Hugging Face's logo

WalidBouss
/
one_vision-visual_cot-38k_samples

Safetensors
llava
Model card Files
xet
Community
WalidBouss commited on
Commit
ac8cd63
·
verified ·
1 Parent(s): d1aaf5c

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. added_tokens.json +6 -0
  2. config.json +94 -0
  3. generation_config.json +14 -0
  4. model.safetensors.index.json +772 -0
  5. special_tokens_map.json +20 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +53 -0
  8. trainer_state.json +2133 -0
  9. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lmms-lab/llava-onevision-qwen2-7b-si",
3
+ "add_faster_video": false,
4
+ "add_time_instruction": false,
5
+ "architectures": [
6
+ "LlavaQwenForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 151643,
10
+ "eos_token_id": 151645,
11
+ "faster_token_stride": 10,
12
+ "force_sample": false,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 3584,
15
+ "ignore_index": -100,
16
+ "image_aspect_ratio": "anyres_max_9",
17
+ "image_crop_resolution": null,
18
+ "image_grid_pinpoints": [
19
+ [
20
+ 384,
21
+ 384
22
+ ],
23
+ [
24
+ 384,
25
+ 768
26
+ ],
27
+ [
28
+ 768,
29
+ 384
30
+ ],
31
+ [
32
+ 768,
33
+ 768
34
+ ]
35
+ ],
36
+ "image_split_resolution": null,
37
+ "image_token_index": 151646,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 18944,
40
+ "max_position_embeddings": 32768,
41
+ "max_window_layers": 28,
42
+ "mm_hidden_size": 1152,
43
+ "mm_newline_position": "grid",
44
+ "mm_patch_merge_type": "spatial_unpad",
45
+ "mm_projector_lr": null,
46
+ "mm_projector_type": "mlp2x_gelu",
47
+ "mm_resampler_type": null,
48
+ "mm_spatial_pool_mode": "bilinear",
49
+ "mm_spatial_pool_stride": null,
50
+ "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
51
+ "mm_use_im_patch_token": false,
52
+ "mm_use_im_start_end": false,
53
+ "mm_vision_select_feature": "patch",
54
+ "mm_vision_select_layer": -2,
55
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
56
+ "mm_vision_tower_lr": null,
57
+ "model_type": "llava",
58
+ "num_attention_heads": 28,
59
+ "num_hidden_layers": 28,
60
+ "num_key_value_heads": 4,
61
+ "pos_skipping_range": 4096,
62
+ "projector_hidden_act": "gelu",
63
+ "rms_norm_eps": 1e-06,
64
+ "rope_scaling": null,
65
+ "rope_theta": 1000000.0,
66
+ "sliding_window": 131072,
67
+ "text_config": {
68
+ "model_type": "llama"
69
+ },
70
+ "tie_word_embeddings": false,
71
+ "tokenizer_model_max_length": 16384,
72
+ "tokenizer_padding_side": "right",
73
+ "torch_dtype": "bfloat16",
74
+ "transformers_version": "4.43.1",
75
+ "use_cache": false,
76
+ "use_mm_proj": true,
77
+ "use_pos_skipping": false,
78
+ "use_sliding_window": false,
79
+ "vision_config": {
80
+ "hidden_size": 1024,
81
+ "image_size": 336,
82
+ "intermediate_size": 4096,
83
+ "model_type": "clip_vision_model",
84
+ "num_attention_heads": 16,
85
+ "num_hidden_layers": 24,
86
+ "patch_size": 14,
87
+ "projection_dim": 768,
88
+ "vocab_size": 32000
89
+ },
90
+ "vision_feature_layer": -2,
91
+ "vision_feature_select_strategy": "default",
92
+ "vision_tower_pretrained": null,
93
+ "vocab_size": 152064
94
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.43.1"
14
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,772 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060697664
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.image_newline": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
346
+ "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
347
+ "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
348
+ "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
349
+ "model.norm.weight": "model-00003-of-00004.safetensors",
350
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
351
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
352
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
353
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
354
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
355
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
356
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
357
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
358
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
359
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
360
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
361
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
362
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
363
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
364
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
365
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
366
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
367
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
368
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
369
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
370
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
371
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
372
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
373
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
374
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
375
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
760
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
761
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
762
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
763
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
764
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
765
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
766
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
767
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
768
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
769
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
770
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
771
+ }
772
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 16384,
47
+ "pad_token": "<|endoftext|>",
48
+ "padding_side": "right",
49
+ "processor_class": "LlavaProcessor",
50
+ "split_special_tokens": false,
51
+ "tokenizer_class": "Qwen2Tokenizer",
52
+ "unk_token": null
53
+ }
trainer_state.json ADDED
@@ -0,0 +1,2133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.3412726626377533,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0011375755421258443,
13
+ "grad_norm": 7.252706903111892,
14
+ "learning_rate": 7.407407407407407e-07,
15
+ "loss": 1.412,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0022751510842516885,
20
+ "grad_norm": 8.622248143674112,
21
+ "learning_rate": 1.4814814814814815e-06,
22
+ "loss": 1.486,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0034127266263775328,
27
+ "grad_norm": 7.023012815723608,
28
+ "learning_rate": 2.222222222222222e-06,
29
+ "loss": 1.4828,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.004550302168503377,
34
+ "grad_norm": 6.665729995787034,
35
+ "learning_rate": 2.962962962962963e-06,
36
+ "loss": 1.4857,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.005687877710629221,
41
+ "grad_norm": 6.544551660595376,
42
+ "learning_rate": 3.7037037037037037e-06,
43
+ "loss": 1.2733,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0068254532527550656,
48
+ "grad_norm": 5.76674887523466,
49
+ "learning_rate": 4.444444444444444e-06,
50
+ "loss": 1.3368,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.00796302879488091,
55
+ "grad_norm": 3.496668631685638,
56
+ "learning_rate": 5.185185185185185e-06,
57
+ "loss": 1.2026,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.009100604337006754,
62
+ "grad_norm": 2.871434183971456,
63
+ "learning_rate": 5.925925925925926e-06,
64
+ "loss": 1.1447,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.010238179879132598,
69
+ "grad_norm": 4.375669967214979,
70
+ "learning_rate": 6.666666666666667e-06,
71
+ "loss": 1.1398,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.011375755421258443,
76
+ "grad_norm": 2.6750161678621494,
77
+ "learning_rate": 7.4074074074074075e-06,
78
+ "loss": 1.1125,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.012513330963384287,
83
+ "grad_norm": 2.5960245365420795,
84
+ "learning_rate": 8.148148148148148e-06,
85
+ "loss": 1.0485,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.013650906505510131,
90
+ "grad_norm": 2.2437210938587584,
91
+ "learning_rate": 8.888888888888888e-06,
92
+ "loss": 0.9705,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.014788482047635975,
97
+ "grad_norm": 1.7076930327589486,
98
+ "learning_rate": 9.62962962962963e-06,
99
+ "loss": 0.9693,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.01592605758976182,
104
+ "grad_norm": 1.5720016563835741,
105
+ "learning_rate": 1.037037037037037e-05,
106
+ "loss": 0.9268,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.017063633131887666,
111
+ "grad_norm": 1.5049616059812596,
112
+ "learning_rate": 1.1111111111111113e-05,
113
+ "loss": 1.0427,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.018201208674013508,
118
+ "grad_norm": 1.670625778019347,
119
+ "learning_rate": 1.1851851851851852e-05,
120
+ "loss": 0.7984,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.019338784216139354,
125
+ "grad_norm": 1.5156920640819538,
126
+ "learning_rate": 1.2592592592592593e-05,
127
+ "loss": 0.8934,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.020476359758265197,
132
+ "grad_norm": 1.3859154498920394,
133
+ "learning_rate": 1.3333333333333333e-05,
134
+ "loss": 0.9602,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.021613935300391043,
139
+ "grad_norm": 1.3086540529666517,
140
+ "learning_rate": 1.4074074074074075e-05,
141
+ "loss": 0.8253,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.022751510842516885,
146
+ "grad_norm": 1.3062556535833154,
147
+ "learning_rate": 1.4814814814814815e-05,
148
+ "loss": 0.8987,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.02388908638464273,
153
+ "grad_norm": 1.3475867604944103,
154
+ "learning_rate": 1.555555555555556e-05,
155
+ "loss": 0.8483,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.025026661926768574,
160
+ "grad_norm": 1.4066019321159149,
161
+ "learning_rate": 1.6296296296296297e-05,
162
+ "loss": 0.8765,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.02616423746889442,
167
+ "grad_norm": 1.356056753489974,
168
+ "learning_rate": 1.7037037037037038e-05,
169
+ "loss": 0.7376,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.027301813011020262,
174
+ "grad_norm": 1.2273100266100156,
175
+ "learning_rate": 1.7777777777777777e-05,
176
+ "loss": 0.7735,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.028439388553146108,
181
+ "grad_norm": 1.3325688789427055,
182
+ "learning_rate": 1.851851851851852e-05,
183
+ "loss": 0.9376,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.02957696409527195,
188
+ "grad_norm": 1.2459636758267958,
189
+ "learning_rate": 1.925925925925926e-05,
190
+ "loss": 0.7574,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.030714539637397797,
195
+ "grad_norm": 1.2914174266728426,
196
+ "learning_rate": 2e-05,
197
+ "loss": 0.8459,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.03185211517952364,
202
+ "grad_norm": 1.1150255281605015,
203
+ "learning_rate": 1.999993201860564e-05,
204
+ "loss": 0.9413,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.032989690721649485,
209
+ "grad_norm": 1.1925573330854713,
210
+ "learning_rate": 1.9999728075346848e-05,
211
+ "loss": 0.7652,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.03412726626377533,
216
+ "grad_norm": 1.1659470654782442,
217
+ "learning_rate": 1.9999388172996495e-05,
218
+ "loss": 0.9115,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.03526484180590117,
223
+ "grad_norm": 1.1687557894773881,
224
+ "learning_rate": 1.999891231617599e-05,
225
+ "loss": 0.8744,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.036402417348027016,
230
+ "grad_norm": 1.1588348230291718,
231
+ "learning_rate": 1.999830051135521e-05,
232
+ "loss": 0.8677,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.03753999289015286,
237
+ "grad_norm": 1.132149944460972,
238
+ "learning_rate": 1.9997552766852434e-05,
239
+ "loss": 0.9,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.03867756843227871,
244
+ "grad_norm": 1.1863064139153197,
245
+ "learning_rate": 1.9996669092834194e-05,
246
+ "loss": 0.8074,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.03981514397440455,
251
+ "grad_norm": 1.220841646039248,
252
+ "learning_rate": 1.9995649501315172e-05,
253
+ "loss": 0.8674,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.04095271951653039,
258
+ "grad_norm": 1.23854307526539,
259
+ "learning_rate": 1.9994494006158018e-05,
260
+ "loss": 0.9159,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.04209029505865624,
265
+ "grad_norm": 1.090587831686784,
266
+ "learning_rate": 1.9993202623073173e-05,
267
+ "loss": 0.8779,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.043227870600782085,
272
+ "grad_norm": 1.0923548595966273,
273
+ "learning_rate": 1.999177536961863e-05,
274
+ "loss": 0.8266,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.044365446142907924,
279
+ "grad_norm": 1.1486258645801408,
280
+ "learning_rate": 1.9990212265199738e-05,
281
+ "loss": 0.8896,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.04550302168503377,
286
+ "grad_norm": 1.1394380414139478,
287
+ "learning_rate": 1.998851333106889e-05,
288
+ "loss": 0.8282,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.046640597227159616,
293
+ "grad_norm": 1.0624229488933081,
294
+ "learning_rate": 1.9986678590325273e-05,
295
+ "loss": 0.731,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.04777817276928546,
300
+ "grad_norm": 1.0270694900173014,
301
+ "learning_rate": 1.9984708067914533e-05,
302
+ "loss": 0.8598,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.0489157483114113,
307
+ "grad_norm": 1.053755980685397,
308
+ "learning_rate": 1.998260179062844e-05,
309
+ "loss": 0.7883,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.05005332385353715,
314
+ "grad_norm": 1.1027980315848285,
315
+ "learning_rate": 1.9980359787104533e-05,
316
+ "loss": 0.8248,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.05119089939566299,
321
+ "grad_norm": 1.054761323115589,
322
+ "learning_rate": 1.9977982087825714e-05,
323
+ "loss": 0.8647,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.05232847493778884,
328
+ "grad_norm": 1.0147641458879657,
329
+ "learning_rate": 1.9975468725119842e-05,
330
+ "loss": 0.8707,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.05346605047991468,
335
+ "grad_norm": 1.0320732494589604,
336
+ "learning_rate": 1.99728197331593e-05,
337
+ "loss": 0.7407,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.054603626022040525,
342
+ "grad_norm": 1.1478872729853458,
343
+ "learning_rate": 1.9970035147960524e-05,
344
+ "loss": 0.7818,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.05574120156416637,
349
+ "grad_norm": 1.1399868087609295,
350
+ "learning_rate": 1.996711500738351e-05,
351
+ "loss": 0.8373,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.056878777106292217,
356
+ "grad_norm": 1.0526771432986117,
357
+ "learning_rate": 1.99640593511313e-05,
358
+ "loss": 0.8203,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.058016352648418056,
363
+ "grad_norm": 1.0653301252742073,
364
+ "learning_rate": 1.996086822074945e-05,
365
+ "loss": 0.8281,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.0591539281905439,
370
+ "grad_norm": 1.0561063282716783,
371
+ "learning_rate": 1.995754165962546e-05,
372
+ "loss": 0.72,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.06029150373266975,
377
+ "grad_norm": 1.0839260823800712,
378
+ "learning_rate": 1.9954079712988183e-05,
379
+ "loss": 0.791,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.061429079274795594,
384
+ "grad_norm": 1.0146390764424258,
385
+ "learning_rate": 1.995048242790721e-05,
386
+ "loss": 0.7455,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.06256665481692143,
391
+ "grad_norm": 1.0962320578557068,
392
+ "learning_rate": 1.9946749853292233e-05,
393
+ "loss": 0.8347,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.06370423035904728,
398
+ "grad_norm": 1.1182191442676654,
399
+ "learning_rate": 1.9942882039892378e-05,
400
+ "loss": 0.8298,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.06484180590117312,
405
+ "grad_norm": 0.985261942271752,
406
+ "learning_rate": 1.9938879040295508e-05,
407
+ "loss": 0.7321,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.06597938144329897,
412
+ "grad_norm": 1.0605922824848177,
413
+ "learning_rate": 1.993474090892753e-05,
414
+ "loss": 0.864,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.06711695698542482,
419
+ "grad_norm": 1.1264056870803152,
420
+ "learning_rate": 1.9930467702051632e-05,
421
+ "loss": 0.8403,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.06825453252755066,
426
+ "grad_norm": 1.0395490010303334,
427
+ "learning_rate": 1.992605947776752e-05,
428
+ "loss": 0.8243,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.06939210806967651,
433
+ "grad_norm": 1.0708140874889909,
434
+ "learning_rate": 1.9921516296010645e-05,
435
+ "loss": 0.7053,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.07052968361180234,
440
+ "grad_norm": 1.1040066296881672,
441
+ "learning_rate": 1.991683821855137e-05,
442
+ "loss": 0.8089,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.07166725915392819,
447
+ "grad_norm": 1.0964641303072902,
448
+ "learning_rate": 1.9912025308994146e-05,
449
+ "loss": 0.9017,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.07280483469605403,
454
+ "grad_norm": 1.0643750074791034,
455
+ "learning_rate": 1.9907077632776632e-05,
456
+ "loss": 0.8678,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.07394241023817988,
461
+ "grad_norm": 1.0767194772302087,
462
+ "learning_rate": 1.9901995257168808e-05,
463
+ "loss": 0.8098,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.07507998578030572,
468
+ "grad_norm": 0.9814291648591228,
469
+ "learning_rate": 1.989677825127208e-05,
470
+ "loss": 0.9009,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.07621756132243157,
475
+ "grad_norm": 1.0424860021982505,
476
+ "learning_rate": 1.9891426686018308e-05,
477
+ "loss": 0.7733,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.07735513686455742,
482
+ "grad_norm": 1.0702692819494843,
483
+ "learning_rate": 1.9885940634168863e-05,
484
+ "loss": 0.8821,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.07849271240668326,
489
+ "grad_norm": 1.1408260155810739,
490
+ "learning_rate": 1.988032017031364e-05,
491
+ "loss": 0.8307,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.0796302879488091,
496
+ "grad_norm": 1.0327202463855523,
497
+ "learning_rate": 1.9874565370870037e-05,
498
+ "loss": 0.8242,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.08076786349093494,
503
+ "grad_norm": 1.0467929360052353,
504
+ "learning_rate": 1.9868676314081907e-05,
505
+ "loss": 0.8197,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.08190543903306079,
510
+ "grad_norm": 1.0401393378664532,
511
+ "learning_rate": 1.9862653080018508e-05,
512
+ "loss": 0.7963,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.08304301457518663,
517
+ "grad_norm": 1.0193314873859287,
518
+ "learning_rate": 1.985649575057341e-05,
519
+ "loss": 0.7183,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.08418059011731248,
524
+ "grad_norm": 1.1038745628343372,
525
+ "learning_rate": 1.9850204409463387e-05,
526
+ "loss": 0.8222,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.08531816565943832,
531
+ "grad_norm": 1.2332738343888963,
532
+ "learning_rate": 1.9843779142227258e-05,
533
+ "loss": 0.9721,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.08645574120156417,
538
+ "grad_norm": 1.091825396970584,
539
+ "learning_rate": 1.9837220036224755e-05,
540
+ "loss": 0.8735,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.08759331674369002,
545
+ "grad_norm": 1.0836987966746667,
546
+ "learning_rate": 1.983052718063531e-05,
547
+ "loss": 0.8209,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.08873089228581585,
552
+ "grad_norm": 1.1355629551230897,
553
+ "learning_rate": 1.9823700666456854e-05,
554
+ "loss": 0.8062,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.0898684678279417,
559
+ "grad_norm": 1.0972904393016396,
560
+ "learning_rate": 1.981674058650458e-05,
561
+ "loss": 0.79,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.09100604337006754,
566
+ "grad_norm": 1.0822786867657195,
567
+ "learning_rate": 1.9809647035409673e-05,
568
+ "loss": 0.8685,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.09214361891219339,
573
+ "grad_norm": 1.0499861096027099,
574
+ "learning_rate": 1.980242010961803e-05,
575
+ "loss": 0.8869,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.09328119445431923,
580
+ "grad_norm": 1.1565333695689672,
581
+ "learning_rate": 1.9795059907388955e-05,
582
+ "loss": 0.7683,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.09441876999644508,
587
+ "grad_norm": 1.1404697343493142,
588
+ "learning_rate": 1.9787566528793806e-05,
589
+ "loss": 0.8392,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.09555634553857092,
594
+ "grad_norm": 1.0072701040551242,
595
+ "learning_rate": 1.977994007571465e-05,
596
+ "loss": 0.7045,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.09669392108069677,
601
+ "grad_norm": 1.019073621193679,
602
+ "learning_rate": 1.977218065184287e-05,
603
+ "loss": 0.7104,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.0978314966228226,
608
+ "grad_norm": 1.0557815862870046,
609
+ "learning_rate": 1.9764288362677757e-05,
610
+ "loss": 0.7672,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.09896907216494845,
615
+ "grad_norm": 1.1380481668336246,
616
+ "learning_rate": 1.975626331552507e-05,
617
+ "loss": 0.9107,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.1001066477070743,
622
+ "grad_norm": 1.093169407323706,
623
+ "learning_rate": 1.9748105619495593e-05,
624
+ "loss": 0.7914,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.10124422324920014,
629
+ "grad_norm": 1.087351595099475,
630
+ "learning_rate": 1.973981538550364e-05,
631
+ "loss": 0.7814,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.10238179879132599,
636
+ "grad_norm": 1.0728410820828704,
637
+ "learning_rate": 1.9731392726265538e-05,
638
+ "loss": 0.7555,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.10351937433345183,
643
+ "grad_norm": 1.2233426634088327,
644
+ "learning_rate": 1.9722837756298112e-05,
645
+ "loss": 0.818,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.10465694987557768,
650
+ "grad_norm": 1.0575926671469376,
651
+ "learning_rate": 1.971415059191712e-05,
652
+ "loss": 0.7764,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.10579452541770352,
657
+ "grad_norm": 1.088708118649049,
658
+ "learning_rate": 1.9705331351235673e-05,
659
+ "loss": 0.7902,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.10693210095982936,
664
+ "grad_norm": 1.128811241106672,
665
+ "learning_rate": 1.9696380154162628e-05,
666
+ "loss": 0.7237,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.1080696765019552,
671
+ "grad_norm": 1.193909132920539,
672
+ "learning_rate": 1.9687297122400952e-05,
673
+ "loss": 0.8515,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.10920725204408105,
678
+ "grad_norm": 1.0847877557011065,
679
+ "learning_rate": 1.967808237944608e-05,
680
+ "loss": 0.7833,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.1103448275862069,
685
+ "grad_norm": 1.0860109471141504,
686
+ "learning_rate": 1.9668736050584224e-05,
687
+ "loss": 0.87,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.11148240312833274,
692
+ "grad_norm": 1.0232679660737842,
693
+ "learning_rate": 1.9659258262890683e-05,
694
+ "loss": 0.864,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.11261997867045859,
699
+ "grad_norm": 1.0289877842833908,
700
+ "learning_rate": 1.96496491452281e-05,
701
+ "loss": 0.7928,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.11375755421258443,
706
+ "grad_norm": 1.1247393636130563,
707
+ "learning_rate": 1.963990882824472e-05,
708
+ "loss": 0.7534,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.11489512975471028,
713
+ "grad_norm": 1.0570565178567373,
714
+ "learning_rate": 1.96300374443726e-05,
715
+ "loss": 0.8005,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.11603270529683611,
720
+ "grad_norm": 0.9867357643569166,
721
+ "learning_rate": 1.962003512782584e-05,
722
+ "loss": 0.7223,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.11717028083896196,
727
+ "grad_norm": 1.0928156643350972,
728
+ "learning_rate": 1.960990201459872e-05,
729
+ "loss": 0.7677,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.1183078563810878,
734
+ "grad_norm": 1.021316668974268,
735
+ "learning_rate": 1.959963824246387e-05,
736
+ "loss": 0.7598,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.11944543192321365,
741
+ "grad_norm": 1.003907848763008,
742
+ "learning_rate": 1.95892439509704e-05,
743
+ "loss": 0.7464,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.1205830074653395,
748
+ "grad_norm": 1.0107143173657256,
749
+ "learning_rate": 1.9578719281442002e-05,
750
+ "loss": 0.8703,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.12172058300746534,
755
+ "grad_norm": 1.0427993123321293,
756
+ "learning_rate": 1.9568064376975013e-05,
757
+ "loss": 0.8458,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.12285815854959119,
762
+ "grad_norm": 0.9471895655219162,
763
+ "learning_rate": 1.9557279382436483e-05,
764
+ "loss": 0.8744,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.12399573409171703,
769
+ "grad_norm": 1.0474061833411126,
770
+ "learning_rate": 1.9546364444462207e-05,
771
+ "loss": 0.7278,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.12513330963384287,
776
+ "grad_norm": 0.9851209978746495,
777
+ "learning_rate": 1.953531971145473e-05,
778
+ "loss": 0.8167,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.1262708851759687,
783
+ "grad_norm": 1.0280704738378832,
784
+ "learning_rate": 1.9524145333581315e-05,
785
+ "loss": 0.7167,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.12740846071809456,
790
+ "grad_norm": 0.9443890480132111,
791
+ "learning_rate": 1.9512841462771927e-05,
792
+ "loss": 0.8822,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.1285460362602204,
797
+ "grad_norm": 0.9717455193006768,
798
+ "learning_rate": 1.9501408252717136e-05,
799
+ "loss": 0.8707,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.12968361180234625,
804
+ "grad_norm": 1.092473392232703,
805
+ "learning_rate": 1.9489845858866066e-05,
806
+ "loss": 0.7959,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.1308211873444721,
811
+ "grad_norm": 1.1056495100925654,
812
+ "learning_rate": 1.947815443842424e-05,
813
+ "loss": 0.7132,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.13195876288659794,
818
+ "grad_norm": 1.0058537198089237,
819
+ "learning_rate": 1.9466334150351475e-05,
820
+ "loss": 0.8592,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.1330963384287238,
825
+ "grad_norm": 1.0234629362307024,
826
+ "learning_rate": 1.9454385155359704e-05,
827
+ "loss": 0.7982,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.13423391397084963,
832
+ "grad_norm": 0.9907144940751352,
833
+ "learning_rate": 1.9442307615910793e-05,
834
+ "loss": 0.7626,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.13537148951297548,
839
+ "grad_norm": 1.0610884551525839,
840
+ "learning_rate": 1.9430101696214335e-05,
841
+ "loss": 0.7694,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.13650906505510133,
846
+ "grad_norm": 1.136255401471595,
847
+ "learning_rate": 1.9417767562225422e-05,
848
+ "loss": 0.8427,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.13764664059722717,
853
+ "grad_norm": 0.983990428831828,
854
+ "learning_rate": 1.9405305381642376e-05,
855
+ "loss": 0.8446,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.13878421613935302,
860
+ "grad_norm": 1.1301380622416057,
861
+ "learning_rate": 1.9392715323904483e-05,
862
+ "loss": 0.7658,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.13992179168147884,
867
+ "grad_norm": 1.0031223316843825,
868
+ "learning_rate": 1.9379997560189677e-05,
869
+ "loss": 0.7684,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.14105936722360468,
874
+ "grad_norm": 1.0654113241033707,
875
+ "learning_rate": 1.936715226341222e-05,
876
+ "loss": 0.781,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.14219694276573053,
881
+ "grad_norm": 0.9271001409058074,
882
+ "learning_rate": 1.9354179608220347e-05,
883
+ "loss": 0.7363,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.14333451830785637,
888
+ "grad_norm": 1.0866976883120223,
889
+ "learning_rate": 1.93410797709939e-05,
890
+ "loss": 0.8719,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.14447209384998222,
895
+ "grad_norm": 1.0143165560250647,
896
+ "learning_rate": 1.9327852929841918e-05,
897
+ "loss": 0.7418,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.14560966939210807,
902
+ "grad_norm": 1.0794908238570715,
903
+ "learning_rate": 1.9314499264600218e-05,
904
+ "loss": 0.9511,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.1467472449342339,
909
+ "grad_norm": 1.0543849611899816,
910
+ "learning_rate": 1.9301018956828966e-05,
911
+ "loss": 0.7261,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.14788482047635976,
916
+ "grad_norm": 0.9853708931945785,
917
+ "learning_rate": 1.9287412189810174e-05,
918
+ "loss": 0.7949,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.1490223960184856,
923
+ "grad_norm": 0.9782889131523694,
924
+ "learning_rate": 1.9273679148545246e-05,
925
+ "loss": 0.7894,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.15015997156061145,
930
+ "grad_norm": 1.0694826655849514,
931
+ "learning_rate": 1.9259820019752445e-05,
932
+ "loss": 0.8288,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.1512975471027373,
937
+ "grad_norm": 0.9707247690290827,
938
+ "learning_rate": 1.9245834991864344e-05,
939
+ "loss": 0.7973,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.15243512264486314,
944
+ "grad_norm": 0.97334767003227,
945
+ "learning_rate": 1.9231724255025286e-05,
946
+ "loss": 0.8146,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.153572698186989,
951
+ "grad_norm": 0.9354396394568825,
952
+ "learning_rate": 1.9217488001088784e-05,
953
+ "loss": 0.7446,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.15471027372911483,
958
+ "grad_norm": 0.9395461051827337,
959
+ "learning_rate": 1.9203126423614916e-05,
960
+ "loss": 0.8077,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.15584784927124068,
965
+ "grad_norm": 0.9750295198016627,
966
+ "learning_rate": 1.9188639717867695e-05,
967
+ "loss": 0.7134,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.15698542481336653,
972
+ "grad_norm": 1.004306726572393,
973
+ "learning_rate": 1.9174028080812415e-05,
974
+ "loss": 0.7295,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.15812300035549234,
979
+ "grad_norm": 1.0670488030887912,
980
+ "learning_rate": 1.9159291711112962e-05,
981
+ "loss": 0.9652,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.1592605758976182,
986
+ "grad_norm": 0.959021129913344,
987
+ "learning_rate": 1.914443080912913e-05,
988
+ "loss": 0.7656,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.16039815143974404,
993
+ "grad_norm": 1.0733667782620868,
994
+ "learning_rate": 1.9129445576913886e-05,
995
+ "loss": 0.7651,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.16153572698186988,
1000
+ "grad_norm": 0.9954726556545452,
1001
+ "learning_rate": 1.9114336218210635e-05,
1002
+ "loss": 0.715,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.16267330252399573,
1007
+ "grad_norm": 0.9972323730973797,
1008
+ "learning_rate": 1.909910293845042e-05,
1009
+ "loss": 0.6975,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.16381087806612157,
1014
+ "grad_norm": 0.9913964052548584,
1015
+ "learning_rate": 1.9083745944749163e-05,
1016
+ "loss": 0.7253,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.16494845360824742,
1021
+ "grad_norm": 0.9819193678083898,
1022
+ "learning_rate": 1.9068265445904838e-05,
1023
+ "loss": 0.7467,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.16608602915037327,
1028
+ "grad_norm": 1.0151841007728057,
1029
+ "learning_rate": 1.905266165239462e-05,
1030
+ "loss": 0.8109,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.1672236046924991,
1035
+ "grad_norm": 0.9838304949608468,
1036
+ "learning_rate": 1.903693477637204e-05,
1037
+ "loss": 0.7765,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.16836118023462496,
1042
+ "grad_norm": 0.942271667758485,
1043
+ "learning_rate": 1.902108503166409e-05,
1044
+ "loss": 0.7697,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.1694987557767508,
1049
+ "grad_norm": 0.9992910291972015,
1050
+ "learning_rate": 1.9005112633768315e-05,
1051
+ "loss": 0.758,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.17063633131887665,
1056
+ "grad_norm": 1.034597439114661,
1057
+ "learning_rate": 1.8989017799849896e-05,
1058
+ "loss": 0.7424,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.1717739068610025,
1063
+ "grad_norm": 0.9794734575939594,
1064
+ "learning_rate": 1.897280074873868e-05,
1065
+ "loss": 0.6354,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.17291148240312834,
1070
+ "grad_norm": 0.9930145480636745,
1071
+ "learning_rate": 1.8956461700926215e-05,
1072
+ "loss": 0.8608,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.1740490579452542,
1077
+ "grad_norm": 1.028876703411256,
1078
+ "learning_rate": 1.8940000878562758e-05,
1079
+ "loss": 0.717,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.17518663348738003,
1084
+ "grad_norm": 0.9475138167941232,
1085
+ "learning_rate": 1.8923418505454238e-05,
1086
+ "loss": 0.7061,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.17632420902950588,
1091
+ "grad_norm": 1.0267930452512193,
1092
+ "learning_rate": 1.8906714807059218e-05,
1093
+ "loss": 0.8186,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.1774617845716317,
1098
+ "grad_norm": 1.0643772128505595,
1099
+ "learning_rate": 1.8889890010485847e-05,
1100
+ "loss": 0.6661,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.17859936011375754,
1105
+ "grad_norm": 1.066349966150257,
1106
+ "learning_rate": 1.8872944344488747e-05,
1107
+ "loss": 0.7617,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.1797369356558834,
1112
+ "grad_norm": 0.9619934443330037,
1113
+ "learning_rate": 1.885587803946592e-05,
1114
+ "loss": 0.7127,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.18087451119800924,
1119
+ "grad_norm": 1.004371603307917,
1120
+ "learning_rate": 1.883869132745561e-05,
1121
+ "loss": 0.7539,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.18201208674013508,
1126
+ "grad_norm": 1.0106558200612026,
1127
+ "learning_rate": 1.8821384442133145e-05,
1128
+ "loss": 0.8286,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.18314966228226093,
1133
+ "grad_norm": 1.0380867326359198,
1134
+ "learning_rate": 1.8803957618807764e-05,
1135
+ "loss": 0.826,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.18428723782438677,
1140
+ "grad_norm": 1.0155843819783557,
1141
+ "learning_rate": 1.878641109441942e-05,
1142
+ "loss": 0.739,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.18542481336651262,
1147
+ "grad_norm": 0.9916382609123128,
1148
+ "learning_rate": 1.876874510753554e-05,
1149
+ "loss": 0.9736,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.18656238890863847,
1154
+ "grad_norm": 0.9382307275493679,
1155
+ "learning_rate": 1.8750959898347828e-05,
1156
+ "loss": 0.8839,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.1876999644507643,
1161
+ "grad_norm": 1.038587474509486,
1162
+ "learning_rate": 1.8733055708668928e-05,
1163
+ "loss": 0.8258,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.18883753999289016,
1168
+ "grad_norm": 1.133352025192882,
1169
+ "learning_rate": 1.871503278192921e-05,
1170
+ "loss": 0.7396,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.189975115535016,
1175
+ "grad_norm": 1.0035615462799168,
1176
+ "learning_rate": 1.8696891363173405e-05,
1177
+ "loss": 0.736,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.19111269107714185,
1182
+ "grad_norm": 0.9854553689824346,
1183
+ "learning_rate": 1.86786316990573e-05,
1184
+ "loss": 0.7483,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.1922502666192677,
1189
+ "grad_norm": 1.0713592511805936,
1190
+ "learning_rate": 1.866025403784439e-05,
1191
+ "loss": 0.7571,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.19338784216139354,
1196
+ "grad_norm": 1.0505443529749097,
1197
+ "learning_rate": 1.8641758629402468e-05,
1198
+ "loss": 0.8198,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.1945254177035194,
1203
+ "grad_norm": 0.999013320748331,
1204
+ "learning_rate": 1.862314572520028e-05,
1205
+ "loss": 0.8081,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.1956629932456452,
1210
+ "grad_norm": 1.0043036302243753,
1211
+ "learning_rate": 1.8604415578304052e-05,
1212
+ "loss": 0.8008,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.19680056878777105,
1217
+ "grad_norm": 0.9628077082215138,
1218
+ "learning_rate": 1.8585568443374087e-05,
1219
+ "loss": 0.7795,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.1979381443298969,
1224
+ "grad_norm": 0.9838858995474212,
1225
+ "learning_rate": 1.8566604576661288e-05,
1226
+ "loss": 0.7328,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.19907571987202274,
1231
+ "grad_norm": 0.9813195544795628,
1232
+ "learning_rate": 1.8547524236003675e-05,
1233
+ "loss": 0.8816,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.2002132954141486,
1238
+ "grad_norm": 0.9499983935703465,
1239
+ "learning_rate": 1.852832768082288e-05,
1240
+ "loss": 0.8321,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.20135087095627444,
1245
+ "grad_norm": 1.0242912390679038,
1246
+ "learning_rate": 1.850901517212062e-05,
1247
+ "loss": 0.715,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.20248844649840028,
1252
+ "grad_norm": 1.0605111053806962,
1253
+ "learning_rate": 1.8489586972475154e-05,
1254
+ "loss": 0.7838,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.20362602204052613,
1259
+ "grad_norm": 0.9853924717398025,
1260
+ "learning_rate": 1.8470043346037698e-05,
1261
+ "loss": 0.8206,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.20476359758265197,
1266
+ "grad_norm": 0.9475510993055148,
1267
+ "learning_rate": 1.8450384558528848e-05,
1268
+ "loss": 0.8305,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.20590117312477782,
1273
+ "grad_norm": 0.9554542547364111,
1274
+ "learning_rate": 1.843061087723496e-05,
1275
+ "loss": 0.7735,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.20703874866690367,
1280
+ "grad_norm": 0.9392624041198877,
1281
+ "learning_rate": 1.8410722571004524e-05,
1282
+ "loss": 0.7179,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.2081763242090295,
1287
+ "grad_norm": 0.9205638857801508,
1288
+ "learning_rate": 1.8390719910244487e-05,
1289
+ "loss": 0.7482,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.20931389975115536,
1294
+ "grad_norm": 1.0155955750650456,
1295
+ "learning_rate": 1.8370603166916616e-05,
1296
+ "loss": 0.8632,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.2104514752932812,
1301
+ "grad_norm": 0.9256662805897953,
1302
+ "learning_rate": 1.8350372614533753e-05,
1303
+ "loss": 0.7618,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.21158905083540705,
1308
+ "grad_norm": 0.9614934193864958,
1309
+ "learning_rate": 1.8330028528156138e-05,
1310
+ "loss": 0.7873,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.2127266263775329,
1315
+ "grad_norm": 0.9409854803070374,
1316
+ "learning_rate": 1.830957118438764e-05,
1317
+ "loss": 0.7676,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.21386420191965871,
1322
+ "grad_norm": 1.0117832834333376,
1323
+ "learning_rate": 1.8289000861372006e-05,
1324
+ "loss": 0.6853,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.21500177746178456,
1329
+ "grad_norm": 0.9436331107279641,
1330
+ "learning_rate": 1.826831783878909e-05,
1331
+ "loss": 0.7664,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.2161393530039104,
1336
+ "grad_norm": 0.9518709375119045,
1337
+ "learning_rate": 1.8247522397851028e-05,
1338
+ "loss": 0.7979,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.21727692854603625,
1343
+ "grad_norm": 0.950510190670522,
1344
+ "learning_rate": 1.8226614821298444e-05,
1345
+ "loss": 0.9146,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.2184145040881621,
1350
+ "grad_norm": 1.0001640495640078,
1351
+ "learning_rate": 1.820559539339657e-05,
1352
+ "loss": 0.8066,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.21955207963028794,
1357
+ "grad_norm": 1.0515205356048116,
1358
+ "learning_rate": 1.8184464399931414e-05,
1359
+ "loss": 0.7605,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.2206896551724138,
1364
+ "grad_norm": 0.9518221695117551,
1365
+ "learning_rate": 1.8163222128205853e-05,
1366
+ "loss": 0.77,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.22182723071453964,
1371
+ "grad_norm": 0.9658190130336755,
1372
+ "learning_rate": 1.8141868867035745e-05,
1373
+ "loss": 0.7553,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.22296480625666548,
1378
+ "grad_norm": 0.944099728059088,
1379
+ "learning_rate": 1.8120404906745973e-05,
1380
+ "loss": 0.7851,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.22410238179879133,
1385
+ "grad_norm": 0.9818110526183947,
1386
+ "learning_rate": 1.8098830539166536e-05,
1387
+ "loss": 0.7935,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.22523995734091717,
1392
+ "grad_norm": 1.0679918663170498,
1393
+ "learning_rate": 1.8077146057628547e-05,
1394
+ "loss": 0.7782,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.22637753288304302,
1399
+ "grad_norm": 0.9636654090223082,
1400
+ "learning_rate": 1.8055351756960262e-05,
1401
+ "loss": 0.7111,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.22751510842516887,
1406
+ "grad_norm": 1.0273549839107226,
1407
+ "learning_rate": 1.8033447933483076e-05,
1408
+ "loss": 0.7937,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.2286526839672947,
1413
+ "grad_norm": 0.9768073027947863,
1414
+ "learning_rate": 1.8011434885007482e-05,
1415
+ "loss": 0.6585,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.22979025950942056,
1420
+ "grad_norm": 1.0757919457820178,
1421
+ "learning_rate": 1.7989312910829023e-05,
1422
+ "loss": 0.8112,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.2309278350515464,
1427
+ "grad_norm": 1.07129922697845,
1428
+ "learning_rate": 1.796708231172423e-05,
1429
+ "loss": 0.7197,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.23206541059367222,
1434
+ "grad_norm": 0.9064139244148179,
1435
+ "learning_rate": 1.7944743389946524e-05,
1436
+ "loss": 0.8407,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.23320298613579807,
1441
+ "grad_norm": 1.0566497130819101,
1442
+ "learning_rate": 1.792229644922212e-05,
1443
+ "loss": 0.6641,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.23434056167792391,
1448
+ "grad_norm": 1.1821144067979144,
1449
+ "learning_rate": 1.789974179474588e-05,
1450
+ "loss": 0.8014,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.23547813722004976,
1455
+ "grad_norm": 1.004667649949057,
1456
+ "learning_rate": 1.7877079733177185e-05,
1457
+ "loss": 0.7442,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.2366157127621756,
1462
+ "grad_norm": 1.0680994058446738,
1463
+ "learning_rate": 1.7854310572635733e-05,
1464
+ "loss": 0.8034,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.23775328830430145,
1469
+ "grad_norm": 1.0075812686052639,
1470
+ "learning_rate": 1.7831434622697386e-05,
1471
+ "loss": 0.6922,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.2388908638464273,
1476
+ "grad_norm": 1.0078124911781743,
1477
+ "learning_rate": 1.780845219438994e-05,
1478
+ "loss": 0.8086,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.24002843938855314,
1483
+ "grad_norm": 1.0012945867152467,
1484
+ "learning_rate": 1.7785363600188894e-05,
1485
+ "loss": 0.7705,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.241166014930679,
1490
+ "grad_norm": 1.1225575837862554,
1491
+ "learning_rate": 1.776216915401322e-05,
1492
+ "loss": 0.7568,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.24230359047280484,
1497
+ "grad_norm": 0.9417229426258661,
1498
+ "learning_rate": 1.773886917122107e-05,
1499
+ "loss": 0.7634,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.24344116601493068,
1504
+ "grad_norm": 1.0736164163302175,
1505
+ "learning_rate": 1.771546396860551e-05,
1506
+ "loss": 0.7334,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.24457874155705653,
1511
+ "grad_norm": 1.0980435254209089,
1512
+ "learning_rate": 1.7691953864390208e-05,
1513
+ "loss": 0.8121,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.24571631709918237,
1518
+ "grad_norm": 0.9581368725405702,
1519
+ "learning_rate": 1.766833917822509e-05,
1520
+ "loss": 0.7622,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.24685389264130822,
1525
+ "grad_norm": 0.94688646103546,
1526
+ "learning_rate": 1.7644620231182015e-05,
1527
+ "loss": 0.8606,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.24799146818343407,
1532
+ "grad_norm": 1.000027690442481,
1533
+ "learning_rate": 1.7620797345750403e-05,
1534
+ "loss": 0.6355,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.2491290437255599,
1539
+ "grad_norm": 1.0030472762272575,
1540
+ "learning_rate": 1.759687084583285e-05,
1541
+ "loss": 0.7331,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.25026661926768573,
1546
+ "grad_norm": 0.933093406691675,
1547
+ "learning_rate": 1.7572841056740722e-05,
1548
+ "loss": 0.8011,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.2514041948098116,
1553
+ "grad_norm": 0.9421445936097415,
1554
+ "learning_rate": 1.7548708305189724e-05,
1555
+ "loss": 0.7891,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.2525417703519374,
1560
+ "grad_norm": 0.9681375218542562,
1561
+ "learning_rate": 1.7524472919295488e-05,
1562
+ "loss": 0.8035,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.25367934589406327,
1567
+ "grad_norm": 0.9614473856459215,
1568
+ "learning_rate": 1.7500135228569067e-05,
1569
+ "loss": 0.7541,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.2548169214361891,
1574
+ "grad_norm": 1.0407809945974127,
1575
+ "learning_rate": 1.7475695563912506e-05,
1576
+ "loss": 0.7616,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.25595449697831496,
1581
+ "grad_norm": 0.9557104322965116,
1582
+ "learning_rate": 1.7451154257614287e-05,
1583
+ "loss": 0.7465,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.2570920725204408,
1588
+ "grad_norm": 1.0178852691492593,
1589
+ "learning_rate": 1.742651164334486e-05,
1590
+ "loss": 0.8887,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.25822964806256665,
1595
+ "grad_norm": 1.0183556677477257,
1596
+ "learning_rate": 1.7401768056152083e-05,
1597
+ "loss": 0.7316,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.2593672236046925,
1602
+ "grad_norm": 0.9967963519853643,
1603
+ "learning_rate": 1.7376923832456665e-05,
1604
+ "loss": 0.7435,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.26050479914681834,
1609
+ "grad_norm": 0.9398084773931321,
1610
+ "learning_rate": 1.7351979310047603e-05,
1611
+ "loss": 0.8236,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.2616423746889442,
1616
+ "grad_norm": 0.9702704929040705,
1617
+ "learning_rate": 1.7326934828077574e-05,
1618
+ "loss": 0.7236,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.26277995023107004,
1623
+ "grad_norm": 0.9607473172752993,
1624
+ "learning_rate": 1.7301790727058344e-05,
1625
+ "loss": 0.8514,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.2639175257731959,
1630
+ "grad_norm": 0.99121388037334,
1631
+ "learning_rate": 1.727654734885612e-05,
1632
+ "loss": 0.7258,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.26505510131532173,
1637
+ "grad_norm": 0.9178575823375061,
1638
+ "learning_rate": 1.7251205036686913e-05,
1639
+ "loss": 0.7234,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.2661926768574476,
1644
+ "grad_norm": 0.9301556936555667,
1645
+ "learning_rate": 1.7225764135111867e-05,
1646
+ "loss": 0.7478,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.2673302523995734,
1651
+ "grad_norm": 0.951109081614099,
1652
+ "learning_rate": 1.7200224990032577e-05,
1653
+ "loss": 0.7419,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.26846782794169927,
1658
+ "grad_norm": 0.9160961470408167,
1659
+ "learning_rate": 1.7174587948686375e-05,
1660
+ "loss": 0.826,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.2696054034838251,
1665
+ "grad_norm": 1.057499137690602,
1666
+ "learning_rate": 1.7148853359641627e-05,
1667
+ "loss": 0.7286,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.27074297902595096,
1672
+ "grad_norm": 0.9295330730635258,
1673
+ "learning_rate": 1.7123021572792982e-05,
1674
+ "loss": 0.7782,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.2718805545680768,
1679
+ "grad_norm": 0.9975452115416533,
1680
+ "learning_rate": 1.7097092939356622e-05,
1681
+ "loss": 0.7519,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.27301813011020265,
1686
+ "grad_norm": 0.9230592215185579,
1687
+ "learning_rate": 1.7071067811865477e-05,
1688
+ "loss": 0.7086,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.2741557056523285,
1693
+ "grad_norm": 0.9191258196691511,
1694
+ "learning_rate": 1.7044946544164434e-05,
1695
+ "loss": 0.7791,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.27529328119445434,
1700
+ "grad_norm": 0.9937503180909131,
1701
+ "learning_rate": 1.7018729491405537e-05,
1702
+ "loss": 0.7141,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.2764308567365802,
1707
+ "grad_norm": 0.9546990458403812,
1708
+ "learning_rate": 1.6992417010043144e-05,
1709
+ "loss": 0.9387,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.27756843227870603,
1714
+ "grad_norm": 0.9694759038261794,
1715
+ "learning_rate": 1.6966009457829088e-05,
1716
+ "loss": 0.7102,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.2787060078208318,
1721
+ "grad_norm": 1.010514886312666,
1722
+ "learning_rate": 1.6939507193807818e-05,
1723
+ "loss": 0.7188,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.27984358336295767,
1728
+ "grad_norm": 0.9552012342525721,
1729
+ "learning_rate": 1.6912910578311503e-05,
1730
+ "loss": 0.7223,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.2809811589050835,
1735
+ "grad_norm": 0.9577918842168219,
1736
+ "learning_rate": 1.688621997295515e-05,
1737
+ "loss": 0.8556,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.28211873444720936,
1742
+ "grad_norm": 0.9347260963706611,
1743
+ "learning_rate": 1.685943574063166e-05,
1744
+ "loss": 0.6894,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.2832563099893352,
1749
+ "grad_norm": 0.9796117501965532,
1750
+ "learning_rate": 1.6832558245506937e-05,
1751
+ "loss": 0.8972,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.28439388553146105,
1756
+ "grad_norm": 0.9620774960278952,
1757
+ "learning_rate": 1.6805587853014895e-05,
1758
+ "loss": 0.8795,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.2855314610735869,
1763
+ "grad_norm": 0.9779292355070162,
1764
+ "learning_rate": 1.6778524929852513e-05,
1765
+ "loss": 0.7849,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.28666903661571275,
1770
+ "grad_norm": 1.1391374042408926,
1771
+ "learning_rate": 1.6751369843974842e-05,
1772
+ "loss": 0.8935,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.2878066121578386,
1777
+ "grad_norm": 0.9763354939311976,
1778
+ "learning_rate": 1.6724122964590002e-05,
1779
+ "loss": 0.6899,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.28894418769996444,
1784
+ "grad_norm": 1.0505980346872885,
1785
+ "learning_rate": 1.6696784662154165e-05,
1786
+ "loss": 0.7091,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.2900817632420903,
1791
+ "grad_norm": 0.961207072486454,
1792
+ "learning_rate": 1.666935530836651e-05,
1793
+ "loss": 0.77,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.29121933878421613,
1798
+ "grad_norm": 1.022189843385111,
1799
+ "learning_rate": 1.6641835276164182e-05,
1800
+ "loss": 0.8021,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.292356914326342,
1805
+ "grad_norm": 0.9676687321518108,
1806
+ "learning_rate": 1.6614224939717217e-05,
1807
+ "loss": 0.7338,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.2934944898684678,
1812
+ "grad_norm": 1.031020389826052,
1813
+ "learning_rate": 1.658652467442345e-05,
1814
+ "loss": 0.8083,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.29463206541059367,
1819
+ "grad_norm": 0.9420183191034406,
1820
+ "learning_rate": 1.6558734856903406e-05,
1821
+ "loss": 0.651,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.2957696409527195,
1826
+ "grad_norm": 0.9746154980433869,
1827
+ "learning_rate": 1.6530855864995194e-05,
1828
+ "loss": 0.8235,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.29690721649484536,
1833
+ "grad_norm": 0.9637613954906972,
1834
+ "learning_rate": 1.650288807774937e-05,
1835
+ "loss": 0.7806,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.2980447920369712,
1840
+ "grad_norm": 0.9521280823765289,
1841
+ "learning_rate": 1.6474831875423765e-05,
1842
+ "loss": 0.7848,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.29918236757909705,
1847
+ "grad_norm": 0.9106705929775119,
1848
+ "learning_rate": 1.644668763947833e-05,
1849
+ "loss": 0.7158,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.3003199431212229,
1854
+ "grad_norm": 1.1111068932353543,
1855
+ "learning_rate": 1.6418455752569945e-05,
1856
+ "loss": 0.7949,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.30145751866334874,
1861
+ "grad_norm": 0.993566678238848,
1862
+ "learning_rate": 1.639013659854722e-05,
1863
+ "loss": 0.7514,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.3025950942054746,
1868
+ "grad_norm": 0.9530703838625129,
1869
+ "learning_rate": 1.6361730562445264e-05,
1870
+ "loss": 0.7807,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.30373266974760044,
1875
+ "grad_norm": 0.8949330809420218,
1876
+ "learning_rate": 1.6333238030480473e-05,
1877
+ "loss": 0.6888,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.3048702452897263,
1882
+ "grad_norm": 0.8988538789326558,
1883
+ "learning_rate": 1.6304659390045253e-05,
1884
+ "loss": 0.7264,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.30600782083185213,
1889
+ "grad_norm": 1.0074831146025507,
1890
+ "learning_rate": 1.627599502970277e-05,
1891
+ "loss": 0.7832,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.307145396373978,
1896
+ "grad_norm": 0.9898618247508415,
1897
+ "learning_rate": 1.624724533918166e-05,
1898
+ "loss": 0.7412,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.3082829719161038,
1903
+ "grad_norm": 0.9571059882247707,
1904
+ "learning_rate": 1.6218410709370735e-05,
1905
+ "loss": 0.7214,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.30942054745822967,
1910
+ "grad_norm": 1.0048100811814527,
1911
+ "learning_rate": 1.6189491532313665e-05,
1912
+ "loss": 0.8121,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.3105581230003555,
1917
+ "grad_norm": 0.887082066422311,
1918
+ "learning_rate": 1.6160488201203643e-05,
1919
+ "loss": 0.8081,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.31169569854248136,
1924
+ "grad_norm": 1.003918167712565,
1925
+ "learning_rate": 1.6131401110378045e-05,
1926
+ "loss": 0.7442,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.3128332740846072,
1931
+ "grad_norm": 0.9479739767796763,
1932
+ "learning_rate": 1.6102230655313076e-05,
1933
+ "loss": 0.7854,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.31397084962673305,
1938
+ "grad_norm": 0.9644306636148626,
1939
+ "learning_rate": 1.607297723261837e-05,
1940
+ "loss": 0.852,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.3151084251688589,
1945
+ "grad_norm": 0.9590037676007116,
1946
+ "learning_rate": 1.6043641240031623e-05,
1947
+ "loss": 0.7551,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.3162460007109847,
1952
+ "grad_norm": 0.8703921927089772,
1953
+ "learning_rate": 1.6014223076413173e-05,
1954
+ "loss": 0.7418,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.31738357625311053,
1959
+ "grad_norm": 0.9581454527420551,
1960
+ "learning_rate": 1.5984723141740578e-05,
1961
+ "loss": 0.7117,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.3185211517952364,
1966
+ "grad_norm": 0.9806012064667501,
1967
+ "learning_rate": 1.595514183710317e-05,
1968
+ "loss": 0.8572,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.3196587273373622,
1973
+ "grad_norm": 0.8953483309121879,
1974
+ "learning_rate": 1.592547956469662e-05,
1975
+ "loss": 0.8641,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.32079630287948807,
1980
+ "grad_norm": 0.8922059600985867,
1981
+ "learning_rate": 1.5895736727817457e-05,
1982
+ "loss": 0.7629,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.3219338784216139,
1987
+ "grad_norm": 0.924903003131493,
1988
+ "learning_rate": 1.5865913730857583e-05,
1989
+ "loss": 0.6772,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.32307145396373976,
1994
+ "grad_norm": 0.9253210263661452,
1995
+ "learning_rate": 1.5836010979298785e-05,
1996
+ "loss": 0.7024,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.3242090295058656,
2001
+ "grad_norm": 0.9598832346761834,
2002
+ "learning_rate": 1.580602887970721e-05,
2003
+ "loss": 0.6624,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.32534660504799146,
2008
+ "grad_norm": 0.9502477784841414,
2009
+ "learning_rate": 1.5775967839727843e-05,
2010
+ "loss": 0.7923,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.3264841805901173,
2015
+ "grad_norm": 0.9306848601779047,
2016
+ "learning_rate": 1.574582826807897e-05,
2017
+ "loss": 0.6541,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.32762175613224315,
2022
+ "grad_norm": 0.9355305194278158,
2023
+ "learning_rate": 1.5715610574546612e-05,
2024
+ "loss": 0.6918,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.328759331674369,
2029
+ "grad_norm": 1.0272254475487725,
2030
+ "learning_rate": 1.5685315169978955e-05,
2031
+ "loss": 0.8111,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.32989690721649484,
2036
+ "grad_norm": 1.0334588348504568,
2037
+ "learning_rate": 1.565494246628077e-05,
2038
+ "loss": 0.7289,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.3310344827586207,
2043
+ "grad_norm": 0.9170599752827013,
2044
+ "learning_rate": 1.562449287640781e-05,
2045
+ "loss": 0.7852,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.33217205830074653,
2050
+ "grad_norm": 0.9222463038652008,
2051
+ "learning_rate": 1.5593966814361183e-05,
2052
+ "loss": 0.7118,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.3333096338428724,
2057
+ "grad_norm": 1.0228401075311697,
2058
+ "learning_rate": 1.556336469518174e-05,
2059
+ "loss": 0.7166,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.3344472093849982,
2064
+ "grad_norm": 0.9867811982354191,
2065
+ "learning_rate": 1.553268693494444e-05,
2066
+ "loss": 0.7237,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.33558478492712407,
2071
+ "grad_norm": 0.929004653861396,
2072
+ "learning_rate": 1.5501933950752655e-05,
2073
+ "loss": 0.7315,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.3367223604692499,
2078
+ "grad_norm": 0.9711989755609595,
2079
+ "learning_rate": 1.5471106160732543e-05,
2080
+ "loss": 0.6733,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.33785993601137576,
2085
+ "grad_norm": 1.0543195742090818,
2086
+ "learning_rate": 1.5440203984027323e-05,
2087
+ "loss": 0.7116,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.3389975115535016,
2092
+ "grad_norm": 1.0061655744197207,
2093
+ "learning_rate": 1.5409227840791617e-05,
2094
+ "loss": 0.7517,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.34013508709562745,
2099
+ "grad_norm": 0.9690488111835885,
2100
+ "learning_rate": 1.5378178152185703e-05,
2101
+ "loss": 0.8389,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.3412726626377533,
2106
+ "grad_norm": 0.9582246999248494,
2107
+ "learning_rate": 1.5347055340369806e-05,
2108
+ "loss": 0.798,
2109
+ "step": 300
2110
+ }
2111
+ ],
2112
+ "logging_steps": 1.0,
2113
+ "max_steps": 879,
2114
+ "num_input_tokens_seen": 0,
2115
+ "num_train_epochs": 1,
2116
+ "save_steps": 100,
2117
+ "stateful_callbacks": {
2118
+ "TrainerControl": {
2119
+ "args": {
2120
+ "should_epoch_stop": false,
2121
+ "should_evaluate": false,
2122
+ "should_log": false,
2123
+ "should_save": true,
2124
+ "should_training_stop": false
2125
+ },
2126
+ "attributes": {}
2127
+ }
2128
+ },
2129
+ "total_flos": 435534387740672.0,
2130
+ "train_batch_size": 1,
2131
+ "trial_name": null,
2132
+ "trial_params": null
2133
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff