Hugging Face's logo

Ba2han
/
augment-translate-ft

Image-Text-to-Text
Transformers
Safetensors
gemma3
Generated from Trainer
sft
trl
unsloth
conversational
text-generation-inference
Model card Files
xet
 Community
Ba2han commited on
Commit
3f152d3
·
verified ·
1 Parent(s): c8bbe9f

Delete last-checkpoint

Browse files
Files changed (18) hide show
  1. last-checkpoint/added_tokens.json +0 -3
  2. last-checkpoint/chat_template.jinja +0 -47
  3. last-checkpoint/config.json +0 -100
  4. last-checkpoint/generation_config.json +0 -10
  5. last-checkpoint/model-00001-of-00002.safetensors +0 -3
  6. last-checkpoint/model-00002-of-00002.safetensors +0 -3
  7. last-checkpoint/model.safetensors.index.json +0 -891
  8. last-checkpoint/optimizer.pt +0 -3
  9. last-checkpoint/preprocessor_config.json +0 -29
  10. last-checkpoint/processor_config.json +0 -4
  11. last-checkpoint/rng_state.pth +0 -3
  12. last-checkpoint/scheduler.pt +0 -3
  13. last-checkpoint/special_tokens_map.json +0 -33
  14. last-checkpoint/tokenizer.json +0 -3
  15. last-checkpoint/tokenizer.model +0 -3
  16. last-checkpoint/tokenizer_config.json +0 -0
  17. last-checkpoint/trainer_state.json +0 -1875
  18. last-checkpoint/training_args.bin +0 -3
last-checkpoint/added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "<image_soft_token>": 262144
3
- }
 
 
 
 
last-checkpoint/chat_template.jinja DELETED
@@ -1,47 +0,0 @@
1
- {{ bos_token }}
2
- {%- if messages[0]['role'] == 'system' -%}
3
- {%- if messages[0]['content'] is string -%}
4
- {%- set first_user_prefix = messages[0]['content'] + '
5
-
6
- ' -%}
7
- {%- else -%}
8
- {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
-
10
- ' -%}
11
- {%- endif -%}
12
- {%- set loop_messages = messages[1:] -%}
13
- {%- else -%}
14
- {%- set first_user_prefix = "" -%}
15
- {%- set loop_messages = messages -%}
16
- {%- endif -%}
17
- {%- for message in loop_messages -%}
18
- {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
- {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
- {%- endif -%}
21
- {%- if (message['role'] == 'assistant') -%}
22
- {%- set role = "model" -%}
23
- {%- else -%}
24
- {%- set role = message['role'] -%}
25
- {%- endif -%}
26
- {{ '<start_of_turn>' + role + '
27
- ' + (first_user_prefix if loop.first else "") }}
28
- {%- if message['content'] is string -%}
29
- {{ message['content'] | trim }}
30
- {%- elif message['content'] is iterable -%}
31
- {%- for item in message['content'] -%}
32
- {%- if item['type'] == 'image' -%}
33
- {{ '<start_of_image>' }}
34
- {%- elif item['type'] == 'text' -%}
35
- {{ item['text'] | trim }}
36
- {%- endif -%}
37
- {%- endfor -%}
38
- {%- else -%}
39
- {{ raise_exception("Invalid content type") }}
40
- {%- endif -%}
41
- {{ '<end_of_turn>
42
- ' }}
43
- {%- endfor -%}
44
- {%- if add_generation_prompt -%}
45
- {{ '<start_of_turn>model
46
- ' }}
47
- {%- endif -%}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/config.json DELETED
@@ -1,100 +0,0 @@
1
- {
2
- "architectures": [
3
- "Gemma3ForConditionalGeneration"
4
- ],
5
- "boi_token_index": 255999,
6
- "bos_token_id": 2,
7
- "dtype": "bfloat16",
8
- "eoi_token_index": 256000,
9
- "eos_token_id": 106,
10
- "image_token_index": 262144,
11
- "initializer_range": 0.02,
12
- "mm_tokens_per_image": 256,
13
- "model_type": "gemma3",
14
- "pad_token_id": 0,
15
- "text_config": {
16
- "_sliding_window_pattern": 6,
17
- "attention_bias": false,
18
- "attention_dropout": 0.0,
19
- "attn_logit_softcapping": null,
20
- "cache_implementation": "hybrid",
21
- "dtype": "bfloat16",
22
- "final_logit_softcapping": null,
23
- "head_dim": 256,
24
- "hidden_activation": "gelu_pytorch_tanh",
25
- "hidden_size": 2560,
26
- "initializer_range": 0.02,
27
- "intermediate_size": 10240,
28
- "layer_types": [
29
- "sliding_attention",
30
- "sliding_attention",
31
- "sliding_attention",
32
- "sliding_attention",
33
- "sliding_attention",
34
- "full_attention",
35
- "sliding_attention",
36
- "sliding_attention",
37
- "sliding_attention",
38
- "sliding_attention",
39
- "sliding_attention",
40
- "full_attention",
41
- "sliding_attention",
42
- "sliding_attention",
43
- "sliding_attention",
44
- "sliding_attention",
45
- "sliding_attention",
46
- "full_attention",
47
- "sliding_attention",
48
- "sliding_attention",
49
- "sliding_attention",
50
- "sliding_attention",
51
- "sliding_attention",
52
- "full_attention",
53
- "sliding_attention",
54
- "sliding_attention",
55
- "sliding_attention",
56
- "sliding_attention",
57
- "sliding_attention",
58
- "full_attention",
59
- "sliding_attention",
60
- "sliding_attention",
61
- "sliding_attention",
62
- "sliding_attention"
63
- ],
64
- "max_position_embeddings": 131072,
65
- "model_type": "gemma3_text",
66
- "num_attention_heads": 8,
67
- "num_hidden_layers": 34,
68
- "num_key_value_heads": 4,
69
- "query_pre_attn_scalar": 256,
70
- "rms_norm_eps": 1e-06,
71
- "rope_local_base_freq": 10000.0,
72
- "rope_scaling": {
73
- "factor": 8.0,
74
- "rope_type": "linear"
75
- },
76
- "rope_theta": 1000000.0,
77
- "sliding_window": 1024,
78
- "use_bidirectional_attention": false,
79
- "use_cache": true,
80
- "vocab_size": 262208
81
- },
82
- "transformers_version": "4.57.1",
83
- "unsloth_fixed": true,
84
- "unsloth_version": "2025.11.3",
85
- "vision_config": {
86
- "attention_dropout": 0.0,
87
- "dtype": "bfloat16",
88
- "hidden_act": "gelu_pytorch_tanh",
89
- "hidden_size": 1152,
90
- "image_size": 896,
91
- "intermediate_size": 4304,
92
- "layer_norm_eps": 1e-06,
93
- "model_type": "siglip_vision_model",
94
- "num_attention_heads": 16,
95
- "num_channels": 3,
96
- "num_hidden_layers": 27,
97
- "patch_size": 14,
98
- "vision_use_head": false
99
- }
100
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/generation_config.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 2,
4
- "cache_implementation": "hybrid",
5
- "eos_token_id": [
6
- 106
7
- ],
8
- "pad_token_id": 0,
9
- "transformers_version": "4.57.1"
10
- }
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:03c697183ec3d4c9ee41fb5d7eb5497a2276ae4bb9712e636c229f91a877bdd7
3
- size 4961251752
 
 
 
 
last-checkpoint/model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f23e1978c0181acc10e8ddd3143d44875ac855750d9cbd324267aa4a6cc3670
3
- size 3639026128
 
 
 
 
last-checkpoint/model.safetensors.index.json DELETED
@@ -1,891 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 4300079472,
4
- "total_size": 8600158944
5
- },
6
- "weight_map": {
7
- "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
- "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
- "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
- "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
- "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
14
- "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
15
- "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
16
- "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
17
- "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
- "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
19
- "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
20
- "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
- "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
- "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
- "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
- "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
- "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
- "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
27
- "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
28
- "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
29
- "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
30
- "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
- "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
32
- "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
- "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
- "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
- "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
- "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
- "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
- "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
- "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
40
- "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
41
- "language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
42
- "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
43
- "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
44
- "language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
45
- "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
46
- "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
47
- "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
48
- "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
49
- "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
50
- "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
51
- "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
52
- "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
53
- "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
54
- "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
55
- "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
- "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
57
- "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
58
- "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
- "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
60
- "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
61
- "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
62
- "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
63
- "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
64
- "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
- "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
66
- "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
67
- "language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
68
- "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
- "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
- "language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
71
- "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
72
- "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
73
- "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
74
- "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
- "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
76
- "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
77
- "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
- "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
79
- "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
80
- "language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
81
- "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
- "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
- "language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
84
- "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
- "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
- "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
87
- "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
88
- "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
- "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
90
- "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
91
- "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
92
- "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
93
- "language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
94
- "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
- "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
- "language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
97
- "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
- "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
99
- "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
100
- "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
101
- "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
102
- "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
103
- "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
104
- "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
105
- "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
106
- "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
107
- "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
108
- "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
- "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
110
- "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
111
- "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
112
- "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
113
- "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
114
- "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
115
- "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
116
- "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
117
- "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
118
- "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
119
- "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
120
- "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
121
- "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
122
- "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
123
- "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
124
- "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
125
- "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
- "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
- "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
128
- "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
129
- "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
- "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
131
- "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
132
- "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
133
- "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
134
- "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
135
- "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
136
- "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
137
- "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
138
- "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
139
- "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
140
- "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
141
- "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
142
- "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
- "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
144
- "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
145
- "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
146
- "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
147
- "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
148
- "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
149
- "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
- "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
- "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
- "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
- "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
- "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
- "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
- "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
157
- "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
158
- "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
159
- "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
160
- "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
161
- "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
162
- "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
163
- "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
164
- "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
- "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
- "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
167
- "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
168
- "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
169
- "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
170
- "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
171
- "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
172
- "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
173
- "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
- "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
175
- "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
176
- "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
- "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
178
- "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
179
- "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
180
- "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
181
- "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
182
- "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
183
- "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
184
- "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
185
- "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
186
- "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
187
- "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
188
- "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
189
- "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
190
- "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
191
- "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
192
- "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
193
- "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
194
- "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
195
- "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
196
- "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
197
- "language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
198
- "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
199
- "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
200
- "language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
201
- "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
202
- "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
203
- "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
204
- "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
205
- "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
206
- "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
207
- "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
208
- "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
209
- "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
210
- "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
211
- "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
- "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
- "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
214
- "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
215
- "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
216
- "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
217
- "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
218
- "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
219
- "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
220
- "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
221
- "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
222
- "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
223
- "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
224
- "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
225
- "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
226
- "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
227
- "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
228
- "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
229
- "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
- "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
- "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
- "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
233
- "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
- "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
235
- "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
236
- "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
237
- "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
238
- "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
239
- "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
240
- "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
- "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
- "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
243
- "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
244
- "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
245
- "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
246
- "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
247
- "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
248
- "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
249
- "language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
250
- "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
251
- "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
252
- "language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
253
- "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
254
- "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
255
- "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
256
- "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
257
- "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
258
- "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
259
- "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
260
- "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
261
- "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
262
- "language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
263
- "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
264
- "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
265
- "language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
266
- "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
267
- "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
268
- "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
269
- "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
270
- "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
271
- "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
272
- "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
273
- "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
274
- "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
275
- "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
276
- "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
277
- "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
278
- "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
279
- "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
280
- "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
281
- "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
282
- "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
283
- "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
284
- "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
285
- "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
286
- "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
287
- "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
288
- "language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
- "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
- "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
- "language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
- "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
- "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
- "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
- "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
- "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
- "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
- "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
- "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
300
- "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
301
- "language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
302
- "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
- "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
- "language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
305
- "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
- "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
- "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
308
- "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
309
- "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
310
- "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
311
- "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
312
- "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
313
- "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
314
- "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
315
- "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
- "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
- "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
318
- "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
- "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
- "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
- "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
- "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
- "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
- "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
- "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
326
- "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
327
- "language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
328
- "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
329
- "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
330
- "language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
331
- "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
332
- "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
333
- "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
334
- "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
335
- "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
336
- "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
337
- "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
338
- "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
339
- "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
340
- "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
341
- "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
342
- "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
343
- "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
344
- "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
345
- "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
346
- "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
347
- "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
348
- "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
349
- "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
350
- "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
351
- "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
352
- "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
353
- "language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
354
- "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
355
- "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
356
- "language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
357
- "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
358
- "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
359
- "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
360
- "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
361
- "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
362
- "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
363
- "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
364
- "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
365
- "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
366
- "language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
367
- "language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
368
- "language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
369
- "language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
370
- "language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
371
- "language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
372
- "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
373
- "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
374
- "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
375
- "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
376
- "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
377
- "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
378
- "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
379
- "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
380
- "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
381
- "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
382
- "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
383
- "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
384
- "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
385
- "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
386
- "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
387
- "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
388
- "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
389
- "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
390
- "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
391
- "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
392
- "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
393
- "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
394
- "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
395
- "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
396
- "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
397
- "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
398
- "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
399
- "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
400
- "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
401
- "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
402
- "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
403
- "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
404
- "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
405
- "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
406
- "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
407
- "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
408
- "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
409
- "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
410
- "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
411
- "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
412
- "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
413
- "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
414
- "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
415
- "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
416
- "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
417
- "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
418
- "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
419
- "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
420
- "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
421
- "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
422
- "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
423
- "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
424
- "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
- "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
426
- "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
427
- "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
428
- "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
429
- "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
430
- "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
431
- "language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
432
- "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
433
- "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
434
- "language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
435
- "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
436
- "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
437
- "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
438
- "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
439
- "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
440
- "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
441
- "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
442
- "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
443
- "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
444
- "language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
445
- "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
446
- "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
447
- "language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
448
- "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
449
- "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
450
- "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
451
- "multi_modal_projector.mm_input_projection_weight": "model-00001-of-00002.safetensors",
452
- "multi_modal_projector.mm_soft_emb_norm.weight": "model-00001-of-00002.safetensors",
453
- "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
454
- "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
455
- "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
456
- "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
457
- "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
458
- "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
459
- "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
460
- "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
461
- "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
462
- "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
463
- "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
464
- "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
465
- "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
466
- "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
467
- "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
468
- "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
469
- "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
470
- "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
471
- "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
472
- "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
473
- "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
474
- "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
475
- "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
476
- "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
477
- "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
478
- "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
479
- "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
480
- "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
481
- "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
482
- "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
483
- "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
484
- "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
485
- "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
486
- "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
487
- "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
- "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
489
- "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
490
- "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
491
- "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
492
- "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
493
- "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
494
- "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
495
- "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
496
- "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
497
- "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
498
- "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
499
- "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
500
- "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
501
- "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
- "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
503
- "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
- "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
505
- "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
506
- "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
507
- "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
508
- "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
509
- "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
510
- "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
511
- "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
512
- "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
513
- "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
514
- "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
515
- "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
516
- "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
517
- "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
518
- "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
519
- "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
520
- "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
521
- "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
522
- "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
523
- "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
524
- "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
525
- "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
526
- "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
527
- "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
528
- "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
529
- "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
530
- "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
531
- "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
532
- "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
533
- "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
534
- "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
535
- "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
536
- "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
537
- "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
538
- "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
539
- "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
540
- "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
541
- "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
542
- "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
543
- "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
544
- "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
545
- "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
546
- "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
547
- "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
548
- "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
549
- "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
550
- "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
551
- "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
552
- "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
553
- "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
554
- "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
555
- "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
556
- "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
557
- "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
558
- "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
559
- "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
560
- "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
561
- "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
562
- "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
563
- "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
564
- "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
565
- "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
566
- "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
567
- "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
568
- "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
569
- "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
570
- "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
571
- "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
572
- "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
573
- "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
574
- "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
575
- "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
576
- "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
577
- "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
578
- "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
579
- "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
580
- "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
581
- "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
582
- "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
583
- "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
584
- "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
585
- "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
586
- "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
587
- "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
588
- "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
589
- "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
590
- "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
591
- "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
592
- "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
593
- "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
594
- "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
595
- "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
596
- "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
597
- "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
598
- "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
599
- "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
600
- "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
601
- "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
602
- "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
603
- "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
604
- "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
605
- "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
606
- "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
607
- "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
608
- "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
609
- "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
610
- "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
611
- "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
612
- "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
613
- "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
614
- "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
615
- "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
616
- "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
617
- "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
618
- "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
619
- "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
620
- "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
621
- "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
622
- "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
623
- "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
624
- "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
625
- "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
626
- "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
627
- "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
628
- "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
629
- "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
630
- "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
631
- "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
632
- "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
633
- "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
634
- "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
635
- "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
636
- "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
637
- "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
638
- "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
639
- "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
640
- "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
641
- "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
642
- "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
643
- "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
644
- "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
645
- "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
646
- "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
647
- "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
648
- "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
649
- "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
650
- "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
651
- "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
652
- "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
653
- "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
654
- "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
655
- "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
656
- "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
657
- "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
658
- "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
659
- "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
660
- "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
661
- "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
662
- "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
663
- "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
664
- "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
665
- "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
666
- "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
667
- "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
668
- "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
669
- "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
670
- "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
671
- "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
672
- "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
673
- "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
674
- "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
675
- "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
676
- "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
677
- "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
678
- "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
679
- "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
680
- "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
681
- "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
682
- "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
683
- "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
684
- "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
685
- "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
686
- "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
687
- "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
688
- "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
689
- "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
690
- "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
691
- "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
692
- "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
693
- "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
694
- "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
695
- "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
696
- "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
697
- "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
698
- "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
699
- "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
700
- "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
701
- "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
702
- "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
703
- "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
704
- "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
705
- "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
706
- "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
707
- "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
708
- "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
709
- "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
710
- "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
711
- "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
712
- "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
713
- "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
714
- "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
715
- "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
716
- "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
717
- "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
718
- "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
719
- "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
720
- "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
721
- "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
722
- "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
723
- "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
724
- "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
725
- "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
726
- "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
727
- "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
728
- "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
729
- "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
730
- "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
731
- "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
732
- "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
733
- "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
734
- "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
735
- "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
736
- "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
737
- "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
738
- "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
739
- "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
740
- "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
741
- "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
742
- "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
743
- "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
744
- "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
745
- "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
746
- "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
747
- "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
748
- "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
749
- "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
750
- "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
751
- "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
752
- "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
753
- "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
754
- "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
755
- "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
756
- "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
757
- "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
758
- "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
759
- "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
760
- "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
761
- "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
762
- "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
763
- "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
764
- "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
765
- "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
766
- "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
767
- "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
768
- "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
769
- "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
770
- "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
771
- "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
772
- "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
773
- "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
774
- "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
775
- "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
776
- "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
777
- "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
778
- "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
779
- "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
780
- "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
781
- "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
782
- "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
783
- "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
784
- "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
785
- "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
786
- "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
787
- "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
788
- "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
789
- "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
790
- "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
791
- "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
792
- "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
793
- "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
794
- "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
795
- "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
796
- "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
797
- "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
798
- "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
799
- "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
800
- "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
801
- "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
802
- "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
803
- "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
804
- "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
805
- "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
806
- "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
807
- "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
808
- "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
809
- "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
810
- "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
811
- "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
812
- "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
813
- "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
814
- "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
815
- "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
816
- "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
817
- "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
818
- "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
819
- "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
820
- "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
821
- "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
822
- "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
823
- "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
824
- "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
825
- "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
826
- "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
827
- "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
828
- "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
829
- "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
830
- "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
831
- "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
832
- "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
833
- "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
834
- "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
835
- "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
836
- "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
837
- "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
838
- "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
839
- "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
840
- "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
841
- "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
842
- "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
843
- "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
844
- "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
845
- "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
846
- "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
847
- "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
848
- "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
849
- "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
850
- "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
851
- "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
852
- "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
853
- "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
854
- "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
855
- "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
856
- "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
857
- "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
858
- "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
859
- "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
860
- "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
861
- "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
862
- "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
863
- "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
864
- "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
865
- "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
866
- "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
867
- "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
868
- "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
869
- "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
870
- "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
871
- "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
872
- "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
873
- "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
874
- "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
875
- "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
876
- "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
877
- "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
878
- "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
879
- "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
880
- "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
881
- "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
882
- "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
883
- "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
884
- "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
885
- "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
886
- "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
887
- "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
888
- "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
889
- "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
890
- }
891
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d9e8ae18452278b808cfcebf861894adb0a1396067774b811c476c206ae8f04
3
- size 11890947145
 
 
 
 
last-checkpoint/preprocessor_config.json DELETED
@@ -1,29 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/processor_config.json DELETED
@@ -1,4 +0,0 @@
1
- {
2
- "image_seq_length": 256,
3
- "processor_class": "Gemma3Processor"
4
- }
 
 
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
3
- size 14645
 
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eb088b53c1bbdda30530e9a2f6310b5323c6a896d711e49c8a265e58e230b2d
3
- size 1465
 
 
 
 
last-checkpoint/special_tokens_map.json DELETED
@@ -1,33 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
- size 33384568
 
 
 
 
last-checkpoint/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
- size 4689074
 
 
 
 
last-checkpoint/tokenizer_config.json DELETED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/trainer_state.json DELETED
@@ -1,1875 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.32444101773323053,
6
- "eval_steps": 500,
7
- "global_step": 263,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.001233616037008481,
14
- "grad_norm": 6.71875,
15
- "learning_rate": 0.0,
16
- "loss": 1.248,
17
- "step": 1
18
- },
19
- {
20
- "epoch": 0.002467232074016962,
21
- "grad_norm": 7.0625,
22
- "learning_rate": 1e-06,
23
- "loss": 1.3869,
24
- "step": 2
25
- },
26
- {
27
- "epoch": 0.0037008481110254433,
28
- "grad_norm": 6.4375,
29
- "learning_rate": 2e-06,
30
- "loss": 1.1873,
31
- "step": 3
32
- },
33
- {
34
- "epoch": 0.004934464148033924,
35
- "grad_norm": 6.0,
36
- "learning_rate": 3e-06,
37
- "loss": 1.307,
38
- "step": 4
39
- },
40
- {
41
- "epoch": 0.006168080185042405,
42
- "grad_norm": 5.65625,
43
- "learning_rate": 4e-06,
44
- "loss": 1.3342,
45
- "step": 5
46
- },
47
- {
48
- "epoch": 0.0074016962220508865,
49
- "grad_norm": 4.90625,
50
- "learning_rate": 4.9999999999999996e-06,
51
- "loss": 1.1798,
52
- "step": 6
53
- },
54
- {
55
- "epoch": 0.008635312259059369,
56
- "grad_norm": 4.75,
57
- "learning_rate": 6e-06,
58
- "loss": 1.1951,
59
- "step": 7
60
- },
61
- {
62
- "epoch": 0.009868928296067848,
63
- "grad_norm": 4.46875,
64
- "learning_rate": 7e-06,
65
- "loss": 1.2497,
66
- "step": 8
67
- },
68
- {
69
- "epoch": 0.01110254433307633,
70
- "grad_norm": 4.4375,
71
- "learning_rate": 8e-06,
72
- "loss": 1.2303,
73
- "step": 9
74
- },
75
- {
76
- "epoch": 0.01233616037008481,
77
- "grad_norm": 3.84375,
78
- "learning_rate": 9e-06,
79
- "loss": 1.077,
80
- "step": 10
81
- },
82
- {
83
- "epoch": 0.013569776407093292,
84
- "grad_norm": 3.375,
85
- "learning_rate": 9.999999999999999e-06,
86
- "loss": 1.1018,
87
- "step": 11
88
- },
89
- {
90
- "epoch": 0.014803392444101773,
91
- "grad_norm": 3.53125,
92
- "learning_rate": 1.1e-05,
93
- "loss": 1.1497,
94
- "step": 12
95
- },
96
- {
97
- "epoch": 0.016037008481110254,
98
- "grad_norm": 3.484375,
99
- "learning_rate": 1.2e-05,
100
- "loss": 1.1544,
101
- "step": 13
102
- },
103
- {
104
- "epoch": 0.017270624518118737,
105
- "grad_norm": 3.328125,
106
- "learning_rate": 1.3000000000000001e-05,
107
- "loss": 1.1325,
108
- "step": 14
109
- },
110
- {
111
- "epoch": 0.018504240555127217,
112
- "grad_norm": 3.703125,
113
- "learning_rate": 1.4e-05,
114
- "loss": 1.2333,
115
- "step": 15
116
- },
117
- {
118
- "epoch": 0.019737856592135696,
119
- "grad_norm": 3.4375,
120
- "learning_rate": 1.5e-05,
121
- "loss": 1.1316,
122
- "step": 16
123
- },
124
- {
125
- "epoch": 0.02097147262914418,
126
- "grad_norm": 3.3125,
127
- "learning_rate": 1.4999968269041147e-05,
128
- "loss": 1.0587,
129
- "step": 17
130
- },
131
- {
132
- "epoch": 0.02220508866615266,
133
- "grad_norm": 3.265625,
134
- "learning_rate": 1.4999873076433081e-05,
135
- "loss": 1.1082,
136
- "step": 18
137
- },
138
- {
139
- "epoch": 0.02343870470316114,
140
- "grad_norm": 2.875,
141
- "learning_rate": 1.4999714422981284e-05,
142
- "loss": 0.9257,
143
- "step": 19
144
- },
145
- {
146
- "epoch": 0.02467232074016962,
147
- "grad_norm": 2.796875,
148
- "learning_rate": 1.4999492310028218e-05,
149
- "loss": 0.9563,
150
- "step": 20
151
- },
152
- {
153
- "epoch": 0.025905936777178104,
154
- "grad_norm": 2.875,
155
- "learning_rate": 1.4999206739453307e-05,
156
- "loss": 1.023,
157
- "step": 21
158
- },
159
- {
160
- "epoch": 0.027139552814186584,
161
- "grad_norm": 3.0,
162
- "learning_rate": 1.4998857713672935e-05,
163
- "loss": 0.9719,
164
- "step": 22
165
- },
166
- {
167
- "epoch": 0.028373168851195067,
168
- "grad_norm": 3.4375,
169
- "learning_rate": 1.4998445235640414e-05,
170
- "loss": 1.0854,
171
- "step": 23
172
- },
173
- {
174
- "epoch": 0.029606784888203546,
175
- "grad_norm": 3.09375,
176
- "learning_rate": 1.4997969308845963e-05,
177
- "loss": 1.0053,
178
- "step": 24
179
- },
180
- {
181
- "epoch": 0.03084040092521203,
182
- "grad_norm": 2.859375,
183
- "learning_rate": 1.4997429937316679e-05,
184
- "loss": 0.9063,
185
- "step": 25
186
- },
187
- {
188
- "epoch": 0.03207401696222051,
189
- "grad_norm": 2.71875,
190
- "learning_rate": 1.4996827125616506e-05,
191
- "loss": 0.8936,
192
- "step": 26
193
- },
194
- {
195
- "epoch": 0.03330763299922899,
196
- "grad_norm": 3.0,
197
- "learning_rate": 1.4996160878846183e-05,
198
- "loss": 1.0101,
199
- "step": 27
200
- },
201
- {
202
- "epoch": 0.034541249036237474,
203
- "grad_norm": 2.9375,
204
- "learning_rate": 1.4995431202643219e-05,
205
- "loss": 1.0398,
206
- "step": 28
207
- },
208
- {
209
- "epoch": 0.035774865073245954,
210
- "grad_norm": 2.8125,
211
- "learning_rate": 1.4994638103181834e-05,
212
- "loss": 0.899,
213
- "step": 29
214
- },
215
- {
216
- "epoch": 0.03700848111025443,
217
- "grad_norm": 2.671875,
218
- "learning_rate": 1.499378158717291e-05,
219
- "loss": 0.9018,
220
- "step": 30
221
- },
222
- {
223
- "epoch": 0.03824209714726291,
224
- "grad_norm": 2.78125,
225
- "learning_rate": 1.4992861661863935e-05,
226
- "loss": 0.9789,
227
- "step": 31
228
- },
229
- {
230
- "epoch": 0.03947571318427139,
231
- "grad_norm": 2.84375,
232
- "learning_rate": 1.4991878335038935e-05,
233
- "loss": 1.0518,
234
- "step": 32
235
- },
236
- {
237
- "epoch": 0.04070932922127988,
238
- "grad_norm": 2.59375,
239
- "learning_rate": 1.499083161501842e-05,
240
- "loss": 0.9835,
241
- "step": 33
242
- },
243
- {
244
- "epoch": 0.04194294525828836,
245
- "grad_norm": 2.640625,
246
- "learning_rate": 1.4989721510659303e-05,
247
- "loss": 0.9702,
248
- "step": 34
249
- },
250
- {
251
- "epoch": 0.04317656129529684,
252
- "grad_norm": 2.625,
253
- "learning_rate": 1.4988548031354836e-05,
254
- "loss": 0.9326,
255
- "step": 35
256
- },
257
- {
258
- "epoch": 0.04441017733230532,
259
- "grad_norm": 2.703125,
260
- "learning_rate": 1.4987311187034512e-05,
261
- "loss": 0.8922,
262
- "step": 36
263
- },
264
- {
265
- "epoch": 0.045643793369313804,
266
- "grad_norm": 3.078125,
267
- "learning_rate": 1.4986010988164002e-05,
268
- "loss": 1.0141,
269
- "step": 37
270
- },
271
- {
272
- "epoch": 0.04687740940632228,
273
- "grad_norm": 2.890625,
274
- "learning_rate": 1.4984647445745055e-05,
275
- "loss": 0.9227,
276
- "step": 38
277
- },
278
- {
279
- "epoch": 0.04811102544333076,
280
- "grad_norm": 2.8125,
281
- "learning_rate": 1.4983220571315407e-05,
282
- "loss": 0.8882,
283
- "step": 39
284
- },
285
- {
286
- "epoch": 0.04934464148033924,
287
- "grad_norm": 2.90625,
288
- "learning_rate": 1.4981730376948682e-05,
289
- "loss": 0.9169,
290
- "step": 40
291
- },
292
- {
293
- "epoch": 0.05057825751734773,
294
- "grad_norm": 2.703125,
295
- "learning_rate": 1.4980176875254293e-05,
296
- "loss": 0.8736,
297
- "step": 41
298
- },
299
- {
300
- "epoch": 0.05181187355435621,
301
- "grad_norm": 2.8125,
302
- "learning_rate": 1.4978560079377331e-05,
303
- "loss": 1.0533,
304
- "step": 42
305
- },
306
- {
307
- "epoch": 0.05304548959136469,
308
- "grad_norm": 2.828125,
309
- "learning_rate": 1.497688000299846e-05,
310
- "loss": 0.8594,
311
- "step": 43
312
- },
313
- {
314
- "epoch": 0.05427910562837317,
315
- "grad_norm": 2.640625,
316
- "learning_rate": 1.4975136660333796e-05,
317
- "loss": 0.8611,
318
- "step": 44
319
- },
320
- {
321
- "epoch": 0.05551272166538165,
322
- "grad_norm": 2.8125,
323
- "learning_rate": 1.4973330066134787e-05,
324
- "loss": 0.8746,
325
- "step": 45
326
- },
327
- {
328
- "epoch": 0.05674633770239013,
329
- "grad_norm": 2.6875,
330
- "learning_rate": 1.4971460235688093e-05,
331
- "loss": 0.8591,
332
- "step": 46
333
- },
334
- {
335
- "epoch": 0.05797995373939861,
336
- "grad_norm": 2.4375,
337
- "learning_rate": 1.4969527184815445e-05,
338
- "loss": 0.807,
339
- "step": 47
340
- },
341
- {
342
- "epoch": 0.05921356977640709,
343
- "grad_norm": 2.921875,
344
- "learning_rate": 1.4967530929873532e-05,
345
- "loss": 1.0917,
346
- "step": 48
347
- },
348
- {
349
- "epoch": 0.06044718581341557,
350
- "grad_norm": 2.9375,
351
- "learning_rate": 1.4965471487753841e-05,
352
- "loss": 0.9761,
353
- "step": 49
354
- },
355
- {
356
- "epoch": 0.06168080185042406,
357
- "grad_norm": 2.546875,
358
- "learning_rate": 1.4963348875882524e-05,
359
- "loss": 0.8561,
360
- "step": 50
361
- },
362
- {
363
- "epoch": 0.06291441788743253,
364
- "grad_norm": 2.984375,
365
- "learning_rate": 1.4961163112220248e-05,
366
- "loss": 0.9811,
367
- "step": 51
368
- },
369
- {
370
- "epoch": 0.06414803392444102,
371
- "grad_norm": 2.78125,
372
- "learning_rate": 1.495891421526205e-05,
373
- "loss": 0.8307,
374
- "step": 52
375
- },
376
- {
377
- "epoch": 0.0653816499614495,
378
- "grad_norm": 2.859375,
379
- "learning_rate": 1.4956602204037171e-05,
380
- "loss": 0.8901,
381
- "step": 53
382
- },
383
- {
384
- "epoch": 0.06661526599845798,
385
- "grad_norm": 2.71875,
386
- "learning_rate": 1.49542270981089e-05,
387
- "loss": 0.923,
388
- "step": 54
389
- },
390
- {
391
- "epoch": 0.06784888203546646,
392
- "grad_norm": 2.796875,
393
- "learning_rate": 1.4951788917574407e-05,
394
- "loss": 0.9071,
395
- "step": 55
396
- },
397
- {
398
- "epoch": 0.06908249807247495,
399
- "grad_norm": 2.78125,
400
- "learning_rate": 1.4949287683064572e-05,
401
- "loss": 0.9699,
402
- "step": 56
403
- },
404
- {
405
- "epoch": 0.07031611410948342,
406
- "grad_norm": 2.625,
407
- "learning_rate": 1.4946723415743818e-05,
408
- "loss": 0.8934,
409
- "step": 57
410
- },
411
- {
412
- "epoch": 0.07154973014649191,
413
- "grad_norm": 2.609375,
414
- "learning_rate": 1.4944096137309916e-05,
415
- "loss": 0.8535,
416
- "step": 58
417
- },
418
- {
419
- "epoch": 0.07278334618350038,
420
- "grad_norm": 2.734375,
421
- "learning_rate": 1.494140586999382e-05,
422
- "loss": 0.8834,
423
- "step": 59
424
- },
425
- {
426
- "epoch": 0.07401696222050887,
427
- "grad_norm": 2.546875,
428
- "learning_rate": 1.4938652636559461e-05,
429
- "loss": 0.8252,
430
- "step": 60
431
- },
432
- {
433
- "epoch": 0.07525057825751735,
434
- "grad_norm": 2.75,
435
- "learning_rate": 1.4935836460303579e-05,
436
- "loss": 0.9216,
437
- "step": 61
438
- },
439
- {
440
- "epoch": 0.07648419429452583,
441
- "grad_norm": 2.78125,
442
- "learning_rate": 1.493295736505549e-05,
443
- "loss": 0.9662,
444
- "step": 62
445
- },
446
- {
447
- "epoch": 0.07771781033153431,
448
- "grad_norm": 2.796875,
449
- "learning_rate": 1.493001537517692e-05,
450
- "loss": 0.9442,
451
- "step": 63
452
- },
453
- {
454
- "epoch": 0.07895142636854278,
455
- "grad_norm": 2.921875,
456
- "learning_rate": 1.4927010515561777e-05,
457
- "loss": 0.8907,
458
- "step": 64
459
- },
460
- {
461
- "epoch": 0.08018504240555127,
462
- "grad_norm": 2.703125,
463
- "learning_rate": 1.4923942811635948e-05,
464
- "loss": 0.8383,
465
- "step": 65
466
- },
467
- {
468
- "epoch": 0.08141865844255976,
469
- "grad_norm": 2.78125,
470
- "learning_rate": 1.4920812289357082e-05,
471
- "loss": 0.9024,
472
- "step": 66
473
- },
474
- {
475
- "epoch": 0.08265227447956823,
476
- "grad_norm": 2.828125,
477
- "learning_rate": 1.4917618975214377e-05,
478
- "loss": 0.8793,
479
- "step": 67
480
- },
481
- {
482
- "epoch": 0.08388589051657672,
483
- "grad_norm": 2.921875,
484
- "learning_rate": 1.4914362896228338e-05,
485
- "loss": 0.8629,
486
- "step": 68
487
- },
488
- {
489
- "epoch": 0.0851195065535852,
490
- "grad_norm": 2.828125,
491
- "learning_rate": 1.491104407995057e-05,
492
- "loss": 0.8802,
493
- "step": 69
494
- },
495
- {
496
- "epoch": 0.08635312259059368,
497
- "grad_norm": 2.75,
498
- "learning_rate": 1.4907662554463534e-05,
499
- "loss": 0.8722,
500
- "step": 70
501
- },
502
- {
503
- "epoch": 0.08758673862760216,
504
- "grad_norm": 2.640625,
505
- "learning_rate": 1.4904218348380306e-05,
506
- "loss": 0.8971,
507
- "step": 71
508
- },
509
- {
510
- "epoch": 0.08882035466461063,
511
- "grad_norm": 2.578125,
512
- "learning_rate": 1.4900711490844346e-05,
513
- "loss": 0.8287,
514
- "step": 72
515
- },
516
- {
517
- "epoch": 0.09005397070161912,
518
- "grad_norm": 2.703125,
519
- "learning_rate": 1.4897142011529236e-05,
520
- "loss": 0.9449,
521
- "step": 73
522
- },
523
- {
524
- "epoch": 0.09128758673862761,
525
- "grad_norm": 2.9375,
526
- "learning_rate": 1.4893509940638448e-05,
527
- "loss": 0.9576,
528
- "step": 74
529
- },
530
- {
531
- "epoch": 0.09252120277563608,
532
- "grad_norm": 3.046875,
533
- "learning_rate": 1.4889815308905071e-05,
534
- "loss": 0.9262,
535
- "step": 75
536
- },
537
- {
538
- "epoch": 0.09375481881264457,
539
- "grad_norm": 2.796875,
540
- "learning_rate": 1.488605814759156e-05,
541
- "loss": 0.9876,
542
- "step": 76
543
- },
544
- {
545
- "epoch": 0.09498843484965304,
546
- "grad_norm": 2.96875,
547
- "learning_rate": 1.4882238488489474e-05,
548
- "loss": 0.8828,
549
- "step": 77
550
- },
551
- {
552
- "epoch": 0.09622205088666153,
553
- "grad_norm": 2.8125,
554
- "learning_rate": 1.487835636391919e-05,
555
- "loss": 0.8688,
556
- "step": 78
557
- },
558
- {
559
- "epoch": 0.09745566692367001,
560
- "grad_norm": 2.78125,
561
- "learning_rate": 1.487441180672966e-05,
562
- "loss": 0.9276,
563
- "step": 79
564
- },
565
- {
566
- "epoch": 0.09868928296067848,
567
- "grad_norm": 2.90625,
568
- "learning_rate": 1.48704048502981e-05,
569
- "loss": 0.927,
570
- "step": 80
571
- },
572
- {
573
- "epoch": 0.09992289899768697,
574
- "grad_norm": 2.578125,
575
- "learning_rate": 1.486633552852973e-05,
576
- "loss": 0.7675,
577
- "step": 81
578
- },
579
- {
580
- "epoch": 0.10115651503469546,
581
- "grad_norm": 2.734375,
582
- "learning_rate": 1.486220387585748e-05,
583
- "loss": 0.8741,
584
- "step": 82
585
- },
586
- {
587
- "epoch": 0.10239013107170393,
588
- "grad_norm": 3.078125,
589
- "learning_rate": 1.4858009927241694e-05,
590
- "loss": 1.0708,
591
- "step": 83
592
- },
593
- {
594
- "epoch": 0.10362374710871242,
595
- "grad_norm": 2.96875,
596
- "learning_rate": 1.4853753718169845e-05,
597
- "loss": 0.9001,
598
- "step": 84
599
- },
600
- {
601
- "epoch": 0.10485736314572089,
602
- "grad_norm": 2.890625,
603
- "learning_rate": 1.4849435284656223e-05,
604
- "loss": 0.914,
605
- "step": 85
606
- },
607
- {
608
- "epoch": 0.10609097918272938,
609
- "grad_norm": 2.828125,
610
- "learning_rate": 1.4845054663241638e-05,
611
- "loss": 0.884,
612
- "step": 86
613
- },
614
- {
615
- "epoch": 0.10732459521973786,
616
- "grad_norm": 2.90625,
617
- "learning_rate": 1.4840611890993105e-05,
618
- "loss": 0.9372,
619
- "step": 87
620
- },
621
- {
622
- "epoch": 0.10855821125674633,
623
- "grad_norm": 2.8125,
624
- "learning_rate": 1.4836107005503543e-05,
625
- "loss": 0.9541,
626
- "step": 88
627
- },
628
- {
629
- "epoch": 0.10979182729375482,
630
- "grad_norm": 2.703125,
631
- "learning_rate": 1.4831540044891436e-05,
632
- "loss": 0.9014,
633
- "step": 89
634
- },
635
- {
636
- "epoch": 0.1110254433307633,
637
- "grad_norm": 2.578125,
638
- "learning_rate": 1.4826911047800533e-05,
639
- "loss": 0.805,
640
- "step": 90
641
- },
642
- {
643
- "epoch": 0.11225905936777178,
644
- "grad_norm": 2.90625,
645
- "learning_rate": 1.4822220053399501e-05,
646
- "loss": 0.9061,
647
- "step": 91
648
- },
649
- {
650
- "epoch": 0.11349267540478027,
651
- "grad_norm": 2.609375,
652
- "learning_rate": 1.4817467101381607e-05,
653
- "loss": 0.8259,
654
- "step": 92
655
- },
656
- {
657
- "epoch": 0.11472629144178874,
658
- "grad_norm": 2.609375,
659
- "learning_rate": 1.481265223196438e-05,
660
- "loss": 0.7689,
661
- "step": 93
662
- },
663
- {
664
- "epoch": 0.11595990747879723,
665
- "grad_norm": 2.8125,
666
- "learning_rate": 1.4807775485889265e-05,
667
- "loss": 0.8978,
668
- "step": 94
669
- },
670
- {
671
- "epoch": 0.11719352351580571,
672
- "grad_norm": 2.640625,
673
- "learning_rate": 1.4802836904421283e-05,
674
- "loss": 0.8649,
675
- "step": 95
676
- },
677
- {
678
- "epoch": 0.11842713955281418,
679
- "grad_norm": 2.84375,
680
- "learning_rate": 1.479783652934868e-05,
681
- "loss": 0.9111,
682
- "step": 96
683
- },
684
- {
685
- "epoch": 0.11966075558982267,
686
- "grad_norm": 2.765625,
687
- "learning_rate": 1.4792774402982574e-05,
688
- "loss": 0.8746,
689
- "step": 97
690
- },
691
- {
692
- "epoch": 0.12089437162683114,
693
- "grad_norm": 2.828125,
694
- "learning_rate": 1.4787650568156603e-05,
695
- "loss": 0.8713,
696
- "step": 98
697
- },
698
- {
699
- "epoch": 0.12212798766383963,
700
- "grad_norm": 3.0,
701
- "learning_rate": 1.4782465068226546e-05,
702
- "loss": 1.0504,
703
- "step": 99
704
- },
705
- {
706
- "epoch": 0.12336160370084812,
707
- "grad_norm": 2.59375,
708
- "learning_rate": 1.4777217947069972e-05,
709
- "loss": 0.836,
710
- "step": 100
711
- },
712
- {
713
- "epoch": 0.12459521973785659,
714
- "grad_norm": 2.625,
715
- "learning_rate": 1.477190924908587e-05,
716
- "loss": 0.9062,
717
- "step": 101
718
- },
719
- {
720
- "epoch": 0.12582883577486506,
721
- "grad_norm": 2.734375,
722
- "learning_rate": 1.4766539019194254e-05,
723
- "loss": 0.8326,
724
- "step": 102
725
- },
726
- {
727
- "epoch": 0.12706245181187356,
728
- "grad_norm": 2.921875,
729
- "learning_rate": 1.4761107302835808e-05,
730
- "loss": 1.0209,
731
- "step": 103
732
- },
733
- {
734
- "epoch": 0.12829606784888203,
735
- "grad_norm": 3.171875,
736
- "learning_rate": 1.475561414597148e-05,
737
- "loss": 0.8731,
738
- "step": 104
739
- },
740
- {
741
- "epoch": 0.1295296838858905,
742
- "grad_norm": 2.953125,
743
- "learning_rate": 1.4750059595082105e-05,
744
- "loss": 1.0162,
745
- "step": 105
746
- },
747
- {
748
- "epoch": 0.130763299922899,
749
- "grad_norm": 2.59375,
750
- "learning_rate": 1.4744443697168013e-05,
751
- "loss": 0.8062,
752
- "step": 106
753
- },
754
- {
755
- "epoch": 0.13199691595990748,
756
- "grad_norm": 2.75,
757
- "learning_rate": 1.4738766499748621e-05,
758
- "loss": 0.8803,
759
- "step": 107
760
- },
761
- {
762
- "epoch": 0.13323053199691595,
763
- "grad_norm": 2.859375,
764
- "learning_rate": 1.4733028050862042e-05,
765
- "loss": 0.8974,
766
- "step": 108
767
- },
768
- {
769
- "epoch": 0.13446414803392445,
770
- "grad_norm": 2.828125,
771
- "learning_rate": 1.4727228399064672e-05,
772
- "loss": 0.9204,
773
- "step": 109
774
- },
775
- {
776
- "epoch": 0.13569776407093292,
777
- "grad_norm": 2.890625,
778
- "learning_rate": 1.4721367593430782e-05,
779
- "loss": 0.9693,
780
- "step": 110
781
- },
782
- {
783
- "epoch": 0.1369313801079414,
784
- "grad_norm": 3.0625,
785
- "learning_rate": 1.4715445683552098e-05,
786
- "loss": 0.9835,
787
- "step": 111
788
- },
789
- {
790
- "epoch": 0.1381649961449499,
791
- "grad_norm": 2.796875,
792
- "learning_rate": 1.4709462719537392e-05,
793
- "loss": 0.947,
794
- "step": 112
795
- },
796
- {
797
- "epoch": 0.13939861218195837,
798
- "grad_norm": 2.8125,
799
- "learning_rate": 1.4703418752012042e-05,
800
- "loss": 0.8622,
801
- "step": 113
802
- },
803
- {
804
- "epoch": 0.14063222821896684,
805
- "grad_norm": 2.734375,
806
- "learning_rate": 1.469731383211762e-05,
807
- "loss": 0.8848,
808
- "step": 114
809
- },
810
- {
811
- "epoch": 0.14186584425597532,
812
- "grad_norm": 3.203125,
813
- "learning_rate": 1.4691148011511447e-05,
814
- "loss": 0.9425,
815
- "step": 115
816
- },
817
- {
818
- "epoch": 0.14309946029298382,
819
- "grad_norm": 2.703125,
820
- "learning_rate": 1.4684921342366167e-05,
821
- "loss": 0.8893,
822
- "step": 116
823
- },
824
- {
825
- "epoch": 0.1443330763299923,
826
- "grad_norm": 2.609375,
827
- "learning_rate": 1.467863387736929e-05,
828
- "loss": 0.7976,
829
- "step": 117
830
- },
831
- {
832
- "epoch": 0.14556669236700076,
833
- "grad_norm": 2.546875,
834
- "learning_rate": 1.4672285669722767e-05,
835
- "loss": 0.843,
836
- "step": 118
837
- },
838
- {
839
- "epoch": 0.14680030840400926,
840
- "grad_norm": 3.015625,
841
- "learning_rate": 1.4665876773142517e-05,
842
- "loss": 0.9341,
843
- "step": 119
844
- },
845
- {
846
- "epoch": 0.14803392444101773,
847
- "grad_norm": 2.671875,
848
- "learning_rate": 1.4659407241857991e-05,
849
- "loss": 0.9336,
850
- "step": 120
851
- },
852
- {
853
- "epoch": 0.1492675404780262,
854
- "grad_norm": 2.6875,
855
- "learning_rate": 1.4652877130611702e-05,
856
- "loss": 0.8282,
857
- "step": 121
858
- },
859
- {
860
- "epoch": 0.1505011565150347,
861
- "grad_norm": 2.984375,
862
- "learning_rate": 1.4646286494658772e-05,
863
- "loss": 0.9196,
864
- "step": 122
865
- },
866
- {
867
- "epoch": 0.15173477255204318,
868
- "grad_norm": 2.703125,
869
- "learning_rate": 1.4639635389766448e-05,
870
- "loss": 0.8443,
871
- "step": 123
872
- },
873
- {
874
- "epoch": 0.15296838858905165,
875
- "grad_norm": 3.09375,
876
- "learning_rate": 1.4632923872213653e-05,
877
- "loss": 1.0012,
878
- "step": 124
879
- },
880
- {
881
- "epoch": 0.15420200462606015,
882
- "grad_norm": 2.65625,
883
- "learning_rate": 1.4626151998790484e-05,
884
- "loss": 0.7756,
885
- "step": 125
886
- },
887
- {
888
- "epoch": 0.15543562066306862,
889
- "grad_norm": 2.8125,
890
- "learning_rate": 1.4619319826797755e-05,
891
- "loss": 0.9635,
892
- "step": 126
893
- },
894
- {
895
- "epoch": 0.1566692367000771,
896
- "grad_norm": 3.09375,
897
- "learning_rate": 1.4612427414046496e-05,
898
- "loss": 0.9628,
899
- "step": 127
900
- },
901
- {
902
- "epoch": 0.15790285273708557,
903
- "grad_norm": 4.59375,
904
- "learning_rate": 1.460547481885747e-05,
905
- "loss": 0.7604,
906
- "step": 128
907
- },
908
- {
909
- "epoch": 0.15913646877409407,
910
- "grad_norm": 2.609375,
911
- "learning_rate": 1.4598462100060683e-05,
912
- "loss": 0.7931,
913
- "step": 129
914
- },
915
- {
916
- "epoch": 0.16037008481110254,
917
- "grad_norm": 2.640625,
918
- "learning_rate": 1.4591389316994878e-05,
919
- "loss": 0.9052,
920
- "step": 130
921
- },
922
- {
923
- "epoch": 0.16160370084811101,
924
- "grad_norm": 2.671875,
925
- "learning_rate": 1.4584256529507036e-05,
926
- "loss": 0.7923,
927
- "step": 131
928
- },
929
- {
930
- "epoch": 0.16283731688511952,
931
- "grad_norm": 2.703125,
932
- "learning_rate": 1.4577063797951877e-05,
933
- "loss": 0.812,
934
- "step": 132
935
- },
936
- {
937
- "epoch": 0.164070932922128,
938
- "grad_norm": 2.8125,
939
- "learning_rate": 1.456981118319134e-05,
940
- "loss": 0.909,
941
- "step": 133
942
- },
943
- {
944
- "epoch": 0.16530454895913646,
945
- "grad_norm": 2.609375,
946
- "learning_rate": 1.4562498746594067e-05,
947
- "loss": 0.8217,
948
- "step": 134
949
- },
950
- {
951
- "epoch": 0.16653816499614496,
952
- "grad_norm": 2.875,
953
- "learning_rate": 1.455512655003489e-05,
954
- "loss": 0.848,
955
- "step": 135
956
- },
957
- {
958
- "epoch": 0.16777178103315343,
959
- "grad_norm": 2.65625,
960
- "learning_rate": 1.4547694655894313e-05,
961
- "loss": 0.8453,
962
- "step": 136
963
- },
964
- {
965
- "epoch": 0.1690053970701619,
966
- "grad_norm": 2.734375,
967
- "learning_rate": 1.4540203127057964e-05,
968
- "loss": 0.8832,
969
- "step": 137
970
- },
971
- {
972
- "epoch": 0.1702390131071704,
973
- "grad_norm": 3.3125,
974
- "learning_rate": 1.4532652026916087e-05,
975
- "loss": 0.8883,
976
- "step": 138
977
- },
978
- {
979
- "epoch": 0.17147262914417888,
980
- "grad_norm": 2.8125,
981
- "learning_rate": 1.4525041419362983e-05,
982
- "loss": 0.9908,
983
- "step": 139
984
- },
985
- {
986
- "epoch": 0.17270624518118735,
987
- "grad_norm": 2.625,
988
- "learning_rate": 1.4517371368796487e-05,
989
- "loss": 0.8058,
990
- "step": 140
991
- },
992
- {
993
- "epoch": 0.17393986121819582,
994
- "grad_norm": 2.890625,
995
- "learning_rate": 1.4509641940117414e-05,
996
- "loss": 0.9513,
997
- "step": 141
998
- },
999
- {
1000
- "epoch": 0.17517347725520432,
1001
- "grad_norm": 2.59375,
1002
- "learning_rate": 1.4501853198729012e-05,
1003
- "loss": 0.9095,
1004
- "step": 142
1005
- },
1006
- {
1007
- "epoch": 0.1764070932922128,
1008
- "grad_norm": 2.953125,
1009
- "learning_rate": 1.4494005210536415e-05,
1010
- "loss": 0.8964,
1011
- "step": 143
1012
- },
1013
- {
1014
- "epoch": 0.17764070932922127,
1015
- "grad_norm": 2.703125,
1016
- "learning_rate": 1.4486098041946069e-05,
1017
- "loss": 0.8261,
1018
- "step": 144
1019
- },
1020
- {
1021
- "epoch": 0.17887432536622977,
1022
- "grad_norm": 2.921875,
1023
- "learning_rate": 1.4478131759865184e-05,
1024
- "loss": 0.9094,
1025
- "step": 145
1026
- },
1027
- {
1028
- "epoch": 0.18010794140323824,
1029
- "grad_norm": 2.5625,
1030
- "learning_rate": 1.4470106431701167e-05,
1031
- "loss": 0.8588,
1032
- "step": 146
1033
- },
1034
- {
1035
- "epoch": 0.18134155744024671,
1036
- "grad_norm": 3.0,
1037
- "learning_rate": 1.4462022125361049e-05,
1038
- "loss": 0.91,
1039
- "step": 147
1040
- },
1041
- {
1042
- "epoch": 0.18257517347725521,
1043
- "grad_norm": 2.640625,
1044
- "learning_rate": 1.4453878909250906e-05,
1045
- "loss": 0.8121,
1046
- "step": 148
1047
- },
1048
- {
1049
- "epoch": 0.1838087895142637,
1050
- "grad_norm": 2.75,
1051
- "learning_rate": 1.4445676852275284e-05,
1052
- "loss": 0.7903,
1053
- "step": 149
1054
- },
1055
- {
1056
- "epoch": 0.18504240555127216,
1057
- "grad_norm": 3.0625,
1058
- "learning_rate": 1.443741602383662e-05,
1059
- "loss": 0.9914,
1060
- "step": 150
1061
- },
1062
- {
1063
- "epoch": 0.18627602158828066,
1064
- "grad_norm": 2.953125,
1065
- "learning_rate": 1.4429096493834651e-05,
1066
- "loss": 0.888,
1067
- "step": 151
1068
- },
1069
- {
1070
- "epoch": 0.18750963762528913,
1071
- "grad_norm": 2.65625,
1072
- "learning_rate": 1.4420718332665817e-05,
1073
- "loss": 0.9122,
1074
- "step": 152
1075
- },
1076
- {
1077
- "epoch": 0.1887432536622976,
1078
- "grad_norm": 2.53125,
1079
- "learning_rate": 1.441228161122268e-05,
1080
- "loss": 0.7929,
1081
- "step": 153
1082
- },
1083
- {
1084
- "epoch": 0.18997686969930608,
1085
- "grad_norm": 3.046875,
1086
- "learning_rate": 1.4403786400893304e-05,
1087
- "loss": 0.8813,
1088
- "step": 154
1089
- },
1090
- {
1091
- "epoch": 0.19121048573631458,
1092
- "grad_norm": 2.453125,
1093
- "learning_rate": 1.4395232773560669e-05,
1094
- "loss": 0.8264,
1095
- "step": 155
1096
- },
1097
- {
1098
- "epoch": 0.19244410177332305,
1099
- "grad_norm": 2.578125,
1100
- "learning_rate": 1.4386620801602056e-05,
1101
- "loss": 0.7507,
1102
- "step": 156
1103
- },
1104
- {
1105
- "epoch": 0.19367771781033152,
1106
- "grad_norm": 2.5625,
1107
- "learning_rate": 1.437795055788843e-05,
1108
- "loss": 0.8193,
1109
- "step": 157
1110
- },
1111
- {
1112
- "epoch": 0.19491133384734002,
1113
- "grad_norm": 2.671875,
1114
- "learning_rate": 1.4369222115783834e-05,
1115
- "loss": 0.8513,
1116
- "step": 158
1117
- },
1118
- {
1119
- "epoch": 0.1961449498843485,
1120
- "grad_norm": 2.734375,
1121
- "learning_rate": 1.4360435549144754e-05,
1122
- "loss": 0.8354,
1123
- "step": 159
1124
- },
1125
- {
1126
- "epoch": 0.19737856592135697,
1127
- "grad_norm": 2.671875,
1128
- "learning_rate": 1.4351590932319506e-05,
1129
- "loss": 0.9582,
1130
- "step": 160
1131
- },
1132
- {
1133
- "epoch": 0.19861218195836547,
1134
- "grad_norm": 3.234375,
1135
- "learning_rate": 1.4342688340147608e-05,
1136
- "loss": 0.7834,
1137
- "step": 161
1138
- },
1139
- {
1140
- "epoch": 0.19984579799537394,
1141
- "grad_norm": 2.703125,
1142
- "learning_rate": 1.4333727847959127e-05,
1143
- "loss": 0.8968,
1144
- "step": 162
1145
- },
1146
- {
1147
- "epoch": 0.20107941403238241,
1148
- "grad_norm": 2.921875,
1149
- "learning_rate": 1.4324709531574074e-05,
1150
- "loss": 0.8036,
1151
- "step": 163
1152
- },
1153
- {
1154
- "epoch": 0.20231303006939091,
1155
- "grad_norm": 2.875,
1156
- "learning_rate": 1.4315633467301734e-05,
1157
- "loss": 0.8167,
1158
- "step": 164
1159
- },
1160
- {
1161
- "epoch": 0.2035466461063994,
1162
- "grad_norm": 2.46875,
1163
- "learning_rate": 1.4306499731940028e-05,
1164
- "loss": 0.9044,
1165
- "step": 165
1166
- },
1167
- {
1168
- "epoch": 0.20478026214340786,
1169
- "grad_norm": 2.921875,
1170
- "learning_rate": 1.4297308402774876e-05,
1171
- "loss": 0.9659,
1172
- "step": 166
1173
- },
1174
- {
1175
- "epoch": 0.20601387818041633,
1176
- "grad_norm": 2.46875,
1177
- "learning_rate": 1.4288059557579525e-05,
1178
- "loss": 0.7808,
1179
- "step": 167
1180
- },
1181
- {
1182
- "epoch": 0.20724749421742483,
1183
- "grad_norm": 2.875,
1184
- "learning_rate": 1.4278753274613905e-05,
1185
- "loss": 0.8324,
1186
- "step": 168
1187
- },
1188
- {
1189
- "epoch": 0.2084811102544333,
1190
- "grad_norm": 2.921875,
1191
- "learning_rate": 1.4269389632623956e-05,
1192
- "loss": 0.9517,
1193
- "step": 169
1194
- },
1195
- {
1196
- "epoch": 0.20971472629144178,
1197
- "grad_norm": 2.765625,
1198
- "learning_rate": 1.4259968710840966e-05,
1199
- "loss": 0.8388,
1200
- "step": 170
1201
- },
1202
- {
1203
- "epoch": 0.21094834232845028,
1204
- "grad_norm": 3.3125,
1205
- "learning_rate": 1.4250490588980909e-05,
1206
- "loss": 0.9859,
1207
- "step": 171
1208
- },
1209
- {
1210
- "epoch": 0.21218195836545875,
1211
- "grad_norm": 3.0625,
1212
- "learning_rate": 1.4240955347243754e-05,
1213
- "loss": 0.9722,
1214
- "step": 172
1215
- },
1216
- {
1217
- "epoch": 0.21341557440246722,
1218
- "grad_norm": 3.46875,
1219
- "learning_rate": 1.4231363066312796e-05,
1220
- "loss": 0.8547,
1221
- "step": 173
1222
- },
1223
- {
1224
- "epoch": 0.21464919043947572,
1225
- "grad_norm": 2.78125,
1226
- "learning_rate": 1.4221713827353977e-05,
1227
- "loss": 0.9056,
1228
- "step": 174
1229
- },
1230
- {
1231
- "epoch": 0.2158828064764842,
1232
- "grad_norm": 2.921875,
1233
- "learning_rate": 1.4212007712015189e-05,
1234
- "loss": 0.9332,
1235
- "step": 175
1236
- },
1237
- {
1238
- "epoch": 0.21711642251349267,
1239
- "grad_norm": 2.6875,
1240
- "learning_rate": 1.4202244802425593e-05,
1241
- "loss": 0.8194,
1242
- "step": 176
1243
- },
1244
- {
1245
- "epoch": 0.21835003855050117,
1246
- "grad_norm": 2.828125,
1247
- "learning_rate": 1.4192425181194916e-05,
1248
- "loss": 0.8258,
1249
- "step": 177
1250
- },
1251
- {
1252
- "epoch": 0.21958365458750964,
1253
- "grad_norm": 2.546875,
1254
- "learning_rate": 1.4182548931412758e-05,
1255
- "loss": 0.8196,
1256
- "step": 178
1257
- },
1258
- {
1259
- "epoch": 0.2208172706245181,
1260
- "grad_norm": 2.84375,
1261
- "learning_rate": 1.417261613664789e-05,
1262
- "loss": 0.9566,
1263
- "step": 179
1264
- },
1265
- {
1266
- "epoch": 0.2220508866615266,
1267
- "grad_norm": 2.734375,
1268
- "learning_rate": 1.4162626880947532e-05,
1269
- "loss": 0.8546,
1270
- "step": 180
1271
- },
1272
- {
1273
- "epoch": 0.2232845026985351,
1274
- "grad_norm": 2.640625,
1275
- "learning_rate": 1.4152581248836662e-05,
1276
- "loss": 0.8267,
1277
- "step": 181
1278
- },
1279
- {
1280
- "epoch": 0.22451811873554356,
1281
- "grad_norm": 2.8125,
1282
- "learning_rate": 1.4142479325317296e-05,
1283
- "loss": 0.8538,
1284
- "step": 182
1285
- },
1286
- {
1287
- "epoch": 0.22575173477255203,
1288
- "grad_norm": 2.75,
1289
- "learning_rate": 1.4132321195867752e-05,
1290
- "loss": 0.905,
1291
- "step": 183
1292
- },
1293
- {
1294
- "epoch": 0.22698535080956053,
1295
- "grad_norm": 2.40625,
1296
- "learning_rate": 1.4122106946441953e-05,
1297
- "loss": 0.7483,
1298
- "step": 184
1299
- },
1300
- {
1301
- "epoch": 0.228218966846569,
1302
- "grad_norm": 2.59375,
1303
- "learning_rate": 1.4111836663468674e-05,
1304
- "loss": 0.794,
1305
- "step": 185
1306
- },
1307
- {
1308
- "epoch": 0.22945258288357748,
1309
- "grad_norm": 2.515625,
1310
- "learning_rate": 1.4101510433850832e-05,
1311
- "loss": 0.8334,
1312
- "step": 186
1313
- },
1314
- {
1315
- "epoch": 0.23068619892058598,
1316
- "grad_norm": 2.703125,
1317
- "learning_rate": 1.409112834496474e-05,
1318
- "loss": 0.9246,
1319
- "step": 187
1320
- },
1321
- {
1322
- "epoch": 0.23191981495759445,
1323
- "grad_norm": 2.828125,
1324
- "learning_rate": 1.4080690484659364e-05,
1325
- "loss": 0.9389,
1326
- "step": 188
1327
- },
1328
- {
1329
- "epoch": 0.23315343099460292,
1330
- "grad_norm": 2.34375,
1331
- "learning_rate": 1.407019694125559e-05,
1332
- "loss": 0.8251,
1333
- "step": 189
1334
- },
1335
- {
1336
- "epoch": 0.23438704703161142,
1337
- "grad_norm": 2.71875,
1338
- "learning_rate": 1.4059647803545468e-05,
1339
- "loss": 0.8254,
1340
- "step": 190
1341
- },
1342
- {
1343
- "epoch": 0.2356206630686199,
1344
- "grad_norm": 2.921875,
1345
- "learning_rate": 1.404904316079147e-05,
1346
- "loss": 0.836,
1347
- "step": 191
1348
- },
1349
- {
1350
- "epoch": 0.23685427910562837,
1351
- "grad_norm": 2.609375,
1352
- "learning_rate": 1.4038383102725718e-05,
1353
- "loss": 0.7996,
1354
- "step": 192
1355
- },
1356
- {
1357
- "epoch": 0.23808789514263684,
1358
- "grad_norm": 2.734375,
1359
- "learning_rate": 1.4027667719549248e-05,
1360
- "loss": 0.8071,
1361
- "step": 193
1362
- },
1363
- {
1364
- "epoch": 0.23932151117964534,
1365
- "grad_norm": 2.6875,
1366
- "learning_rate": 1.4016897101931226e-05,
1367
- "loss": 0.871,
1368
- "step": 194
1369
- },
1370
- {
1371
- "epoch": 0.2405551272166538,
1372
- "grad_norm": 2.984375,
1373
- "learning_rate": 1.4006071341008194e-05,
1374
- "loss": 0.8901,
1375
- "step": 195
1376
- },
1377
- {
1378
- "epoch": 0.24178874325366229,
1379
- "grad_norm": 2.484375,
1380
- "learning_rate": 1.3995190528383292e-05,
1381
- "loss": 0.7841,
1382
- "step": 196
1383
- },
1384
- {
1385
- "epoch": 0.2430223592906708,
1386
- "grad_norm": 2.828125,
1387
- "learning_rate": 1.398425475612548e-05,
1388
- "loss": 0.9283,
1389
- "step": 197
1390
- },
1391
- {
1392
- "epoch": 0.24425597532767926,
1393
- "grad_norm": 2.546875,
1394
- "learning_rate": 1.3973264116768773e-05,
1395
- "loss": 0.8176,
1396
- "step": 198
1397
- },
1398
- {
1399
- "epoch": 0.24548959136468773,
1400
- "grad_norm": 2.453125,
1401
- "learning_rate": 1.3962218703311444e-05,
1402
- "loss": 0.7888,
1403
- "step": 199
1404
- },
1405
- {
1406
- "epoch": 0.24672320740169623,
1407
- "grad_norm": 2.828125,
1408
- "learning_rate": 1.3951118609215242e-05,
1409
- "loss": 0.9003,
1410
- "step": 200
1411
- },
1412
- {
1413
- "epoch": 0.2479568234387047,
1414
- "grad_norm": 2.828125,
1415
- "learning_rate": 1.39399639284046e-05,
1416
- "loss": 0.9171,
1417
- "step": 201
1418
- },
1419
- {
1420
- "epoch": 0.24919043947571318,
1421
- "grad_norm": 2.921875,
1422
- "learning_rate": 1.3928754755265844e-05,
1423
- "loss": 0.9043,
1424
- "step": 202
1425
- },
1426
- {
1427
- "epoch": 0.2504240555127217,
1428
- "grad_norm": 2.734375,
1429
- "learning_rate": 1.391749118464639e-05,
1430
- "loss": 0.9581,
1431
- "step": 203
1432
- },
1433
- {
1434
- "epoch": 0.2516576715497301,
1435
- "grad_norm": 2.703125,
1436
- "learning_rate": 1.3906173311853943e-05,
1437
- "loss": 0.8983,
1438
- "step": 204
1439
- },
1440
- {
1441
- "epoch": 0.2528912875867386,
1442
- "grad_norm": 2.734375,
1443
- "learning_rate": 1.3894801232655692e-05,
1444
- "loss": 0.7514,
1445
- "step": 205
1446
- },
1447
- {
1448
- "epoch": 0.2541249036237471,
1449
- "grad_norm": 3.78125,
1450
- "learning_rate": 1.3883375043277498e-05,
1451
- "loss": 1.0556,
1452
- "step": 206
1453
- },
1454
- {
1455
- "epoch": 0.25535851966075557,
1456
- "grad_norm": 3.125,
1457
- "learning_rate": 1.387189484040308e-05,
1458
- "loss": 0.9795,
1459
- "step": 207
1460
- },
1461
- {
1462
- "epoch": 0.25659213569776407,
1463
- "grad_norm": 2.8125,
1464
- "learning_rate": 1.3860360721173195e-05,
1465
- "loss": 0.8939,
1466
- "step": 208
1467
- },
1468
- {
1469
- "epoch": 0.25782575173477257,
1470
- "grad_norm": 2.671875,
1471
- "learning_rate": 1.384877278318482e-05,
1472
- "loss": 0.7896,
1473
- "step": 209
1474
- },
1475
- {
1476
- "epoch": 0.259059367771781,
1477
- "grad_norm": 2.84375,
1478
- "learning_rate": 1.3837131124490328e-05,
1479
- "loss": 0.928,
1480
- "step": 210
1481
- },
1482
- {
1483
- "epoch": 0.2602929838087895,
1484
- "grad_norm": 2.625,
1485
- "learning_rate": 1.3825435843596644e-05,
1486
- "loss": 0.8116,
1487
- "step": 211
1488
- },
1489
- {
1490
- "epoch": 0.261526599845798,
1491
- "grad_norm": 2.65625,
1492
- "learning_rate": 1.3813687039464431e-05,
1493
- "loss": 0.8786,
1494
- "step": 212
1495
- },
1496
- {
1497
- "epoch": 0.26276021588280646,
1498
- "grad_norm": 2.734375,
1499
- "learning_rate": 1.3801884811507244e-05,
1500
- "loss": 0.8351,
1501
- "step": 213
1502
- },
1503
- {
1504
- "epoch": 0.26399383191981496,
1505
- "grad_norm": 2.875,
1506
- "learning_rate": 1.3790029259590681e-05,
1507
- "loss": 1.0575,
1508
- "step": 214
1509
- },
1510
- {
1511
- "epoch": 0.26522744795682346,
1512
- "grad_norm": 2.78125,
1513
- "learning_rate": 1.3778120484031554e-05,
1514
- "loss": 0.9084,
1515
- "step": 215
1516
- },
1517
- {
1518
- "epoch": 0.2664610639938319,
1519
- "grad_norm": 2.890625,
1520
- "learning_rate": 1.3766158585597025e-05,
1521
- "loss": 0.8379,
1522
- "step": 216
1523
- },
1524
- {
1525
- "epoch": 0.2676946800308404,
1526
- "grad_norm": 2.53125,
1527
- "learning_rate": 1.3754143665503761e-05,
1528
- "loss": 0.7727,
1529
- "step": 217
1530
- },
1531
- {
1532
- "epoch": 0.2689282960678489,
1533
- "grad_norm": 2.796875,
1534
- "learning_rate": 1.3742075825417085e-05,
1535
- "loss": 0.8714,
1536
- "step": 218
1537
- },
1538
- {
1539
- "epoch": 0.27016191210485735,
1540
- "grad_norm": 2.8125,
1541
- "learning_rate": 1.3729955167450092e-05,
1542
- "loss": 0.8959,
1543
- "step": 219
1544
- },
1545
- {
1546
- "epoch": 0.27139552814186585,
1547
- "grad_norm": 2.703125,
1548
- "learning_rate": 1.3717781794162813e-05,
1549
- "loss": 0.8023,
1550
- "step": 220
1551
- },
1552
- {
1553
- "epoch": 0.27262914417887435,
1554
- "grad_norm": 2.625,
1555
- "learning_rate": 1.3705555808561329e-05,
1556
- "loss": 0.8788,
1557
- "step": 221
1558
- },
1559
- {
1560
- "epoch": 0.2738627602158828,
1561
- "grad_norm": 2.671875,
1562
- "learning_rate": 1.3693277314096907e-05,
1563
- "loss": 0.8071,
1564
- "step": 222
1565
- },
1566
- {
1567
- "epoch": 0.2750963762528913,
1568
- "grad_norm": 2.984375,
1569
- "learning_rate": 1.3680946414665117e-05,
1570
- "loss": 1.037,
1571
- "step": 223
1572
- },
1573
- {
1574
- "epoch": 0.2763299922898998,
1575
- "grad_norm": 2.609375,
1576
- "learning_rate": 1.3668563214604968e-05,
1577
- "loss": 0.8609,
1578
- "step": 224
1579
- },
1580
- {
1581
- "epoch": 0.27756360832690824,
1582
- "grad_norm": 2.6875,
1583
- "learning_rate": 1.3656127818698005e-05,
1584
- "loss": 0.8023,
1585
- "step": 225
1586
- },
1587
- {
1588
- "epoch": 0.27879722436391674,
1589
- "grad_norm": 2.9375,
1590
- "learning_rate": 1.364364033216744e-05,
1591
- "loss": 0.8773,
1592
- "step": 226
1593
- },
1594
- {
1595
- "epoch": 0.2800308404009252,
1596
- "grad_norm": 2.875,
1597
- "learning_rate": 1.363110086067725e-05,
1598
- "loss": 0.8701,
1599
- "step": 227
1600
- },
1601
- {
1602
- "epoch": 0.2812644564379337,
1603
- "grad_norm": 3.0,
1604
- "learning_rate": 1.3618509510331292e-05,
1605
- "loss": 1.0324,
1606
- "step": 228
1607
- },
1608
- {
1609
- "epoch": 0.2824980724749422,
1610
- "grad_norm": 2.421875,
1611
- "learning_rate": 1.3605866387672396e-05,
1612
- "loss": 0.7342,
1613
- "step": 229
1614
- },
1615
- {
1616
- "epoch": 0.28373168851195063,
1617
- "grad_norm": 3.0625,
1618
- "learning_rate": 1.3593171599681469e-05,
1619
- "loss": 1.0176,
1620
- "step": 230
1621
- },
1622
- {
1623
- "epoch": 0.28496530454895913,
1624
- "grad_norm": 2.78125,
1625
- "learning_rate": 1.3580425253776593e-05,
1626
- "loss": 0.7673,
1627
- "step": 231
1628
- },
1629
- {
1630
- "epoch": 0.28619892058596763,
1631
- "grad_norm": 2.4375,
1632
- "learning_rate": 1.3567627457812107e-05,
1633
- "loss": 0.7595,
1634
- "step": 232
1635
- },
1636
- {
1637
- "epoch": 0.2874325366229761,
1638
- "grad_norm": 2.734375,
1639
- "learning_rate": 1.35547783200777e-05,
1640
- "loss": 0.8567,
1641
- "step": 233
1642
- },
1643
- {
1644
- "epoch": 0.2886661526599846,
1645
- "grad_norm": 2.546875,
1646
- "learning_rate": 1.3541877949297497e-05,
1647
- "loss": 0.7637,
1648
- "step": 234
1649
- },
1650
- {
1651
- "epoch": 0.2898997686969931,
1652
- "grad_norm": 2.765625,
1653
- "learning_rate": 1.3528926454629128e-05,
1654
- "loss": 0.8102,
1655
- "step": 235
1656
- },
1657
- {
1658
- "epoch": 0.2911333847340015,
1659
- "grad_norm": 2.78125,
1660
- "learning_rate": 1.3515923945662829e-05,
1661
- "loss": 0.8473,
1662
- "step": 236
1663
- },
1664
- {
1665
- "epoch": 0.29236700077101,
1666
- "grad_norm": 3.296875,
1667
- "learning_rate": 1.3502870532420477e-05,
1668
- "loss": 0.8666,
1669
- "step": 237
1670
- },
1671
- {
1672
- "epoch": 0.2936006168080185,
1673
- "grad_norm": 2.78125,
1674
- "learning_rate": 1.3489766325354697e-05,
1675
- "loss": 0.8621,
1676
- "step": 238
1677
- },
1678
- {
1679
- "epoch": 0.29483423284502697,
1680
- "grad_norm": 2.71875,
1681
- "learning_rate": 1.3476611435347898e-05,
1682
- "loss": 0.8762,
1683
- "step": 239
1684
- },
1685
- {
1686
- "epoch": 0.29606784888203547,
1687
- "grad_norm": 2.671875,
1688
- "learning_rate": 1.3463405973711359e-05,
1689
- "loss": 0.834,
1690
- "step": 240
1691
- },
1692
- {
1693
- "epoch": 0.29730146491904397,
1694
- "grad_norm": 2.671875,
1695
- "learning_rate": 1.3450150052184264e-05,
1696
- "loss": 0.8045,
1697
- "step": 241
1698
- },
1699
- {
1700
- "epoch": 0.2985350809560524,
1701
- "grad_norm": 2.796875,
1702
- "learning_rate": 1.3436843782932776e-05,
1703
- "loss": 0.8966,
1704
- "step": 242
1705
- },
1706
- {
1707
- "epoch": 0.2997686969930609,
1708
- "grad_norm": 2.625,
1709
- "learning_rate": 1.3423487278549074e-05,
1710
- "loss": 0.816,
1711
- "step": 243
1712
- },
1713
- {
1714
- "epoch": 0.3010023130300694,
1715
- "grad_norm": 2.9375,
1716
- "learning_rate": 1.3410080652050414e-05,
1717
- "loss": 1.0124,
1718
- "step": 244
1719
- },
1720
- {
1721
- "epoch": 0.30223592906707786,
1722
- "grad_norm": 3.4375,
1723
- "learning_rate": 1.3396624016878157e-05,
1724
- "loss": 0.9205,
1725
- "step": 245
1726
- },
1727
- {
1728
- "epoch": 0.30346954510408636,
1729
- "grad_norm": 2.734375,
1730
- "learning_rate": 1.3383117486896819e-05,
1731
- "loss": 0.8574,
1732
- "step": 246
1733
- },
1734
- {
1735
- "epoch": 0.30470316114109486,
1736
- "grad_norm": 2.546875,
1737
- "learning_rate": 1.3369561176393105e-05,
1738
- "loss": 0.7445,
1739
- "step": 247
1740
- },
1741
- {
1742
- "epoch": 0.3059367771781033,
1743
- "grad_norm": 2.671875,
1744
- "learning_rate": 1.3355955200074944e-05,
1745
- "loss": 0.8033,
1746
- "step": 248
1747
- },
1748
- {
1749
- "epoch": 0.3071703932151118,
1750
- "grad_norm": 2.609375,
1751
- "learning_rate": 1.3342299673070518e-05,
1752
- "loss": 0.7991,
1753
- "step": 249
1754
- },
1755
- {
1756
- "epoch": 0.3084040092521203,
1757
- "grad_norm": 2.921875,
1758
- "learning_rate": 1.3328594710927282e-05,
1759
- "loss": 0.845,
1760
- "step": 250
1761
- },
1762
- {
1763
- "epoch": 0.30963762528912875,
1764
- "grad_norm": 2.84375,
1765
- "learning_rate": 1.3314840429610994e-05,
1766
- "loss": 0.8651,
1767
- "step": 251
1768
- },
1769
- {
1770
- "epoch": 0.31087124132613725,
1771
- "grad_norm": 3.1875,
1772
- "learning_rate": 1.3301036945504729e-05,
1773
- "loss": 0.8845,
1774
- "step": 252
1775
- },
1776
- {
1777
- "epoch": 0.3121048573631457,
1778
- "grad_norm": 2.765625,
1779
- "learning_rate": 1.32871843754079e-05,
1780
- "loss": 0.8365,
1781
- "step": 253
1782
- },
1783
- {
1784
- "epoch": 0.3133384734001542,
1785
- "grad_norm": 3.140625,
1786
- "learning_rate": 1.3273282836535258e-05,
1787
- "loss": 0.944,
1788
- "step": 254
1789
- },
1790
- {
1791
- "epoch": 0.3145720894371627,
1792
- "grad_norm": 2.75,
1793
- "learning_rate": 1.3259332446515915e-05,
1794
- "loss": 0.8001,
1795
- "step": 255
1796
- },
1797
- {
1798
- "epoch": 0.31580570547417114,
1799
- "grad_norm": 2.609375,
1800
- "learning_rate": 1.3245333323392335e-05,
1801
- "loss": 0.8206,
1802
- "step": 256
1803
- },
1804
- {
1805
- "epoch": 0.31703932151117964,
1806
- "grad_norm": 2.953125,
1807
- "learning_rate": 1.3231285585619347e-05,
1808
- "loss": 0.9388,
1809
- "step": 257
1810
- },
1811
- {
1812
- "epoch": 0.31827293754818814,
1813
- "grad_norm": 2.90625,
1814
- "learning_rate": 1.3217189352063137e-05,
1815
- "loss": 0.9575,
1816
- "step": 258
1817
- },
1818
- {
1819
- "epoch": 0.3195065535851966,
1820
- "grad_norm": 2.703125,
1821
- "learning_rate": 1.3203044742000232e-05,
1822
- "loss": 0.8216,
1823
- "step": 259
1824
- },
1825
- {
1826
- "epoch": 0.3207401696222051,
1827
- "grad_norm": 3.25,
1828
- "learning_rate": 1.3188851875116517e-05,
1829
- "loss": 0.8773,
1830
- "step": 260
1831
- },
1832
- {
1833
- "epoch": 0.3219737856592136,
1834
- "grad_norm": 2.5625,
1835
- "learning_rate": 1.3174610871506197e-05,
1836
- "loss": 0.7536,
1837
- "step": 261
1838
- },
1839
- {
1840
- "epoch": 0.32320740169622203,
1841
- "grad_norm": 3.234375,
1842
- "learning_rate": 1.316032185167079e-05,
1843
- "loss": 0.9915,
1844
- "step": 262
1845
- },
1846
- {
1847
- "epoch": 0.32444101773323053,
1848
- "grad_norm": 2.671875,
1849
- "learning_rate": 1.3145984936518113e-05,
1850
- "loss": 0.7831,
1851
- "step": 263
1852
- }
1853
- ],
1854
- "logging_steps": 1,
1855
- "max_steps": 1095,
1856
- "num_input_tokens_seen": 0,
1857
- "num_train_epochs": 2,
1858
- "save_steps": 263,
1859
- "stateful_callbacks": {
1860
- "TrainerControl": {
1861
- "args": {
1862
- "should_epoch_stop": false,
1863
- "should_evaluate": false,
1864
- "should_log": false,
1865
- "should_save": true,
1866
- "should_training_stop": false
1867
- },
1868
- "attributes": {}
1869
- }
1870
- },
1871
- "total_flos": 8.54765681289696e+16,
1872
- "train_batch_size": 1,
1873
- "trial_name": null,
1874
- "trial_params": null
1875
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e820973b850a8a27748f78ed62e9249dc3221b0b56cb992844b2506032fb8870
3
- size 6353