"
11
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60553f8c19765d402c9510d32ef04df1dfad4996cd662fa9d9baf94276c3843c
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:a88627f0772ee709fec2138a546231d1ea11d428fb138c1433639c4c75359b4f
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 sha256:79fd41237c221daf006ad4eb595e1a90e9c5a0797aa3682d4e7367e35a65cf89
3
+ size 8739224196
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d1d69dbb7686d54a0f16b1fa5318ef79ca163f63ef26c25fb3afd818b9bb61
3
+ size 1064
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": "<end_of_turn>",
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 sha256:7666402c0617d170e6b0a985b3130c3fb0795393aa0970600994a5d9aae12351
3
+ size 33384822
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,2134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.8531816565943833,
6
+ "eval_steps": 500,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0028439388553146107,
14
+ "grad_norm": 1512.0,
15
+ "learning_rate": 2.0000000000000003e-06,
16
+ "loss": 10.5863,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.005687877710629221,
21
+ "grad_norm": 2544.0,
22
+ "learning_rate": 4.000000000000001e-06,
23
+ "loss": 10.6061,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.008531816565943833,
28
+ "grad_norm": 1344.0,
29
+ "learning_rate": 6e-06,
30
+ "loss": 9.0523,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.011375755421258443,
35
+ "grad_norm": 604.0,
36
+ "learning_rate": 8.000000000000001e-06,
37
+ "loss": 6.3641,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.014219694276573054,
42
+ "grad_norm": 358.0,
43
+ "learning_rate": 1e-05,
44
+ "loss": 5.1062,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.017063633131887666,
49
+ "grad_norm": 402.0,
50
+ "learning_rate": 9.999793896876868e-06,
51
+ "loss": 4.2008,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.019907571987202274,
56
+ "grad_norm": 155.0,
57
+ "learning_rate": 9.999175604498867e-06,
58
+ "loss": 3.4295,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.022751510842516885,
63
+ "grad_norm": 81.0,
64
+ "learning_rate": 9.998145173838796e-06,
65
+ "loss": 2.7242,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.025595449697831497,
70
+ "grad_norm": 40.0,
71
+ "learning_rate": 9.996702689846645e-06,
72
+ "loss": 2.4419,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.028439388553146108,
77
+ "grad_norm": 28.5,
78
+ "learning_rate": 9.994848271442595e-06,
79
+ "loss": 2.1389,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.031283327408460716,
84
+ "grad_norm": 42.75,
85
+ "learning_rate": 9.992582071507217e-06,
86
+ "loss": 1.9961,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.03412726626377533,
91
+ "grad_norm": 17.375,
92
+ "learning_rate": 9.989904276868865e-06,
93
+ "loss": 1.9048,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.03697120511908994,
98
+ "grad_norm": 32.5,
99
+ "learning_rate": 9.986815108288273e-06,
100
+ "loss": 1.7912,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.03981514397440455,
105
+ "grad_norm": 15.25,
106
+ "learning_rate": 9.98331482044036e-06,
107
+ "loss": 1.8195,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.04265908282971916,
112
+ "grad_norm": 11.8125,
113
+ "learning_rate": 9.979403701893226e-06,
114
+ "loss": 1.7316,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.04550302168503377,
119
+ "grad_norm": 14.3125,
120
+ "learning_rate": 9.975082075084375e-06,
121
+ "loss": 1.7444,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.048346960540348385,
126
+ "grad_norm": 9.0,
127
+ "learning_rate": 9.970350296294114e-06,
128
+ "loss": 1.7287,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.05119089939566299,
133
+ "grad_norm": 9.5,
134
+ "learning_rate": 9.9652087556162e-06,
135
+ "loss": 1.6426,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.0540348382509776,
140
+ "grad_norm": 26.25,
141
+ "learning_rate": 9.959657876925671e-06,
142
+ "loss": 1.6523,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.056878777106292217,
147
+ "grad_norm": 8.4375,
148
+ "learning_rate": 9.9536981178439e-06,
149
+ "loss": 1.6343,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.059722715961606825,
154
+ "grad_norm": 13.4375,
155
+ "learning_rate": 9.94732996970087e-06,
156
+ "loss": 1.6042,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.06256665481692143,
161
+ "grad_norm": 8.75,
162
+ "learning_rate": 9.940553957494669e-06,
163
+ "loss": 1.6597,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.06541059367223605,
168
+ "grad_norm": 7.90625,
169
+ "learning_rate": 9.93337063984821e-06,
170
+ "loss": 1.6111,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.06825453252755066,
175
+ "grad_norm": 8.25,
176
+ "learning_rate": 9.925780608963173e-06,
177
+ "loss": 1.5849,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.07109847138286526,
182
+ "grad_norm": 8.0625,
183
+ "learning_rate": 9.917784490571188e-06,
184
+ "loss": 1.5479,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.07394241023817988,
189
+ "grad_norm": 6.78125,
190
+ "learning_rate": 9.909382943882238e-06,
191
+ "loss": 1.5466,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.0767863490934945,
196
+ "grad_norm": 7.8125,
197
+ "learning_rate": 9.900576661530334e-06,
198
+ "loss": 1.5513,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.0796302879488091,
203
+ "grad_norm": 5.65625,
204
+ "learning_rate": 9.89136636951639e-06,
205
+ "loss": 1.5127,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.08247422680412371,
210
+ "grad_norm": 5.625,
211
+ "learning_rate": 9.881752827148391e-06,
212
+ "loss": 1.5828,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.08531816565943832,
217
+ "grad_norm": 6.75,
218
+ "learning_rate": 9.871736826978776e-06,
219
+ "loss": 1.5587,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.08816210451475294,
224
+ "grad_norm": 9.75,
225
+ "learning_rate": 9.861319194739109e-06,
226
+ "loss": 1.4726,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.09100604337006754,
231
+ "grad_norm": 6.0,
232
+ "learning_rate": 9.85050078927201e-06,
233
+ "loss": 1.509,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.09384998222538216,
238
+ "grad_norm": 5.21875,
239
+ "learning_rate": 9.83928250246034e-06,
240
+ "loss": 1.5211,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.09669392108069677,
245
+ "grad_norm": 6.25,
246
+ "learning_rate": 9.82766525915368e-06,
247
+ "loss": 1.5568,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.09953785993601137,
252
+ "grad_norm": 7.625,
253
+ "learning_rate": 9.815650017092078e-06,
254
+ "loss": 1.5097,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.10238179879132599,
259
+ "grad_norm": 5.9375,
260
+ "learning_rate": 9.803237766827098e-06,
261
+ "loss": 1.5636,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.1052257376466406,
266
+ "grad_norm": 4.875,
267
+ "learning_rate": 9.790429531640163e-06,
268
+ "loss": 1.5031,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.1080696765019552,
273
+ "grad_norm": 4.3125,
274
+ "learning_rate": 9.77722636745818e-06,
275
+ "loss": 1.4816,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.11091361535726982,
280
+ "grad_norm": 5.125,
281
+ "learning_rate": 9.763629362766495e-06,
282
+ "loss": 1.479,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.11375755421258443,
287
+ "grad_norm": 4.96875,
288
+ "learning_rate": 9.749639638519167e-06,
289
+ "loss": 1.4666,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.11660149306789903,
294
+ "grad_norm": 5.90625,
295
+ "learning_rate": 9.735258348046538e-06,
296
+ "loss": 1.5102,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.11944543192321365,
301
+ "grad_norm": 7.34375,
302
+ "learning_rate": 9.720486676960157e-06,
303
+ "loss": 1.4814,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.12228937077852826,
308
+ "grad_norm": 5.59375,
309
+ "learning_rate": 9.705325843055045e-06,
310
+ "loss": 1.4913,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.12513330963384287,
315
+ "grad_norm": 5.8125,
316
+ "learning_rate": 9.689777096209287e-06,
317
+ "loss": 1.4853,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.12797724848915748,
322
+ "grad_norm": 5.625,
323
+ "learning_rate": 9.673841718281e-06,
324
+ "loss": 1.4569,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.1308211873444721,
329
+ "grad_norm": 4.65625,
330
+ "learning_rate": 9.657521023002644e-06,
331
+ "loss": 1.4717,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.1336651261997867,
336
+ "grad_norm": 4.5625,
337
+ "learning_rate": 9.64081635587273e-06,
338
+ "loss": 1.455,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.13650906505510133,
343
+ "grad_norm": 4.0,
344
+ "learning_rate": 9.623729094044882e-06,
345
+ "loss": 1.4136,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.1393530039104159,
350
+ "grad_norm": 4.71875,
351
+ "learning_rate": 9.606260646214314e-06,
352
+ "loss": 1.4875,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.14219694276573053,
357
+ "grad_norm": 4.6875,
358
+ "learning_rate": 9.588412452501686e-06,
359
+ "loss": 1.4892,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.14504088162104514,
364
+ "grad_norm": 4.3125,
365
+ "learning_rate": 9.570185984334383e-06,
366
+ "loss": 1.4873,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.14788482047635976,
371
+ "grad_norm": 13.0,
372
+ "learning_rate": 9.551582744325213e-06,
373
+ "loss": 1.4418,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.15072875933167437,
378
+ "grad_norm": 8.6875,
379
+ "learning_rate": 9.532604266148521e-06,
380
+ "loss": 1.5109,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.153572698186989,
385
+ "grad_norm": 11.875,
386
+ "learning_rate": 9.513252114413756e-06,
387
+ "loss": 1.4517,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.1564166370423036,
392
+ "grad_norm": 6.0625,
393
+ "learning_rate": 9.493527884536487e-06,
394
+ "loss": 1.4724,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.1592605758976182,
399
+ "grad_norm": 4.90625,
400
+ "learning_rate": 9.473433202606859e-06,
401
+ "loss": 1.4598,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.1621045147529328,
406
+ "grad_norm": 3.984375,
407
+ "learning_rate": 9.452969725255558e-06,
408
+ "loss": 1.449,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.16494845360824742,
413
+ "grad_norm": 6.71875,
414
+ "learning_rate": 9.432139139517222e-06,
415
+ "loss": 1.4507,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.16779239246356203,
420
+ "grad_norm": 6.78125,
421
+ "learning_rate": 9.410943162691359e-06,
422
+ "loss": 1.4529,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.17063633131887665,
427
+ "grad_norm": 5.3125,
428
+ "learning_rate": 9.389383542200779e-06,
429
+ "loss": 1.4399,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.17348027017419126,
434
+ "grad_norm": 5.875,
435
+ "learning_rate": 9.367462055447528e-06,
436
+ "loss": 1.4295,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.17632420902950588,
441
+ "grad_norm": 4.25,
442
+ "learning_rate": 9.34518050966636e-06,
443
+ "loss": 1.4768,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.17916814788482047,
448
+ "grad_norm": 8.3125,
449
+ "learning_rate": 9.322540741775745e-06,
450
+ "loss": 1.4094,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.18201208674013508,
455
+ "grad_norm": 4.90625,
456
+ "learning_rate": 9.299544618226428e-06,
457
+ "loss": 1.4451,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.1848560255954497,
462
+ "grad_norm": 3.5,
463
+ "learning_rate": 9.276194034847565e-06,
464
+ "loss": 1.4308,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.1876999644507643,
469
+ "grad_norm": 4.0,
470
+ "learning_rate": 9.252490916690422e-06,
471
+ "loss": 1.4588,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.19054390330607893,
476
+ "grad_norm": 4.0625,
477
+ "learning_rate": 9.228437217869668e-06,
478
+ "loss": 1.447,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.19338784216139354,
483
+ "grad_norm": 4.375,
484
+ "learning_rate": 9.204034921402282e-06,
485
+ "loss": 1.5121,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.19623178101670813,
490
+ "grad_norm": 5.28125,
491
+ "learning_rate": 9.179286039044072e-06,
492
+ "loss": 1.3924,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.19907571987202274,
497
+ "grad_norm": 4.75,
498
+ "learning_rate": 9.15419261112382e-06,
499
+ "loss": 1.4434,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.20191965872733736,
504
+ "grad_norm": 4.125,
505
+ "learning_rate": 9.128756706375065e-06,
506
+ "loss": 1.4386,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.20476359758265197,
511
+ "grad_norm": 4.1875,
512
+ "learning_rate": 9.102980421765575e-06,
513
+ "loss": 1.4598,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.2076075364379666,
518
+ "grad_norm": 4.625,
519
+ "learning_rate": 9.076865882324453e-06,
520
+ "loss": 1.4183,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.2104514752932812,
525
+ "grad_norm": 3.953125,
526
+ "learning_rate": 9.050415240966953e-06,
527
+ "loss": 1.3908,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.21329541414859582,
532
+ "grad_norm": 3.625,
533
+ "learning_rate": 9.023630678316994e-06,
534
+ "loss": 1.3925,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.2161393530039104,
539
+ "grad_norm": 4.1875,
540
+ "learning_rate": 8.996514402527383e-06,
541
+ "loss": 1.4293,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.21898329185922502,
546
+ "grad_norm": 4.53125,
547
+ "learning_rate": 8.969068649097766e-06,
548
+ "loss": 1.423,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.22182723071453964,
553
+ "grad_norm": 4.59375,
554
+ "learning_rate": 8.941295680690347e-06,
555
+ "loss": 1.409,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.22467116956985425,
560
+ "grad_norm": 4.71875,
561
+ "learning_rate": 8.913197786943335e-06,
562
+ "loss": 1.4607,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.22751510842516887,
567
+ "grad_norm": 4.5625,
568
+ "learning_rate": 8.884777284282193e-06,
569
+ "loss": 1.4299,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.23035904728048348,
574
+ "grad_norm": 4.71875,
575
+ "learning_rate": 8.856036515728666e-06,
576
+ "loss": 1.4253,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.23320298613579807,
581
+ "grad_norm": 7.40625,
582
+ "learning_rate": 8.826977850707612e-06,
583
+ "loss": 1.3903,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.23604692499111268,
588
+ "grad_norm": 5.875,
589
+ "learning_rate": 8.797603684851685e-06,
590
+ "loss": 1.3905,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.2388908638464273,
595
+ "grad_norm": 7.78125,
596
+ "learning_rate": 8.767916439803808e-06,
597
+ "loss": 1.3913,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.2417348027017419,
602
+ "grad_norm": 3.859375,
603
+ "learning_rate": 8.737918563017553e-06,
604
+ "loss": 1.373,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.24457874155705653,
609
+ "grad_norm": 3.640625,
610
+ "learning_rate": 8.707612527555356e-06,
611
+ "loss": 1.4412,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.24742268041237114,
616
+ "grad_norm": 4.0625,
617
+ "learning_rate": 8.677000831884639e-06,
618
+ "loss": 1.4524,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.25026661926768573,
623
+ "grad_norm": 4.40625,
624
+ "learning_rate": 8.646085999671838e-06,
625
+ "loss": 1.3731,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.2531105581230004,
630
+ "grad_norm": 5.46875,
631
+ "learning_rate": 8.614870579574338e-06,
632
+ "loss": 1.432,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.25595449697831496,
637
+ "grad_norm": 5.0,
638
+ "learning_rate": 8.58335714503037e-06,
639
+ "loss": 1.4008,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.2587984358336296,
644
+ "grad_norm": 4.21875,
645
+ "learning_rate": 8.551548294046843e-06,
646
+ "loss": 1.4155,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.2616423746889442,
651
+ "grad_norm": 3.6875,
652
+ "learning_rate": 8.519446648985173e-06,
653
+ "loss": 1.4792,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.2644863135442588,
658
+ "grad_norm": 4.3125,
659
+ "learning_rate": 8.487054856345081e-06,
660
+ "loss": 1.3851,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.2673302523995734,
665
+ "grad_norm": 8.875,
666
+ "learning_rate": 8.454375586546418e-06,
667
+ "loss": 1.3887,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.270174191254888,
672
+ "grad_norm": 4.53125,
673
+ "learning_rate": 8.42141153370901e-06,
674
+ "loss": 1.3538,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.27301813011020265,
679
+ "grad_norm": 5.0625,
680
+ "learning_rate": 8.388165415430551e-06,
681
+ "loss": 1.3666,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.27586206896551724,
686
+ "grad_norm": 3.578125,
687
+ "learning_rate": 8.35463997256257e-06,
688
+ "loss": 1.3942,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.2787060078208318,
693
+ "grad_norm": 3.765625,
694
+ "learning_rate": 8.320837968984456e-06,
695
+ "loss": 1.4039,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.28154994667614647,
700
+ "grad_norm": 3.5625,
701
+ "learning_rate": 8.28676219137561e-06,
702
+ "loss": 1.3956,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.28439388553146105,
707
+ "grad_norm": 3.53125,
708
+ "learning_rate": 8.25241544898571e-06,
709
+ "loss": 1.3483,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.2872378243867757,
714
+ "grad_norm": 5.125,
715
+ "learning_rate": 8.217800573403105e-06,
716
+ "loss": 1.4364,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.2900817632420903,
721
+ "grad_norm": 4.46875,
722
+ "learning_rate": 8.18292041832138e-06,
723
+ "loss": 1.4297,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.2929257020974049,
728
+ "grad_norm": 17.0,
729
+ "learning_rate": 8.147777859304095e-06,
730
+ "loss": 1.4185,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.2957696409527195,
735
+ "grad_norm": 3.65625,
736
+ "learning_rate": 8.112375793547718e-06,
737
+ "loss": 1.3912,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.2986135798080341,
742
+ "grad_norm": 3.78125,
743
+ "learning_rate": 8.076717139642775e-06,
744
+ "loss": 1.3984,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.30145751866334874,
749
+ "grad_norm": 4.59375,
750
+ "learning_rate": 8.040804837333243e-06,
751
+ "loss": 1.3932,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.30430145751866333,
756
+ "grad_norm": 4.28125,
757
+ "learning_rate": 8.004641847274182e-06,
758
+ "loss": 1.4467,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.307145396373978,
763
+ "grad_norm": 4.5625,
764
+ "learning_rate": 7.968231150787674e-06,
765
+ "loss": 1.4019,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.30998933522929256,
770
+ "grad_norm": 4.8125,
771
+ "learning_rate": 7.931575749617027e-06,
772
+ "loss": 1.3639,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.3128332740846072,
777
+ "grad_norm": 4.25,
778
+ "learning_rate": 7.894678665679298e-06,
779
+ "loss": 1.4065,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.3156772129399218,
784
+ "grad_norm": 3.46875,
785
+ "learning_rate": 7.857542940816183e-06,
786
+ "loss": 1.4385,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.3185211517952364,
791
+ "grad_norm": 3.671875,
792
+ "learning_rate": 7.820171636543233e-06,
793
+ "loss": 1.4302,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.321365090650551,
798
+ "grad_norm": 4.6875,
799
+ "learning_rate": 7.782567833797458e-06,
800
+ "loss": 1.4194,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.3242090295058656,
805
+ "grad_norm": 7.28125,
806
+ "learning_rate": 7.744734632683332e-06,
807
+ "loss": 1.424,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.32705296836118025,
812
+ "grad_norm": 3.59375,
813
+ "learning_rate": 7.70667515221722e-06,
814
+ "loss": 1.3662,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.32989690721649484,
819
+ "grad_norm": 4.78125,
820
+ "learning_rate": 7.668392530070238e-06,
821
+ "loss": 1.3813,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.3327408460718095,
826
+ "grad_norm": 3.921875,
827
+ "learning_rate": 7.629889922309576e-06,
828
+ "loss": 1.3609,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.33558478492712407,
833
+ "grad_norm": 4.75,
834
+ "learning_rate": 7.5911705031383235e-06,
835
+ "loss": 1.3524,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.33842872378243866,
840
+ "grad_norm": 3.96875,
841
+ "learning_rate": 7.55223746463376e-06,
842
+ "loss": 1.4071,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.3412726626377533,
847
+ "grad_norm": 3.359375,
848
+ "learning_rate": 7.513094016484225e-06,
849
+ "loss": 1.3828,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.3441166014930679,
854
+ "grad_norm": 3.78125,
855
+ "learning_rate": 7.473743385724478e-06,
856
+ "loss": 1.4123,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.34696054034838253,
861
+ "grad_norm": 3.265625,
862
+ "learning_rate": 7.434188816469681e-06,
863
+ "loss": 1.3437,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.3498044792036971,
868
+ "grad_norm": 9.6875,
869
+ "learning_rate": 7.394433569647935e-06,
870
+ "loss": 1.3295,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.35264841805901176,
875
+ "grad_norm": 4.0,
876
+ "learning_rate": 7.354480922731454e-06,
877
+ "loss": 1.4302,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 0.35549235691432635,
882
+ "grad_norm": 3.546875,
883
+ "learning_rate": 7.3143341694663604e-06,
884
+ "loss": 1.4021,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 0.35833629576964093,
889
+ "grad_norm": 4.65625,
890
+ "learning_rate": 7.273996619601146e-06,
891
+ "loss": 1.3688,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 0.3611802346249556,
896
+ "grad_norm": 4.84375,
897
+ "learning_rate": 7.233471598613815e-06,
898
+ "loss": 1.4139,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 0.36402417348027016,
903
+ "grad_norm": 3.578125,
904
+ "learning_rate": 7.192762447437722e-06,
905
+ "loss": 1.3491,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 0.3668681123355848,
910
+ "grad_norm": 4.25,
911
+ "learning_rate": 7.151872522186147e-06,
912
+ "loss": 1.3805,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 0.3697120511908994,
917
+ "grad_norm": 3.53125,
918
+ "learning_rate": 7.110805193875607e-06,
919
+ "loss": 1.3782,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 0.372555990046214,
924
+ "grad_norm": 5.46875,
925
+ "learning_rate": 7.0695638481479565e-06,
926
+ "loss": 1.3411,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 0.3753999289015286,
931
+ "grad_norm": 3.5625,
932
+ "learning_rate": 7.028151884991254e-06,
933
+ "loss": 1.3842,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 0.3782438677568432,
938
+ "grad_norm": 4.75,
939
+ "learning_rate": 6.986572718459479e-06,
940
+ "loss": 1.3537,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 0.38108780661215785,
945
+ "grad_norm": 3.9375,
946
+ "learning_rate": 6.94482977639106e-06,
947
+ "loss": 1.3981,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 0.38393174546747244,
952
+ "grad_norm": 4.96875,
953
+ "learning_rate": 6.902926500126292e-06,
954
+ "loss": 1.4284,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 0.3867756843227871,
959
+ "grad_norm": 4.4375,
960
+ "learning_rate": 6.8608663442236156e-06,
961
+ "loss": 1.4013,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 0.38961962317810167,
966
+ "grad_norm": 3.71875,
967
+ "learning_rate": 6.818652776174828e-06,
968
+ "loss": 1.436,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 0.39246356203341626,
973
+ "grad_norm": 4.1875,
974
+ "learning_rate": 6.776289276119214e-06,
975
+ "loss": 1.3652,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 0.3953075008887309,
980
+ "grad_norm": 3.671875,
981
+ "learning_rate": 6.733779336556643e-06,
982
+ "loss": 1.4186,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 0.3981514397440455,
987
+ "grad_norm": 11.3125,
988
+ "learning_rate": 6.691126462059636e-06,
989
+ "loss": 1.3899,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 0.40099537859936013,
994
+ "grad_norm": 3.234375,
995
+ "learning_rate": 6.648334168984452e-06,
996
+ "loss": 1.3971,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 0.4038393174546747,
1001
+ "grad_norm": 5.0,
1002
+ "learning_rate": 6.60540598518119e-06,
1003
+ "loss": 1.4499,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 0.40668325630998936,
1008
+ "grad_norm": 3.90625,
1009
+ "learning_rate": 6.562345449702952e-06,
1010
+ "loss": 1.3721,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 0.40952719516530395,
1015
+ "grad_norm": 5.875,
1016
+ "learning_rate": 6.519156112514074e-06,
1017
+ "loss": 1.4166,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 0.41237113402061853,
1022
+ "grad_norm": 6.0,
1023
+ "learning_rate": 6.4758415341974705e-06,
1024
+ "loss": 1.3782,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 0.4152150728759332,
1029
+ "grad_norm": 5.21875,
1030
+ "learning_rate": 6.432405285661087e-06,
1031
+ "loss": 1.3798,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 0.41805901173124776,
1036
+ "grad_norm": 13.5625,
1037
+ "learning_rate": 6.388850947843517e-06,
1038
+ "loss": 1.3277,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 0.4209029505865624,
1043
+ "grad_norm": 5.46875,
1044
+ "learning_rate": 6.345182111418781e-06,
1045
+ "loss": 1.3801,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 0.423746889441877,
1050
+ "grad_norm": 3.703125,
1051
+ "learning_rate": 6.301402376500306e-06,
1052
+ "loss": 1.3789,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 0.42659082829719164,
1057
+ "grad_norm": 3.734375,
1058
+ "learning_rate": 6.257515352344131e-06,
1059
+ "loss": 1.3935,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.4294347671525062,
1064
+ "grad_norm": 3.46875,
1065
+ "learning_rate": 6.213524657051354e-06,
1066
+ "loss": 1.3667,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.4322787060078208,
1071
+ "grad_norm": 4.625,
1072
+ "learning_rate": 6.16943391726985e-06,
1073
+ "loss": 1.3096,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.43512264486313545,
1078
+ "grad_norm": 5.8125,
1079
+ "learning_rate": 6.125246767895287e-06,
1080
+ "loss": 1.3607,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.43796658371845004,
1085
+ "grad_norm": 3.421875,
1086
+ "learning_rate": 6.0809668517714615e-06,
1087
+ "loss": 1.3842,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.4408105225737647,
1092
+ "grad_norm": 12.6875,
1093
+ "learning_rate": 6.036597819389972e-06,
1094
+ "loss": 1.3758,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.44365446142907927,
1099
+ "grad_norm": 3.984375,
1100
+ "learning_rate": 5.992143328589282e-06,
1101
+ "loss": 1.3857,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.44649840028439386,
1106
+ "grad_norm": 3.734375,
1107
+ "learning_rate": 5.947607044253142e-06,
1108
+ "loss": 1.4109,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.4493423391397085,
1113
+ "grad_norm": 4.125,
1114
+ "learning_rate": 5.902992638008475e-06,
1115
+ "loss": 1.3819,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.4521862779950231,
1120
+ "grad_norm": 3.125,
1121
+ "learning_rate": 5.858303787922663e-06,
1122
+ "loss": 1.3695,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.45503021685033773,
1127
+ "grad_norm": 3.484375,
1128
+ "learning_rate": 5.8135441782003354e-06,
1129
+ "loss": 1.3792,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.4578741557056523,
1134
+ "grad_norm": 7.46875,
1135
+ "learning_rate": 5.768717498879635e-06,
1136
+ "loss": 1.3709,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.46071809456096696,
1141
+ "grad_norm": 3.609375,
1142
+ "learning_rate": 5.723827445528003e-06,
1143
+ "loss": 1.3485,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.46356203341628155,
1148
+ "grad_norm": 3.96875,
1149
+ "learning_rate": 5.67887771893752e-06,
1150
+ "loss": 1.4539,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.46640597227159614,
1155
+ "grad_norm": 3.359375,
1156
+ "learning_rate": 5.633872024819796e-06,
1157
+ "loss": 1.3531,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.4692499111269108,
1162
+ "grad_norm": 4.15625,
1163
+ "learning_rate": 5.588814073500481e-06,
1164
+ "loss": 1.362,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.47209384998222537,
1169
+ "grad_norm": 3.953125,
1170
+ "learning_rate": 5.543707579613367e-06,
1171
+ "loss": 1.3842,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.47493778883754,
1176
+ "grad_norm": 3.859375,
1177
+ "learning_rate": 5.498556261794161e-06,
1178
+ "loss": 1.4086,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.4777817276928546,
1183
+ "grad_norm": 3.921875,
1184
+ "learning_rate": 5.45336384237391e-06,
1185
+ "loss": 1.3866,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.48062566654816924,
1190
+ "grad_norm": 4.90625,
1191
+ "learning_rate": 5.4081340470721286e-06,
1192
+ "loss": 1.3711,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.4834696054034838,
1197
+ "grad_norm": 6.25,
1198
+ "learning_rate": 5.362870604689643e-06,
1199
+ "loss": 1.3825,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.4863135442587984,
1204
+ "grad_norm": 4.15625,
1205
+ "learning_rate": 5.31757724680119e-06,
1206
+ "loss": 1.3896,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.48915748311411306,
1211
+ "grad_norm": 3.25,
1212
+ "learning_rate": 5.272257707447776e-06,
1213
+ "loss": 1.3977,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.49200142196942764,
1218
+ "grad_norm": 3.765625,
1219
+ "learning_rate": 5.22691572282884e-06,
1220
+ "loss": 1.3932,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.4948453608247423,
1225
+ "grad_norm": 3.5625,
1226
+ "learning_rate": 5.18155503099424e-06,
1227
+ "loss": 1.3748,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.4976892996800569,
1232
+ "grad_norm": 4.65625,
1233
+ "learning_rate": 5.136179371536076e-06,
1234
+ "loss": 1.3921,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.5005332385353715,
1239
+ "grad_norm": 5.71875,
1240
+ "learning_rate": 5.090792485280401e-06,
1241
+ "loss": 1.3433,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.5033771773906861,
1246
+ "grad_norm": 3.1875,
1247
+ "learning_rate": 5.045398113978816e-06,
1248
+ "loss": 1.3821,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.5062211162460007,
1253
+ "grad_norm": 5.3125,
1254
+ "learning_rate": 5e-06,
1255
+ "loss": 1.3923,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.5090650551013153,
1260
+ "grad_norm": 7.34375,
1261
+ "learning_rate": 4.9546018860211845e-06,
1262
+ "loss": 1.3391,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.5119089939566299,
1267
+ "grad_norm": 3.453125,
1268
+ "learning_rate": 4.9092075147196005e-06,
1269
+ "loss": 1.384,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.5147529328119446,
1274
+ "grad_norm": 4.03125,
1275
+ "learning_rate": 4.863820628463925e-06,
1276
+ "loss": 1.3679,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.5175968716672592,
1281
+ "grad_norm": 3.734375,
1282
+ "learning_rate": 4.818444969005762e-06,
1283
+ "loss": 1.3672,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.5204408105225737,
1288
+ "grad_norm": 5.125,
1289
+ "learning_rate": 4.773084277171161e-06,
1290
+ "loss": 1.3627,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.5232847493778884,
1295
+ "grad_norm": 3.484375,
1296
+ "learning_rate": 4.727742292552225e-06,
1297
+ "loss": 1.3618,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.526128688233203,
1302
+ "grad_norm": 3.703125,
1303
+ "learning_rate": 4.682422753198812e-06,
1304
+ "loss": 1.3619,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.5289726270885176,
1309
+ "grad_norm": 3.390625,
1310
+ "learning_rate": 4.637129395310359e-06,
1311
+ "loss": 1.3711,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.5318165659438322,
1316
+ "grad_norm": 3.40625,
1317
+ "learning_rate": 4.591865952927873e-06,
1318
+ "loss": 1.3999,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.5346605047991468,
1323
+ "grad_norm": 3.109375,
1324
+ "learning_rate": 4.546636157626091e-06,
1325
+ "loss": 1.3572,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.5375044436544615,
1330
+ "grad_norm": 4.21875,
1331
+ "learning_rate": 4.501443738205841e-06,
1332
+ "loss": 1.3415,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.540348382509776,
1337
+ "grad_norm": 6.53125,
1338
+ "learning_rate": 4.456292420386635e-06,
1339
+ "loss": 1.3792,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.5431923213650907,
1344
+ "grad_norm": 5.46875,
1345
+ "learning_rate": 4.41118592649952e-06,
1346
+ "loss": 1.4282,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.5460362602204053,
1351
+ "grad_norm": 3.78125,
1352
+ "learning_rate": 4.366127975180204e-06,
1353
+ "loss": 1.363,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.5488801990757198,
1358
+ "grad_norm": 3.40625,
1359
+ "learning_rate": 4.321122281062481e-06,
1360
+ "loss": 1.3839,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.5517241379310345,
1365
+ "grad_norm": 4.1875,
1366
+ "learning_rate": 4.276172554471998e-06,
1367
+ "loss": 1.3801,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.5545680767863491,
1372
+ "grad_norm": 4.25,
1373
+ "learning_rate": 4.231282501120366e-06,
1374
+ "loss": 1.3819,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.5574120156416636,
1379
+ "grad_norm": 4.75,
1380
+ "learning_rate": 4.1864558217996645e-06,
1381
+ "loss": 1.3207,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.5602559544969783,
1386
+ "grad_norm": 5.8125,
1387
+ "learning_rate": 4.14169621207734e-06,
1388
+ "loss": 1.4097,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.5630998933522929,
1393
+ "grad_norm": 14.3125,
1394
+ "learning_rate": 4.0970073619915264e-06,
1395
+ "loss": 1.4066,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.5659438322076076,
1400
+ "grad_norm": 3.15625,
1401
+ "learning_rate": 4.05239295574686e-06,
1402
+ "loss": 1.3636,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.5687877710629221,
1407
+ "grad_norm": 3.609375,
1408
+ "learning_rate": 4.00785667141072e-06,
1409
+ "loss": 1.3239,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 0.5716317099182368,
1414
+ "grad_norm": 4.5625,
1415
+ "learning_rate": 3.963402180610028e-06,
1416
+ "loss": 1.3242,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 0.5744756487735514,
1421
+ "grad_norm": 5.375,
1422
+ "learning_rate": 3.919033148228542e-06,
1423
+ "loss": 1.3622,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 0.5773195876288659,
1428
+ "grad_norm": 23.125,
1429
+ "learning_rate": 3.874753232104714e-06,
1430
+ "loss": 1.369,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 0.5801635264841806,
1435
+ "grad_norm": 4.0625,
1436
+ "learning_rate": 3.830566082730151e-06,
1437
+ "loss": 1.3779,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 0.5830074653394952,
1442
+ "grad_norm": 6.875,
1443
+ "learning_rate": 3.7864753429486475e-06,
1444
+ "loss": 1.3449,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 0.5858514041948099,
1449
+ "grad_norm": 3.359375,
1450
+ "learning_rate": 3.7424846476558716e-06,
1451
+ "loss": 1.364,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 0.5886953430501244,
1456
+ "grad_norm": 5.15625,
1457
+ "learning_rate": 3.6985976234996957e-06,
1458
+ "loss": 1.3829,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 0.591539281905439,
1463
+ "grad_norm": 4.875,
1464
+ "learning_rate": 3.6548178885812203e-06,
1465
+ "loss": 1.3564,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 0.5943832207607537,
1470
+ "grad_norm": 4.5625,
1471
+ "learning_rate": 3.611149052156483e-06,
1472
+ "loss": 1.399,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 0.5972271596160682,
1477
+ "grad_norm": 3.375,
1478
+ "learning_rate": 3.5675947143389144e-06,
1479
+ "loss": 1.3727,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 0.6000710984713828,
1484
+ "grad_norm": 4.5,
1485
+ "learning_rate": 3.524158465802531e-06,
1486
+ "loss": 1.3863,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 0.6029150373266975,
1491
+ "grad_norm": 3.984375,
1492
+ "learning_rate": 3.4808438874859274e-06,
1493
+ "loss": 1.3578,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 0.6057589761820121,
1498
+ "grad_norm": 9.4375,
1499
+ "learning_rate": 3.437654550297049e-06,
1500
+ "loss": 1.3384,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 0.6086029150373267,
1505
+ "grad_norm": 4.59375,
1506
+ "learning_rate": 3.3945940148188117e-06,
1507
+ "loss": 1.3619,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 0.6114468538926413,
1512
+ "grad_norm": 3.578125,
1513
+ "learning_rate": 3.3516658310155493e-06,
1514
+ "loss": 1.3741,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 0.614290792747956,
1519
+ "grad_norm": 5.09375,
1520
+ "learning_rate": 3.3088735379403648e-06,
1521
+ "loss": 1.3866,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 0.6171347316032705,
1526
+ "grad_norm": 4.28125,
1527
+ "learning_rate": 3.266220663443358e-06,
1528
+ "loss": 1.3863,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 0.6199786704585851,
1533
+ "grad_norm": 6.53125,
1534
+ "learning_rate": 3.223710723880786e-06,
1535
+ "loss": 1.3828,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 0.6228226093138998,
1540
+ "grad_norm": 4.625,
1541
+ "learning_rate": 3.1813472238251742e-06,
1542
+ "loss": 1.3583,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 0.6256665481692144,
1547
+ "grad_norm": 4.03125,
1548
+ "learning_rate": 3.139133655776386e-06,
1549
+ "loss": 1.3711,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 0.6285104870245289,
1554
+ "grad_norm": 3.8125,
1555
+ "learning_rate": 3.0970734998737095e-06,
1556
+ "loss": 1.4109,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 0.6313544258798436,
1561
+ "grad_norm": 3.5625,
1562
+ "learning_rate": 3.055170223608941e-06,
1563
+ "loss": 1.4092,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 0.6341983647351582,
1568
+ "grad_norm": 3.890625,
1569
+ "learning_rate": 3.013427281540523e-06,
1570
+ "loss": 1.3846,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 0.6370423035904728,
1575
+ "grad_norm": 3.8125,
1576
+ "learning_rate": 2.9718481150087475e-06,
1577
+ "loss": 1.3378,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 0.6398862424457874,
1582
+ "grad_norm": 5.75,
1583
+ "learning_rate": 2.9304361518520447e-06,
1584
+ "loss": 1.4083,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 0.642730181301102,
1589
+ "grad_norm": 10.0625,
1590
+ "learning_rate": 2.8891948061243925e-06,
1591
+ "loss": 1.399,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 0.6455741201564167,
1596
+ "grad_norm": 3.984375,
1597
+ "learning_rate": 2.8481274778138567e-06,
1598
+ "loss": 1.3218,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 0.6484180590117312,
1603
+ "grad_norm": 3.34375,
1604
+ "learning_rate": 2.80723755256228e-06,
1605
+ "loss": 1.3727,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 0.6512619978670459,
1610
+ "grad_norm": 5.03125,
1611
+ "learning_rate": 2.766528401386187e-06,
1612
+ "loss": 1.3563,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 0.6541059367223605,
1617
+ "grad_norm": 3.703125,
1618
+ "learning_rate": 2.726003380398854e-06,
1619
+ "loss": 1.3015,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 0.656949875577675,
1624
+ "grad_norm": 4.875,
1625
+ "learning_rate": 2.685665830533642e-06,
1626
+ "loss": 1.3992,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 0.6597938144329897,
1631
+ "grad_norm": 5.28125,
1632
+ "learning_rate": 2.6455190772685463e-06,
1633
+ "loss": 1.3843,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 0.6626377532883043,
1638
+ "grad_norm": 5.375,
1639
+ "learning_rate": 2.6055664303520655e-06,
1640
+ "loss": 1.3088,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 0.665481692143619,
1645
+ "grad_norm": 5.0625,
1646
+ "learning_rate": 2.5658111835303206e-06,
1647
+ "loss": 1.329,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 0.6683256309989335,
1652
+ "grad_norm": 3.390625,
1653
+ "learning_rate": 2.526256614275524e-06,
1654
+ "loss": 1.375,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 0.6711695698542481,
1659
+ "grad_norm": 3.828125,
1660
+ "learning_rate": 2.486905983515778e-06,
1661
+ "loss": 1.363,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 0.6740135087095628,
1666
+ "grad_norm": 9.375,
1667
+ "learning_rate": 2.44776253536624e-06,
1668
+ "loss": 1.3671,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 0.6768574475648773,
1673
+ "grad_norm": 4.09375,
1674
+ "learning_rate": 2.408829496861679e-06,
1675
+ "loss": 1.3624,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 0.679701386420192,
1680
+ "grad_norm": 3.34375,
1681
+ "learning_rate": 2.370110077690425e-06,
1682
+ "loss": 1.3291,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 0.6825453252755066,
1687
+ "grad_norm": 4.25,
1688
+ "learning_rate": 2.331607469929765e-06,
1689
+ "loss": 1.3745,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 0.6853892641308212,
1694
+ "grad_norm": 4.875,
1695
+ "learning_rate": 2.2933248477827814e-06,
1696
+ "loss": 1.394,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 0.6882332029861358,
1701
+ "grad_norm": 3.890625,
1702
+ "learning_rate": 2.2552653673166676e-06,
1703
+ "loss": 1.409,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 0.6910771418414504,
1708
+ "grad_norm": 3.578125,
1709
+ "learning_rate": 2.2174321662025427e-06,
1710
+ "loss": 1.3998,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 0.6939210806967651,
1715
+ "grad_norm": 4.5,
1716
+ "learning_rate": 2.179828363456768e-06,
1717
+ "loss": 1.3898,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 0.6967650195520796,
1722
+ "grad_norm": 4.375,
1723
+ "learning_rate": 2.1424570591838184e-06,
1724
+ "loss": 1.3422,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 0.6996089584073942,
1729
+ "grad_norm": 3.25,
1730
+ "learning_rate": 2.1053213343207045e-06,
1731
+ "loss": 1.3986,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 0.7024528972627089,
1736
+ "grad_norm": 3.828125,
1737
+ "learning_rate": 2.068424250382974e-06,
1738
+ "loss": 1.3767,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 0.7052968361180235,
1743
+ "grad_norm": 3.34375,
1744
+ "learning_rate": 2.031768849212326e-06,
1745
+ "loss": 1.4013,
1746
+ "step": 248
1747
+ },
1748
+ {
1749
+ "epoch": 0.708140774973338,
1750
+ "grad_norm": 3.0625,
1751
+ "learning_rate": 1.995358152725818e-06,
1752
+ "loss": 1.3931,
1753
+ "step": 249
1754
+ },
1755
+ {
1756
+ "epoch": 0.7109847138286527,
1757
+ "grad_norm": 3.578125,
1758
+ "learning_rate": 1.959195162666759e-06,
1759
+ "loss": 1.3763,
1760
+ "step": 250
1761
+ },
1762
+ {
1763
+ "epoch": 0.7138286526839673,
1764
+ "grad_norm": 19.375,
1765
+ "learning_rate": 1.9232828603572255e-06,
1766
+ "loss": 1.3099,
1767
+ "step": 251
1768
+ },
1769
+ {
1770
+ "epoch": 0.7166725915392819,
1771
+ "grad_norm": 3.53125,
1772
+ "learning_rate": 1.8876242064522833e-06,
1773
+ "loss": 1.3458,
1774
+ "step": 252
1775
+ },
1776
+ {
1777
+ "epoch": 0.7195165303945965,
1778
+ "grad_norm": 3.796875,
1779
+ "learning_rate": 1.8522221406959063e-06,
1780
+ "loss": 1.3616,
1781
+ "step": 253
1782
+ },
1783
+ {
1784
+ "epoch": 0.7223604692499112,
1785
+ "grad_norm": 3.234375,
1786
+ "learning_rate": 1.8170795816786202e-06,
1787
+ "loss": 1.3627,
1788
+ "step": 254
1789
+ },
1790
+ {
1791
+ "epoch": 0.7252044081052257,
1792
+ "grad_norm": 3.640625,
1793
+ "learning_rate": 1.7821994265968962e-06,
1794
+ "loss": 1.3499,
1795
+ "step": 255
1796
+ },
1797
+ {
1798
+ "epoch": 0.7280483469605403,
1799
+ "grad_norm": 3.265625,
1800
+ "learning_rate": 1.747584551014291e-06,
1801
+ "loss": 1.3368,
1802
+ "step": 256
1803
+ },
1804
+ {
1805
+ "epoch": 0.730892285815855,
1806
+ "grad_norm": 6.0625,
1807
+ "learning_rate": 1.7132378086243907e-06,
1808
+ "loss": 1.3931,
1809
+ "step": 257
1810
+ },
1811
+ {
1812
+ "epoch": 0.7337362246711696,
1813
+ "grad_norm": 3.40625,
1814
+ "learning_rate": 1.679162031015546e-06,
1815
+ "loss": 1.4312,
1816
+ "step": 258
1817
+ },
1818
+ {
1819
+ "epoch": 0.7365801635264841,
1820
+ "grad_norm": 3.09375,
1821
+ "learning_rate": 1.64536002743743e-06,
1822
+ "loss": 1.3419,
1823
+ "step": 259
1824
+ },
1825
+ {
1826
+ "epoch": 0.7394241023817988,
1827
+ "grad_norm": 3.15625,
1828
+ "learning_rate": 1.6118345845694489e-06,
1829
+ "loss": 1.3392,
1830
+ "step": 260
1831
+ },
1832
+ {
1833
+ "epoch": 0.7422680412371134,
1834
+ "grad_norm": 4.59375,
1835
+ "learning_rate": 1.5785884662909917e-06,
1836
+ "loss": 1.3735,
1837
+ "step": 261
1838
+ },
1839
+ {
1840
+ "epoch": 0.745111980092428,
1841
+ "grad_norm": 3.921875,
1842
+ "learning_rate": 1.5456244134535836e-06,
1843
+ "loss": 1.3798,
1844
+ "step": 262
1845
+ },
1846
+ {
1847
+ "epoch": 0.7479559189477426,
1848
+ "grad_norm": 3.90625,
1849
+ "learning_rate": 1.5129451436549203e-06,
1850
+ "loss": 1.4131,
1851
+ "step": 263
1852
+ },
1853
+ {
1854
+ "epoch": 0.7507998578030572,
1855
+ "grad_norm": 3.6875,
1856
+ "learning_rate": 1.4805533510148268e-06,
1857
+ "loss": 1.338,
1858
+ "step": 264
1859
+ },
1860
+ {
1861
+ "epoch": 0.7536437966583719,
1862
+ "grad_norm": 5.5,
1863
+ "learning_rate": 1.4484517059531588e-06,
1864
+ "loss": 1.3417,
1865
+ "step": 265
1866
+ },
1867
+ {
1868
+ "epoch": 0.7564877355136864,
1869
+ "grad_norm": 4.65625,
1870
+ "learning_rate": 1.416642854969632e-06,
1871
+ "loss": 1.3793,
1872
+ "step": 266
1873
+ },
1874
+ {
1875
+ "epoch": 0.7593316743690011,
1876
+ "grad_norm": 4.03125,
1877
+ "learning_rate": 1.3851294204256638e-06,
1878
+ "loss": 1.3768,
1879
+ "step": 267
1880
+ },
1881
+ {
1882
+ "epoch": 0.7621756132243157,
1883
+ "grad_norm": 4.4375,
1884
+ "learning_rate": 1.3539140003281647e-06,
1885
+ "loss": 1.3619,
1886
+ "step": 268
1887
+ },
1888
+ {
1889
+ "epoch": 0.7650195520796302,
1890
+ "grad_norm": 4.3125,
1891
+ "learning_rate": 1.3229991681153632e-06,
1892
+ "loss": 1.3664,
1893
+ "step": 269
1894
+ },
1895
+ {
1896
+ "epoch": 0.7678634909349449,
1897
+ "grad_norm": 3.96875,
1898
+ "learning_rate": 1.2923874724446472e-06,
1899
+ "loss": 1.3429,
1900
+ "step": 270
1901
+ },
1902
+ {
1903
+ "epoch": 0.7707074297902595,
1904
+ "grad_norm": 4.5,
1905
+ "learning_rate": 1.262081436982448e-06,
1906
+ "loss": 1.38,
1907
+ "step": 271
1908
+ },
1909
+ {
1910
+ "epoch": 0.7735513686455742,
1911
+ "grad_norm": 4.78125,
1912
+ "learning_rate": 1.2320835601961928e-06,
1913
+ "loss": 1.3598,
1914
+ "step": 272
1915
+ },
1916
+ {
1917
+ "epoch": 0.7763953075008887,
1918
+ "grad_norm": 5.21875,
1919
+ "learning_rate": 1.2023963151483165e-06,
1920
+ "loss": 1.3817,
1921
+ "step": 273
1922
+ },
1923
+ {
1924
+ "epoch": 0.7792392463562033,
1925
+ "grad_norm": 3.5,
1926
+ "learning_rate": 1.1730221492923882e-06,
1927
+ "loss": 1.3474,
1928
+ "step": 274
1929
+ },
1930
+ {
1931
+ "epoch": 0.782083185211518,
1932
+ "grad_norm": 4.0,
1933
+ "learning_rate": 1.1439634842713371e-06,
1934
+ "loss": 1.3306,
1935
+ "step": 275
1936
+ },
1937
+ {
1938
+ "epoch": 0.7849271240668325,
1939
+ "grad_norm": 3.34375,
1940
+ "learning_rate": 1.115222715717807e-06,
1941
+ "loss": 1.3564,
1942
+ "step": 276
1943
+ },
1944
+ {
1945
+ "epoch": 0.7877710629221472,
1946
+ "grad_norm": 6.84375,
1947
+ "learning_rate": 1.0868022130566652e-06,
1948
+ "loss": 1.3335,
1949
+ "step": 277
1950
+ },
1951
+ {
1952
+ "epoch": 0.7906150017774618,
1953
+ "grad_norm": 3.609375,
1954
+ "learning_rate": 1.0587043193096535e-06,
1955
+ "loss": 1.3674,
1956
+ "step": 278
1957
+ },
1958
+ {
1959
+ "epoch": 0.7934589406327764,
1960
+ "grad_norm": 3.40625,
1961
+ "learning_rate": 1.030931350902235e-06,
1962
+ "loss": 1.381,
1963
+ "step": 279
1964
+ },
1965
+ {
1966
+ "epoch": 0.796302879488091,
1967
+ "grad_norm": 5.3125,
1968
+ "learning_rate": 1.0034855974726194e-06,
1969
+ "loss": 1.363,
1970
+ "step": 280
1971
+ },
1972
+ {
1973
+ "epoch": 0.7991468183434056,
1974
+ "grad_norm": 4.25,
1975
+ "learning_rate": 9.763693216830055e-07,
1976
+ "loss": 1.3654,
1977
+ "step": 281
1978
+ },
1979
+ {
1980
+ "epoch": 0.8019907571987203,
1981
+ "grad_norm": 5.09375,
1982
+ "learning_rate": 9.495847590330486e-07,
1983
+ "loss": 1.3075,
1984
+ "step": 282
1985
+ },
1986
+ {
1987
+ "epoch": 0.8048346960540348,
1988
+ "grad_norm": 3.375,
1989
+ "learning_rate": 9.231341176755487e-07,
1990
+ "loss": 1.3967,
1991
+ "step": 283
1992
+ },
1993
+ {
1994
+ "epoch": 0.8076786349093494,
1995
+ "grad_norm": 3.375,
1996
+ "learning_rate": 8.970195782344266e-07,
1997
+ "loss": 1.3306,
1998
+ "step": 284
1999
+ },
2000
+ {
2001
+ "epoch": 0.8105225737646641,
2002
+ "grad_norm": 7.40625,
2003
+ "learning_rate": 8.712432936249365e-07,
2004
+ "loss": 1.3871,
2005
+ "step": 285
2006
+ },
2007
+ {
2008
+ "epoch": 0.8133665126199787,
2009
+ "grad_norm": 3.703125,
2010
+ "learning_rate": 8.458073888761826e-07,
2011
+ "loss": 1.3071,
2012
+ "step": 286
2013
+ },
2014
+ {
2015
+ "epoch": 0.8162104514752933,
2016
+ "grad_norm": 4.46875,
2017
+ "learning_rate": 8.207139609559284e-07,
2018
+ "loss": 1.3573,
2019
+ "step": 287
2020
+ },
2021
+ {
2022
+ "epoch": 0.8190543903306079,
2023
+ "grad_norm": 4.9375,
2024
+ "learning_rate": 7.959650785977179e-07,
2025
+ "loss": 1.3381,
2026
+ "step": 288
2027
+ },
2028
+ {
2029
+ "epoch": 0.8218983291859225,
2030
+ "grad_norm": 3.359375,
2031
+ "learning_rate": 7.71562782130334e-07,
2032
+ "loss": 1.3247,
2033
+ "step": 289
2034
+ },
2035
+ {
2036
+ "epoch": 0.8247422680412371,
2037
+ "grad_norm": 3.328125,
2038
+ "learning_rate": 7.475090833095799e-07,
2039
+ "loss": 1.3795,
2040
+ "step": 290
2041
+ },
2042
+ {
2043
+ "epoch": 0.8275862068965517,
2044
+ "grad_norm": 3.75,
2045
+ "learning_rate": 7.238059651524354e-07,
2046
+ "loss": 1.3904,
2047
+ "step": 291
2048
+ },
2049
+ {
2050
+ "epoch": 0.8304301457518664,
2051
+ "grad_norm": 3.515625,
2052
+ "learning_rate": 7.004553817735732e-07,
2053
+ "loss": 1.357,
2054
+ "step": 292
2055
+ },
2056
+ {
2057
+ "epoch": 0.833274084607181,
2058
+ "grad_norm": 3.84375,
2059
+ "learning_rate": 6.774592582242567e-07,
2060
+ "loss": 1.3426,
2061
+ "step": 293
2062
+ },
2063
+ {
2064
+ "epoch": 0.8361180234624955,
2065
+ "grad_norm": 3.640625,
2066
+ "learning_rate": 6.548194903336408e-07,
2067
+ "loss": 1.4078,
2068
+ "step": 294
2069
+ },
2070
+ {
2071
+ "epoch": 0.8389619623178102,
2072
+ "grad_norm": 3.828125,
2073
+ "learning_rate": 6.325379445524732e-07,
2074
+ "loss": 1.3953,
2075
+ "step": 295
2076
+ },
2077
+ {
2078
+ "epoch": 0.8418059011731248,
2079
+ "grad_norm": 8.4375,
2080
+ "learning_rate": 6.106164577992224e-07,
2081
+ "loss": 1.395,
2082
+ "step": 296
2083
+ },
2084
+ {
2085
+ "epoch": 0.8446498400284393,
2086
+ "grad_norm": 4.09375,
2087
+ "learning_rate": 5.890568373086425e-07,
2088
+ "loss": 1.3245,
2089
+ "step": 297
2090
+ },
2091
+ {
2092
+ "epoch": 0.847493778883754,
2093
+ "grad_norm": 3.796875,
2094
+ "learning_rate": 5.678608604827784e-07,
2095
+ "loss": 1.4177,
2096
+ "step": 298
2097
+ },
2098
+ {
2099
+ "epoch": 0.8503377177390686,
2100
+ "grad_norm": 3.203125,
2101
+ "learning_rate": 5.470302747444428e-07,
2102
+ "loss": 1.3888,
2103
+ "step": 299
2104
+ },
2105
+ {
2106
+ "epoch": 0.8531816565943833,
2107
+ "grad_norm": 3.703125,
2108
+ "learning_rate": 5.265667973931416e-07,
2109
+ "loss": 1.3779,
2110
+ "step": 300
2111
+ }
2112
+ ],
2113
+ "logging_steps": 1,
2114
+ "max_steps": 351,
2115
+ "num_input_tokens_seen": 0,
2116
+ "num_train_epochs": 1,
2117
+ "save_steps": 150,
2118
+ "stateful_callbacks": {
2119
+ "TrainerControl": {
2120
+ "args": {
2121
+ "should_epoch_stop": false,
2122
+ "should_evaluate": false,
2123
+ "should_log": false,
2124
+ "should_save": true,
2125
+ "should_training_stop": false
2126
+ },
2127
+ "attributes": {}
2128
+ }
2129
+ },
2130
+ "total_flos": 5.360553841201152e+17,
2131
+ "train_batch_size": 32,
2132
+ "trial_name": null,
2133
+ "trial_params": null
2134
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5dba09eaee4bc1145f845435f18b5200cf62863782b751fbaba3011ed886f8
3
+ size 5624