Hugging Face's logo

prometheus-eval
/
prometheus-vision-13b-v1.0

Image-to-Text
Transformers
PyTorch
English
llava
text-generation
Image-to-Text
Visual Question Answering
Text2Text Generation
Model card Files
xet
Community
1
Seongyun commited on
Commit
5cec83c
·
verified ·
1 Parent(s): 80c2493

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. config.json +41 -0
  2. generation_config.json +10 -0
  3. pytorch_model-00001-of-00003.bin +3 -0
  4. pytorch_model-00002-of-00003.bin +3 -0
  5. pytorch_model-00003-of-00003.bin +3 -0
  6. pytorch_model.bin.index.json +805 -0
  7. special_tokens_map.json +24 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +35 -0
  10. trainer_state.json +1135 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lmsys/vicuna-13b-v1.5",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "freeze_mm_mlp_adapter": false,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "image_aspect_ratio": "pad",
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_length": 4096,
15
+ "max_position_embeddings": 4096,
16
+ "mm_hidden_size": 1024,
17
+ "mm_projector_lr": null,
18
+ "mm_projector_type": "mlp2x_gelu",
19
+ "mm_use_im_patch_token": false,
20
+ "mm_use_im_start_end": false,
21
+ "mm_vision_select_feature": "patch",
22
+ "mm_vision_select_layer": -2,
23
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
24
+ "model_type": "llava",
25
+ "num_attention_heads": 40,
26
+ "num_hidden_layers": 40,
27
+ "num_key_value_heads": 40,
28
+ "pad_token_id": 0,
29
+ "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": null,
32
+ "tie_word_embeddings": false,
33
+ "tokenizer_model_max_length": 2048,
34
+ "tokenizer_padding_side": "right",
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.31.0",
37
+ "tune_mm_mlp_adapter": false,
38
+ "use_cache": true,
39
+ "use_mm_proj": true,
40
+ "vocab_size": 32000
41
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.9,
8
+ "top_p": 0.6,
9
+ "transformers_version": "4.31.0"
10
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30805b8618fb7920b0a169f5dd24cfaaca1ae6406618f5a3820e2c2f5b24d17f
3
+ size 9948726510
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088821004c57c91188b2c3db9e0c002da52f136972c4be6c0f0fcd804ce59ed0
3
+ size 9904162976
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad57dd745bdb13ac6396a11898231085f54844f928ee94d65b41c2f2eda8a61
3
+ size 6849082169
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,805 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26701683712
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
408
+ "model.mm_projector.0.bias": "pytorch_model-00003-of-00003.bin",
409
+ "model.mm_projector.0.weight": "pytorch_model-00003-of-00003.bin",
410
+ "model.mm_projector.2.bias": "pytorch_model-00003-of-00003.bin",
411
+ "model.mm_projector.2.weight": "pytorch_model-00003-of-00003.bin",
412
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin",
413
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin",
414
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin",
415
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
760
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
761
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
762
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
763
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
764
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
765
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
766
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
767
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
768
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
769
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
770
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
771
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
772
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
773
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
774
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
775
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
776
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
777
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
778
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
779
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
780
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
781
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
782
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
783
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
784
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
785
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
786
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
787
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
788
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
789
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
790
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
791
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
792
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
793
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
794
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
795
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
796
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
797
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
798
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
799
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
800
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin",
801
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin",
802
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin",
803
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin"
804
+ }
805
+ }
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
@@ -0,0 +1,1135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 185,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 3.3333333333333333e-06,
13
+ "loss": 1.7688,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 6.666666666666667e-06,
19
+ "loss": 1.7391,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 1e-05,
25
+ "loss": 1.7429,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 1.3333333333333333e-05,
31
+ "loss": 1.5504,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 1.6666666666666667e-05,
37
+ "loss": 1.5264,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 2e-05,
43
+ "loss": 1.4713,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 1.9998459887166635e-05,
49
+ "loss": 1.4709,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 1.9993840023056045e-05,
55
+ "loss": 1.4435,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.05,
60
+ "learning_rate": 1.9986141830690626e-05,
61
+ "loss": 1.4711,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 1.9975367681287358e-05,
67
+ "loss": 1.4134,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.06,
72
+ "learning_rate": 1.9961520893527385e-05,
73
+ "loss": 1.3935,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.06,
78
+ "learning_rate": 1.994460573253382e-05,
79
+ "loss": 1.3918,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 1.9924627408557963e-05,
85
+ "loss": 1.3569,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.08,
90
+ "learning_rate": 1.9901592075374447e-05,
91
+ "loss": 1.3551,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.08,
96
+ "learning_rate": 1.9875506828385723e-05,
97
+ "loss": 1.3527,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.09,
102
+ "learning_rate": 1.9846379702436518e-05,
103
+ "loss": 1.333,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.09,
108
+ "learning_rate": 1.981421966933893e-05,
109
+ "loss": 1.3099,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.1,
114
+ "learning_rate": 1.9779036635108892e-05,
115
+ "loss": 1.323,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.1,
120
+ "learning_rate": 1.9740841436914917e-05,
121
+ "loss": 1.2945,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.11,
126
+ "learning_rate": 1.9699645839739987e-05,
127
+ "loss": 1.3023,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.11,
132
+ "learning_rate": 1.9655462532757677e-05,
133
+ "loss": 1.2992,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.12,
138
+ "learning_rate": 1.9608305125423608e-05,
139
+ "loss": 1.3281,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.12,
144
+ "learning_rate": 1.9558188143283425e-05,
145
+ "loss": 1.2941,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.13,
150
+ "learning_rate": 1.9505127023498603e-05,
151
+ "loss": 1.2721,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.14,
156
+ "learning_rate": 1.9449138110091444e-05,
157
+ "loss": 1.3167,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.14,
162
+ "learning_rate": 1.9390238648910765e-05,
163
+ "loss": 1.293,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.15,
168
+ "learning_rate": 1.932844678231977e-05,
169
+ "loss": 1.2798,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "learning_rate": 1.9263781543607817e-05,
175
+ "loss": 1.2861,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.16,
180
+ "learning_rate": 1.9196262851127695e-05,
181
+ "loss": 1.2495,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.16,
186
+ "learning_rate": 1.9125911502160365e-05,
187
+ "loss": 1.2827,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.17,
192
+ "learning_rate": 1.905274916650891e-05,
193
+ "loss": 1.2822,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.17,
198
+ "learning_rate": 1.897679837982373e-05,
199
+ "loss": 1.2671,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.18,
204
+ "learning_rate": 1.8898082536661097e-05,
205
+ "loss": 1.291,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.18,
210
+ "learning_rate": 1.8816625883277044e-05,
211
+ "loss": 1.2679,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "learning_rate": 1.8732453510159025e-05,
217
+ "loss": 1.2845,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.19,
222
+ "learning_rate": 1.864559134429745e-05,
223
+ "loss": 1.2779,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.2,
228
+ "learning_rate": 1.85560661411996e-05,
229
+ "loss": 1.2692,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.21,
234
+ "learning_rate": 1.846390547664831e-05,
235
+ "loss": 1.229,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.21,
240
+ "learning_rate": 1.836913773820802e-05,
241
+ "loss": 1.2301,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.22,
246
+ "learning_rate": 1.8271792116480767e-05,
247
+ "loss": 1.2511,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.22,
252
+ "learning_rate": 1.8171898596114804e-05,
253
+ "loss": 1.256,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.23,
258
+ "learning_rate": 1.8069487946568675e-05,
259
+ "loss": 1.2418,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.23,
264
+ "learning_rate": 1.79645917126335e-05,
265
+ "loss": 1.2505,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.24,
270
+ "learning_rate": 1.7857242204716497e-05,
271
+ "loss": 1.241,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.24,
276
+ "learning_rate": 1.7747472488888622e-05,
277
+ "loss": 1.2763,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.25,
282
+ "learning_rate": 1.763531637669949e-05,
283
+ "loss": 1.2408,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.25,
288
+ "learning_rate": 1.752080841476264e-05,
289
+ "loss": 1.2506,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.26,
294
+ "learning_rate": 1.7403983874114422e-05,
295
+ "loss": 1.2697,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.26,
300
+ "learning_rate": 1.728487873934969e-05,
301
+ "loss": 1.243,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.27,
306
+ "learning_rate": 1.7163529697537756e-05,
307
+ "loss": 1.2553,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.28,
312
+ "learning_rate": 1.7039974126921946e-05,
313
+ "loss": 1.2179,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.28,
318
+ "learning_rate": 1.691425008540625e-05,
319
+ "loss": 1.2576,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.29,
324
+ "learning_rate": 1.6786396298832622e-05,
325
+ "loss": 1.2363,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.29,
330
+ "learning_rate": 1.6656452149052568e-05,
331
+ "loss": 1.2538,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.3,
336
+ "learning_rate": 1.6524457661796626e-05,
337
+ "loss": 1.2724,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.3,
342
+ "learning_rate": 1.639045349434554e-05,
343
+ "loss": 1.2504,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.31,
348
+ "learning_rate": 1.6254480923006924e-05,
349
+ "loss": 1.2342,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.31,
354
+ "learning_rate": 1.6116581830401193e-05,
355
+ "loss": 1.2184,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.32,
360
+ "learning_rate": 1.5976798692560796e-05,
361
+ "loss": 1.2136,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.32,
366
+ "learning_rate": 1.5835174565846624e-05,
367
+ "loss": 1.244,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.33,
372
+ "learning_rate": 1.5691753073685692e-05,
373
+ "loss": 1.2311,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.34,
378
+ "learning_rate": 1.554657839313413e-05,
379
+ "loss": 1.2291,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.34,
384
+ "learning_rate": 1.539969524126967e-05,
385
+ "loss": 1.2385,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.35,
390
+ "learning_rate": 1.5251148861417733e-05,
391
+ "loss": 1.2122,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.35,
396
+ "learning_rate": 1.5100985009215519e-05,
397
+ "loss": 1.2445,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.36,
402
+ "learning_rate": 1.4949249938518203e-05,
403
+ "loss": 1.2076,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.36,
408
+ "learning_rate": 1.4795990387151719e-05,
409
+ "loss": 1.2294,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.37,
414
+ "learning_rate": 1.464125356251644e-05,
415
+ "loss": 1.2505,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.37,
420
+ "learning_rate": 1.4485087127046256e-05,
421
+ "loss": 1.2479,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.38,
426
+ "learning_rate": 1.4327539183527447e-05,
427
+ "loss": 1.2212,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.38,
432
+ "learning_rate": 1.4168658260281944e-05,
433
+ "loss": 1.2062,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.39,
438
+ "learning_rate": 1.400849329621953e-05,
439
+ "loss": 1.2641,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.39,
444
+ "learning_rate": 1.3847093625763517e-05,
445
+ "loss": 1.221,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.4,
450
+ "learning_rate": 1.3684508963654667e-05,
451
+ "loss": 1.2079,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.41,
456
+ "learning_rate": 1.3520789389637898e-05,
457
+ "loss": 1.2164,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.41,
462
+ "learning_rate": 1.335598533303662e-05,
463
+ "loss": 1.23,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.42,
468
+ "learning_rate": 1.319014755721934e-05,
469
+ "loss": 1.2413,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.42,
474
+ "learning_rate": 1.3023327143963415e-05,
475
+ "loss": 1.2242,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.43,
480
+ "learning_rate": 1.285557547772072e-05,
481
+ "loss": 1.2217,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.43,
486
+ "learning_rate": 1.2686944229790044e-05,
487
+ "loss": 1.2362,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.44,
492
+ "learning_rate": 1.2517485342401201e-05,
493
+ "loss": 1.2078,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.44,
498
+ "learning_rate": 1.2347251012715629e-05,
499
+ "loss": 1.2465,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.45,
504
+ "learning_rate": 1.2176293676748494e-05,
505
+ "loss": 1.2225,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.45,
510
+ "learning_rate": 1.200466599321721e-05,
511
+ "loss": 1.2061,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.46,
516
+ "learning_rate": 1.1832420827321374e-05,
517
+ "loss": 1.2216,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.46,
522
+ "learning_rate": 1.165961123445908e-05,
523
+ "loss": 1.1804,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.47,
528
+ "learning_rate": 1.1486290443884666e-05,
529
+ "loss": 1.2526,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.48,
534
+ "learning_rate": 1.131251184231291e-05,
535
+ "loss": 1.2134,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.48,
540
+ "learning_rate": 1.1138328957474691e-05,
541
+ "loss": 1.2322,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.49,
546
+ "learning_rate": 1.0963795441629275e-05,
547
+ "loss": 1.2102,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.49,
552
+ "learning_rate": 1.0788965055038179e-05,
553
+ "loss": 1.2534,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.5,
558
+ "learning_rate": 1.0613891649405816e-05,
559
+ "loss": 1.2404,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.5,
564
+ "learning_rate": 1.0438629151291944e-05,
565
+ "loss": 1.2152,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.51,
570
+ "learning_rate": 1.0263231545501068e-05,
571
+ "loss": 1.196,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.51,
576
+ "learning_rate": 1.0087752858453923e-05,
577
+ "loss": 1.2154,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.52,
582
+ "learning_rate": 9.91224714154608e-06,
583
+ "loss": 1.1875,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.52,
588
+ "learning_rate": 9.736768454498935e-06,
589
+ "loss": 1.202,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.53,
594
+ "learning_rate": 9.561370848708061e-06,
595
+ "loss": 1.1861,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.54,
600
+ "learning_rate": 9.38610835059419e-06,
601
+ "loss": 1.215,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.54,
606
+ "learning_rate": 9.211034944961825e-06,
607
+ "loss": 1.2148,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.55,
612
+ "learning_rate": 9.036204558370725e-06,
613
+ "loss": 1.2427,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.55,
618
+ "learning_rate": 8.861671042525312e-06,
619
+ "loss": 1.1882,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.56,
624
+ "learning_rate": 8.68748815768709e-06,
625
+ "loss": 1.2084,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.56,
630
+ "learning_rate": 8.513709556115335e-06,
631
+ "loss": 1.2053,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.57,
636
+ "learning_rate": 8.340388765540923e-06,
637
+ "loss": 1.2001,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.57,
642
+ "learning_rate": 8.16757917267863e-06,
643
+ "loss": 1.2031,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.58,
648
+ "learning_rate": 7.995334006782793e-06,
649
+ "loss": 1.2149,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.58,
654
+ "learning_rate": 7.823706323251512e-06,
655
+ "loss": 1.2038,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.59,
660
+ "learning_rate": 7.652748987284375e-06,
661
+ "loss": 1.2453,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.59,
666
+ "learning_rate": 7.4825146575988e-06,
667
+ "loss": 1.1945,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.6,
672
+ "learning_rate": 7.313055770209961e-06,
673
+ "loss": 1.1938,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.61,
678
+ "learning_rate": 7.144424522279283e-06,
679
+ "loss": 1.2203,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.61,
684
+ "learning_rate": 6.976672856036586e-06,
685
+ "loss": 1.1908,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.62,
690
+ "learning_rate": 6.809852442780664e-06,
691
+ "loss": 1.1897,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.62,
696
+ "learning_rate": 6.6440146669633855e-06,
697
+ "loss": 1.2205,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.63,
702
+ "learning_rate": 6.479210610362103e-06,
703
+ "loss": 1.1937,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.63,
708
+ "learning_rate": 6.315491036345338e-06,
709
+ "loss": 1.183,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.64,
714
+ "learning_rate": 6.1529063742364844e-06,
715
+ "loss": 1.2156,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.64,
720
+ "learning_rate": 5.991506703780475e-06,
721
+ "loss": 1.2159,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.65,
726
+ "learning_rate": 5.831341739718055e-06,
727
+ "loss": 1.1891,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.65,
732
+ "learning_rate": 5.672460816472556e-06,
733
+ "loss": 1.1802,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.66,
738
+ "learning_rate": 5.514912872953746e-06,
739
+ "loss": 1.2037,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.66,
744
+ "learning_rate": 5.35874643748356e-06,
745
+ "loss": 1.2053,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.67,
750
+ "learning_rate": 5.204009612848288e-06,
751
+ "loss": 1.1801,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.68,
756
+ "learning_rate": 5.050750061481799e-06,
757
+ "loss": 1.1906,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.68,
762
+ "learning_rate": 4.899014990784485e-06,
763
+ "loss": 1.2055,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.69,
768
+ "learning_rate": 4.748851138582269e-06,
769
+ "loss": 1.182,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.69,
774
+ "learning_rate": 4.6003047587303376e-06,
775
+ "loss": 1.2159,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.7,
780
+ "learning_rate": 4.453421606865869e-06,
781
+ "loss": 1.2238,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.7,
786
+ "learning_rate": 4.308246926314307e-06,
787
+ "loss": 1.2076,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.71,
792
+ "learning_rate": 4.164825434153381e-06,
793
+ "loss": 1.2064,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.71,
798
+ "learning_rate": 4.0232013074392065e-06,
799
+ "loss": 1.2111,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.72,
804
+ "learning_rate": 3.883418169598808e-06,
805
+ "loss": 1.1995,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.72,
810
+ "learning_rate": 3.745519076993078e-06,
811
+ "loss": 1.2339,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.73,
816
+ "learning_rate": 3.609546505654462e-06,
817
+ "loss": 1.1774,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.74,
822
+ "learning_rate": 3.475542338203377e-06,
823
+ "loss": 1.1799,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.74,
828
+ "learning_rate": 3.343547850947434e-06,
829
+ "loss": 1.1655,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.75,
834
+ "learning_rate": 3.2136037011673803e-06,
835
+ "loss": 1.1912,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.75,
840
+ "learning_rate": 3.085749914593752e-06,
841
+ "loss": 1.1725,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.76,
846
+ "learning_rate": 2.9600258730780564e-06,
847
+ "loss": 1.1919,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.76,
852
+ "learning_rate": 2.8364703024622474e-06,
853
+ "loss": 1.2078,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.77,
858
+ "learning_rate": 2.7151212606503164e-06,
859
+ "loss": 1.1955,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.77,
864
+ "learning_rate": 2.5960161258855807e-06,
865
+ "loss": 1.2058,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.78,
870
+ "learning_rate": 2.4791915852373604e-06,
871
+ "loss": 1.181,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.78,
876
+ "learning_rate": 2.3646836233005133e-06,
877
+ "loss": 1.2011,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.79,
882
+ "learning_rate": 2.252527511111381e-06,
883
+ "loss": 1.2147,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.79,
888
+ "learning_rate": 2.1427577952835044e-06,
889
+ "loss": 1.1643,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.8,
894
+ "learning_rate": 2.0354082873665015e-06,
895
+ "loss": 1.197,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.81,
900
+ "learning_rate": 1.9305120534313295e-06,
901
+ "loss": 1.1915,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.81,
906
+ "learning_rate": 1.8281014038851963e-06,
907
+ "loss": 1.1849,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.82,
912
+ "learning_rate": 1.7282078835192362e-06,
913
+ "loss": 1.1688,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.82,
918
+ "learning_rate": 1.6308622617919823e-06,
919
+ "loss": 1.1591,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.83,
924
+ "learning_rate": 1.5360945233516933e-06,
925
+ "loss": 1.1911,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.83,
930
+ "learning_rate": 1.4439338588004005e-06,
931
+ "loss": 1.1419,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.84,
936
+ "learning_rate": 1.3544086557025493e-06,
937
+ "loss": 1.2014,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.84,
942
+ "learning_rate": 1.2675464898409772e-06,
943
+ "loss": 1.2176,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.85,
948
+ "learning_rate": 1.1833741167229584e-06,
949
+ "loss": 1.1694,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.85,
954
+ "learning_rate": 1.1019174633389073e-06,
955
+ "loss": 1.2077,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.86,
960
+ "learning_rate": 1.0232016201762696e-06,
961
+ "loss": 1.1956,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.86,
966
+ "learning_rate": 9.472508334910946e-07,
967
+ "loss": 1.2032,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.87,
972
+ "learning_rate": 8.740884978396358e-07,
973
+ "loss": 1.1866,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 0.88,
978
+ "learning_rate": 8.037371488723078e-07,
979
+ "loss": 1.166,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 0.88,
984
+ "learning_rate": 7.36218456392187e-07,
985
+ "loss": 1.218,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 0.89,
990
+ "learning_rate": 6.715532176802298e-07,
991
+ "loss": 1.2047,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 0.89,
996
+ "learning_rate": 6.097613510892364e-07,
997
+ "loss": 1.172,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 0.9,
1002
+ "learning_rate": 5.508618899085583e-07,
1003
+ "loss": 1.2032,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 0.9,
1008
+ "learning_rate": 4.948729765014004e-07,
1009
+ "loss": 1.2064,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 0.91,
1014
+ "learning_rate": 4.4181185671657634e-07,
1015
+ "loss": 1.2207,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 0.91,
1020
+ "learning_rate": 3.916948745763938e-07,
1021
+ "loss": 1.1999,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 0.92,
1026
+ "learning_rate": 3.445374672423252e-07,
1027
+ "loss": 1.2194,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 0.92,
1032
+ "learning_rate": 3.0035416026001573e-07,
1033
+ "loss": 1.1676,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 0.93,
1038
+ "learning_rate": 2.591585630850835e-07,
1039
+ "loss": 1.1848,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 0.94,
1044
+ "learning_rate": 2.2096336489111025e-07,
1045
+ "loss": 1.177,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 0.94,
1050
+ "learning_rate": 1.8578033066107392e-07,
1051
+ "loss": 1.1548,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 0.95,
1056
+ "learning_rate": 1.5362029756348373e-07,
1057
+ "loss": 1.196,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 0.95,
1062
+ "learning_rate": 1.2449317161427942e-07,
1063
+ "loss": 1.2112,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 0.96,
1068
+ "learning_rate": 9.840792462555426e-08,
1069
+ "loss": 1.2175,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 0.96,
1074
+ "learning_rate": 7.53725914420378e-08,
1075
+ "loss": 1.1724,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 0.97,
1080
+ "learning_rate": 5.539426746618337e-08,
1081
+ "loss": 1.2084,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 0.97,
1086
+ "learning_rate": 3.847910647261754e-08,
1087
+ "loss": 1.1959,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 0.98,
1092
+ "learning_rate": 2.4632318712646264e-08,
1093
+ "loss": 1.1975,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 0.98,
1098
+ "learning_rate": 1.3858169309376446e-08,
1099
+ "loss": 1.1917,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 0.99,
1104
+ "learning_rate": 6.1599769439590896e-09,
1105
+ "loss": 1.2194,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 0.99,
1110
+ "learning_rate": 1.540112833366969e-09,
1111
+ "loss": 1.1811,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 1.0,
1116
+ "learning_rate": 0.0,
1117
+ "loss": 1.1073,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 1.0,
1122
+ "step": 185,
1123
+ "total_flos": 210210073214976.0,
1124
+ "train_loss": 1.2432800080325153,
1125
+ "train_runtime": 3708.5887,
1126
+ "train_samples_per_second": 6.365,
1127
+ "train_steps_per_second": 0.05
1128
+ }
1129
+ ],
1130
+ "max_steps": 185,
1131
+ "num_train_epochs": 1,
1132
+ "total_flos": 210210073214976.0,
1133
+ "trial_name": null,
1134
+ "trial_params": null
1135
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f679b179762020c52e47875c6a4aa32445a3df0514f8f5daba6d8da71c46f85
3
+ size 5947