Hugging Face's logo

Efficient-Large-Model
/
VILA-13b-4bit-awq

Text Generation
Transformers
Safetensors
llava_llama
VILA
VLM
Inference Endpoints
Model card Files Community
kentang1998 commited on
Commit
c2cf21b
•
1 Parent(s): a3077a2

[Major] Add VILA-13b-awq checkpoints

Browse files
Files changed (9) hide show
  1. config.json +43 -0
  2. generation_config.json +7 -0
  3. model.safetensors.index.json +765 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +42 -0
  7. trainer_state.json +3150 -0
  8. training_args.bin +3 -0
  9. vila-13b-w4-g128-awq-real-v2.pt +3 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/llama-2-13b-mmc4-coyo-paper_reproduce",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "freeze_mm_mlp_adapter": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "image_aspect_ratio": "pad",
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 13824,
16
+ "max_position_embeddings": 4096,
17
+ "mm_hidden_size": 1024,
18
+ "mm_projector_lr": null,
19
+ "mm_projector_type": "mlp2x_gelu",
20
+ "mm_use_im_patch_token": false,
21
+ "mm_use_im_start_end": false,
22
+ "mm_vision_select_feature": "patch",
23
+ "mm_vision_select_layer": -2,
24
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
25
+ "model_type": "llava_llama",
26
+ "num_attention_heads": 40,
27
+ "num_hidden_layers": 40,
28
+ "num_key_value_heads": 40,
29
+ "pad_token_id": 0,
30
+ "pretraining_tp": 1,
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
34
+ "tie_word_embeddings": false,
35
+ "tokenizer_model_max_length": 4096,
36
+ "tokenizer_padding_side": "right",
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.36.2",
39
+ "tune_mm_mlp_adapter": false,
40
+ "use_cache": true,
41
+ "use_mm_proj": true,
42
+ "vocab_size": 32000
43
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.36.2"
7
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,765 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26701678592
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
368
+ "model.mm_projector.0.bias": "model-00006-of-00006.safetensors",
369
+ "model.mm_projector.0.weight": "model-00006-of-00006.safetensors",
370
+ "model.mm_projector.2.bias": "model-00006-of-00006.safetensors",
371
+ "model.mm_projector.2.weight": "model-00006-of-00006.safetensors",
372
+ "model.norm.weight": "model-00006-of-00006.safetensors",
373
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00006-of-00006.safetensors",
374
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00006-of-00006.safetensors",
375
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00006-of-00006.safetensors",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00006-of-00006.safetensors",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00006-of-00006.safetensors",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00006-of-00006.safetensors",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00006-of-00006.safetensors",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00006-of-00006.safetensors",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00006-of-00006.safetensors",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00006-of-00006.safetensors",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00006-of-00006.safetensors",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00006-of-00006.safetensors",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00006-of-00006.safetensors",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00006-of-00006.safetensors",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00006-of-00006.safetensors",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00006-of-00006.safetensors",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00006-of-00006.safetensors",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00006-of-00006.safetensors",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00006-of-00006.safetensors",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00006-of-00006.safetensors",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00006-of-00006.safetensors",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00006-of-00006.safetensors",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00006-of-00006.safetensors",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00006-of-00006.safetensors",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00006-of-00006.safetensors",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00006-of-00006.safetensors",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00006-of-00006.safetensors",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00006-of-00006.safetensors",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00006-of-00006.safetensors",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00006-of-00006.safetensors",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00006-of-00006.safetensors",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00006-of-00006.safetensors",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00006-of-00006.safetensors",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00006-of-00006.safetensors",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00006-of-00006.safetensors",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00006-of-00006.safetensors",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00006-of-00006.safetensors",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00006-of-00006.safetensors",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00006-of-00006.safetensors",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00006-of-00006.safetensors",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00006-of-00006.safetensors",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00006-of-00006.safetensors",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00006-of-00006.safetensors",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00006-of-00006.safetensors",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00006-of-00006.safetensors",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00006-of-00006.safetensors",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00006-of-00006.safetensors",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00006-of-00006.safetensors",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00006-of-00006.safetensors",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00006-of-00006.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00006-of-00006.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00006-of-00006.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00006-of-00006.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00006-of-00006.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00006-of-00006.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00006-of-00006.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00006-of-00006.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00006-of-00006.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00006-of-00006.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00006-of-00006.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00006-of-00006.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00006-of-00006.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00006-of-00006.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00006-of-00006.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00006-of-00006.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00006-of-00006.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00006-of-00006.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00006-of-00006.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00006-of-00006.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00006-of-00006.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00006-of-00006.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00006-of-00006.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00006-of-00006.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00006-of-00006.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00006-of-00006.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00006-of-00006.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00006-of-00006.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00006-of-00006.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00006-of-00006.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00006-of-00006.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00006-of-00006.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00006-of-00006.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00006-of-00006.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00006-of-00006.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00006-of-00006.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00006-of-00006.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00006-of-00006.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00006-of-00006.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00006-of-00006.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00006-of-00006.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00006-of-00006.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00006-of-00006.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00006-of-00006.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00006-of-00006.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00006-of-00006.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00006-of-00006.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00006-of-00006.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00006-of-00006.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00006-of-00006.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00006-of-00006.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00006-of-00006.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00006-of-00006.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00006-of-00006.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00006-of-00006.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00006-of-00006.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00006-of-00006.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00006-of-00006.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00006-of-00006.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00006-of-00006.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00006-of-00006.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00006-of-00006.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00006-of-00006.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00006-of-00006.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00006-of-00006.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00006-of-00006.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00006-of-00006.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00006-of-00006.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00006-of-00006.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00006-of-00006.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00006-of-00006.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00006-of-00006.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00006-of-00006.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00006-of-00006.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00006-of-00006.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00006-of-00006.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00006-of-00006.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00006-of-00006.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00006-of-00006.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00006-of-00006.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00006-of-00006.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00006-of-00006.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00006-of-00006.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00006-of-00006.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00006-of-00006.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00006-of-00006.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00006-of-00006.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00006-of-00006.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00006-of-00006.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00006-of-00006.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00006-of-00006.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00006-of-00006.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00006-of-00006.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00006-of-00006.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00006-of-00006.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00006-of-00006.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00006-of-00006.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00006-of-00006.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00006-of-00006.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00006-of-00006.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00006-of-00006.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00006-of-00006.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00006-of-00006.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00006-of-00006.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00006-of-00006.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00006-of-00006.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00006-of-00006.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00006-of-00006.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00006-of-00006.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00006-of-00006.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00006-of-00006.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00006-of-00006.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00006-of-00006.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00006-of-00006.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00006-of-00006.safetensors",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00006-of-00006.safetensors",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00006-of-00006.safetensors",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00006-of-00006.safetensors",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00006-of-00006.safetensors",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00006-of-00006.safetensors",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00006-of-00006.safetensors",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00006-of-00006.safetensors",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00006-of-00006.safetensors",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00006-of-00006.safetensors",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00006-of-00006.safetensors",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00006-of-00006.safetensors",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00006-of-00006.safetensors",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00006-of-00006.safetensors",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00006-of-00006.safetensors",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00006-of-00006.safetensors",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00006-of-00006.safetensors",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00006-of-00006.safetensors",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00006-of-00006.safetensors",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00006-of-00006.safetensors",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00006-of-00006.safetensors",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00006-of-00006.safetensors",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00006-of-00006.safetensors",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00006-of-00006.safetensors",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00006-of-00006.safetensors",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00006-of-00006.safetensors",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00006-of-00006.safetensors",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00006-of-00006.safetensors",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00006-of-00006.safetensors",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00006-of-00006.safetensors",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00006-of-00006.safetensors",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00006-of-00006.safetensors",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00006-of-00006.safetensors",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00006-of-00006.safetensors",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
760
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00006-of-00006.safetensors",
761
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00006-of-00006.safetensors",
762
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00006-of-00006.safetensors",
763
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00006-of-00006.safetensors"
764
+ }
765
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 4096,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
trainer_state.json ADDED
@@ -0,0 +1,3150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 520,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 6.25e-06,
14
+ "loss": 2.1094,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 1.25e-05,
20
+ "loss": 2.1719,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 1.8750000000000002e-05,
26
+ "loss": 1.8203,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 2.5e-05,
32
+ "loss": 1.1953,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 3.125e-05,
38
+ "loss": 1.0938,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 3.7500000000000003e-05,
44
+ "loss": 1.125,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 4.375e-05,
50
+ "loss": 1.0625,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 5e-05,
56
+ "loss": 1.0859,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 5.6250000000000005e-05,
62
+ "loss": 1.0156,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "learning_rate": 6.25e-05,
68
+ "loss": 1.0,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.02,
73
+ "learning_rate": 6.875e-05,
74
+ "loss": 0.9844,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.02,
79
+ "learning_rate": 7.500000000000001e-05,
80
+ "loss": 0.9805,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.03,
85
+ "learning_rate": 8.125000000000001e-05,
86
+ "loss": 0.9727,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.03,
91
+ "learning_rate": 8.75e-05,
92
+ "loss": 0.9648,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.03,
97
+ "learning_rate": 9.375e-05,
98
+ "loss": 0.9258,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.03,
103
+ "learning_rate": 0.0001,
104
+ "loss": 0.9531,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.03,
109
+ "learning_rate": 9.999902864657691e-05,
110
+ "loss": 0.9453,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.03,
115
+ "learning_rate": 9.999611462404875e-05,
116
+ "loss": 0.957,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.04,
121
+ "learning_rate": 9.999125804563732e-05,
122
+ "loss": 0.9375,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.04,
127
+ "learning_rate": 9.998445910004082e-05,
128
+ "loss": 0.9102,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.04,
133
+ "learning_rate": 9.997571805142639e-05,
134
+ "loss": 0.9375,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.04,
139
+ "learning_rate": 9.996503523941994e-05,
140
+ "loss": 0.918,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.04,
145
+ "learning_rate": 9.99524110790929e-05,
146
+ "loss": 0.8906,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.05,
151
+ "learning_rate": 9.993784606094612e-05,
152
+ "loss": 0.9102,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.05,
157
+ "learning_rate": 9.992134075089084e-05,
158
+ "loss": 0.8984,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.05,
163
+ "learning_rate": 9.99028957902266e-05,
164
+ "loss": 0.8945,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.05,
169
+ "learning_rate": 9.988251189561645e-05,
170
+ "loss": 0.9219,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.05,
175
+ "learning_rate": 9.986018985905901e-05,
176
+ "loss": 0.8789,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.06,
181
+ "learning_rate": 9.983593054785776e-05,
182
+ "loss": 0.8984,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.06,
187
+ "learning_rate": 9.980973490458728e-05,
188
+ "loss": 0.8945,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.06,
193
+ "learning_rate": 9.978160394705668e-05,
194
+ "loss": 0.8789,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.06,
199
+ "learning_rate": 9.975153876827008e-05,
200
+ "loss": 0.9062,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.06,
205
+ "learning_rate": 9.971954053638399e-05,
206
+ "loss": 0.875,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.07,
211
+ "learning_rate": 9.968561049466214e-05,
212
+ "loss": 0.8594,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.07,
217
+ "learning_rate": 9.964974996142698e-05,
218
+ "loss": 0.8672,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.07,
223
+ "learning_rate": 9.961196033000861e-05,
224
+ "loss": 0.8711,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.07,
229
+ "learning_rate": 9.957224306869053e-05,
230
+ "loss": 0.8828,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.07,
235
+ "learning_rate": 9.953059972065265e-05,
236
+ "loss": 0.8594,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.07,
241
+ "learning_rate": 9.948703190391131e-05,
242
+ "loss": 0.8672,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.08,
247
+ "learning_rate": 9.944154131125642e-05,
248
+ "loss": 0.8789,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.08,
253
+ "learning_rate": 9.939412971018574e-05,
254
+ "loss": 0.875,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.08,
259
+ "learning_rate": 9.934479894283606e-05,
260
+ "loss": 0.8672,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.08,
265
+ "learning_rate": 9.92935509259118e-05,
266
+ "loss": 0.8594,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.08,
271
+ "learning_rate": 9.924038765061042e-05,
272
+ "loss": 0.8711,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.09,
277
+ "learning_rate": 9.918531118254507e-05,
278
+ "loss": 0.8672,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.09,
283
+ "learning_rate": 9.912832366166442e-05,
284
+ "loss": 0.8516,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.09,
289
+ "learning_rate": 9.906942730216939e-05,
290
+ "loss": 0.8477,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.09,
295
+ "learning_rate": 9.900862439242719e-05,
296
+ "loss": 0.8555,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.09,
301
+ "learning_rate": 9.894591729488242e-05,
302
+ "loss": 0.875,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.1,
307
+ "learning_rate": 9.888130844596524e-05,
308
+ "loss": 0.8438,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.1,
313
+ "learning_rate": 9.881480035599667e-05,
314
+ "loss": 0.8516,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.1,
319
+ "learning_rate": 9.874639560909117e-05,
320
+ "loss": 0.8789,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.1,
325
+ "learning_rate": 9.867609686305617e-05,
326
+ "loss": 0.8711,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.1,
331
+ "learning_rate": 9.860390684928873e-05,
332
+ "loss": 0.8594,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.11,
337
+ "learning_rate": 9.852982837266955e-05,
338
+ "loss": 0.8555,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.11,
343
+ "learning_rate": 9.84538643114539e-05,
344
+ "loss": 0.8633,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.11,
349
+ "learning_rate": 9.837601761715983e-05,
350
+ "loss": 0.8438,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.11,
355
+ "learning_rate": 9.829629131445342e-05,
356
+ "loss": 0.8438,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.11,
361
+ "learning_rate": 9.82146885010314e-05,
362
+ "loss": 0.8555,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.12,
367
+ "learning_rate": 9.81312123475006e-05,
368
+ "loss": 0.8477,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.12,
373
+ "learning_rate": 9.804586609725499e-05,
374
+ "loss": 0.875,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.12,
379
+ "learning_rate": 9.79586530663494e-05,
380
+ "loss": 0.8555,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.12,
385
+ "learning_rate": 9.78695766433709e-05,
386
+ "loss": 0.8438,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.12,
391
+ "learning_rate": 9.777864028930705e-05,
392
+ "loss": 0.8594,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.12,
397
+ "learning_rate": 9.768584753741134e-05,
398
+ "loss": 0.8203,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.13,
403
+ "learning_rate": 9.759120199306613e-05,
404
+ "loss": 0.8281,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.13,
409
+ "learning_rate": 9.74947073336423e-05,
410
+ "loss": 0.8438,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.13,
415
+ "learning_rate": 9.73963673083566e-05,
416
+ "loss": 0.8594,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.13,
421
+ "learning_rate": 9.72961857381258e-05,
422
+ "loss": 0.8555,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.13,
427
+ "learning_rate": 9.719416651541839e-05,
428
+ "loss": 0.8242,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.14,
433
+ "learning_rate": 9.709031360410318e-05,
434
+ "loss": 0.8555,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.14,
439
+ "learning_rate": 9.698463103929542e-05,
440
+ "loss": 0.8359,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.14,
445
+ "learning_rate": 9.687712292719997e-05,
446
+ "loss": 0.8438,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.14,
451
+ "learning_rate": 9.67677934449517e-05,
452
+ "loss": 0.8594,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.14,
457
+ "learning_rate": 9.665664684045333e-05,
458
+ "loss": 0.8516,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.15,
463
+ "learning_rate": 9.654368743221022e-05,
464
+ "loss": 0.8242,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.15,
469
+ "learning_rate": 9.642891960916268e-05,
470
+ "loss": 0.8281,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.15,
475
+ "learning_rate": 9.631234783051544e-05,
476
+ "loss": 0.832,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.15,
481
+ "learning_rate": 9.619397662556435e-05,
482
+ "loss": 0.8398,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.15,
487
+ "learning_rate": 9.607381059352038e-05,
488
+ "loss": 0.8359,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.16,
493
+ "learning_rate": 9.595185440333103e-05,
494
+ "loss": 0.8086,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.16,
499
+ "learning_rate": 9.582811279349882e-05,
500
+ "loss": 0.8281,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.16,
505
+ "learning_rate": 9.570259057189717e-05,
506
+ "loss": 0.8125,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.16,
511
+ "learning_rate": 9.557529261558367e-05,
512
+ "loss": 0.8359,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.16,
517
+ "learning_rate": 9.544622387061055e-05,
518
+ "loss": 0.8398,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.17,
523
+ "learning_rate": 9.53153893518325e-05,
524
+ "loss": 0.8516,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.17,
529
+ "learning_rate": 9.518279414271183e-05,
530
+ "loss": 0.8555,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.17,
535
+ "learning_rate": 9.504844339512095e-05,
536
+ "loss": 0.8438,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.17,
541
+ "learning_rate": 9.491234232914221e-05,
542
+ "loss": 0.8203,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.17,
547
+ "learning_rate": 9.477449623286505e-05,
548
+ "loss": 0.8242,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.17,
553
+ "learning_rate": 9.463491046218058e-05,
554
+ "loss": 0.8164,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.18,
559
+ "learning_rate": 9.449359044057345e-05,
560
+ "loss": 0.8164,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.18,
565
+ "learning_rate": 9.435054165891109e-05,
566
+ "loss": 0.8164,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.18,
571
+ "learning_rate": 9.420576967523049e-05,
572
+ "loss": 0.8359,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.18,
577
+ "learning_rate": 9.405928011452211e-05,
578
+ "loss": 0.8398,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.18,
583
+ "learning_rate": 9.391107866851143e-05,
584
+ "loss": 0.8164,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.19,
589
+ "learning_rate": 9.376117109543769e-05,
590
+ "loss": 0.8516,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.19,
595
+ "learning_rate": 9.360956321983028e-05,
596
+ "loss": 0.8281,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.19,
601
+ "learning_rate": 9.345626093228233e-05,
602
+ "loss": 0.8164,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.19,
607
+ "learning_rate": 9.330127018922194e-05,
608
+ "loss": 0.8555,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.19,
613
+ "learning_rate": 9.314459701268065e-05,
614
+ "loss": 0.8125,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.2,
619
+ "learning_rate": 9.298624749005951e-05,
620
+ "loss": 0.8242,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.2,
625
+ "learning_rate": 9.282622777389258e-05,
626
+ "loss": 0.8281,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.2,
631
+ "learning_rate": 9.266454408160779e-05,
632
+ "loss": 0.832,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.2,
637
+ "learning_rate": 9.250120269528546e-05,
638
+ "loss": 0.8242,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.2,
643
+ "learning_rate": 9.233620996141421e-05,
644
+ "loss": 0.8438,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.21,
649
+ "learning_rate": 9.21695722906443e-05,
650
+ "loss": 0.8281,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.21,
655
+ "learning_rate": 9.200129615753859e-05,
656
+ "loss": 0.8203,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.21,
661
+ "learning_rate": 9.183138810032099e-05,
662
+ "loss": 0.8398,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.21,
667
+ "learning_rate": 9.165985472062246e-05,
668
+ "loss": 0.8359,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.21,
673
+ "learning_rate": 9.148670268322438e-05,
674
+ "loss": 0.8281,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.22,
679
+ "learning_rate": 9.131193871579975e-05,
680
+ "loss": 0.8125,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.22,
685
+ "learning_rate": 9.113556960865167e-05,
686
+ "loss": 0.8359,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.22,
691
+ "learning_rate": 9.09576022144496e-05,
692
+ "loss": 0.8281,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.22,
697
+ "learning_rate": 9.077804344796302e-05,
698
+ "loss": 0.8047,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.22,
703
+ "learning_rate": 9.059690028579284e-05,
704
+ "loss": 0.8125,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.23,
709
+ "learning_rate": 9.041417976610027e-05,
710
+ "loss": 0.8203,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.23,
715
+ "learning_rate": 9.022988898833342e-05,
716
+ "loss": 0.832,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.23,
721
+ "learning_rate": 9.004403511295141e-05,
722
+ "loss": 0.8242,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.23,
727
+ "learning_rate": 8.985662536114613e-05,
728
+ "loss": 0.8203,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.23,
733
+ "learning_rate": 8.966766701456177e-05,
734
+ "loss": 0.8164,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.23,
739
+ "learning_rate": 8.947716741501177e-05,
740
+ "loss": 0.8242,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.24,
745
+ "learning_rate": 8.928513396419368e-05,
746
+ "loss": 0.8008,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.24,
751
+ "learning_rate": 8.90915741234015e-05,
752
+ "loss": 0.8125,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.24,
757
+ "learning_rate": 8.889649541323574e-05,
758
+ "loss": 0.832,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.24,
763
+ "learning_rate": 8.869990541331138e-05,
764
+ "loss": 0.8047,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.24,
769
+ "learning_rate": 8.850181176196315e-05,
770
+ "loss": 0.8086,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.25,
775
+ "learning_rate": 8.83022221559489e-05,
776
+ "loss": 0.8164,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.25,
781
+ "learning_rate": 8.810114435015054e-05,
782
+ "loss": 0.8047,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.25,
787
+ "learning_rate": 8.789858615727265e-05,
788
+ "loss": 0.8047,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.25,
793
+ "learning_rate": 8.7694555447539e-05,
794
+ "loss": 0.8359,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.25,
799
+ "learning_rate": 8.748906014838672e-05,
800
+ "loss": 0.832,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.26,
805
+ "learning_rate": 8.728210824415827e-05,
806
+ "loss": 0.8086,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.26,
811
+ "learning_rate": 8.707370777579133e-05,
812
+ "loss": 0.8008,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.26,
817
+ "learning_rate": 8.68638668405062e-05,
818
+ "loss": 0.8164,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.26,
823
+ "learning_rate": 8.665259359149132e-05,
824
+ "loss": 0.8125,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.26,
829
+ "learning_rate": 8.643989623758643e-05,
830
+ "loss": 0.8281,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.27,
835
+ "learning_rate": 8.622578304296364e-05,
836
+ "loss": 0.8125,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.27,
841
+ "learning_rate": 8.601026232680634e-05,
842
+ "loss": 0.8047,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.27,
847
+ "learning_rate": 8.579334246298593e-05,
848
+ "loss": 0.8008,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.27,
853
+ "learning_rate": 8.557503187973651e-05,
854
+ "loss": 0.8164,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.27,
859
+ "learning_rate": 8.535533905932738e-05,
860
+ "loss": 0.8164,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.28,
865
+ "learning_rate": 8.513427253773346e-05,
866
+ "loss": 0.8047,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.28,
871
+ "learning_rate": 8.491184090430364e-05,
872
+ "loss": 0.8008,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.28,
877
+ "learning_rate": 8.468805280142709e-05,
878
+ "loss": 0.7969,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.28,
883
+ "learning_rate": 8.446291692419736e-05,
884
+ "loss": 0.8086,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.28,
889
+ "learning_rate": 8.423644202007467e-05,
890
+ "loss": 0.7969,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.28,
895
+ "learning_rate": 8.400863688854597e-05,
896
+ "loss": 0.8281,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.29,
901
+ "learning_rate": 8.377951038078302e-05,
902
+ "loss": 0.8203,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.29,
907
+ "learning_rate": 8.354907139929851e-05,
908
+ "loss": 0.8164,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.29,
913
+ "learning_rate": 8.33173288976002e-05,
914
+ "loss": 0.8203,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.29,
919
+ "learning_rate": 8.308429187984297e-05,
920
+ "loss": 0.8125,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.29,
925
+ "learning_rate": 8.284996940047903e-05,
926
+ "loss": 0.8242,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.3,
931
+ "learning_rate": 8.261437056390606e-05,
932
+ "loss": 0.8125,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.3,
937
+ "learning_rate": 8.237750452411353e-05,
938
+ "loss": 0.8164,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.3,
943
+ "learning_rate": 8.213938048432697e-05,
944
+ "loss": 0.8164,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.3,
949
+ "learning_rate": 8.190000769665044e-05,
950
+ "loss": 0.8203,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.3,
955
+ "learning_rate": 8.1659395461707e-05,
956
+ "loss": 0.7969,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.31,
961
+ "learning_rate": 8.141755312827736e-05,
962
+ "loss": 0.8125,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.31,
967
+ "learning_rate": 8.117449009293668e-05,
968
+ "loss": 0.8086,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.31,
973
+ "learning_rate": 8.093021579968941e-05,
974
+ "loss": 0.8047,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.31,
979
+ "learning_rate": 8.068473973960238e-05,
980
+ "loss": 0.8047,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.31,
985
+ "learning_rate": 8.043807145043604e-05,
986
+ "loss": 0.793,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.32,
991
+ "learning_rate": 8.019022051627388e-05,
992
+ "loss": 0.8359,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.32,
997
+ "learning_rate": 7.994119656715002e-05,
998
+ "loss": 0.7891,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.32,
1003
+ "learning_rate": 7.969100927867507e-05,
1004
+ "loss": 0.8047,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.32,
1009
+ "learning_rate": 7.943966837166023e-05,
1010
+ "loss": 0.8008,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.32,
1015
+ "learning_rate": 7.91871836117395e-05,
1016
+ "loss": 0.8125,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.33,
1021
+ "learning_rate": 7.89335648089903e-05,
1022
+ "loss": 0.793,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.33,
1027
+ "learning_rate": 7.86788218175523e-05,
1028
+ "loss": 0.8125,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.33,
1033
+ "learning_rate": 7.842296453524463e-05,
1034
+ "loss": 0.8047,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.33,
1039
+ "learning_rate": 7.81660029031811e-05,
1040
+ "loss": 0.7969,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.33,
1045
+ "learning_rate": 7.79079469053842e-05,
1046
+ "loss": 0.7969,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.33,
1051
+ "learning_rate": 7.764880656839696e-05,
1052
+ "loss": 0.8203,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.34,
1057
+ "learning_rate": 7.738859196089358e-05,
1058
+ "loss": 0.8008,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.34,
1063
+ "learning_rate": 7.712731319328798e-05,
1064
+ "loss": 0.8203,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.34,
1069
+ "learning_rate": 7.68649804173412e-05,
1070
+ "loss": 0.7891,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.34,
1075
+ "learning_rate": 7.660160382576683e-05,
1076
+ "loss": 0.8008,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.34,
1081
+ "learning_rate": 7.633719365183504e-05,
1082
+ "loss": 0.8125,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.35,
1087
+ "learning_rate": 7.60717601689749e-05,
1088
+ "loss": 0.793,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.35,
1093
+ "learning_rate": 7.580531369037533e-05,
1094
+ "loss": 0.7969,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.35,
1099
+ "learning_rate": 7.553786456858429e-05,
1100
+ "loss": 0.7969,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.35,
1105
+ "learning_rate": 7.526942319510655e-05,
1106
+ "loss": 0.8008,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.35,
1111
+ "learning_rate": 7.500000000000001e-05,
1112
+ "loss": 0.8008,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.36,
1117
+ "learning_rate": 7.472960545147038e-05,
1118
+ "loss": 0.8008,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.36,
1123
+ "learning_rate": 7.445825005546448e-05,
1124
+ "loss": 0.8125,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.36,
1129
+ "learning_rate": 7.4185944355262e-05,
1130
+ "loss": 0.8203,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.36,
1135
+ "learning_rate": 7.391269893106592e-05,
1136
+ "loss": 0.8164,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.36,
1141
+ "learning_rate": 7.363852439959135e-05,
1142
+ "loss": 0.8203,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.37,
1147
+ "learning_rate": 7.33634314136531e-05,
1148
+ "loss": 0.8164,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.37,
1153
+ "learning_rate": 7.308743066175172e-05,
1154
+ "loss": 0.7969,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.37,
1159
+ "learning_rate": 7.281053286765815e-05,
1160
+ "loss": 0.7852,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.37,
1165
+ "learning_rate": 7.253274878999727e-05,
1166
+ "loss": 0.8164,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.37,
1171
+ "learning_rate": 7.225408922182961e-05,
1172
+ "loss": 0.8203,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.38,
1177
+ "learning_rate": 7.197456499023225e-05,
1178
+ "loss": 0.7891,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.38,
1183
+ "learning_rate": 7.169418695587791e-05,
1184
+ "loss": 0.8125,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.38,
1189
+ "learning_rate": 7.141296601261314e-05,
1190
+ "loss": 0.8008,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.38,
1195
+ "learning_rate": 7.113091308703498e-05,
1196
+ "loss": 0.7891,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.38,
1201
+ "learning_rate": 7.084803913806641e-05,
1202
+ "loss": 0.8086,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.38,
1207
+ "learning_rate": 7.056435515653059e-05,
1208
+ "loss": 0.8125,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.39,
1213
+ "learning_rate": 7.027987216472377e-05,
1214
+ "loss": 0.8125,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.39,
1219
+ "learning_rate": 6.999460121598704e-05,
1220
+ "loss": 0.7852,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.39,
1225
+ "learning_rate": 6.970855339427698e-05,
1226
+ "loss": 0.7891,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.39,
1231
+ "learning_rate": 6.942173981373474e-05,
1232
+ "loss": 0.8125,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.39,
1237
+ "learning_rate": 6.91341716182545e-05,
1238
+ "loss": 0.8125,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.4,
1243
+ "learning_rate": 6.884585998105026e-05,
1244
+ "loss": 0.8047,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.4,
1249
+ "learning_rate": 6.855681610422189e-05,
1250
+ "loss": 0.8008,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.4,
1255
+ "learning_rate": 6.826705121831976e-05,
1256
+ "loss": 0.8047,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.4,
1261
+ "learning_rate": 6.797657658190839e-05,
1262
+ "loss": 0.8164,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.4,
1267
+ "learning_rate": 6.768540348112907e-05,
1268
+ "loss": 0.8047,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.41,
1273
+ "learning_rate": 6.739354322926136e-05,
1274
+ "loss": 0.8164,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.41,
1279
+ "learning_rate": 6.710100716628344e-05,
1280
+ "loss": 0.7969,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.41,
1285
+ "learning_rate": 6.680780665843155e-05,
1286
+ "loss": 0.7969,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.41,
1291
+ "learning_rate": 6.651395309775837e-05,
1292
+ "loss": 0.793,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.41,
1297
+ "learning_rate": 6.621945790169036e-05,
1298
+ "loss": 0.8047,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.42,
1303
+ "learning_rate": 6.592433251258423e-05,
1304
+ "loss": 0.7969,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.42,
1309
+ "learning_rate": 6.562858839728223e-05,
1310
+ "loss": 0.7969,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.42,
1315
+ "learning_rate": 6.533223704666672e-05,
1316
+ "loss": 0.7773,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.42,
1321
+ "learning_rate": 6.503528997521366e-05,
1322
+ "loss": 0.8086,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.42,
1327
+ "learning_rate": 6.473775872054521e-05,
1328
+ "loss": 0.8086,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.42,
1333
+ "learning_rate": 6.44396548429815e-05,
1334
+ "loss": 0.793,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.43,
1339
+ "learning_rate": 6.414098992509138e-05,
1340
+ "loss": 0.7852,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.43,
1345
+ "learning_rate": 6.384177557124247e-05,
1346
+ "loss": 0.7969,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.43,
1351
+ "learning_rate": 6.354202340715026e-05,
1352
+ "loss": 0.8164,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.43,
1357
+ "learning_rate": 6.324174507942637e-05,
1358
+ "loss": 0.7695,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.43,
1363
+ "learning_rate": 6.294095225512603e-05,
1364
+ "loss": 0.7852,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.44,
1369
+ "learning_rate": 6.263965662129487e-05,
1370
+ "loss": 0.7891,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.44,
1375
+ "learning_rate": 6.233786988451468e-05,
1376
+ "loss": 0.8008,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.44,
1381
+ "learning_rate": 6.203560377044866e-05,
1382
+ "loss": 0.793,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.44,
1387
+ "learning_rate": 6.173287002338577e-05,
1388
+ "loss": 0.793,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.44,
1393
+ "learning_rate": 6.142968040578449e-05,
1394
+ "loss": 0.7969,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.45,
1399
+ "learning_rate": 6.112604669781572e-05,
1400
+ "loss": 0.8047,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.45,
1405
+ "learning_rate": 6.0821980696905146e-05,
1406
+ "loss": 0.7812,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.45,
1411
+ "learning_rate": 6.0517494217274794e-05,
1412
+ "loss": 0.8047,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.45,
1417
+ "learning_rate": 6.021259908948402e-05,
1418
+ "loss": 0.7734,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.45,
1423
+ "learning_rate": 5.9907307159969884e-05,
1424
+ "loss": 0.7734,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.46,
1429
+ "learning_rate": 5.960163029058682e-05,
1430
+ "loss": 0.793,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.46,
1435
+ "learning_rate": 5.9295580358145744e-05,
1436
+ "loss": 0.7812,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.46,
1441
+ "learning_rate": 5.898916925395264e-05,
1442
+ "loss": 0.7969,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.46,
1447
+ "learning_rate": 5.868240888334653e-05,
1448
+ "loss": 0.7891,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.46,
1453
+ "learning_rate": 5.837531116523682e-05,
1454
+ "loss": 0.7695,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.47,
1459
+ "learning_rate": 5.806788803164034e-05,
1460
+ "loss": 0.7812,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.47,
1465
+ "learning_rate": 5.7760151427217576e-05,
1466
+ "loss": 0.8008,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.47,
1471
+ "learning_rate": 5.745211330880872e-05,
1472
+ "loss": 0.7969,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.47,
1477
+ "learning_rate": 5.714378564496901e-05,
1478
+ "loss": 0.7773,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.47,
1483
+ "learning_rate": 5.683518041550368e-05,
1484
+ "loss": 0.7812,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.47,
1489
+ "learning_rate": 5.6526309611002594e-05,
1490
+ "loss": 0.7773,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.48,
1495
+ "learning_rate": 5.621718523237427e-05,
1496
+ "loss": 0.7969,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.48,
1501
+ "learning_rate": 5.590781929037965e-05,
1502
+ "loss": 0.7852,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.48,
1507
+ "learning_rate": 5.559822380516539e-05,
1508
+ "loss": 0.8008,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.48,
1513
+ "learning_rate": 5.5288410805796895e-05,
1514
+ "loss": 0.7852,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.48,
1519
+ "learning_rate": 5.497839232979084e-05,
1520
+ "loss": 0.8008,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.49,
1525
+ "learning_rate": 5.466818042264753e-05,
1526
+ "loss": 0.7969,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.49,
1531
+ "learning_rate": 5.435778713738292e-05,
1532
+ "loss": 0.793,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.49,
1537
+ "learning_rate": 5.404722453406017e-05,
1538
+ "loss": 0.7812,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.49,
1543
+ "learning_rate": 5.373650467932122e-05,
1544
+ "loss": 0.7773,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.49,
1549
+ "learning_rate": 5.3425639645917834e-05,
1550
+ "loss": 0.793,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.5,
1555
+ "learning_rate": 5.311464151224261e-05,
1556
+ "loss": 0.7734,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.5,
1561
+ "learning_rate": 5.2803522361859594e-05,
1562
+ "loss": 0.7773,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.5,
1567
+ "learning_rate": 5.249229428303486e-05,
1568
+ "loss": 0.7773,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.5,
1573
+ "learning_rate": 5.218096936826681e-05,
1574
+ "loss": 0.7812,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.5,
1579
+ "learning_rate": 5.18695597138163e-05,
1580
+ "loss": 0.8047,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.51,
1585
+ "learning_rate": 5.155807741923666e-05,
1586
+ "loss": 0.7852,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.51,
1591
+ "learning_rate": 5.124653458690365e-05,
1592
+ "loss": 0.7617,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.51,
1597
+ "learning_rate": 5.0934943321545115e-05,
1598
+ "loss": 0.7852,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.51,
1603
+ "learning_rate": 5.062331572977076e-05,
1604
+ "loss": 0.7852,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.51,
1609
+ "learning_rate": 5.031166391960168e-05,
1610
+ "loss": 0.7812,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.52,
1615
+ "learning_rate": 5e-05,
1616
+ "loss": 0.8008,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.52,
1621
+ "learning_rate": 4.968833608039832e-05,
1622
+ "loss": 0.7852,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.52,
1627
+ "learning_rate": 4.9376684270229254e-05,
1628
+ "loss": 0.7773,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.52,
1633
+ "learning_rate": 4.9065056678454904e-05,
1634
+ "loss": 0.7812,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.52,
1639
+ "learning_rate": 4.875346541309637e-05,
1640
+ "loss": 0.793,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.53,
1645
+ "learning_rate": 4.844192258076336e-05,
1646
+ "loss": 0.7812,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.53,
1651
+ "learning_rate": 4.813044028618373e-05,
1652
+ "loss": 0.8008,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.53,
1657
+ "learning_rate": 4.781903063173321e-05,
1658
+ "loss": 0.793,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.53,
1663
+ "learning_rate": 4.750770571696514e-05,
1664
+ "loss": 0.7852,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.53,
1669
+ "learning_rate": 4.7196477638140404e-05,
1670
+ "loss": 0.7617,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.53,
1675
+ "learning_rate": 4.68853584877574e-05,
1676
+ "loss": 0.7734,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.54,
1681
+ "learning_rate": 4.657436035408217e-05,
1682
+ "loss": 0.7734,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.54,
1687
+ "learning_rate": 4.626349532067879e-05,
1688
+ "loss": 0.7773,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.54,
1693
+ "learning_rate": 4.595277546593984e-05,
1694
+ "loss": 0.7695,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.54,
1699
+ "learning_rate": 4.564221286261709e-05,
1700
+ "loss": 0.7891,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.54,
1705
+ "learning_rate": 4.5331819577352474e-05,
1706
+ "loss": 0.7734,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.55,
1711
+ "learning_rate": 4.502160767020918e-05,
1712
+ "loss": 0.7734,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.55,
1717
+ "learning_rate": 4.471158919420312e-05,
1718
+ "loss": 0.793,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.55,
1723
+ "learning_rate": 4.4401776194834613e-05,
1724
+ "loss": 0.7812,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.55,
1729
+ "learning_rate": 4.409218070962036e-05,
1730
+ "loss": 0.7891,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.55,
1735
+ "learning_rate": 4.378281476762576e-05,
1736
+ "loss": 0.7773,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.56,
1741
+ "learning_rate": 4.347369038899744e-05,
1742
+ "loss": 0.7734,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.56,
1747
+ "learning_rate": 4.316481958449634e-05,
1748
+ "loss": 0.7812,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.56,
1753
+ "learning_rate": 4.285621435503101e-05,
1754
+ "loss": 0.7734,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.56,
1759
+ "learning_rate": 4.254788669119127e-05,
1760
+ "loss": 0.7812,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.56,
1765
+ "learning_rate": 4.223984857278242e-05,
1766
+ "loss": 0.7812,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.57,
1771
+ "learning_rate": 4.1932111968359664e-05,
1772
+ "loss": 0.7773,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.57,
1777
+ "learning_rate": 4.162468883476319e-05,
1778
+ "loss": 0.7891,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.57,
1783
+ "learning_rate": 4.131759111665349e-05,
1784
+ "loss": 0.7773,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.57,
1789
+ "learning_rate": 4.101083074604737e-05,
1790
+ "loss": 0.7773,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.57,
1795
+ "learning_rate": 4.0704419641854274e-05,
1796
+ "loss": 0.8008,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.57,
1801
+ "learning_rate": 4.03983697094132e-05,
1802
+ "loss": 0.7656,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.58,
1807
+ "learning_rate": 4.0092692840030134e-05,
1808
+ "loss": 0.7773,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.58,
1813
+ "learning_rate": 3.978740091051599e-05,
1814
+ "loss": 0.7695,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.58,
1819
+ "learning_rate": 3.9482505782725224e-05,
1820
+ "loss": 0.7578,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.58,
1825
+ "learning_rate": 3.917801930309486e-05,
1826
+ "loss": 0.7812,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.58,
1831
+ "learning_rate": 3.887395330218429e-05,
1832
+ "loss": 0.7773,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.59,
1837
+ "learning_rate": 3.857031959421553e-05,
1838
+ "loss": 0.7773,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.59,
1843
+ "learning_rate": 3.8267129976614254e-05,
1844
+ "loss": 0.7734,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.59,
1849
+ "learning_rate": 3.7964396229551364e-05,
1850
+ "loss": 0.7617,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.59,
1855
+ "learning_rate": 3.7662130115485314e-05,
1856
+ "loss": 0.7656,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.59,
1861
+ "learning_rate": 3.7360343378705124e-05,
1862
+ "loss": 0.7852,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.6,
1867
+ "learning_rate": 3.705904774487396e-05,
1868
+ "loss": 0.7812,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.6,
1873
+ "learning_rate": 3.675825492057364e-05,
1874
+ "loss": 0.7773,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.6,
1879
+ "learning_rate": 3.6457976592849754e-05,
1880
+ "loss": 0.7695,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.6,
1885
+ "learning_rate": 3.6158224428757535e-05,
1886
+ "loss": 0.7578,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.6,
1891
+ "learning_rate": 3.585901007490863e-05,
1892
+ "loss": 0.793,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.61,
1897
+ "learning_rate": 3.556034515701852e-05,
1898
+ "loss": 0.7656,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.61,
1903
+ "learning_rate": 3.5262241279454785e-05,
1904
+ "loss": 0.7617,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.61,
1909
+ "learning_rate": 3.4964710024786354e-05,
1910
+ "loss": 0.7812,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.61,
1915
+ "learning_rate": 3.4667762953333295e-05,
1916
+ "loss": 0.7539,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.61,
1921
+ "learning_rate": 3.4371411602717784e-05,
1922
+ "loss": 0.7812,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.62,
1927
+ "learning_rate": 3.4075667487415785e-05,
1928
+ "loss": 0.7656,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.62,
1933
+ "learning_rate": 3.3780542098309654e-05,
1934
+ "loss": 0.7578,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.62,
1939
+ "learning_rate": 3.3486046902241664e-05,
1940
+ "loss": 0.7539,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.62,
1945
+ "learning_rate": 3.319219334156847e-05,
1946
+ "loss": 0.7656,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.62,
1951
+ "learning_rate": 3.289899283371657e-05,
1952
+ "loss": 0.7695,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.62,
1957
+ "learning_rate": 3.2606456770738636e-05,
1958
+ "loss": 0.7773,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.63,
1963
+ "learning_rate": 3.231459651887093e-05,
1964
+ "loss": 0.793,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.63,
1969
+ "learning_rate": 3.2023423418091626e-05,
1970
+ "loss": 0.7656,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.63,
1975
+ "learning_rate": 3.173294878168025e-05,
1976
+ "loss": 0.7617,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.63,
1981
+ "learning_rate": 3.1443183895778105e-05,
1982
+ "loss": 0.7773,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.63,
1987
+ "learning_rate": 3.115414001894974e-05,
1988
+ "loss": 0.7578,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.64,
1993
+ "learning_rate": 3.086582838174551e-05,
1994
+ "loss": 0.7656,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.64,
1999
+ "learning_rate": 3.0578260186265265e-05,
2000
+ "loss": 0.7539,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.64,
2005
+ "learning_rate": 3.029144660572304e-05,
2006
+ "loss": 0.7656,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.64,
2011
+ "learning_rate": 3.000539878401296e-05,
2012
+ "loss": 0.7734,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.64,
2017
+ "learning_rate": 2.9720127835276256e-05,
2018
+ "loss": 0.7617,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.65,
2023
+ "learning_rate": 2.9435644843469436e-05,
2024
+ "loss": 0.7734,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.65,
2029
+ "learning_rate": 2.9151960861933614e-05,
2030
+ "loss": 0.7539,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.65,
2035
+ "learning_rate": 2.886908691296504e-05,
2036
+ "loss": 0.7852,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.65,
2041
+ "learning_rate": 2.858703398738686e-05,
2042
+ "loss": 0.7852,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.65,
2047
+ "learning_rate": 2.8305813044122097e-05,
2048
+ "loss": 0.7656,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.66,
2053
+ "learning_rate": 2.8025435009767747e-05,
2054
+ "loss": 0.7656,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.66,
2059
+ "learning_rate": 2.774591077817038e-05,
2060
+ "loss": 0.7656,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.66,
2065
+ "learning_rate": 2.746725121000273e-05,
2066
+ "loss": 0.7656,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.66,
2071
+ "learning_rate": 2.718946713234185e-05,
2072
+ "loss": 0.7617,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.66,
2077
+ "learning_rate": 2.6912569338248315e-05,
2078
+ "loss": 0.7656,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.67,
2083
+ "learning_rate": 2.66365685863469e-05,
2084
+ "loss": 0.7578,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.67,
2089
+ "learning_rate": 2.636147560040866e-05,
2090
+ "loss": 0.7695,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.67,
2095
+ "learning_rate": 2.6087301068934106e-05,
2096
+ "loss": 0.7617,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.67,
2101
+ "learning_rate": 2.581405564473801e-05,
2102
+ "loss": 0.7695,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.67,
2107
+ "learning_rate": 2.5541749944535554e-05,
2108
+ "loss": 0.7617,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.68,
2113
+ "learning_rate": 2.527039454852963e-05,
2114
+ "loss": 0.7812,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.68,
2119
+ "learning_rate": 2.500000000000001e-05,
2120
+ "loss": 0.7578,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.68,
2125
+ "learning_rate": 2.473057680489348e-05,
2126
+ "loss": 0.7617,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.68,
2131
+ "learning_rate": 2.4462135431415733e-05,
2132
+ "loss": 0.7656,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.68,
2137
+ "learning_rate": 2.4194686309624663e-05,
2138
+ "loss": 0.75,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.68,
2143
+ "learning_rate": 2.39282398310251e-05,
2144
+ "loss": 0.7617,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.69,
2149
+ "learning_rate": 2.366280634816496e-05,
2150
+ "loss": 0.7656,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.69,
2155
+ "learning_rate": 2.3398396174233178e-05,
2156
+ "loss": 0.7695,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.69,
2161
+ "learning_rate": 2.3135019582658802e-05,
2162
+ "loss": 0.7422,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.69,
2167
+ "learning_rate": 2.2872686806712035e-05,
2168
+ "loss": 0.7695,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.69,
2173
+ "learning_rate": 2.261140803910644e-05,
2174
+ "loss": 0.7695,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.7,
2179
+ "learning_rate": 2.235119343160303e-05,
2180
+ "loss": 0.7539,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.7,
2185
+ "learning_rate": 2.2092053094615813e-05,
2186
+ "loss": 0.7695,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.7,
2191
+ "learning_rate": 2.1833997096818898e-05,
2192
+ "loss": 0.7773,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.7,
2197
+ "learning_rate": 2.157703546475539e-05,
2198
+ "loss": 0.7461,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.7,
2203
+ "learning_rate": 2.132117818244771e-05,
2204
+ "loss": 0.75,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.71,
2209
+ "learning_rate": 2.1066435191009715e-05,
2210
+ "loss": 0.7422,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.71,
2215
+ "learning_rate": 2.0812816388260518e-05,
2216
+ "loss": 0.7617,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.71,
2221
+ "learning_rate": 2.056033162833977e-05,
2222
+ "loss": 0.7695,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.71,
2227
+ "learning_rate": 2.0308990721324927e-05,
2228
+ "loss": 0.7617,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.71,
2233
+ "learning_rate": 2.0058803432849987e-05,
2234
+ "loss": 0.7656,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.72,
2239
+ "learning_rate": 1.980977948372612e-05,
2240
+ "loss": 0.7461,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.72,
2245
+ "learning_rate": 1.9561928549563968e-05,
2246
+ "loss": 0.7461,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.72,
2251
+ "learning_rate": 1.931526026039764e-05,
2252
+ "loss": 0.7461,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.72,
2257
+ "learning_rate": 1.906978420031059e-05,
2258
+ "loss": 0.7422,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 0.72,
2263
+ "learning_rate": 1.8825509907063327e-05,
2264
+ "loss": 0.75,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 0.72,
2269
+ "learning_rate": 1.8582446871722636e-05,
2270
+ "loss": 0.7344,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 0.73,
2275
+ "learning_rate": 1.8340604538293015e-05,
2276
+ "loss": 0.7461,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 0.73,
2281
+ "learning_rate": 1.8099992303349577e-05,
2282
+ "loss": 0.7422,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 0.73,
2287
+ "learning_rate": 1.7860619515673033e-05,
2288
+ "loss": 0.7617,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 0.73,
2293
+ "learning_rate": 1.7622495475886487e-05,
2294
+ "loss": 0.7539,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 0.73,
2299
+ "learning_rate": 1.738562943609396e-05,
2300
+ "loss": 0.7539,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 0.74,
2305
+ "learning_rate": 1.7150030599520984e-05,
2306
+ "loss": 0.7617,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 0.74,
2311
+ "learning_rate": 1.691570812015704e-05,
2312
+ "loss": 0.7422,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 0.74,
2317
+ "learning_rate": 1.6682671102399805e-05,
2318
+ "loss": 0.75,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 0.74,
2323
+ "learning_rate": 1.6450928600701504e-05,
2324
+ "loss": 0.75,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 0.74,
2329
+ "learning_rate": 1.622048961921699e-05,
2330
+ "loss": 0.7617,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 0.75,
2335
+ "learning_rate": 1.599136311145402e-05,
2336
+ "loss": 0.7695,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 0.75,
2341
+ "learning_rate": 1.5763557979925324e-05,
2342
+ "loss": 0.7461,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 0.75,
2347
+ "learning_rate": 1.553708307580265e-05,
2348
+ "loss": 0.7617,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 0.75,
2353
+ "learning_rate": 1.531194719857292e-05,
2354
+ "loss": 0.793,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 0.75,
2359
+ "learning_rate": 1.5088159095696363e-05,
2360
+ "loss": 0.7539,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 0.76,
2365
+ "learning_rate": 1.4865727462266543e-05,
2366
+ "loss": 0.7734,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 0.76,
2371
+ "learning_rate": 1.4644660940672627e-05,
2372
+ "loss": 0.7734,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 0.76,
2377
+ "learning_rate": 1.4424968120263504e-05,
2378
+ "loss": 0.7461,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 0.76,
2383
+ "learning_rate": 1.4206657537014079e-05,
2384
+ "loss": 0.7578,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 0.76,
2389
+ "learning_rate": 1.398973767319368e-05,
2390
+ "loss": 0.7578,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 0.77,
2395
+ "learning_rate": 1.3774216957036367e-05,
2396
+ "loss": 0.7539,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 0.77,
2401
+ "learning_rate": 1.3560103762413584e-05,
2402
+ "loss": 0.7539,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 0.77,
2407
+ "learning_rate": 1.3347406408508695e-05,
2408
+ "loss": 0.7539,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 0.77,
2413
+ "learning_rate": 1.3136133159493802e-05,
2414
+ "loss": 0.7617,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 0.77,
2419
+ "learning_rate": 1.2926292224208664e-05,
2420
+ "loss": 0.7422,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 0.78,
2425
+ "learning_rate": 1.2717891755841722e-05,
2426
+ "loss": 0.7734,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 0.78,
2431
+ "learning_rate": 1.2510939851613285e-05,
2432
+ "loss": 0.7734,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 0.78,
2437
+ "learning_rate": 1.230544455246101e-05,
2438
+ "loss": 0.75,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 0.78,
2443
+ "learning_rate": 1.2101413842727345e-05,
2444
+ "loss": 0.7461,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 0.78,
2449
+ "learning_rate": 1.1898855649849461e-05,
2450
+ "loss": 0.7539,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 0.78,
2455
+ "learning_rate": 1.1697777844051105e-05,
2456
+ "loss": 0.7305,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 0.79,
2461
+ "learning_rate": 1.1498188238036861e-05,
2462
+ "loss": 0.7422,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 0.79,
2467
+ "learning_rate": 1.130009458668863e-05,
2468
+ "loss": 0.75,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 0.79,
2473
+ "learning_rate": 1.1103504586764263e-05,
2474
+ "loss": 0.7539,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 0.79,
2479
+ "learning_rate": 1.090842587659851e-05,
2480
+ "loss": 0.7617,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 0.79,
2485
+ "learning_rate": 1.0714866035806326e-05,
2486
+ "loss": 0.7422,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 0.8,
2491
+ "learning_rate": 1.0522832584988234e-05,
2492
+ "loss": 0.7617,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 0.8,
2497
+ "learning_rate": 1.0332332985438248e-05,
2498
+ "loss": 0.7656,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 0.8,
2503
+ "learning_rate": 1.0143374638853891e-05,
2504
+ "loss": 0.7656,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 0.8,
2509
+ "learning_rate": 9.955964887048607e-06,
2510
+ "loss": 0.7656,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 0.8,
2515
+ "learning_rate": 9.770111011666583e-06,
2516
+ "loss": 0.7617,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 0.81,
2521
+ "learning_rate": 9.58582023389974e-06,
2522
+ "loss": 0.7461,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 0.81,
2527
+ "learning_rate": 9.403099714207175e-06,
2528
+ "loss": 0.7539,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 0.81,
2533
+ "learning_rate": 9.221956552036992e-06,
2534
+ "loss": 0.7422,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 0.81,
2539
+ "learning_rate": 9.042397785550405e-06,
2540
+ "loss": 0.7461,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 0.81,
2545
+ "learning_rate": 8.864430391348332e-06,
2546
+ "loss": 0.7578,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 0.82,
2551
+ "learning_rate": 8.688061284200266e-06,
2552
+ "loss": 0.7383,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 0.82,
2557
+ "learning_rate": 8.513297316775625e-06,
2558
+ "loss": 0.7539,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 0.82,
2563
+ "learning_rate": 8.34014527937756e-06,
2564
+ "loss": 0.75,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 0.82,
2569
+ "learning_rate": 8.168611899679013e-06,
2570
+ "loss": 0.7383,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 0.82,
2575
+ "learning_rate": 7.998703842461431e-06,
2576
+ "loss": 0.7695,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 0.82,
2581
+ "learning_rate": 7.830427709355725e-06,
2582
+ "loss": 0.7383,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 0.83,
2587
+ "learning_rate": 7.663790038585793e-06,
2588
+ "loss": 0.7578,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 0.83,
2593
+ "learning_rate": 7.498797304714544e-06,
2594
+ "loss": 0.7539,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 0.83,
2599
+ "learning_rate": 7.33545591839222e-06,
2600
+ "loss": 0.7227,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 0.83,
2605
+ "learning_rate": 7.173772226107434e-06,
2606
+ "loss": 0.75,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 0.83,
2611
+ "learning_rate": 7.013752509940485e-06,
2612
+ "loss": 0.7617,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 0.84,
2617
+ "learning_rate": 6.855402987319348e-06,
2618
+ "loss": 0.7344,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 0.84,
2623
+ "learning_rate": 6.698729810778065e-06,
2624
+ "loss": 0.7539,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 0.84,
2629
+ "learning_rate": 6.54373906771768e-06,
2630
+ "loss": 0.7656,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 0.84,
2635
+ "learning_rate": 6.390436780169734e-06,
2636
+ "loss": 0.7344,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 0.84,
2641
+ "learning_rate": 6.238828904562316e-06,
2642
+ "loss": 0.7305,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 0.85,
2647
+ "learning_rate": 6.088921331488568e-06,
2648
+ "loss": 0.7617,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 0.85,
2653
+ "learning_rate": 5.94071988547788e-06,
2654
+ "loss": 0.7422,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 0.85,
2659
+ "learning_rate": 5.794230324769517e-06,
2660
+ "loss": 0.7383,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 0.85,
2665
+ "learning_rate": 5.649458341088915e-06,
2666
+ "loss": 0.7617,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 0.85,
2671
+ "learning_rate": 5.506409559426573e-06,
2672
+ "loss": 0.7461,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 0.86,
2677
+ "learning_rate": 5.365089537819434e-06,
2678
+ "loss": 0.75,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 0.86,
2683
+ "learning_rate": 5.2255037671349535e-06,
2684
+ "loss": 0.7266,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 0.86,
2689
+ "learning_rate": 5.087657670857798e-06,
2690
+ "loss": 0.7578,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 0.86,
2695
+ "learning_rate": 4.951556604879048e-06,
2696
+ "loss": 0.75,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 0.86,
2701
+ "learning_rate": 4.8172058572881765e-06,
2702
+ "loss": 0.7461,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 0.87,
2707
+ "learning_rate": 4.684610648167503e-06,
2708
+ "loss": 0.7578,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 0.87,
2713
+ "learning_rate": 4.5537761293894535e-06,
2714
+ "loss": 0.7578,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 0.87,
2719
+ "learning_rate": 4.424707384416344e-06,
2720
+ "loss": 0.7383,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 0.87,
2725
+ "learning_rate": 4.29740942810285e-06,
2726
+ "loss": 0.7383,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 0.87,
2731
+ "learning_rate": 4.1718872065011904e-06,
2732
+ "loss": 0.7422,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 0.88,
2737
+ "learning_rate": 4.048145596668967e-06,
2738
+ "loss": 0.7305,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 0.88,
2743
+ "learning_rate": 3.9261894064796135e-06,
2744
+ "loss": 0.7617,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 0.88,
2749
+ "learning_rate": 3.8060233744356633e-06,
2750
+ "loss": 0.7695,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 0.88,
2755
+ "learning_rate": 3.687652169484568e-06,
2756
+ "loss": 0.7383,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 0.88,
2761
+ "learning_rate": 3.5710803908373224e-06,
2762
+ "loss": 0.75,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 0.88,
2767
+ "learning_rate": 3.4563125677897932e-06,
2768
+ "loss": 0.7578,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 0.89,
2773
+ "learning_rate": 3.343353159546675e-06,
2774
+ "loss": 0.7383,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 0.89,
2779
+ "learning_rate": 3.2322065550483007e-06,
2780
+ "loss": 0.7461,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 0.89,
2785
+ "learning_rate": 3.1228770728000455e-06,
2786
+ "loss": 0.7461,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 0.89,
2791
+ "learning_rate": 3.0153689607045845e-06,
2792
+ "loss": 0.7539,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 0.89,
2797
+ "learning_rate": 2.9096863958968268e-06,
2798
+ "loss": 0.7422,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 0.9,
2803
+ "learning_rate": 2.8058334845816213e-06,
2804
+ "loss": 0.7461,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 0.9,
2809
+ "learning_rate": 2.7038142618741992e-06,
2810
+ "loss": 0.7617,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 0.9,
2815
+ "learning_rate": 2.603632691643415e-06,
2816
+ "loss": 0.7422,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 0.9,
2821
+ "learning_rate": 2.5052926663577e-06,
2822
+ "loss": 0.7656,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 0.9,
2827
+ "learning_rate": 2.408798006933882e-06,
2828
+ "loss": 0.7461,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 0.91,
2833
+ "learning_rate": 2.314152462588659e-06,
2834
+ "loss": 0.7422,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 0.91,
2839
+ "learning_rate": 2.221359710692961e-06,
2840
+ "loss": 0.75,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 0.91,
2845
+ "learning_rate": 2.1304233566290964e-06,
2846
+ "loss": 0.7578,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 0.91,
2851
+ "learning_rate": 2.041346933650612e-06,
2852
+ "loss": 0.7539,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 0.91,
2857
+ "learning_rate": 1.9541339027450256e-06,
2858
+ "loss": 0.75,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 0.92,
2863
+ "learning_rate": 1.8687876524993987e-06,
2864
+ "loss": 0.7656,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 0.92,
2869
+ "learning_rate": 1.785311498968617e-06,
2870
+ "loss": 0.7578,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 0.92,
2875
+ "learning_rate": 1.70370868554659e-06,
2876
+ "loss": 0.7305,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 0.92,
2881
+ "learning_rate": 1.6239823828401945e-06,
2882
+ "loss": 0.7266,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 0.92,
2887
+ "learning_rate": 1.5461356885461075e-06,
2888
+ "loss": 0.7617,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 0.93,
2893
+ "learning_rate": 1.4701716273304521e-06,
2894
+ "loss": 0.7383,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 0.93,
2899
+ "learning_rate": 1.3960931507112752e-06,
2900
+ "loss": 0.7617,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 0.93,
2905
+ "learning_rate": 1.3239031369438326e-06,
2906
+ "loss": 0.75,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 0.93,
2911
+ "learning_rate": 1.2536043909088191e-06,
2912
+ "loss": 0.7539,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 0.93,
2917
+ "learning_rate": 1.1851996440033319e-06,
2918
+ "loss": 0.7578,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 0.93,
2923
+ "learning_rate": 1.118691554034773e-06,
2924
+ "loss": 0.75,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 0.94,
2929
+ "learning_rate": 1.0540827051175818e-06,
2930
+ "loss": 0.75,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 0.94,
2935
+ "learning_rate": 9.913756075728087e-07,
2936
+ "loss": 0.7695,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 0.94,
2941
+ "learning_rate": 9.305726978306173e-07,
2942
+ "loss": 0.75,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 0.94,
2947
+ "learning_rate": 8.716763383355864e-07,
2948
+ "loss": 0.7656,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 0.94,
2953
+ "learning_rate": 8.146888174549339e-07,
2954
+ "loss": 0.7773,
2955
+ "step": 491
2956
+ },
2957
+ {
2958
+ "epoch": 0.95,
2959
+ "learning_rate": 7.596123493895991e-07,
2960
+ "loss": 0.7695,
2961
+ "step": 492
2962
+ },
2963
+ {
2964
+ "epoch": 0.95,
2965
+ "learning_rate": 7.064490740882057e-07,
2966
+ "loss": 0.7461,
2967
+ "step": 493
2968
+ },
2969
+ {
2970
+ "epoch": 0.95,
2971
+ "learning_rate": 6.552010571639456e-07,
2972
+ "loss": 0.7539,
2973
+ "step": 494
2974
+ },
2975
+ {
2976
+ "epoch": 0.95,
2977
+ "learning_rate": 6.058702898142643e-07,
2978
+ "loss": 0.7656,
2979
+ "step": 495
2980
+ },
2981
+ {
2982
+ "epoch": 0.95,
2983
+ "learning_rate": 5.584586887435739e-07,
2984
+ "loss": 0.7539,
2985
+ "step": 496
2986
+ },
2987
+ {
2988
+ "epoch": 0.96,
2989
+ "learning_rate": 5.129680960887007e-07,
2990
+ "loss": 0.7461,
2991
+ "step": 497
2992
+ },
2993
+ {
2994
+ "epoch": 0.96,
2995
+ "learning_rate": 4.6940027934735954e-07,
2996
+ "loss": 0.7656,
2997
+ "step": 498
2998
+ },
2999
+ {
3000
+ "epoch": 0.96,
3001
+ "learning_rate": 4.277569313094809e-07,
3002
+ "loss": 0.7656,
3003
+ "step": 499
3004
+ },
3005
+ {
3006
+ "epoch": 0.96,
3007
+ "learning_rate": 3.8803966999139684e-07,
3008
+ "loss": 0.7734,
3009
+ "step": 500
3010
+ },
3011
+ {
3012
+ "epoch": 0.96,
3013
+ "learning_rate": 3.50250038573019e-07,
3014
+ "loss": 0.7461,
3015
+ "step": 501
3016
+ },
3017
+ {
3018
+ "epoch": 0.97,
3019
+ "learning_rate": 3.143895053378698e-07,
3020
+ "loss": 0.7539,
3021
+ "step": 502
3022
+ },
3023
+ {
3024
+ "epoch": 0.97,
3025
+ "learning_rate": 2.8045946361601183e-07,
3026
+ "loss": 0.7383,
3027
+ "step": 503
3028
+ },
3029
+ {
3030
+ "epoch": 0.97,
3031
+ "learning_rate": 2.4846123172992954e-07,
3032
+ "loss": 0.7422,
3033
+ "step": 504
3034
+ },
3035
+ {
3036
+ "epoch": 0.97,
3037
+ "learning_rate": 2.1839605294330933e-07,
3038
+ "loss": 0.7578,
3039
+ "step": 505
3040
+ },
3041
+ {
3042
+ "epoch": 0.97,
3043
+ "learning_rate": 1.9026509541272275e-07,
3044
+ "loss": 0.7422,
3045
+ "step": 506
3046
+ },
3047
+ {
3048
+ "epoch": 0.97,
3049
+ "learning_rate": 1.640694521422459e-07,
3050
+ "loss": 0.7422,
3051
+ "step": 507
3052
+ },
3053
+ {
3054
+ "epoch": 0.98,
3055
+ "learning_rate": 1.3981014094099353e-07,
3056
+ "loss": 0.7461,
3057
+ "step": 508
3058
+ },
3059
+ {
3060
+ "epoch": 0.98,
3061
+ "learning_rate": 1.1748810438355628e-07,
3062
+ "loss": 0.75,
3063
+ "step": 509
3064
+ },
3065
+ {
3066
+ "epoch": 0.98,
3067
+ "learning_rate": 9.710420977340762e-08,
3068
+ "loss": 0.7461,
3069
+ "step": 510
3070
+ },
3071
+ {
3072
+ "epoch": 0.98,
3073
+ "learning_rate": 7.865924910916977e-08,
3074
+ "loss": 0.7539,
3075
+ "step": 511
3076
+ },
3077
+ {
3078
+ "epoch": 0.98,
3079
+ "learning_rate": 6.215393905388278e-08,
3080
+ "loss": 0.7578,
3081
+ "step": 512
3082
+ },
3083
+ {
3084
+ "epoch": 0.99,
3085
+ "learning_rate": 4.7588920907110094e-08,
3086
+ "loss": 0.7422,
3087
+ "step": 513
3088
+ },
3089
+ {
3090
+ "epoch": 0.99,
3091
+ "learning_rate": 3.496476058006959e-08,
3092
+ "loss": 0.7422,
3093
+ "step": 514
3094
+ },
3095
+ {
3096
+ "epoch": 0.99,
3097
+ "learning_rate": 2.4281948573617874e-08,
3098
+ "loss": 0.7578,
3099
+ "step": 515
3100
+ },
3101
+ {
3102
+ "epoch": 0.99,
3103
+ "learning_rate": 1.5540899959187727e-08,
3104
+ "loss": 0.7539,
3105
+ "step": 516
3106
+ },
3107
+ {
3108
+ "epoch": 0.99,
3109
+ "learning_rate": 8.741954362678772e-09,
3110
+ "loss": 0.7656,
3111
+ "step": 517
3112
+ },
3113
+ {
3114
+ "epoch": 1.0,
3115
+ "learning_rate": 3.885375951256931e-09,
3116
+ "loss": 0.75,
3117
+ "step": 518
3118
+ },
3119
+ {
3120
+ "epoch": 1.0,
3121
+ "learning_rate": 9.713534230904041e-10,
3122
+ "loss": 0.75,
3123
+ "step": 519
3124
+ },
3125
+ {
3126
+ "epoch": 1.0,
3127
+ "learning_rate": 0.0,
3128
+ "loss": 0.7578,
3129
+ "step": 520
3130
+ },
3131
+ {
3132
+ "epoch": 1.0,
3133
+ "step": 520,
3134
+ "total_flos": 2.976872756622131e+16,
3135
+ "train_loss": 0.17339993990384617,
3136
+ "train_runtime": 2924.9681,
3137
+ "train_samples_per_second": 728.716,
3138
+ "train_steps_per_second": 0.178
3139
+ }
3140
+ ],
3141
+ "logging_steps": 1.0,
3142
+ "max_steps": 520,
3143
+ "num_input_tokens_seen": 0,
3144
+ "num_train_epochs": 1,
3145
+ "save_steps": 200,
3146
+ "total_flos": 2.976872756622131e+16,
3147
+ "train_batch_size": 8,
3148
+ "trial_name": null,
3149
+ "trial_params": null
3150
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b87ca0b3571ff01ae796139be5d9fe5f3592d4094c477db08bddf3bc2dd38c8
3
+ size 6523
vila-13b-w4-g128-awq-real-v2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530a4fc2ab4b9e9adddd9cd4501335af5a5bcd53b7c8becae4909e475abb9b23
3
+ size 7400195675