binxia commited on
Commit
64cb98d
1 Parent(s): 2f02e7f

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoint/llmga-llama3-8b-it-full-finetune",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "freeze_mm_mlp_adapter": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "image_aspect_ratio": "resizesquare",
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "mm_hidden_size": 1024,
19
+ "mm_patch_merge_type": "flat",
20
+ "mm_projector_lr": null,
21
+ "mm_projector_type": "mlp2x_gelu",
22
+ "mm_use_im_patch_token": false,
23
+ "mm_use_im_start_end": false,
24
+ "mm_vision_select_feature": "patch",
25
+ "mm_vision_select_layer": -2,
26
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
27
+ "model_type": "llava_llama",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 32,
30
+ "num_key_value_heads": 8,
31
+ "pretraining_tp": 1,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "tokenizer_model_max_length": 2048,
37
+ "tokenizer_padding_side": "right",
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.41.2",
40
+ "tune_mm_mlp_adapter": false,
41
+ "use_cache": true,
42
+ "use_mm_proj": true,
43
+ "vocab_size": 128256
44
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 128001,
7
+ 128009
8
+ ],
9
+ "max_length": 4096,
10
+ "temperature": 0.6,
11
+ "top_p": 0.9,
12
+ "transformers_version": "4.41.2"
13
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12bca96a3a97a98d5ca749b4556eeb3870169c67d6af1fb330a6a86078dbb54b
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6719c2c2b46aece557172624de93bd51f112441332b5f44f36ae6ad33951284
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb61a11d4359f1c7006b163388673b2a7a83f7ce90d19fcff6a4356ae1c2465c
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554b0dce465c59d0c271dccafb07bcfadfd827fc34e326b37048ae185693bfc5
3
+ size 1817174936
model.safetensors.index.json ADDED
@@ -0,0 +1,693 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16709496832
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
297
+ "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
298
+ "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
299
+ "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
300
+ "model.norm.weight": "model-00004-of-00004.safetensors",
301
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00004-of-00004.safetensors",
302
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00004-of-00004.safetensors",
303
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
304
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00004-of-00004.safetensors",
305
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00004-of-00004.safetensors",
306
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00004-of-00004.safetensors",
307
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00004-of-00004.safetensors",
308
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
309
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
310
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
311
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
312
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
313
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
314
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
315
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
316
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
317
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
318
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
319
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
320
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00004-of-00004.safetensors",
321
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00004-of-00004.safetensors",
322
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00004-of-00004.safetensors",
323
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00004-of-00004.safetensors",
324
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
325
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
326
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
327
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
328
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
329
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
331
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
332
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
333
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
334
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
335
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00004-of-00004.safetensors",
337
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00004-of-00004.safetensors",
338
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00004-of-00004.safetensors",
339
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00004-of-00004.safetensors",
340
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
341
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
342
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
343
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
344
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
345
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
346
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
347
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
348
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
349
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
350
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
351
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
352
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00004-of-00004.safetensors",
353
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00004-of-00004.safetensors",
354
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00004-of-00004.safetensors",
355
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00004-of-00004.safetensors",
356
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
357
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
358
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
359
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
360
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
361
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
362
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
363
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
364
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
365
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
366
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
367
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
368
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00004-of-00004.safetensors",
369
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00004-of-00004.safetensors",
370
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00004-of-00004.safetensors",
371
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00004-of-00004.safetensors",
372
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
373
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
374
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
375
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00004-of-00004.safetensors",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00004-of-00004.safetensors",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00004-of-00004.safetensors",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00004-of-00004.safetensors",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00004-of-00004.safetensors",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00004-of-00004.safetensors",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00004-of-00004.safetensors",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00004-of-00004.safetensors",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00004-of-00004.safetensors",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00004-of-00004.safetensors",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00004-of-00004.safetensors",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00004-of-00004.safetensors",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00004-of-00004.safetensors",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00004-of-00004.safetensors",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00004-of-00004.safetensors",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00004-of-00004.safetensors",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00004-of-00004.safetensors",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00004-of-00004.safetensors",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00004-of-00004.safetensors",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00004-of-00004.safetensors",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00004-of-00004.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00004-of-00004.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00004-of-00004.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00004-of-00004.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00004-of-00004.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00004-of-00004.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00004-of-00004.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00004-of-00004.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00004-of-00004.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00004-of-00004.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00004-of-00004.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00004-of-00004.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00004-of-00004.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00004-of-00004.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00004-of-00004.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00004-of-00004.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00004-of-00004.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00004-of-00004.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00004-of-00004.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00004-of-00004.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00004-of-00004.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00004-of-00004.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00004-of-00004.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00004-of-00004.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00004-of-00004.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00004-of-00004.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00004-of-00004.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00004-of-00004.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00004-of-00004.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00004-of-00004.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00004-of-00004.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00004-of-00004.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00004-of-00004.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00004-of-00004.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00004-of-00004.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00004-of-00004.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00004-of-00004.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00004-of-00004.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00004-of-00004.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00004-of-00004.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00004-of-00004.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00004-of-00004.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00004-of-00004.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00004-of-00004.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00004-of-00004.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00004-of-00004.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00004-of-00004.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00004-of-00004.safetensors"
692
+ }
693
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|reserved_special_token_0|>",
17
+ "unk_token": {
18
+ "content": "<|reserved_special_token_0|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|reserved_special_token_0|>",
2062
+ "padding_side": "right",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast",
2064
+ "unk_token": "<|reserved_special_token_0|>"
2065
+ }
trainer_state.json ADDED
@@ -0,0 +1,2002 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 280,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0035714285714285713,
13
+ "grad_norm": 2.8542327447781655,
14
+ "learning_rate": 2.222222222222222e-06,
15
+ "loss": 1.2459,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.007142857142857143,
20
+ "grad_norm": 3.2008343511486888,
21
+ "learning_rate": 4.444444444444444e-06,
22
+ "loss": 1.2209,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.010714285714285714,
27
+ "grad_norm": 2.5713840881424925,
28
+ "learning_rate": 6.666666666666667e-06,
29
+ "loss": 1.2089,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.014285714285714285,
34
+ "grad_norm": 1.955191718766848,
35
+ "learning_rate": 8.888888888888888e-06,
36
+ "loss": 1.0984,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.017857142857142856,
41
+ "grad_norm": 2.117930426021548,
42
+ "learning_rate": 1.1111111111111113e-05,
43
+ "loss": 1.001,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.02142857142857143,
48
+ "grad_norm": 5.368009843070649,
49
+ "learning_rate": 1.3333333333333333e-05,
50
+ "loss": 0.9729,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.025,
55
+ "grad_norm": 2.6030409421004315,
56
+ "learning_rate": 1.555555555555556e-05,
57
+ "loss": 0.9481,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.02857142857142857,
62
+ "grad_norm": 2.4961632055644256,
63
+ "learning_rate": 1.7777777777777777e-05,
64
+ "loss": 0.8393,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.03214285714285714,
69
+ "grad_norm": 2.366915137111893,
70
+ "learning_rate": 2e-05,
71
+ "loss": 0.7796,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.03571428571428571,
76
+ "grad_norm": 2.323220568477207,
77
+ "learning_rate": 1.9999328066483867e-05,
78
+ "loss": 0.7788,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.039285714285714285,
83
+ "grad_norm": 1.936852006950086,
84
+ "learning_rate": 1.9997312356234385e-05,
85
+ "loss": 0.7202,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.04285714285714286,
90
+ "grad_norm": 2.0208748078757965,
91
+ "learning_rate": 1.999395314013622e-05,
92
+ "loss": 0.5943,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.04642857142857143,
97
+ "grad_norm": 2.0052413798661766,
98
+ "learning_rate": 1.998925086962334e-05,
99
+ "loss": 0.5392,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.05,
104
+ "grad_norm": 2.1438278959706687,
105
+ "learning_rate": 1.998320617661839e-05,
106
+ "loss": 0.5334,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.05357142857142857,
111
+ "grad_norm": 1.7068775254192634,
112
+ "learning_rate": 1.997581987344772e-05,
113
+ "loss": 0.5014,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.05714285714285714,
118
+ "grad_norm": 1.9194172128721236,
119
+ "learning_rate": 1.9967092952732266e-05,
120
+ "loss": 0.4964,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.060714285714285714,
125
+ "grad_norm": 1.858301483386355,
126
+ "learning_rate": 1.9957026587254136e-05,
127
+ "loss": 0.4843,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.06428571428571428,
132
+ "grad_norm": 1.608800232721517,
133
+ "learning_rate": 1.9945622129799e-05,
134
+ "loss": 0.4586,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.06785714285714285,
139
+ "grad_norm": 1.6662313175415042,
140
+ "learning_rate": 1.9932881112974298e-05,
141
+ "loss": 0.4879,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.07142857142857142,
146
+ "grad_norm": 1.743091779375127,
147
+ "learning_rate": 1.9918805249003272e-05,
148
+ "loss": 0.4174,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.075,
153
+ "grad_norm": 1.7071719867098498,
154
+ "learning_rate": 1.9903396429494882e-05,
155
+ "loss": 0.423,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.07857142857142857,
160
+ "grad_norm": 1.4872510145523106,
161
+ "learning_rate": 1.9886656725189575e-05,
162
+ "loss": 0.4247,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.08214285714285714,
167
+ "grad_norm": 1.4662548028627673,
168
+ "learning_rate": 1.9868588385681035e-05,
169
+ "loss": 0.353,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.08571428571428572,
174
+ "grad_norm": 1.2910547643569992,
175
+ "learning_rate": 1.9849193839113833e-05,
176
+ "loss": 0.2913,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.08928571428571429,
181
+ "grad_norm": 1.2204351230084813,
182
+ "learning_rate": 1.9828475691857148e-05,
183
+ "loss": 0.2707,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.09285714285714286,
188
+ "grad_norm": 1.3717201569579562,
189
+ "learning_rate": 1.9806436728154484e-05,
190
+ "loss": 0.3425,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.09642857142857143,
195
+ "grad_norm": 1.17629244354678,
196
+ "learning_rate": 1.9783079909749516e-05,
197
+ "loss": 0.2771,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.1,
202
+ "grad_norm": 1.1945359382636211,
203
+ "learning_rate": 1.975840837548807e-05,
204
+ "loss": 0.3211,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.10357142857142858,
209
+ "grad_norm": 1.3376592216303969,
210
+ "learning_rate": 1.9732425440896298e-05,
211
+ "loss": 0.3301,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.10714285714285714,
216
+ "grad_norm": 1.3450447765698734,
217
+ "learning_rate": 1.9705134597735113e-05,
218
+ "loss": 0.3195,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.11071428571428571,
223
+ "grad_norm": 0.9886589945902243,
224
+ "learning_rate": 1.9676539513530967e-05,
225
+ "loss": 0.246,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.11428571428571428,
230
+ "grad_norm": 1.2275546257818077,
231
+ "learning_rate": 1.9646644031082948e-05,
232
+ "loss": 0.3145,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.11785714285714285,
237
+ "grad_norm": 1.3539593128551837,
238
+ "learning_rate": 1.9615452167946383e-05,
239
+ "loss": 0.3316,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.12142857142857143,
244
+ "grad_norm": 1.283776358581948,
245
+ "learning_rate": 1.958296811589293e-05,
246
+ "loss": 0.2939,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.125,
251
+ "grad_norm": 1.7849067225456108,
252
+ "learning_rate": 1.954919624034725e-05,
253
+ "loss": 0.3578,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.12857142857142856,
258
+ "grad_norm": 1.0954369777387916,
259
+ "learning_rate": 1.951414107980036e-05,
260
+ "loss": 0.265,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.13214285714285715,
265
+ "grad_norm": 1.1139647009348417,
266
+ "learning_rate": 1.9477807345199717e-05,
267
+ "loss": 0.2516,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.1357142857142857,
272
+ "grad_norm": 1.0058557775589556,
273
+ "learning_rate": 1.9440199919316125e-05,
274
+ "loss": 0.2823,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.1392857142857143,
279
+ "grad_norm": 1.3874195280252404,
280
+ "learning_rate": 1.9401323856087573e-05,
281
+ "loss": 0.2589,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.14285714285714285,
286
+ "grad_norm": 1.1059724872637073,
287
+ "learning_rate": 1.936118437994003e-05,
288
+ "loss": 0.3127,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.14642857142857144,
293
+ "grad_norm": 1.4336617434314778,
294
+ "learning_rate": 1.9319786885085366e-05,
295
+ "loss": 0.2788,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.15,
300
+ "grad_norm": 1.184578032516573,
301
+ "learning_rate": 1.927713693479643e-05,
302
+ "loss": 0.2891,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.15357142857142858,
307
+ "grad_norm": 1.1818501699215336,
308
+ "learning_rate": 1.923324026065944e-05,
309
+ "loss": 0.2951,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.15714285714285714,
314
+ "grad_norm": 1.0975108683871662,
315
+ "learning_rate": 1.918810276180372e-05,
316
+ "loss": 0.2184,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.16071428571428573,
321
+ "grad_norm": 1.1218315646897867,
322
+ "learning_rate": 1.9141730504108923e-05,
323
+ "loss": 0.2297,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.16428571428571428,
328
+ "grad_norm": 1.056967251433103,
329
+ "learning_rate": 1.9094129719389886e-05,
330
+ "loss": 0.2118,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.16785714285714284,
335
+ "grad_norm": 1.0992433056470872,
336
+ "learning_rate": 1.904530680455914e-05,
337
+ "loss": 0.2941,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.17142857142857143,
342
+ "grad_norm": 1.233231717888253,
343
+ "learning_rate": 1.8995268320767254e-05,
344
+ "loss": 0.2458,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.175,
349
+ "grad_norm": 1.063969135221994,
350
+ "learning_rate": 1.894402099252109e-05,
351
+ "loss": 0.2752,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.17857142857142858,
356
+ "grad_norm": 1.2463378053837864,
357
+ "learning_rate": 1.889157170678015e-05,
358
+ "loss": 0.2654,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.18214285714285713,
363
+ "grad_norm": 1.142139802192778,
364
+ "learning_rate": 1.8837927512031022e-05,
365
+ "loss": 0.2991,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.18571428571428572,
370
+ "grad_norm": 1.3979732581315991,
371
+ "learning_rate": 1.8783095617340193e-05,
372
+ "loss": 0.2277,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.18928571428571428,
377
+ "grad_norm": 0.945360454505982,
378
+ "learning_rate": 1.872708339138522e-05,
379
+ "loss": 0.1957,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.19285714285714287,
384
+ "grad_norm": 1.1124113891661973,
385
+ "learning_rate": 1.866989836146449e-05,
386
+ "loss": 0.254,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.19642857142857142,
391
+ "grad_norm": 1.223628442154201,
392
+ "learning_rate": 1.861154821248565e-05,
393
+ "loss": 0.2185,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.2,
398
+ "grad_norm": 1.0447822547318244,
399
+ "learning_rate": 1.8552040785932846e-05,
400
+ "loss": 0.2167,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.20357142857142857,
405
+ "grad_norm": 1.0215491299481245,
406
+ "learning_rate": 1.849138407881296e-05,
407
+ "loss": 0.2341,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.20714285714285716,
412
+ "grad_norm": 1.04110956091982,
413
+ "learning_rate": 1.8429586242580884e-05,
414
+ "loss": 0.257,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.21071428571428572,
419
+ "grad_norm": 1.0970335540731302,
420
+ "learning_rate": 1.8366655582044096e-05,
421
+ "loss": 0.2612,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.21428571428571427,
426
+ "grad_norm": 1.5414206823739205,
427
+ "learning_rate": 1.83026005542466e-05,
428
+ "loss": 0.3208,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.21785714285714286,
433
+ "grad_norm": 1.1115383818307014,
434
+ "learning_rate": 1.8237429767332407e-05,
435
+ "loss": 0.286,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.22142857142857142,
440
+ "grad_norm": 0.9397263766552314,
441
+ "learning_rate": 1.8171151979388715e-05,
442
+ "loss": 0.2484,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.225,
447
+ "grad_norm": 1.0153689250082296,
448
+ "learning_rate": 1.8103776097268942e-05,
449
+ "loss": 0.2659,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.22857142857142856,
454
+ "grad_norm": 0.9284042621070391,
455
+ "learning_rate": 1.803531117539577e-05,
456
+ "loss": 0.1991,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.23214285714285715,
461
+ "grad_norm": 0.9342315130686223,
462
+ "learning_rate": 1.7965766414544328e-05,
463
+ "loss": 0.2032,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.2357142857142857,
468
+ "grad_norm": 1.072773106151265,
469
+ "learning_rate": 1.7895151160605758e-05,
470
+ "loss": 0.2448,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.2392857142857143,
475
+ "grad_norm": 1.1178318721781217,
476
+ "learning_rate": 1.782347490333123e-05,
477
+ "loss": 0.2496,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.24285714285714285,
482
+ "grad_norm": 1.023124180885441,
483
+ "learning_rate": 1.775074727505667e-05,
484
+ "loss": 0.2168,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.24642857142857144,
489
+ "grad_norm": 0.9996638909558939,
490
+ "learning_rate": 1.7676978049408262e-05,
491
+ "loss": 0.2362,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.25,
496
+ "grad_norm": 0.8713422474197986,
497
+ "learning_rate": 1.7602177139989046e-05,
498
+ "loss": 0.1897,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.25357142857142856,
503
+ "grad_norm": 1.0498129217931838,
504
+ "learning_rate": 1.7526354599046637e-05,
505
+ "loss": 0.2514,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.2571428571428571,
510
+ "grad_norm": 0.8958335737383101,
511
+ "learning_rate": 1.7449520616122344e-05,
512
+ "loss": 0.2137,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.26071428571428573,
517
+ "grad_norm": 0.9491324981957817,
518
+ "learning_rate": 1.7371685516681825e-05,
519
+ "loss": 0.1908,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.2642857142857143,
524
+ "grad_norm": 0.8474993073986217,
525
+ "learning_rate": 1.7292859760727493e-05,
526
+ "loss": 0.2113,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.26785714285714285,
531
+ "grad_norm": 0.9763010793347767,
532
+ "learning_rate": 1.721305394139282e-05,
533
+ "loss": 0.1616,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.2714285714285714,
538
+ "grad_norm": 0.8756798542172813,
539
+ "learning_rate": 1.7132278783518756e-05,
540
+ "loss": 0.2389,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.275,
545
+ "grad_norm": 0.84872169147024,
546
+ "learning_rate": 1.7050545142212483e-05,
547
+ "loss": 0.2337,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.2785714285714286,
552
+ "grad_norm": 0.8331599870610199,
553
+ "learning_rate": 1.696786400138859e-05,
554
+ "loss": 0.1975,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.28214285714285714,
559
+ "grad_norm": 0.9769440268150504,
560
+ "learning_rate": 1.6884246472293018e-05,
561
+ "loss": 0.2096,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.2857142857142857,
566
+ "grad_norm": 0.8822887283843762,
567
+ "learning_rate": 1.679970379200983e-05,
568
+ "loss": 0.2178,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.2892857142857143,
573
+ "grad_norm": 1.040368028081877,
574
+ "learning_rate": 1.6714247321951106e-05,
575
+ "loss": 0.2668,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.29285714285714287,
580
+ "grad_norm": 1.0378300096521034,
581
+ "learning_rate": 1.6627888546330136e-05,
582
+ "loss": 0.2742,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.29642857142857143,
587
+ "grad_norm": 1.0081956925343618,
588
+ "learning_rate": 1.654063907061807e-05,
589
+ "loss": 0.2317,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.3,
594
+ "grad_norm": 0.9295295553823995,
595
+ "learning_rate": 1.64525106199843e-05,
596
+ "loss": 0.2155,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.30357142857142855,
601
+ "grad_norm": 1.1067271100643354,
602
+ "learning_rate": 1.6363515037720774e-05,
603
+ "loss": 0.2173,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.30714285714285716,
608
+ "grad_norm": 0.8455456352551043,
609
+ "learning_rate": 1.6273664283650393e-05,
610
+ "loss": 0.2296,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.3107142857142857,
615
+ "grad_norm": 0.7511551059374534,
616
+ "learning_rate": 1.6182970432519772e-05,
617
+ "loss": 0.2117,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.3142857142857143,
622
+ "grad_norm": 1.27007129583062,
623
+ "learning_rate": 1.609144567237658e-05,
624
+ "loss": 0.2458,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.31785714285714284,
629
+ "grad_norm": 0.8492452536821289,
630
+ "learning_rate": 1.5999102302931585e-05,
631
+ "loss": 0.2187,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.32142857142857145,
636
+ "grad_norm": 1.1577254689751963,
637
+ "learning_rate": 1.5905952733905777e-05,
638
+ "loss": 0.2655,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.325,
643
+ "grad_norm": 1.0482100964602592,
644
+ "learning_rate": 1.5812009483362643e-05,
645
+ "loss": 0.308,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.32857142857142857,
650
+ "grad_norm": 1.1600584410906734,
651
+ "learning_rate": 1.5717285176025913e-05,
652
+ "loss": 0.2034,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.33214285714285713,
657
+ "grad_norm": 1.0208452713577167,
658
+ "learning_rate": 1.5621792541582968e-05,
659
+ "loss": 0.2886,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.3357142857142857,
664
+ "grad_norm": 0.949057228666076,
665
+ "learning_rate": 1.552554441297413e-05,
666
+ "loss": 0.2233,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.3392857142857143,
671
+ "grad_norm": 1.1702785572108525,
672
+ "learning_rate": 1.5428553724668103e-05,
673
+ "loss": 0.2553,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.34285714285714286,
678
+ "grad_norm": 0.8302656215189927,
679
+ "learning_rate": 1.533083351092372e-05,
680
+ "loss": 0.2366,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.3464285714285714,
685
+ "grad_norm": 0.7111981015865874,
686
+ "learning_rate": 1.5232396904038352e-05,
687
+ "loss": 0.1443,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.35,
692
+ "grad_norm": 1.2280877546433842,
693
+ "learning_rate": 1.5133257132583074e-05,
694
+ "loss": 0.2611,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.3535714285714286,
699
+ "grad_norm": 0.8800901835863867,
700
+ "learning_rate": 1.503342751962493e-05,
701
+ "loss": 0.2847,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.35714285714285715,
706
+ "grad_norm": 0.9166060274088821,
707
+ "learning_rate": 1.4932921480936491e-05,
708
+ "loss": 0.1499,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.3607142857142857,
713
+ "grad_norm": 1.0017986138200043,
714
+ "learning_rate": 1.4831752523192949e-05,
715
+ "loss": 0.2172,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.36428571428571427,
720
+ "grad_norm": 1.095933130496475,
721
+ "learning_rate": 1.4729934242157005e-05,
722
+ "loss": 0.2998,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.3678571428571429,
727
+ "grad_norm": 0.9962381045121098,
728
+ "learning_rate": 1.4627480320851775e-05,
729
+ "loss": 0.2737,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.37142857142857144,
734
+ "grad_norm": 0.8702970432647809,
735
+ "learning_rate": 1.4524404527721977e-05,
736
+ "loss": 0.2522,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.375,
741
+ "grad_norm": 0.985504195424588,
742
+ "learning_rate": 1.4420720714783635e-05,
743
+ "loss": 0.2358,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.37857142857142856,
748
+ "grad_norm": 1.2118284574664568,
749
+ "learning_rate": 1.4316442815762543e-05,
750
+ "loss": 0.2662,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.3821428571428571,
755
+ "grad_norm": 0.82084189003784,
756
+ "learning_rate": 1.4211584844221771e-05,
757
+ "loss": 0.1882,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.38571428571428573,
762
+ "grad_norm": 0.7069507409286877,
763
+ "learning_rate": 1.4106160891678422e-05,
764
+ "loss": 0.1951,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.3892857142857143,
769
+ "grad_norm": 0.7689161582894709,
770
+ "learning_rate": 1.4000185125709919e-05,
771
+ "loss": 0.1725,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.39285714285714285,
776
+ "grad_norm": 0.7676679280673471,
777
+ "learning_rate": 1.3893671788050073e-05,
778
+ "loss": 0.1585,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.3964285714285714,
783
+ "grad_norm": 0.77471395404216,
784
+ "learning_rate": 1.3786635192675184e-05,
785
+ "loss": 0.2206,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.4,
790
+ "grad_norm": 0.9984901548871592,
791
+ "learning_rate": 1.3679089723880427e-05,
792
+ "loss": 0.2617,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.4035714285714286,
797
+ "grad_norm": 1.0400909733079975,
798
+ "learning_rate": 1.35710498343468e-05,
799
+ "loss": 0.1769,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.40714285714285714,
804
+ "grad_norm": 1.002292537016592,
805
+ "learning_rate": 1.3462530043198874e-05,
806
+ "loss": 0.2586,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.4107142857142857,
811
+ "grad_norm": 0.6551106931796162,
812
+ "learning_rate": 1.3353544934053618e-05,
813
+ "loss": 0.1673,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.4142857142857143,
818
+ "grad_norm": 0.9060227081683486,
819
+ "learning_rate": 1.324410915306055e-05,
820
+ "loss": 0.228,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.41785714285714287,
825
+ "grad_norm": 0.785686533390065,
826
+ "learning_rate": 1.3134237406933493e-05,
827
+ "loss": 0.2083,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.42142857142857143,
832
+ "grad_norm": 0.8497309507466154,
833
+ "learning_rate": 1.3023944460974183e-05,
834
+ "loss": 0.2009,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.425,
839
+ "grad_norm": 0.8470251087419485,
840
+ "learning_rate": 1.2913245137088024e-05,
841
+ "loss": 0.2061,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.42857142857142855,
846
+ "grad_norm": 0.9589921778817803,
847
+ "learning_rate": 1.2802154311792196e-05,
848
+ "loss": 0.1537,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.43214285714285716,
853
+ "grad_norm": 0.9947480480371786,
854
+ "learning_rate": 1.2690686914216475e-05,
855
+ "loss": 0.2773,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.4357142857142857,
860
+ "grad_norm": 0.8212329827096161,
861
+ "learning_rate": 1.2578857924096935e-05,
862
+ "loss": 0.2148,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.4392857142857143,
867
+ "grad_norm": 1.0285447504055023,
868
+ "learning_rate": 1.2466682369762883e-05,
869
+ "loss": 0.2163,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.44285714285714284,
874
+ "grad_norm": 1.0445202414513237,
875
+ "learning_rate": 1.2354175326117252e-05,
876
+ "loss": 0.2626,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.44642857142857145,
881
+ "grad_norm": 0.9733002033825501,
882
+ "learning_rate": 1.2241351912610726e-05,
883
+ "loss": 0.3042,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.45,
888
+ "grad_norm": 0.7648220446696808,
889
+ "learning_rate": 1.212822729120989e-05,
890
+ "loss": 0.228,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.45357142857142857,
895
+ "grad_norm": 0.7866538639716522,
896
+ "learning_rate": 1.2014816664359671e-05,
897
+ "loss": 0.2181,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.45714285714285713,
902
+ "grad_norm": 0.8064363725412049,
903
+ "learning_rate": 1.190113527294032e-05,
904
+ "loss": 0.2415,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.4607142857142857,
909
+ "grad_norm": 0.7803983228981857,
910
+ "learning_rate": 1.178719839421925e-05,
911
+ "loss": 0.1576,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.4642857142857143,
916
+ "grad_norm": 0.9439425043263437,
917
+ "learning_rate": 1.1673021339797967e-05,
918
+ "loss": 0.2844,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.46785714285714286,
923
+ "grad_norm": 0.8150618613103979,
924
+ "learning_rate": 1.15586194535544e-05,
925
+ "loss": 0.1969,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.4714285714285714,
930
+ "grad_norm": 0.7772114342406427,
931
+ "learning_rate": 1.1444008109580884e-05,
932
+ "loss": 0.1383,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.475,
937
+ "grad_norm": 1.0738272204622934,
938
+ "learning_rate": 1.1329202710118088e-05,
939
+ "loss": 0.2481,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.4785714285714286,
944
+ "grad_norm": 0.7852428793449633,
945
+ "learning_rate": 1.1214218683485159e-05,
946
+ "loss": 0.2216,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.48214285714285715,
951
+ "grad_norm": 0.7378172524312823,
952
+ "learning_rate": 1.1099071482006361e-05,
953
+ "loss": 0.1732,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.4857142857142857,
958
+ "grad_norm": 0.7273259562797488,
959
+ "learning_rate": 1.0983776579934483e-05,
960
+ "loss": 0.1985,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.48928571428571427,
965
+ "grad_norm": 1.0411454605240655,
966
+ "learning_rate": 1.0868349471371316e-05,
967
+ "loss": 0.3302,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.4928571428571429,
972
+ "grad_norm": 1.1149497038574403,
973
+ "learning_rate": 1.0752805668185442e-05,
974
+ "loss": 0.2199,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.49642857142857144,
979
+ "grad_norm": 0.9853475126131891,
980
+ "learning_rate": 1.0637160697927651e-05,
981
+ "loss": 0.2238,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.5,
986
+ "grad_norm": 0.7975162036724801,
987
+ "learning_rate": 1.0521430101744238e-05,
988
+ "loss": 0.2225,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.5035714285714286,
993
+ "grad_norm": 0.7778773518681362,
994
+ "learning_rate": 1.040562943228849e-05,
995
+ "loss": 0.2107,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.5071428571428571,
1000
+ "grad_norm": 0.7016828398202349,
1001
+ "learning_rate": 1.0289774251630602e-05,
1002
+ "loss": 0.1646,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.5107142857142857,
1007
+ "grad_norm": 0.8960386929571689,
1008
+ "learning_rate": 1.0173880129166358e-05,
1009
+ "loss": 0.2033,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.5142857142857142,
1014
+ "grad_norm": 0.6604103212473279,
1015
+ "learning_rate": 1.0057962639524799e-05,
1016
+ "loss": 0.1605,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.5178571428571429,
1021
+ "grad_norm": 1.383210847230254,
1022
+ "learning_rate": 9.942037360475205e-06,
1023
+ "loss": 0.2616,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.5214285714285715,
1028
+ "grad_norm": 0.9233268580117602,
1029
+ "learning_rate": 9.826119870833644e-06,
1030
+ "loss": 0.2682,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.525,
1035
+ "grad_norm": 0.9098722370866834,
1036
+ "learning_rate": 9.710225748369402e-06,
1037
+ "loss": 0.2005,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.5285714285714286,
1042
+ "grad_norm": 0.7043270611487241,
1043
+ "learning_rate": 9.594370567711512e-06,
1044
+ "loss": 0.1361,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.5321428571428571,
1049
+ "grad_norm": 0.945912907239272,
1050
+ "learning_rate": 9.478569898255765e-06,
1051
+ "loss": 0.27,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.5357142857142857,
1056
+ "grad_norm": 0.7227418929195129,
1057
+ "learning_rate": 9.362839302072354e-06,
1058
+ "loss": 0.1523,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.5392857142857143,
1063
+ "grad_norm": 0.901696864239785,
1064
+ "learning_rate": 9.247194331814561e-06,
1065
+ "loss": 0.2297,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.5428571428571428,
1070
+ "grad_norm": 0.6952433582976846,
1071
+ "learning_rate": 9.131650528628688e-06,
1072
+ "loss": 0.1879,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.5464285714285714,
1077
+ "grad_norm": 0.8968896375753643,
1078
+ "learning_rate": 9.016223420065519e-06,
1079
+ "loss": 0.1998,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.55,
1084
+ "grad_norm": 1.0357021485704796,
1085
+ "learning_rate": 8.900928517993644e-06,
1086
+ "loss": 0.289,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.5535714285714286,
1091
+ "grad_norm": 0.9263285065897571,
1092
+ "learning_rate": 8.785781316514841e-06,
1093
+ "loss": 0.2387,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.5571428571428572,
1098
+ "grad_norm": 0.8130477337572882,
1099
+ "learning_rate": 8.670797289881915e-06,
1100
+ "loss": 0.2393,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.5607142857142857,
1105
+ "grad_norm": 0.8664747661731167,
1106
+ "learning_rate": 8.555991890419116e-06,
1107
+ "loss": 0.2295,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.5642857142857143,
1112
+ "grad_norm": 0.7139524830413835,
1113
+ "learning_rate": 8.441380546445603e-06,
1114
+ "loss": 0.1683,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.5678571428571428,
1119
+ "grad_norm": 1.1700171170245692,
1120
+ "learning_rate": 8.326978660202034e-06,
1121
+ "loss": 0.3086,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.5714285714285714,
1126
+ "grad_norm": 0.772880515075922,
1127
+ "learning_rate": 8.212801605780754e-06,
1128
+ "loss": 0.1811,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.575,
1133
+ "grad_norm": 0.7715213885473983,
1134
+ "learning_rate": 8.098864727059685e-06,
1135
+ "loss": 0.2182,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.5785714285714286,
1140
+ "grad_norm": 1.2255567186716825,
1141
+ "learning_rate": 7.985183335640332e-06,
1142
+ "loss": 0.2629,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.5821428571428572,
1147
+ "grad_norm": 0.7057680167932003,
1148
+ "learning_rate": 7.871772708790114e-06,
1149
+ "loss": 0.1414,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.5857142857142857,
1154
+ "grad_norm": 0.7076516916675438,
1155
+ "learning_rate": 7.758648087389277e-06,
1156
+ "loss": 0.1953,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.5892857142857143,
1161
+ "grad_norm": 0.9193199539199463,
1162
+ "learning_rate": 7.64582467388275e-06,
1163
+ "loss": 0.2648,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.5928571428571429,
1168
+ "grad_norm": 0.7694356287549676,
1169
+ "learning_rate": 7.533317630237117e-06,
1170
+ "loss": 0.2015,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.5964285714285714,
1175
+ "grad_norm": 0.9020767096753005,
1176
+ "learning_rate": 7.421142075903067e-06,
1177
+ "loss": 0.2151,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.6,
1182
+ "grad_norm": 0.9010708295786384,
1183
+ "learning_rate": 7.3093130857835245e-06,
1184
+ "loss": 0.1934,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.6035714285714285,
1189
+ "grad_norm": 0.9781518043714732,
1190
+ "learning_rate": 7.197845688207805e-06,
1191
+ "loss": 0.2783,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.6071428571428571,
1196
+ "grad_norm": 0.8062846336754722,
1197
+ "learning_rate": 7.086754862911982e-06,
1198
+ "loss": 0.1876,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.6107142857142858,
1203
+ "grad_norm": 0.8993288898038415,
1204
+ "learning_rate": 6.976055539025819e-06,
1205
+ "loss": 0.2765,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.6142857142857143,
1210
+ "grad_norm": 0.9544638260763084,
1211
+ "learning_rate": 6.865762593066514e-06,
1212
+ "loss": 0.2224,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.6178571428571429,
1217
+ "grad_norm": 0.7861637636734311,
1218
+ "learning_rate": 6.755890846939454e-06,
1219
+ "loss": 0.2351,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.6214285714285714,
1224
+ "grad_norm": 1.526261650246375,
1225
+ "learning_rate": 6.646455065946386e-06,
1226
+ "loss": 0.3024,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.625,
1231
+ "grad_norm": 0.8243808604395686,
1232
+ "learning_rate": 6.537469956801128e-06,
1233
+ "loss": 0.2193,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.6285714285714286,
1238
+ "grad_norm": 0.9068394658105672,
1239
+ "learning_rate": 6.428950165653204e-06,
1240
+ "loss": 0.1525,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.6321428571428571,
1245
+ "grad_norm": 0.8066101085303891,
1246
+ "learning_rate": 6.320910276119576e-06,
1247
+ "loss": 0.232,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.6357142857142857,
1252
+ "grad_norm": 0.849276264490868,
1253
+ "learning_rate": 6.213364807324817e-06,
1254
+ "loss": 0.2112,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.6392857142857142,
1259
+ "grad_norm": 0.9467657676513234,
1260
+ "learning_rate": 6.106328211949928e-06,
1261
+ "loss": 0.257,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.6428571428571429,
1266
+ "grad_norm": 0.8690174893226397,
1267
+ "learning_rate": 5.999814874290084e-06,
1268
+ "loss": 0.2214,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.6464285714285715,
1273
+ "grad_norm": 0.875769130127647,
1274
+ "learning_rate": 5.893839108321584e-06,
1275
+ "loss": 0.2033,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.65,
1280
+ "grad_norm": 0.6946362310360622,
1281
+ "learning_rate": 5.7884151557782305e-06,
1282
+ "loss": 0.1731,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.6535714285714286,
1287
+ "grad_norm": 1.059540577971593,
1288
+ "learning_rate": 5.68355718423746e-06,
1289
+ "loss": 0.2825,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.6571428571428571,
1294
+ "grad_norm": 0.871973114594604,
1295
+ "learning_rate": 5.579279285216369e-06,
1296
+ "loss": 0.266,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.6607142857142857,
1301
+ "grad_norm": 0.9362769886838416,
1302
+ "learning_rate": 5.4755954722780236e-06,
1303
+ "loss": 0.2261,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.6642857142857143,
1308
+ "grad_norm": 1.0156195729999553,
1309
+ "learning_rate": 5.372519679148227e-06,
1310
+ "loss": 0.2772,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.6678571428571428,
1315
+ "grad_norm": 1.1707981800497014,
1316
+ "learning_rate": 5.270065757843e-06,
1317
+ "loss": 0.2357,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.6714285714285714,
1322
+ "grad_norm": 1.1200974625591849,
1323
+ "learning_rate": 5.168247476807054e-06,
1324
+ "loss": 0.2955,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.675,
1329
+ "grad_norm": 0.7302141966698424,
1330
+ "learning_rate": 5.067078519063514e-06,
1331
+ "loss": 0.2351,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.6785714285714286,
1336
+ "grad_norm": 0.9547345238061237,
1337
+ "learning_rate": 4.966572480375076e-06,
1338
+ "loss": 0.2201,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.6821428571428572,
1343
+ "grad_norm": 0.9859252903039029,
1344
+ "learning_rate": 4.86674286741693e-06,
1345
+ "loss": 0.2634,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.6857142857142857,
1350
+ "grad_norm": 1.2303560929176436,
1351
+ "learning_rate": 4.767603095961652e-06,
1352
+ "loss": 0.3092,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.6892857142857143,
1357
+ "grad_norm": 0.902957152854701,
1358
+ "learning_rate": 4.669166489076283e-06,
1359
+ "loss": 0.2614,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.6928571428571428,
1364
+ "grad_norm": 0.7887211722266535,
1365
+ "learning_rate": 4.571446275331903e-06,
1366
+ "loss": 0.1946,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.6964285714285714,
1371
+ "grad_norm": 0.9681771399551783,
1372
+ "learning_rate": 4.47445558702587e-06,
1373
+ "loss": 0.2515,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.7,
1378
+ "grad_norm": 0.8387940708324988,
1379
+ "learning_rate": 4.378207458417035e-06,
1380
+ "loss": 0.2442,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.7035714285714286,
1385
+ "grad_norm": 1.2905572299013393,
1386
+ "learning_rate": 4.282714823974088e-06,
1387
+ "loss": 0.2412,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.7071428571428572,
1392
+ "grad_norm": 0.9660020289811414,
1393
+ "learning_rate": 4.187990516637361e-06,
1394
+ "loss": 0.2183,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.7107142857142857,
1399
+ "grad_norm": 0.9987611883772257,
1400
+ "learning_rate": 4.094047266094225e-06,
1401
+ "loss": 0.2111,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.7142857142857143,
1406
+ "grad_norm": 0.6971224340534188,
1407
+ "learning_rate": 4.000897697068418e-06,
1408
+ "loss": 0.1147,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.7178571428571429,
1413
+ "grad_norm": 0.8499318496594657,
1414
+ "learning_rate": 3.908554327623425e-06,
1415
+ "loss": 0.2028,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.7214285714285714,
1420
+ "grad_norm": 0.9757223338840971,
1421
+ "learning_rate": 3.817029567480228e-06,
1422
+ "loss": 0.2687,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.725,
1427
+ "grad_norm": 0.9724129336265752,
1428
+ "learning_rate": 3.7263357163496118e-06,
1429
+ "loss": 0.2951,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.7285714285714285,
1434
+ "grad_norm": 0.846692248077101,
1435
+ "learning_rate": 3.6364849622792262e-06,
1436
+ "loss": 0.2116,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.7321428571428571,
1441
+ "grad_norm": 0.7244565494778341,
1442
+ "learning_rate": 3.5474893800157005e-06,
1443
+ "loss": 0.1824,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.7357142857142858,
1448
+ "grad_norm": 1.0573449443528709,
1449
+ "learning_rate": 3.459360929381931e-06,
1450
+ "loss": 0.1647,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.7392857142857143,
1455
+ "grad_norm": 1.3741948680591016,
1456
+ "learning_rate": 3.372111453669864e-06,
1457
+ "loss": 0.29,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.7428571428571429,
1462
+ "grad_norm": 1.0221267171956534,
1463
+ "learning_rate": 3.2857526780488925e-06,
1464
+ "loss": 0.2258,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.7464285714285714,
1469
+ "grad_norm": 0.7776596440463766,
1470
+ "learning_rate": 3.2002962079901743e-06,
1471
+ "loss": 0.2101,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.75,
1476
+ "grad_norm": 0.8390204592490403,
1477
+ "learning_rate": 3.115753527706986e-06,
1478
+ "loss": 0.2355,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.7535714285714286,
1483
+ "grad_norm": 0.6624410313645264,
1484
+ "learning_rate": 3.0321359986114096e-06,
1485
+ "loss": 0.1756,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.7571428571428571,
1490
+ "grad_norm": 1.0623528998074427,
1491
+ "learning_rate": 2.9494548577875195e-06,
1492
+ "loss": 0.1945,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.7607142857142857,
1497
+ "grad_norm": 1.1302403323388186,
1498
+ "learning_rate": 2.8677212164812464e-06,
1499
+ "loss": 0.2234,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.7642857142857142,
1504
+ "grad_norm": 0.8609060708419913,
1505
+ "learning_rate": 2.786946058607187e-06,
1506
+ "loss": 0.2657,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.7678571428571429,
1511
+ "grad_norm": 0.9847057932243088,
1512
+ "learning_rate": 2.70714023927251e-06,
1513
+ "loss": 0.2727,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.7714285714285715,
1518
+ "grad_norm": 1.3326482318392308,
1519
+ "learning_rate": 2.628314483318178e-06,
1520
+ "loss": 0.2287,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.775,
1525
+ "grad_norm": 0.9202719280439493,
1526
+ "learning_rate": 2.5504793838776585e-06,
1527
+ "loss": 0.2034,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.7785714285714286,
1532
+ "grad_norm": 0.9299327013502574,
1533
+ "learning_rate": 2.473645400953366e-06,
1534
+ "loss": 0.2584,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.7821428571428571,
1539
+ "grad_norm": 0.9697882855786745,
1540
+ "learning_rate": 2.3978228600109564e-06,
1541
+ "loss": 0.2023,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.7857142857142857,
1546
+ "grad_norm": 1.0868782541786108,
1547
+ "learning_rate": 2.323021950591743e-06,
1548
+ "loss": 0.2423,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.7892857142857143,
1553
+ "grad_norm": 0.9406345195120313,
1554
+ "learning_rate": 2.249252724943336e-06,
1555
+ "loss": 0.2093,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.7928571428571428,
1560
+ "grad_norm": 0.8299606398290135,
1561
+ "learning_rate": 2.176525096668769e-06,
1562
+ "loss": 0.2024,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.7964285714285714,
1567
+ "grad_norm": 0.9557718556324724,
1568
+ "learning_rate": 2.1048488393942455e-06,
1569
+ "loss": 0.2651,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.8,
1574
+ "grad_norm": 1.020716425877873,
1575
+ "learning_rate": 2.0342335854556738e-06,
1576
+ "loss": 0.218,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.8035714285714286,
1581
+ "grad_norm": 0.8247593195528904,
1582
+ "learning_rate": 1.964688824604234e-06,
1583
+ "loss": 0.2224,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.8071428571428572,
1588
+ "grad_norm": 0.7141792575779932,
1589
+ "learning_rate": 1.896223902731058e-06,
1590
+ "loss": 0.148,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.8107142857142857,
1595
+ "grad_norm": 0.6798152535391203,
1596
+ "learning_rate": 1.8288480206112879e-06,
1597
+ "loss": 0.1693,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.8142857142857143,
1602
+ "grad_norm": 0.7865744423081975,
1603
+ "learning_rate": 1.7625702326675952e-06,
1604
+ "loss": 0.2307,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.8178571428571428,
1609
+ "grad_norm": 0.8961338272400713,
1610
+ "learning_rate": 1.6973994457534026e-06,
1611
+ "loss": 0.1763,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.8214285714285714,
1616
+ "grad_norm": 1.0891294721112785,
1617
+ "learning_rate": 1.6333444179559078e-06,
1618
+ "loss": 0.251,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.825,
1623
+ "grad_norm": 0.9895358178842029,
1624
+ "learning_rate": 1.5704137574191202e-06,
1625
+ "loss": 0.2457,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.8285714285714286,
1630
+ "grad_norm": 0.8797961625322609,
1631
+ "learning_rate": 1.5086159211870445e-06,
1632
+ "loss": 0.2974,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.8321428571428572,
1637
+ "grad_norm": 1.0022630637461174,
1638
+ "learning_rate": 1.447959214067155e-06,
1639
+ "loss": 0.2911,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.8357142857142857,
1644
+ "grad_norm": 0.9292460119394966,
1645
+ "learning_rate": 1.3884517875143544e-06,
1646
+ "loss": 0.253,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.8392857142857143,
1651
+ "grad_norm": 0.8525100768549407,
1652
+ "learning_rate": 1.3301016385355093e-06,
1653
+ "loss": 0.2574,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.8428571428571429,
1658
+ "grad_norm": 0.7616448289314827,
1659
+ "learning_rate": 1.2729166086147803e-06,
1660
+ "loss": 0.1935,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.8464285714285714,
1665
+ "grad_norm": 0.9032528436222605,
1666
+ "learning_rate": 1.216904382659806e-06,
1667
+ "loss": 0.2136,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.85,
1672
+ "grad_norm": 0.9221094277183024,
1673
+ "learning_rate": 1.1620724879689793e-06,
1674
+ "loss": 0.2366,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.8535714285714285,
1679
+ "grad_norm": 0.8128301362566547,
1680
+ "learning_rate": 1.1084282932198543e-06,
1681
+ "loss": 0.205,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.8571428571428571,
1686
+ "grad_norm": 0.8351463450189537,
1687
+ "learning_rate": 1.0559790074789134e-06,
1688
+ "loss": 0.2451,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.8607142857142858,
1693
+ "grad_norm": 0.8132844496379037,
1694
+ "learning_rate": 1.00473167923275e-06,
1695
+ "loss": 0.1986,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.8642857142857143,
1700
+ "grad_norm": 0.8413773702315226,
1701
+ "learning_rate": 9.546931954408622e-07,
1702
+ "loss": 0.2568,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.8678571428571429,
1707
+ "grad_norm": 0.864722633477625,
1708
+ "learning_rate": 9.058702806101172e-07,
1709
+ "loss": 0.2647,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.8714285714285714,
1714
+ "grad_norm": 0.8564326198019813,
1715
+ "learning_rate": 8.582694958910809e-07,
1716
+ "loss": 0.2082,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.875,
1721
+ "grad_norm": 1.0551157545813,
1722
+ "learning_rate": 8.118972381962853e-07,
1723
+ "loss": 0.3371,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.8785714285714286,
1728
+ "grad_norm": 0.7703975629143833,
1729
+ "learning_rate": 7.667597393405602e-07,
1730
+ "loss": 0.2341,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.8821428571428571,
1735
+ "grad_norm": 0.6061411407576762,
1736
+ "learning_rate": 7.228630652035717e-07,
1737
+ "loss": 0.1415,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.8857142857142857,
1742
+ "grad_norm": 1.1824816837626368,
1743
+ "learning_rate": 6.802131149146374e-07,
1744
+ "loss": 0.2504,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.8892857142857142,
1749
+ "grad_norm": 0.7388040182293693,
1750
+ "learning_rate": 6.388156200599726e-07,
1751
+ "loss": 0.1832,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.8928571428571429,
1756
+ "grad_norm": 0.7414017170453198,
1757
+ "learning_rate": 5.986761439124289e-07,
1758
+ "loss": 0.175,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.8964285714285715,
1763
+ "grad_norm": 0.9715948557202785,
1764
+ "learning_rate": 5.598000806838766e-07,
1765
+ "loss": 0.3161,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.9,
1770
+ "grad_norm": 0.6724183434948179,
1771
+ "learning_rate": 5.221926548002876e-07,
1772
+ "loss": 0.1827,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.9035714285714286,
1777
+ "grad_norm": 0.7818282617469353,
1778
+ "learning_rate": 4.858589201996433e-07,
1779
+ "loss": 0.2202,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.9071428571428571,
1784
+ "grad_norm": 0.8204974648639228,
1785
+ "learning_rate": 4.5080375965275256e-07,
1786
+ "loss": 0.1967,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.9107142857142857,
1791
+ "grad_norm": 1.0856778296057459,
1792
+ "learning_rate": 4.1703188410707087e-07,
1793
+ "loss": 0.2444,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.9142857142857143,
1798
+ "grad_norm": 0.8449959915498736,
1799
+ "learning_rate": 3.845478320536178e-07,
1800
+ "loss": 0.2371,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.9178571428571428,
1805
+ "grad_norm": 0.9495844646371367,
1806
+ "learning_rate": 3.5335596891705406e-07,
1807
+ "loss": 0.2335,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.9214285714285714,
1812
+ "grad_norm": 0.8901968360351575,
1813
+ "learning_rate": 3.2346048646903494e-07,
1814
+ "loss": 0.2204,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.925,
1819
+ "grad_norm": 0.8923998294274479,
1820
+ "learning_rate": 2.9486540226488556e-07,
1821
+ "loss": 0.2567,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.9285714285714286,
1826
+ "grad_norm": 0.815717327935455,
1827
+ "learning_rate": 2.6757455910370486e-07,
1828
+ "loss": 0.2578,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.9321428571428572,
1833
+ "grad_norm": 0.7291953617908891,
1834
+ "learning_rate": 2.41591624511931e-07,
1835
+ "loss": 0.1857,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.9357142857142857,
1840
+ "grad_norm": 1.8534979443451833,
1841
+ "learning_rate": 2.169200902504842e-07,
1842
+ "loss": 0.2899,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.9392857142857143,
1847
+ "grad_norm": 0.8961982311920613,
1848
+ "learning_rate": 1.9356327184551716e-07,
1849
+ "loss": 0.1946,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.9428571428571428,
1854
+ "grad_norm": 0.8300414662763644,
1855
+ "learning_rate": 1.7152430814285303e-07,
1856
+ "loss": 0.253,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.9464285714285714,
1861
+ "grad_norm": 1.1075650320032002,
1862
+ "learning_rate": 1.5080616088616884e-07,
1863
+ "loss": 0.2717,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.95,
1868
+ "grad_norm": 1.16743264805072,
1869
+ "learning_rate": 1.3141161431896809e-07,
1870
+ "loss": 0.3116,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.9535714285714286,
1875
+ "grad_norm": 0.8257674956219426,
1876
+ "learning_rate": 1.1334327481042573e-07,
1877
+ "loss": 0.1874,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.9571428571428572,
1882
+ "grad_norm": 0.9283778527162151,
1883
+ "learning_rate": 9.660357050512158e-08,
1884
+ "loss": 0.2219,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.9607142857142857,
1889
+ "grad_norm": 0.956684846701526,
1890
+ "learning_rate": 8.119475099673035e-08,
1891
+ "loss": 0.2465,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.9642857142857143,
1896
+ "grad_norm": 0.6856186450599495,
1897
+ "learning_rate": 6.711888702570556e-08,
1898
+ "loss": 0.2051,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.9678571428571429,
1903
+ "grad_norm": 0.8013460800051045,
1904
+ "learning_rate": 5.437787020100116e-08,
1905
+ "loss": 0.2108,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.9714285714285714,
1910
+ "grad_norm": 0.9855143079178192,
1911
+ "learning_rate": 4.297341274586475e-08,
1912
+ "loss": 0.2287,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.975,
1917
+ "grad_norm": 0.9501486308995364,
1918
+ "learning_rate": 3.290704726773619e-08,
1919
+ "loss": 0.2572,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.9785714285714285,
1924
+ "grad_norm": 0.8054069093536848,
1925
+ "learning_rate": 2.4180126552284523e-08,
1926
+ "loss": 0.2522,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.9821428571428571,
1931
+ "grad_norm": 1.2803070465419621,
1932
+ "learning_rate": 1.6793823381614506e-08,
1933
+ "loss": 0.2266,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.9857142857142858,
1938
+ "grad_norm": 0.8212197677595763,
1939
+ "learning_rate": 1.0749130376659366e-08,
1940
+ "loss": 0.2241,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.9892857142857143,
1945
+ "grad_norm": 1.3359306690870951,
1946
+ "learning_rate": 6.046859863781951e-09,
1947
+ "loss": 0.3035,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.9928571428571429,
1952
+ "grad_norm": 0.8933949606817133,
1953
+ "learning_rate": 2.6876437656153663e-09,
1954
+ "loss": 0.2186,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.9964285714285714,
1959
+ "grad_norm": 0.7916708816942223,
1960
+ "learning_rate": 6.719335161364804e-10,
1961
+ "loss": 0.2021,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 1.0,
1966
+ "grad_norm": 0.8075329735012263,
1967
+ "learning_rate": 0.0,
1968
+ "loss": 0.2782,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 1.0,
1973
+ "step": 280,
1974
+ "total_flos": 478920998780928.0,
1975
+ "train_loss": 0.2742149087467364,
1976
+ "train_runtime": 2790.475,
1977
+ "train_samples_per_second": 12.839,
1978
+ "train_steps_per_second": 0.1
1979
+ }
1980
+ ],
1981
+ "logging_steps": 1.0,
1982
+ "max_steps": 280,
1983
+ "num_input_tokens_seen": 0,
1984
+ "num_train_epochs": 1,
1985
+ "save_steps": 50000,
1986
+ "stateful_callbacks": {
1987
+ "TrainerControl": {
1988
+ "args": {
1989
+ "should_epoch_stop": false,
1990
+ "should_evaluate": false,
1991
+ "should_log": false,
1992
+ "should_save": false,
1993
+ "should_training_stop": false
1994
+ },
1995
+ "attributes": {}
1996
+ }
1997
+ },
1998
+ "total_flos": 478920998780928.0,
1999
+ "train_batch_size": 2,
2000
+ "trial_name": null,
2001
+ "trial_params": null
2002
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92a10ac482fa09851715296269ef6582c2bb357bc3ce545e0c0395e0353ae01
3
+ size 7288