gsmyrnis commited on
Commit
1cfc1ec
·
verified ·
1 Parent(s): 45756c8

Training in progress, epoch 0

Browse files
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json CHANGED
@@ -1,36 +1,29 @@
1
  {
2
- "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
  "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128001,
10
- "head_dim": 128,
11
  "hidden_act": "silu",
12
- "hidden_size": 4096,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 14336,
15
- "max_position_embeddings": 131072,
16
- "mlp_bias": false,
17
- "model_type": "llama",
18
- "num_attention_heads": 32,
19
- "num_hidden_layers": 32,
20
- "num_key_value_heads": 8,
21
- "pretraining_tp": 1,
22
- "rms_norm_eps": 1e-05,
23
- "rope_scaling": {
24
- "factor": 8.0,
25
- "high_freq_factor": 4.0,
26
- "low_freq_factor": 1.0,
27
- "original_max_position_embeddings": 8192,
28
- "rope_type": "llama3"
29
- },
30
- "rope_theta": 500000.0,
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.46.1",
34
  "use_cache": false,
35
- "vocab_size": 128256
 
36
  }
 
1
  {
2
+ "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
3
  "architectures": [
4
+ "Qwen2ForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
 
9
  "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
 
 
 
 
 
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.46.1",
26
  "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:257f8252a4e8aaa5813b7c8ded2b25cde3cb4c8fd06818d9dbc2706b3e1b740a
3
- size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa74d3337037b065e2fd242baafdc2ad8d19170a78bdfe792a2d19b0523fb40
3
+ size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a73c963e6fb0af11f31031e569cbe3a23395e2f8a84aa9e2172dd19f513516a
3
- size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c583809f0b64cec9dae236d607fd496cce984f05a504f0a98ddb05487c48842d
3
+ size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b3f017114fe64991b64483e010c888fdfe9a1187eb42b73440b2251113db5e4
3
- size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aefe10321b5a0fd6dbfd9ecaa5782173d8ca50e5dbd1c12e9a11606b73b0879f
3
+ size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e15649683e03bcb8c5b711eb33935a574530c0958ad7af28203b6ccd17b71fc2
3
- size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c37b838a024b8a14eff4df1bc991a287142d4926bdbb99eda7e8ae8ffcb1f43
3
+ size 1089994880
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 16060522496
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00004-of-00004.safetensors",
@@ -10,289 +10,337 @@
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.norm.weight": "model-00004-of-00004.safetensors"
297
  }
298
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 15231233024
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00004-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.bias": "model-00001-of-00004.safetensors",
14
  "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
  "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
  "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
  "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
  "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
  "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
  "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
  "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
  "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
  "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
  "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
  "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
  "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
  "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
  "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
  "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
  "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
  "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
  "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
  "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
  "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
  "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
  "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
  "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
  "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
  "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
  "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
  "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
  "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
  "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
  "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
  "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
  "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
  "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
  "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
  "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
  "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
  "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
  "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
  "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
  "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
  "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
  "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
  "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
  "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
  "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
  "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
  "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
  "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
  "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
  "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
  "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
  "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
  "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
  "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
  "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
  "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
  "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
  "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
  "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
  "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
  "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
  "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
  "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
  "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
  "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
  "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
  "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
  "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
  "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
  "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
  "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
  "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
  "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
  "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
  "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
  "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
  "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
  "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
  "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
  "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
  "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
  "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
  "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
  "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
  "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
  "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
  "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
  "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
  "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
  "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
  "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
  "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
  "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
  "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
  "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
  "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
  "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
  "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
  "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
  "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
  "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
  "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
  "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
  "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
  "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
  "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
  "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
  "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
  "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
  "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
  "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
  "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
  "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
  "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
  "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
  "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
  "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
  "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
  "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
  "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
  "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
  "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
  "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
  "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
  "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
  "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
  "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
  "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
  "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
  "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
  "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
  "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
  "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
  "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
  "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
  "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
  "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
  "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
  "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
  "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
  "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
  "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
  "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
  "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
  "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
  "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
  "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
  "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
  "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
  "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
  "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
  "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
  "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
  "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
  "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
  "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
  "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
  "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
  "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
  "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
  "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
  "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
  "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
  "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
  "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
  "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
260
  "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
  "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
  "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
  "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
  "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
  "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
  "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
  "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
  "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
272
  "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
  "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
  "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
  "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
  "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
  "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
  "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
  "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
  "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
  "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
  "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
  "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
  "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
  "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
  "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
  "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
  "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
  "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
  "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
  "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
  "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
  "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
  "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
  "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
  "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
  "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
  "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
  "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
  "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
  "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
  "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
  "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
  "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
  "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
  "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
  "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
  "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
  "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
  "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
  "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
  "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
  "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
  "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
  "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
  "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
  "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
  "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
  "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
  "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
  }
346
  }
special_tokens_map.json CHANGED
@@ -1,17 +1,31 @@
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": "<|eot_id|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
- },
16
- "pad_token": "<|eot_id|>"
17
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
29
  "single_word": false
30
+ }
 
31
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json CHANGED
@@ -1,2065 +1,208 @@
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": "<|finetune_right_pad_id|>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  },
43
- "128005": {
44
- "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
88
  "single_word": false,
89
  "special": true
90
  },
91
- "128011": {
92
- "content": "<|reserved_special_token_3|>",
93
  "lstrip": false,
94
  "normalized": false,
95
  "rstrip": false,
96
  "single_word": false,
97
  "special": true
98
  },
99
- "128012": {
100
- "content": "<|reserved_special_token_4|>",
101
  "lstrip": false,
102
  "normalized": false,
103
  "rstrip": false,
104
  "single_word": false,
105
  "special": true
106
  },
107
- "128013": {
108
- "content": "<|reserved_special_token_5|>",
109
  "lstrip": false,
110
  "normalized": false,
111
  "rstrip": false,
112
  "single_word": false,
113
  "special": true
114
  },
115
- "128014": {
116
- "content": "<|reserved_special_token_6|>",
117
  "lstrip": false,
118
  "normalized": false,
119
  "rstrip": false,
120
  "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_7|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_8|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_9|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_10|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_11|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_12|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_13|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_14|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_15|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_16|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_17|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_18|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_19|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_20|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_21|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_22|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_23|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_24|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_25|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_26|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_27|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_28|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_29|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_30|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_31|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_32|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_33|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_34|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_35|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_36|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_37|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_38|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_39|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_40|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_41|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_42|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_43|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_44|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_45|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_46|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_47|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_48|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_49|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_50|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_51|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_52|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_53|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_54|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_55|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_56|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_57|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_58|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_59|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_60|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_61|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_62|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_63|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_64|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_65|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_66|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_67|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_68|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_69|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_70|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_71|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_72|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_73|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_74|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_75|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_76|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_77|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_78|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_79|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_80|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_81|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_82|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_83|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_84|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_85|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_86|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_87|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_88|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_89|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_90|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_91|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_92|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_93|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_94|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_95|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_96|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_97|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_98|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_99|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_100|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_101|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_102|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_103|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_104|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_105|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_106|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_107|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_108|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_109|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_110|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_111|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_112|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_113|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_114|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_115|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_116|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_117|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_118|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_119|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_120|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_121|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_122|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_123|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_124|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_125|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_126|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_127|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_128|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_129|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_130|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_131|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_132|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_133|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_134|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_135|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_136|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_137|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_138|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_139|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_140|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_141|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_142|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_143|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_144|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_145|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_146|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_147|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_148|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_149|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_150|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_151|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_152|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_153|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_154|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_155|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_156|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_157|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_158|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_159|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_160|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_161|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_162|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_163|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_164|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_165|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_166|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_167|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_168|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_169|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_170|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_171|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_172|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_173|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_174|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_175|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_176|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_177|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_178|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_179|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_180|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_181|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_182|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_183|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_184|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_185|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_186|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_187|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_188|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_189|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_190|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_191|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_192|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_193|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_194|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_195|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_196|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_197|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_198|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_199|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_200|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_201|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_202|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_203|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_204|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_205|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_206|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_207|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_208|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_209|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_210|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_211|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_212|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_213|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_214|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_215|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_216|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_217|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_218|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_219|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_220|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_221|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_222|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_223|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_224|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_225|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_226|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_227|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_228|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_229|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_230|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_231|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_232|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_233|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_234|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_235|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_236|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_237|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_238|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_239|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_240|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
  },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_241|>",
1997
  "lstrip": false,
1998
  "normalized": false,
1999
  "rstrip": false,
2000
  "single_word": false,
2001
- "special": true
2002
  },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_242|>",
2005
  "lstrip": false,
2006
  "normalized": false,
2007
  "rstrip": false,
2008
  "single_word": false,
2009
- "special": true
2010
  },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_243|>",
2013
  "lstrip": false,
2014
  "normalized": false,
2015
  "rstrip": false,
2016
  "single_word": false,
2017
- "special": true
2018
  },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_244|>",
2021
  "lstrip": false,
2022
  "normalized": false,
2023
  "rstrip": false,
2024
  "single_word": false,
2025
- "special": true
2026
  },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_245|>",
2029
  "lstrip": false,
2030
  "normalized": false,
2031
  "rstrip": false,
2032
  "single_word": false,
2033
- "special": true
2034
  },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_246|>",
2037
  "lstrip": false,
2038
  "normalized": false,
2039
  "rstrip": false,
2040
  "single_word": false,
2041
- "special": true
2042
  },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_247|>",
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": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
- "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|eot_id|>",
2056
- "model_input_names": [
2057
- "input_ids",
2058
- "attention_mask"
 
 
 
 
 
 
 
2059
  ],
 
 
 
 
 
2060
  "model_max_length": 131072,
2061
- "pad_token": "<|eot_id|>",
2062
  "padding_side": "right",
2063
  "split_special_tokens": false,
2064
- "tokenizer_class": "PreTrainedTokenizerFast"
 
2065
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
  },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
  "lstrip": false,
48
  "normalized": false,
49
  "rstrip": false,
50
  "single_word": false,
51
  "special": true
52
  },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": false,
58
  "single_word": false,
59
  "special": true
60
  },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
  "lstrip": false,
64
  "normalized": false,
65
  "rstrip": false,
66
  "single_word": false,
67
  "special": true
68
  },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
  "lstrip": false,
72
  "normalized": false,
73
  "rstrip": false,
74
  "single_word": false,
75
  "special": true
76
  },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
  "lstrip": false,
80
  "normalized": false,
81
  "rstrip": false,
82
  "single_word": false,
83
  "special": true
84
  },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
  "lstrip": false,
88
  "normalized": false,
89
  "rstrip": false,
90
  "single_word": false,
91
  "special": true
92
  },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
  "lstrip": false,
96
  "normalized": false,
97
  "rstrip": false,
98
  "single_word": false,
99
  "special": true
100
  },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
  "lstrip": false,
104
  "normalized": false,
105
  "rstrip": false,
106
  "single_word": false,
107
  "special": true
108
  },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
  "lstrip": false,
112
  "normalized": false,
113
  "rstrip": false,
114
  "single_word": false,
115
  "special": true
116
  },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
  "lstrip": false,
120
  "normalized": false,
121
  "rstrip": false,
122
  "single_word": false,
123
+ "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
124
  },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
  "lstrip": false,
128
  "normalized": false,
129
  "rstrip": false,
130
  "single_word": false,
131
+ "special": false
132
  },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
  "lstrip": false,
136
  "normalized": false,
137
  "rstrip": false,
138
  "single_word": false,
139
+ "special": false
140
  },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
  "lstrip": false,
144
  "normalized": false,
145
  "rstrip": false,
146
  "single_word": false,
147
+ "special": false
148
  },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
  "lstrip": false,
152
  "normalized": false,
153
  "rstrip": false,
154
  "single_word": false,
155
+ "special": false
156
  },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
  "lstrip": false,
160
  "normalized": false,
161
  "rstrip": false,
162
  "single_word": false,
163
+ "special": false
164
  },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
  "lstrip": false,
168
  "normalized": false,
169
  "rstrip": false,
170
  "single_word": false,
171
+ "special": false
172
  },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
  "lstrip": false,
176
  "normalized": false,
177
  "rstrip": false,
178
  "single_word": false,
179
+ "special": false
180
  }
181
  },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
  ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
  "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
  "padding_side": "right",
205
  "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
  }
trainer_log.jsonl CHANGED
@@ -1,13 +1,190 @@
1
- {"current_steps": 10, "total_steps": 99, "loss": 0.8659, "lr": 5e-06, "epoch": 0.30303030303030304, "percentage": 10.1, "elapsed_time": "0:01:01", "remaining_time": "0:09:06"}
2
- {"current_steps": 20, "total_steps": 99, "loss": 0.737, "lr": 5e-06, "epoch": 0.6060606060606061, "percentage": 20.2, "elapsed_time": "0:02:02", "remaining_time": "0:08:03"}
3
- {"current_steps": 30, "total_steps": 99, "loss": 0.6827, "lr": 5e-06, "epoch": 0.9090909090909091, "percentage": 30.3, "elapsed_time": "0:03:03", "remaining_time": "0:07:02"}
4
- {"current_steps": 33, "total_steps": 99, "eval_loss": 0.6528273820877075, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:03:25", "remaining_time": "0:06:51"}
5
- {"current_steps": 40, "total_steps": 99, "loss": 0.6382, "lr": 5e-06, "epoch": 1.2121212121212122, "percentage": 40.4, "elapsed_time": "0:05:35", "remaining_time": "0:08:14"}
6
- {"current_steps": 50, "total_steps": 99, "loss": 0.6149, "lr": 5e-06, "epoch": 1.5151515151515151, "percentage": 50.51, "elapsed_time": "0:06:37", "remaining_time": "0:06:29"}
7
- {"current_steps": 60, "total_steps": 99, "loss": 0.5976, "lr": 5e-06, "epoch": 1.8181818181818183, "percentage": 60.61, "elapsed_time": "0:07:39", "remaining_time": "0:04:58"}
8
- {"current_steps": 66, "total_steps": 99, "eval_loss": 0.6136316061019897, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:08:20", "remaining_time": "0:04:10"}
9
- {"current_steps": 70, "total_steps": 99, "loss": 0.5791, "lr": 5e-06, "epoch": 2.121212121212121, "percentage": 70.71, "elapsed_time": "0:10:34", "remaining_time": "0:04:22"}
10
- {"current_steps": 80, "total_steps": 99, "loss": 0.551, "lr": 5e-06, "epoch": 2.4242424242424243, "percentage": 80.81, "elapsed_time": "0:11:35", "remaining_time": "0:02:45"}
11
- {"current_steps": 90, "total_steps": 99, "loss": 0.5482, "lr": 5e-06, "epoch": 2.7272727272727275, "percentage": 90.91, "elapsed_time": "0:12:38", "remaining_time": "0:01:15"}
12
- {"current_steps": 99, "total_steps": 99, "eval_loss": 0.6033677458763123, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:15:27", "remaining_time": "0:00:00"}
13
- {"current_steps": 99, "total_steps": 99, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:17:04", "remaining_time": "0:00:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 540, "loss": 0.8455, "lr": 1.8518518518518518e-07, "epoch": 0.005535055350553505, "percentage": 0.19, "elapsed_time": "0:00:20", "remaining_time": "3:02:53"}
2
+ {"current_steps": 2, "total_steps": 540, "loss": 0.8315, "lr": 3.7037037037037036e-07, "epoch": 0.01107011070110701, "percentage": 0.37, "elapsed_time": "0:00:36", "remaining_time": "2:44:46"}
3
+ {"current_steps": 3, "total_steps": 540, "loss": 0.854, "lr": 5.555555555555555e-07, "epoch": 0.016605166051660517, "percentage": 0.56, "elapsed_time": "0:00:53", "remaining_time": "2:40:31"}
4
+ {"current_steps": 4, "total_steps": 540, "loss": 0.81, "lr": 7.407407407407407e-07, "epoch": 0.02214022140221402, "percentage": 0.74, "elapsed_time": "0:01:12", "remaining_time": "2:40:53"}
5
+ {"current_steps": 5, "total_steps": 540, "loss": 0.8673, "lr": 9.259259259259259e-07, "epoch": 0.027675276752767528, "percentage": 0.93, "elapsed_time": "0:01:29", "remaining_time": "2:38:51"}
6
+ {"current_steps": 6, "total_steps": 540, "loss": 0.8606, "lr": 1.111111111111111e-06, "epoch": 0.033210332103321034, "percentage": 1.11, "elapsed_time": "0:01:45", "remaining_time": "2:36:12"}
7
+ {"current_steps": 7, "total_steps": 540, "loss": 0.84, "lr": 1.2962962962962962e-06, "epoch": 0.03874538745387454, "percentage": 1.3, "elapsed_time": "0:02:02", "remaining_time": "2:35:34"}
8
+ {"current_steps": 8, "total_steps": 540, "loss": 0.8167, "lr": 1.4814814814814815e-06, "epoch": 0.04428044280442804, "percentage": 1.48, "elapsed_time": "0:02:18", "remaining_time": "2:33:46"}
9
+ {"current_steps": 9, "total_steps": 540, "loss": 0.8045, "lr": 1.6666666666666667e-06, "epoch": 0.04981549815498155, "percentage": 1.67, "elapsed_time": "0:02:37", "remaining_time": "2:34:46"}
10
+ {"current_steps": 10, "total_steps": 540, "loss": 0.7971, "lr": 1.8518518518518519e-06, "epoch": 0.055350553505535055, "percentage": 1.85, "elapsed_time": "0:02:55", "remaining_time": "2:35:04"}
11
+ {"current_steps": 11, "total_steps": 540, "loss": 0.7471, "lr": 2.037037037037037e-06, "epoch": 0.06088560885608856, "percentage": 2.04, "elapsed_time": "0:03:12", "remaining_time": "2:34:25"}
12
+ {"current_steps": 12, "total_steps": 540, "loss": 0.7509, "lr": 2.222222222222222e-06, "epoch": 0.06642066420664207, "percentage": 2.22, "elapsed_time": "0:03:30", "remaining_time": "2:34:41"}
13
+ {"current_steps": 13, "total_steps": 540, "loss": 0.7482, "lr": 2.4074074074074075e-06, "epoch": 0.07195571955719557, "percentage": 2.41, "elapsed_time": "0:03:46", "remaining_time": "2:33:12"}
14
+ {"current_steps": 14, "total_steps": 540, "loss": 0.7068, "lr": 2.5925925925925925e-06, "epoch": 0.07749077490774908, "percentage": 2.59, "elapsed_time": "0:04:05", "remaining_time": "2:33:53"}
15
+ {"current_steps": 15, "total_steps": 540, "loss": 0.7373, "lr": 2.7777777777777783e-06, "epoch": 0.08302583025830258, "percentage": 2.78, "elapsed_time": "0:04:23", "remaining_time": "2:33:30"}
16
+ {"current_steps": 16, "total_steps": 540, "loss": 0.7175, "lr": 2.962962962962963e-06, "epoch": 0.08856088560885608, "percentage": 2.96, "elapsed_time": "0:04:41", "remaining_time": "2:33:50"}
17
+ {"current_steps": 17, "total_steps": 540, "loss": 0.7318, "lr": 3.1481481481481483e-06, "epoch": 0.0940959409594096, "percentage": 3.15, "elapsed_time": "0:05:00", "remaining_time": "2:34:01"}
18
+ {"current_steps": 18, "total_steps": 540, "loss": 0.7455, "lr": 3.3333333333333333e-06, "epoch": 0.0996309963099631, "percentage": 3.33, "elapsed_time": "0:05:18", "remaining_time": "2:33:45"}
19
+ {"current_steps": 19, "total_steps": 540, "loss": 0.7006, "lr": 3.5185185185185187e-06, "epoch": 0.10516605166051661, "percentage": 3.52, "elapsed_time": "0:05:34", "remaining_time": "2:32:49"}
20
+ {"current_steps": 20, "total_steps": 540, "loss": 0.7096, "lr": 3.7037037037037037e-06, "epoch": 0.11070110701107011, "percentage": 3.7, "elapsed_time": "0:05:53", "remaining_time": "2:32:59"}
21
+ {"current_steps": 21, "total_steps": 540, "loss": 0.664, "lr": 3.88888888888889e-06, "epoch": 0.11623616236162361, "percentage": 3.89, "elapsed_time": "0:06:11", "remaining_time": "2:32:52"}
22
+ {"current_steps": 22, "total_steps": 540, "loss": 0.6619, "lr": 4.074074074074074e-06, "epoch": 0.12177121771217712, "percentage": 4.07, "elapsed_time": "0:06:27", "remaining_time": "2:32:01"}
23
+ {"current_steps": 23, "total_steps": 540, "loss": 0.687, "lr": 4.2592592592592596e-06, "epoch": 0.12730627306273062, "percentage": 4.26, "elapsed_time": "0:06:45", "remaining_time": "2:31:52"}
24
+ {"current_steps": 24, "total_steps": 540, "loss": 0.6543, "lr": 4.444444444444444e-06, "epoch": 0.13284132841328414, "percentage": 4.44, "elapsed_time": "0:07:03", "remaining_time": "2:31:46"}
25
+ {"current_steps": 25, "total_steps": 540, "loss": 0.6385, "lr": 4.62962962962963e-06, "epoch": 0.13837638376383765, "percentage": 4.63, "elapsed_time": "0:07:21", "remaining_time": "2:31:31"}
26
+ {"current_steps": 26, "total_steps": 540, "loss": 0.6476, "lr": 4.814814814814815e-06, "epoch": 0.14391143911439114, "percentage": 4.81, "elapsed_time": "0:07:38", "remaining_time": "2:31:09"}
27
+ {"current_steps": 27, "total_steps": 540, "loss": 0.6105, "lr": 5e-06, "epoch": 0.14944649446494465, "percentage": 5.0, "elapsed_time": "0:07:56", "remaining_time": "2:30:51"}
28
+ {"current_steps": 28, "total_steps": 540, "loss": 0.615, "lr": 5.185185185185185e-06, "epoch": 0.15498154981549817, "percentage": 5.19, "elapsed_time": "0:08:12", "remaining_time": "2:30:13"}
29
+ {"current_steps": 29, "total_steps": 540, "loss": 0.6376, "lr": 5.370370370370371e-06, "epoch": 0.16051660516605165, "percentage": 5.37, "elapsed_time": "0:08:30", "remaining_time": "2:29:51"}
30
+ {"current_steps": 30, "total_steps": 540, "loss": 0.6007, "lr": 5.555555555555557e-06, "epoch": 0.16605166051660517, "percentage": 5.56, "elapsed_time": "0:08:47", "remaining_time": "2:29:25"}
31
+ {"current_steps": 31, "total_steps": 540, "loss": 0.6113, "lr": 5.740740740740741e-06, "epoch": 0.17158671586715868, "percentage": 5.74, "elapsed_time": "0:09:04", "remaining_time": "2:28:54"}
32
+ {"current_steps": 32, "total_steps": 540, "loss": 0.5933, "lr": 5.925925925925926e-06, "epoch": 0.17712177121771217, "percentage": 5.93, "elapsed_time": "0:09:21", "remaining_time": "2:28:31"}
33
+ {"current_steps": 33, "total_steps": 540, "loss": 0.5872, "lr": 6.111111111111112e-06, "epoch": 0.18265682656826568, "percentage": 6.11, "elapsed_time": "0:09:40", "remaining_time": "2:28:31"}
34
+ {"current_steps": 34, "total_steps": 540, "loss": 0.5837, "lr": 6.296296296296297e-06, "epoch": 0.1881918819188192, "percentage": 6.3, "elapsed_time": "0:09:57", "remaining_time": "2:28:12"}
35
+ {"current_steps": 35, "total_steps": 540, "loss": 0.6019, "lr": 6.481481481481482e-06, "epoch": 0.1937269372693727, "percentage": 6.48, "elapsed_time": "0:10:14", "remaining_time": "2:27:45"}
36
+ {"current_steps": 36, "total_steps": 540, "loss": 0.5729, "lr": 6.666666666666667e-06, "epoch": 0.1992619926199262, "percentage": 6.67, "elapsed_time": "0:10:31", "remaining_time": "2:27:23"}
37
+ {"current_steps": 37, "total_steps": 540, "loss": 0.567, "lr": 6.851851851851853e-06, "epoch": 0.2047970479704797, "percentage": 6.85, "elapsed_time": "0:10:47", "remaining_time": "2:26:49"}
38
+ {"current_steps": 38, "total_steps": 540, "loss": 0.5866, "lr": 7.0370370370370375e-06, "epoch": 0.21033210332103322, "percentage": 7.04, "elapsed_time": "0:11:04", "remaining_time": "2:26:18"}
39
+ {"current_steps": 39, "total_steps": 540, "loss": 0.5951, "lr": 7.222222222222223e-06, "epoch": 0.2158671586715867, "percentage": 7.22, "elapsed_time": "0:11:19", "remaining_time": "2:25:28"}
40
+ {"current_steps": 40, "total_steps": 540, "loss": 0.5732, "lr": 7.4074074074074075e-06, "epoch": 0.22140221402214022, "percentage": 7.41, "elapsed_time": "0:11:37", "remaining_time": "2:25:22"}
41
+ {"current_steps": 41, "total_steps": 540, "loss": 0.5783, "lr": 7.592592592592594e-06, "epoch": 0.22693726937269373, "percentage": 7.59, "elapsed_time": "0:11:56", "remaining_time": "2:25:25"}
42
+ {"current_steps": 42, "total_steps": 540, "loss": 0.5422, "lr": 7.77777777777778e-06, "epoch": 0.23247232472324722, "percentage": 7.78, "elapsed_time": "0:12:14", "remaining_time": "2:25:05"}
43
+ {"current_steps": 43, "total_steps": 540, "loss": 0.5627, "lr": 7.962962962962963e-06, "epoch": 0.23800738007380073, "percentage": 7.96, "elapsed_time": "0:12:33", "remaining_time": "2:25:04"}
44
+ {"current_steps": 44, "total_steps": 540, "loss": 0.5469, "lr": 8.148148148148148e-06, "epoch": 0.24354243542435425, "percentage": 8.15, "elapsed_time": "0:12:49", "remaining_time": "2:24:39"}
45
+ {"current_steps": 45, "total_steps": 540, "loss": 0.5547, "lr": 8.333333333333334e-06, "epoch": 0.24907749077490776, "percentage": 8.33, "elapsed_time": "0:13:06", "remaining_time": "2:24:13"}
46
+ {"current_steps": 46, "total_steps": 540, "loss": 0.5559, "lr": 8.518518518518519e-06, "epoch": 0.25461254612546125, "percentage": 8.52, "elapsed_time": "0:13:25", "remaining_time": "2:24:10"}
47
+ {"current_steps": 47, "total_steps": 540, "loss": 0.5825, "lr": 8.703703703703705e-06, "epoch": 0.26014760147601473, "percentage": 8.7, "elapsed_time": "0:13:42", "remaining_time": "2:23:46"}
48
+ {"current_steps": 48, "total_steps": 540, "loss": 0.5605, "lr": 8.888888888888888e-06, "epoch": 0.2656826568265683, "percentage": 8.89, "elapsed_time": "0:14:00", "remaining_time": "2:23:34"}
49
+ {"current_steps": 49, "total_steps": 540, "loss": 0.5336, "lr": 9.074074074074075e-06, "epoch": 0.27121771217712176, "percentage": 9.07, "elapsed_time": "0:14:18", "remaining_time": "2:23:24"}
50
+ {"current_steps": 50, "total_steps": 540, "loss": 0.5176, "lr": 9.25925925925926e-06, "epoch": 0.2767527675276753, "percentage": 9.26, "elapsed_time": "0:14:36", "remaining_time": "2:23:09"}
51
+ {"current_steps": 51, "total_steps": 540, "loss": 0.5485, "lr": 9.444444444444445e-06, "epoch": 0.2822878228782288, "percentage": 9.44, "elapsed_time": "0:14:54", "remaining_time": "2:23:00"}
52
+ {"current_steps": 52, "total_steps": 540, "loss": 0.5345, "lr": 9.62962962962963e-06, "epoch": 0.2878228782287823, "percentage": 9.63, "elapsed_time": "0:15:12", "remaining_time": "2:22:40"}
53
+ {"current_steps": 53, "total_steps": 540, "loss": 0.5562, "lr": 9.814814814814815e-06, "epoch": 0.2933579335793358, "percentage": 9.81, "elapsed_time": "0:15:29", "remaining_time": "2:22:18"}
54
+ {"current_steps": 54, "total_steps": 540, "loss": 0.5618, "lr": 1e-05, "epoch": 0.2988929889298893, "percentage": 10.0, "elapsed_time": "0:15:48", "remaining_time": "2:22:12"}
55
+ {"current_steps": 55, "total_steps": 540, "loss": 0.5315, "lr": 9.999895536228031e-06, "epoch": 0.3044280442804428, "percentage": 10.19, "elapsed_time": "0:16:06", "remaining_time": "2:22:05"}
56
+ {"current_steps": 56, "total_steps": 540, "loss": 0.5227, "lr": 9.999582149277188e-06, "epoch": 0.30996309963099633, "percentage": 10.37, "elapsed_time": "0:16:25", "remaining_time": "2:21:57"}
57
+ {"current_steps": 57, "total_steps": 540, "loss": 0.5486, "lr": 9.999059852242508e-06, "epoch": 0.3154981549815498, "percentage": 10.56, "elapsed_time": "0:16:43", "remaining_time": "2:21:45"}
58
+ {"current_steps": 58, "total_steps": 540, "loss": 0.5414, "lr": 9.998328666948437e-06, "epoch": 0.3210332103321033, "percentage": 10.74, "elapsed_time": "0:17:02", "remaining_time": "2:21:35"}
59
+ {"current_steps": 59, "total_steps": 540, "loss": 0.5382, "lr": 9.997388623947927e-06, "epoch": 0.32656826568265684, "percentage": 10.93, "elapsed_time": "0:17:19", "remaining_time": "2:21:11"}
60
+ {"current_steps": 60, "total_steps": 540, "loss": 0.5333, "lr": 9.996239762521152e-06, "epoch": 0.33210332103321033, "percentage": 11.11, "elapsed_time": "0:17:35", "remaining_time": "2:20:42"}
61
+ {"current_steps": 61, "total_steps": 540, "loss": 0.5088, "lr": 9.994882130673869e-06, "epoch": 0.3376383763837638, "percentage": 11.3, "elapsed_time": "0:17:52", "remaining_time": "2:20:23"}
62
+ {"current_steps": 62, "total_steps": 540, "loss": 0.5196, "lr": 9.993315785135417e-06, "epoch": 0.34317343173431736, "percentage": 11.48, "elapsed_time": "0:18:10", "remaining_time": "2:20:10"}
63
+ {"current_steps": 63, "total_steps": 540, "loss": 0.538, "lr": 9.991540791356342e-06, "epoch": 0.34870848708487084, "percentage": 11.67, "elapsed_time": "0:18:27", "remaining_time": "2:19:44"}
64
+ {"current_steps": 64, "total_steps": 540, "loss": 0.5665, "lr": 9.989557223505661e-06, "epoch": 0.35424354243542433, "percentage": 11.85, "elapsed_time": "0:18:43", "remaining_time": "2:19:18"}
65
+ {"current_steps": 65, "total_steps": 540, "loss": 0.5339, "lr": 9.987365164467767e-06, "epoch": 0.35977859778597787, "percentage": 12.04, "elapsed_time": "0:19:02", "remaining_time": "2:19:10"}
66
+ {"current_steps": 66, "total_steps": 540, "loss": 0.5354, "lr": 9.98496470583896e-06, "epoch": 0.36531365313653136, "percentage": 12.22, "elapsed_time": "0:19:20", "remaining_time": "2:18:52"}
67
+ {"current_steps": 67, "total_steps": 540, "loss": 0.5212, "lr": 9.98235594792363e-06, "epoch": 0.37084870848708484, "percentage": 12.41, "elapsed_time": "0:19:37", "remaining_time": "2:18:32"}
68
+ {"current_steps": 68, "total_steps": 540, "loss": 0.5302, "lr": 9.979538999730047e-06, "epoch": 0.3763837638376384, "percentage": 12.59, "elapsed_time": "0:19:55", "remaining_time": "2:18:20"}
69
+ {"current_steps": 69, "total_steps": 540, "loss": 0.5263, "lr": 9.976513978965829e-06, "epoch": 0.38191881918819187, "percentage": 12.78, "elapsed_time": "0:20:11", "remaining_time": "2:17:51"}
70
+ {"current_steps": 70, "total_steps": 540, "loss": 0.5349, "lr": 9.973281012033009e-06, "epoch": 0.3874538745387454, "percentage": 12.96, "elapsed_time": "0:20:27", "remaining_time": "2:17:19"}
71
+ {"current_steps": 71, "total_steps": 540, "loss": 0.5237, "lr": 9.96984023402275e-06, "epoch": 0.3929889298892989, "percentage": 13.15, "elapsed_time": "0:20:43", "remaining_time": "2:16:52"}
72
+ {"current_steps": 72, "total_steps": 540, "loss": 0.53, "lr": 9.966191788709716e-06, "epoch": 0.3985239852398524, "percentage": 13.33, "elapsed_time": "0:21:01", "remaining_time": "2:16:39"}
73
+ {"current_steps": 73, "total_steps": 540, "loss": 0.5222, "lr": 9.962335828546049e-06, "epoch": 0.4040590405904059, "percentage": 13.52, "elapsed_time": "0:21:20", "remaining_time": "2:16:30"}
74
+ {"current_steps": 74, "total_steps": 540, "loss": 0.5288, "lr": 9.958272514655006e-06, "epoch": 0.4095940959409594, "percentage": 13.7, "elapsed_time": "0:21:37", "remaining_time": "2:16:09"}
75
+ {"current_steps": 75, "total_steps": 540, "loss": 0.5211, "lr": 9.954002016824226e-06, "epoch": 0.4151291512915129, "percentage": 13.89, "elapsed_time": "0:21:54", "remaining_time": "2:15:50"}
76
+ {"current_steps": 76, "total_steps": 540, "loss": 0.517, "lr": 9.949524513498636e-06, "epoch": 0.42066420664206644, "percentage": 14.07, "elapsed_time": "0:22:12", "remaining_time": "2:15:33"}
77
+ {"current_steps": 77, "total_steps": 540, "loss": 0.521, "lr": 9.944840191772987e-06, "epoch": 0.4261992619926199, "percentage": 14.26, "elapsed_time": "0:22:29", "remaining_time": "2:15:14"}
78
+ {"current_steps": 78, "total_steps": 540, "loss": 0.4998, "lr": 9.939949247384046e-06, "epoch": 0.4317343173431734, "percentage": 14.44, "elapsed_time": "0:22:48", "remaining_time": "2:15:05"}
79
+ {"current_steps": 79, "total_steps": 540, "loss": 0.5333, "lr": 9.934851884702415e-06, "epoch": 0.43726937269372695, "percentage": 14.63, "elapsed_time": "0:23:06", "remaining_time": "2:14:50"}
80
+ {"current_steps": 80, "total_steps": 540, "loss": 0.5236, "lr": 9.929548316723983e-06, "epoch": 0.44280442804428044, "percentage": 14.81, "elapsed_time": "0:23:24", "remaining_time": "2:14:36"}
81
+ {"current_steps": 81, "total_steps": 540, "loss": 0.5295, "lr": 9.924038765061042e-06, "epoch": 0.4483394833948339, "percentage": 15.0, "elapsed_time": "0:23:42", "remaining_time": "2:14:19"}
82
+ {"current_steps": 82, "total_steps": 540, "loss": 0.4999, "lr": 9.918323459933006e-06, "epoch": 0.45387453874538747, "percentage": 15.19, "elapsed_time": "0:23:59", "remaining_time": "2:13:59"}
83
+ {"current_steps": 83, "total_steps": 540, "loss": 0.5126, "lr": 9.912402640156812e-06, "epoch": 0.45940959409594095, "percentage": 15.37, "elapsed_time": "0:24:17", "remaining_time": "2:13:43"}
84
+ {"current_steps": 84, "total_steps": 540, "loss": 0.5246, "lr": 9.906276553136924e-06, "epoch": 0.46494464944649444, "percentage": 15.56, "elapsed_time": "0:24:35", "remaining_time": "2:13:31"}
85
+ {"current_steps": 85, "total_steps": 540, "loss": 0.505, "lr": 9.899945454855007e-06, "epoch": 0.470479704797048, "percentage": 15.74, "elapsed_time": "0:24:51", "remaining_time": "2:13:05"}
86
+ {"current_steps": 86, "total_steps": 540, "loss": 0.4871, "lr": 9.893409609859221e-06, "epoch": 0.47601476014760147, "percentage": 15.93, "elapsed_time": "0:25:08", "remaining_time": "2:12:46"}
87
+ {"current_steps": 87, "total_steps": 540, "loss": 0.4869, "lr": 9.886669291253178e-06, "epoch": 0.48154981549815495, "percentage": 16.11, "elapsed_time": "0:25:27", "remaining_time": "2:12:31"}
88
+ {"current_steps": 88, "total_steps": 540, "loss": 0.5296, "lr": 9.879724780684518e-06, "epoch": 0.4870848708487085, "percentage": 16.3, "elapsed_time": "0:25:44", "remaining_time": "2:12:11"}
89
+ {"current_steps": 89, "total_steps": 540, "loss": 0.5065, "lr": 9.872576368333152e-06, "epoch": 0.492619926199262, "percentage": 16.48, "elapsed_time": "0:25:59", "remaining_time": "2:11:40"}
90
+ {"current_steps": 90, "total_steps": 540, "loss": 0.5204, "lr": 9.86522435289912e-06, "epoch": 0.4981549815498155, "percentage": 16.67, "elapsed_time": "0:26:17", "remaining_time": "2:11:26"}
91
+ {"current_steps": 91, "total_steps": 540, "loss": 0.5038, "lr": 9.857669041590135e-06, "epoch": 0.503690036900369, "percentage": 16.85, "elapsed_time": "0:26:34", "remaining_time": "2:11:05"}
92
+ {"current_steps": 92, "total_steps": 540, "loss": 0.5319, "lr": 9.849910750108718e-06, "epoch": 0.5092250922509225, "percentage": 17.04, "elapsed_time": "0:26:51", "remaining_time": "2:10:47"}
93
+ {"current_steps": 93, "total_steps": 540, "loss": 0.5095, "lr": 9.841949802639031e-06, "epoch": 0.514760147601476, "percentage": 17.22, "elapsed_time": "0:27:08", "remaining_time": "2:10:25"}
94
+ {"current_steps": 94, "total_steps": 540, "loss": 0.4973, "lr": 9.833786531833311e-06, "epoch": 0.5202952029520295, "percentage": 17.41, "elapsed_time": "0:27:25", "remaining_time": "2:10:05"}
95
+ {"current_steps": 95, "total_steps": 540, "loss": 0.5098, "lr": 9.825421278797984e-06, "epoch": 0.525830258302583, "percentage": 17.59, "elapsed_time": "0:27:37", "remaining_time": "2:09:24"}
96
+ {"current_steps": 96, "total_steps": 540, "loss": 0.5227, "lr": 9.816854393079402e-06, "epoch": 0.5313653136531366, "percentage": 17.78, "elapsed_time": "0:27:53", "remaining_time": "2:08:59"}
97
+ {"current_steps": 97, "total_steps": 540, "loss": 0.5196, "lr": 9.808086232649246e-06, "epoch": 0.5369003690036901, "percentage": 17.96, "elapsed_time": "0:28:11", "remaining_time": "2:08:43"}
98
+ {"current_steps": 98, "total_steps": 540, "loss": 0.5118, "lr": 9.79911716388956e-06, "epoch": 0.5424354243542435, "percentage": 18.15, "elapsed_time": "0:28:27", "remaining_time": "2:08:21"}
99
+ {"current_steps": 99, "total_steps": 540, "loss": 0.5097, "lr": 9.789947561577445e-06, "epoch": 0.5479704797047971, "percentage": 18.33, "elapsed_time": "0:28:43", "remaining_time": "2:07:58"}
100
+ {"current_steps": 100, "total_steps": 540, "loss": 0.5114, "lr": 9.7805778088694e-06, "epoch": 0.5535055350553506, "percentage": 18.52, "elapsed_time": "0:29:02", "remaining_time": "2:07:47"}
101
+ {"current_steps": 101, "total_steps": 540, "loss": 0.5034, "lr": 9.771008297285307e-06, "epoch": 0.559040590405904, "percentage": 18.7, "elapsed_time": "0:29:20", "remaining_time": "2:07:33"}
102
+ {"current_steps": 102, "total_steps": 540, "loss": 0.5102, "lr": 9.761239426692077e-06, "epoch": 0.5645756457564576, "percentage": 18.89, "elapsed_time": "0:29:39", "remaining_time": "2:07:20"}
103
+ {"current_steps": 103, "total_steps": 540, "loss": 0.5207, "lr": 9.75127160528694e-06, "epoch": 0.5701107011070111, "percentage": 19.07, "elapsed_time": "0:29:56", "remaining_time": "2:07:01"}
104
+ {"current_steps": 104, "total_steps": 540, "loss": 0.5199, "lr": 9.741105249580383e-06, "epoch": 0.5756457564575646, "percentage": 19.26, "elapsed_time": "0:30:14", "remaining_time": "2:06:46"}
105
+ {"current_steps": 105, "total_steps": 540, "loss": 0.5427, "lr": 9.730740784378755e-06, "epoch": 0.5811808118081181, "percentage": 19.44, "elapsed_time": "0:30:31", "remaining_time": "2:06:28"}
106
+ {"current_steps": 106, "total_steps": 540, "loss": 0.5372, "lr": 9.7201786427665e-06, "epoch": 0.5867158671586716, "percentage": 19.63, "elapsed_time": "0:30:48", "remaining_time": "2:06:06"}
107
+ {"current_steps": 107, "total_steps": 540, "loss": 0.5041, "lr": 9.709419266088086e-06, "epoch": 0.5922509225092251, "percentage": 19.81, "elapsed_time": "0:31:04", "remaining_time": "2:05:45"}
108
+ {"current_steps": 108, "total_steps": 540, "loss": 0.4827, "lr": 9.698463103929542e-06, "epoch": 0.5977859778597786, "percentage": 20.0, "elapsed_time": "0:31:21", "remaining_time": "2:05:26"}
109
+ {"current_steps": 109, "total_steps": 540, "loss": 0.5244, "lr": 9.687310614099676e-06, "epoch": 0.6033210332103321, "percentage": 20.19, "elapsed_time": "0:31:39", "remaining_time": "2:05:10"}
110
+ {"current_steps": 110, "total_steps": 540, "loss": 0.487, "lr": 9.67596226261095e-06, "epoch": 0.6088560885608856, "percentage": 20.37, "elapsed_time": "0:31:55", "remaining_time": "2:04:48"}
111
+ {"current_steps": 111, "total_steps": 540, "loss": 0.5083, "lr": 9.664418523660004e-06, "epoch": 0.6143911439114391, "percentage": 20.56, "elapsed_time": "0:32:13", "remaining_time": "2:04:31"}
112
+ {"current_steps": 112, "total_steps": 540, "loss": 0.5073, "lr": 9.652679879607843e-06, "epoch": 0.6199261992619927, "percentage": 20.74, "elapsed_time": "0:32:30", "remaining_time": "2:04:14"}
113
+ {"current_steps": 113, "total_steps": 540, "loss": 0.5067, "lr": 9.640746820959684e-06, "epoch": 0.6254612546125461, "percentage": 20.93, "elapsed_time": "0:32:48", "remaining_time": "2:03:59"}
114
+ {"current_steps": 114, "total_steps": 540, "loss": 0.5054, "lr": 9.628619846344453e-06, "epoch": 0.6309963099630996, "percentage": 21.11, "elapsed_time": "0:33:05", "remaining_time": "2:03:41"}
115
+ {"current_steps": 115, "total_steps": 540, "loss": 0.5161, "lr": 9.616299462493952e-06, "epoch": 0.6365313653136532, "percentage": 21.3, "elapsed_time": "0:33:23", "remaining_time": "2:03:23"}
116
+ {"current_steps": 116, "total_steps": 540, "loss": 0.5017, "lr": 9.603786184221693e-06, "epoch": 0.6420664206642066, "percentage": 21.48, "elapsed_time": "0:33:41", "remaining_time": "2:03:07"}
117
+ {"current_steps": 117, "total_steps": 540, "loss": 0.5138, "lr": 9.591080534401371e-06, "epoch": 0.6476014760147601, "percentage": 21.67, "elapsed_time": "0:33:59", "remaining_time": "2:02:53"}
118
+ {"current_steps": 118, "total_steps": 540, "loss": 0.5107, "lr": 9.578183043945031e-06, "epoch": 0.6531365313653137, "percentage": 21.85, "elapsed_time": "0:34:16", "remaining_time": "2:02:36"}
119
+ {"current_steps": 119, "total_steps": 540, "loss": 0.5186, "lr": 9.565094251780872e-06, "epoch": 0.6586715867158671, "percentage": 22.04, "elapsed_time": "0:34:35", "remaining_time": "2:02:23"}
120
+ {"current_steps": 120, "total_steps": 540, "loss": 0.5077, "lr": 9.551814704830734e-06, "epoch": 0.6642066420664207, "percentage": 22.22, "elapsed_time": "0:34:53", "remaining_time": "2:02:08"}
121
+ {"current_steps": 121, "total_steps": 540, "loss": 0.4893, "lr": 9.538344957987245e-06, "epoch": 0.6697416974169742, "percentage": 22.41, "elapsed_time": "0:35:10", "remaining_time": "2:01:49"}
122
+ {"current_steps": 122, "total_steps": 540, "loss": 0.5104, "lr": 9.524685574090627e-06, "epoch": 0.6752767527675276, "percentage": 22.59, "elapsed_time": "0:35:26", "remaining_time": "2:01:26"}
123
+ {"current_steps": 123, "total_steps": 540, "loss": 0.4951, "lr": 9.51083712390519e-06, "epoch": 0.6808118081180812, "percentage": 22.78, "elapsed_time": "0:35:43", "remaining_time": "2:01:07"}
124
+ {"current_steps": 124, "total_steps": 540, "loss": 0.5133, "lr": 9.496800186095466e-06, "epoch": 0.6863468634686347, "percentage": 22.96, "elapsed_time": "0:36:00", "remaining_time": "2:00:49"}
125
+ {"current_steps": 125, "total_steps": 540, "loss": 0.4966, "lr": 9.482575347202047e-06, "epoch": 0.6918819188191881, "percentage": 23.15, "elapsed_time": "0:36:19", "remaining_time": "2:00:34"}
126
+ {"current_steps": 126, "total_steps": 540, "loss": 0.4886, "lr": 9.468163201617063e-06, "epoch": 0.6974169741697417, "percentage": 23.33, "elapsed_time": "0:36:36", "remaining_time": "2:00:17"}
127
+ {"current_steps": 127, "total_steps": 540, "loss": 0.4986, "lr": 9.453564351559348e-06, "epoch": 0.7029520295202952, "percentage": 23.52, "elapsed_time": "0:36:52", "remaining_time": "1:59:53"}
128
+ {"current_steps": 128, "total_steps": 540, "loss": 0.5088, "lr": 9.438779407049282e-06, "epoch": 0.7084870848708487, "percentage": 23.7, "elapsed_time": "0:37:07", "remaining_time": "1:59:30"}
129
+ {"current_steps": 129, "total_steps": 540, "loss": 0.5152, "lr": 9.423808985883289e-06, "epoch": 0.7140221402214022, "percentage": 23.89, "elapsed_time": "0:37:25", "remaining_time": "1:59:14"}
130
+ {"current_steps": 130, "total_steps": 540, "loss": 0.4853, "lr": 9.40865371360804e-06, "epoch": 0.7195571955719557, "percentage": 24.07, "elapsed_time": "0:37:43", "remaining_time": "1:58:57"}
131
+ {"current_steps": 131, "total_steps": 540, "loss": 0.4967, "lr": 9.393314223494297e-06, "epoch": 0.7250922509225092, "percentage": 24.26, "elapsed_time": "0:38:00", "remaining_time": "1:58:41"}
132
+ {"current_steps": 132, "total_steps": 540, "loss": 0.5019, "lr": 9.377791156510456e-06, "epoch": 0.7306273062730627, "percentage": 24.44, "elapsed_time": "0:38:17", "remaining_time": "1:58:21"}
133
+ {"current_steps": 133, "total_steps": 540, "loss": 0.5071, "lr": 9.362085161295768e-06, "epoch": 0.7361623616236163, "percentage": 24.63, "elapsed_time": "0:38:35", "remaining_time": "1:58:06"}
134
+ {"current_steps": 134, "total_steps": 540, "loss": 0.4777, "lr": 9.346196894133239e-06, "epoch": 0.7416974169741697, "percentage": 24.81, "elapsed_time": "0:38:50", "remaining_time": "1:57:41"}
135
+ {"current_steps": 135, "total_steps": 540, "loss": 0.4986, "lr": 9.330127018922195e-06, "epoch": 0.7472324723247232, "percentage": 25.0, "elapsed_time": "0:39:08", "remaining_time": "1:57:26"}
136
+ {"current_steps": 136, "total_steps": 540, "loss": 0.4925, "lr": 9.313876207150544e-06, "epoch": 0.7527675276752768, "percentage": 25.19, "elapsed_time": "0:39:25", "remaining_time": "1:57:05"}
137
+ {"current_steps": 137, "total_steps": 540, "loss": 0.4961, "lr": 9.297445137866726e-06, "epoch": 0.7583025830258303, "percentage": 25.37, "elapsed_time": "0:39:42", "remaining_time": "1:56:49"}
138
+ {"current_steps": 138, "total_steps": 540, "loss": 0.4937, "lr": 9.280834497651334e-06, "epoch": 0.7638376383763837, "percentage": 25.56, "elapsed_time": "0:39:58", "remaining_time": "1:56:27"}
139
+ {"current_steps": 139, "total_steps": 540, "loss": 0.4954, "lr": 9.264044980588415e-06, "epoch": 0.7693726937269373, "percentage": 25.74, "elapsed_time": "0:40:15", "remaining_time": "1:56:08"}
140
+ {"current_steps": 140, "total_steps": 540, "loss": 0.4956, "lr": 9.247077288236488e-06, "epoch": 0.7749077490774908, "percentage": 25.93, "elapsed_time": "0:40:32", "remaining_time": "1:55:49"}
141
+ {"current_steps": 141, "total_steps": 540, "loss": 0.4913, "lr": 9.229932129599206e-06, "epoch": 0.7804428044280443, "percentage": 26.11, "elapsed_time": "0:40:49", "remaining_time": "1:55:32"}
142
+ {"current_steps": 142, "total_steps": 540, "loss": 0.4838, "lr": 9.212610221095748e-06, "epoch": 0.7859778597785978, "percentage": 26.3, "elapsed_time": "0:41:07", "remaining_time": "1:55:14"}
143
+ {"current_steps": 143, "total_steps": 540, "loss": 0.4741, "lr": 9.195112286530874e-06, "epoch": 0.7915129151291513, "percentage": 26.48, "elapsed_time": "0:41:24", "remaining_time": "1:54:58"}
144
+ {"current_steps": 144, "total_steps": 540, "loss": 0.4898, "lr": 9.177439057064684e-06, "epoch": 0.7970479704797048, "percentage": 26.67, "elapsed_time": "0:41:42", "remaining_time": "1:54:42"}
145
+ {"current_steps": 145, "total_steps": 540, "loss": 0.4828, "lr": 9.159591271182058e-06, "epoch": 0.8025830258302583, "percentage": 26.85, "elapsed_time": "0:41:59", "remaining_time": "1:54:24"}
146
+ {"current_steps": 146, "total_steps": 540, "loss": 0.4915, "lr": 9.141569674661816e-06, "epoch": 0.8081180811808119, "percentage": 27.04, "elapsed_time": "0:42:18", "remaining_time": "1:54:09"}
147
+ {"current_steps": 147, "total_steps": 540, "loss": 0.5064, "lr": 9.123375020545534e-06, "epoch": 0.8136531365313653, "percentage": 27.22, "elapsed_time": "0:42:35", "remaining_time": "1:53:52"}
148
+ {"current_steps": 148, "total_steps": 540, "loss": 0.4873, "lr": 9.105008069106093e-06, "epoch": 0.8191881918819188, "percentage": 27.41, "elapsed_time": "0:42:52", "remaining_time": "1:53:32"}
149
+ {"current_steps": 149, "total_steps": 540, "loss": 0.4996, "lr": 9.086469587815904e-06, "epoch": 0.8247232472324724, "percentage": 27.59, "elapsed_time": "0:43:08", "remaining_time": "1:53:12"}
150
+ {"current_steps": 150, "total_steps": 540, "loss": 0.4817, "lr": 9.067760351314838e-06, "epoch": 0.8302583025830258, "percentage": 27.78, "elapsed_time": "0:43:23", "remaining_time": "1:52:49"}
151
+ {"current_steps": 151, "total_steps": 540, "loss": 0.4889, "lr": 9.048881141377863e-06, "epoch": 0.8357933579335793, "percentage": 27.96, "elapsed_time": "0:43:39", "remaining_time": "1:52:28"}
152
+ {"current_steps": 152, "total_steps": 540, "loss": 0.5127, "lr": 9.029832746882372e-06, "epoch": 0.8413284132841329, "percentage": 28.15, "elapsed_time": "0:43:58", "remaining_time": "1:52:14"}
153
+ {"current_steps": 153, "total_steps": 540, "loss": 0.503, "lr": 9.01061596377522e-06, "epoch": 0.8468634686346863, "percentage": 28.33, "elapsed_time": "0:44:16", "remaining_time": "1:51:58"}
154
+ {"current_steps": 154, "total_steps": 540, "loss": 0.5043, "lr": 8.991231595039464e-06, "epoch": 0.8523985239852399, "percentage": 28.52, "elapsed_time": "0:44:31", "remaining_time": "1:51:35"}
155
+ {"current_steps": 155, "total_steps": 540, "loss": 0.4847, "lr": 8.97168045066082e-06, "epoch": 0.8579335793357934, "percentage": 28.7, "elapsed_time": "0:44:49", "remaining_time": "1:51:19"}
156
+ {"current_steps": 156, "total_steps": 540, "loss": 0.4907, "lr": 8.951963347593797e-06, "epoch": 0.8634686346863468, "percentage": 28.89, "elapsed_time": "0:45:04", "remaining_time": "1:50:57"}
157
+ {"current_steps": 157, "total_steps": 540, "loss": 0.4992, "lr": 8.932081109727582e-06, "epoch": 0.8690036900369004, "percentage": 29.07, "elapsed_time": "0:45:20", "remaining_time": "1:50:36"}
158
+ {"current_steps": 158, "total_steps": 540, "loss": 0.4823, "lr": 8.9120345678516e-06, "epoch": 0.8745387453874539, "percentage": 29.26, "elapsed_time": "0:45:37", "remaining_time": "1:50:17"}
159
+ {"current_steps": 159, "total_steps": 540, "loss": 0.4982, "lr": 8.891824559620801e-06, "epoch": 0.8800738007380073, "percentage": 29.44, "elapsed_time": "0:45:53", "remaining_time": "1:49:57"}
160
+ {"current_steps": 160, "total_steps": 540, "loss": 0.4719, "lr": 8.871451929520662e-06, "epoch": 0.8856088560885609, "percentage": 29.63, "elapsed_time": "0:46:10", "remaining_time": "1:49:40"}
161
+ {"current_steps": 161, "total_steps": 540, "loss": 0.4853, "lr": 8.8509175288319e-06, "epoch": 0.8911439114391144, "percentage": 29.81, "elapsed_time": "0:46:28", "remaining_time": "1:49:24"}
162
+ {"current_steps": 162, "total_steps": 540, "loss": 0.5076, "lr": 8.83022221559489e-06, "epoch": 0.8966789667896679, "percentage": 30.0, "elapsed_time": "0:46:45", "remaining_time": "1:49:07"}
163
+ {"current_steps": 163, "total_steps": 540, "loss": 0.505, "lr": 8.80936685457383e-06, "epoch": 0.9022140221402214, "percentage": 30.19, "elapsed_time": "0:47:03", "remaining_time": "1:48:50"}
164
+ {"current_steps": 164, "total_steps": 540, "loss": 0.4934, "lr": 8.78835231722059e-06, "epoch": 0.9077490774907749, "percentage": 30.37, "elapsed_time": "0:47:21", "remaining_time": "1:48:34"}
165
+ {"current_steps": 165, "total_steps": 540, "loss": 0.4789, "lr": 8.767179481638303e-06, "epoch": 0.9132841328413284, "percentage": 30.56, "elapsed_time": "0:47:39", "remaining_time": "1:48:18"}
166
+ {"current_steps": 166, "total_steps": 540, "loss": 0.5107, "lr": 8.74584923254468e-06, "epoch": 0.9188191881918819, "percentage": 30.74, "elapsed_time": "0:47:57", "remaining_time": "1:48:03"}
167
+ {"current_steps": 167, "total_steps": 540, "loss": 0.462, "lr": 8.72436246123503e-06, "epoch": 0.9243542435424354, "percentage": 30.93, "elapsed_time": "0:48:15", "remaining_time": "1:47:46"}
168
+ {"current_steps": 168, "total_steps": 540, "loss": 0.4734, "lr": 8.702720065545024e-06, "epoch": 0.9298892988929889, "percentage": 31.11, "elapsed_time": "0:48:31", "remaining_time": "1:47:27"}
169
+ {"current_steps": 169, "total_steps": 540, "loss": 0.4986, "lr": 8.680922949813177e-06, "epoch": 0.9354243542435424, "percentage": 31.3, "elapsed_time": "0:48:49", "remaining_time": "1:47:11"}
170
+ {"current_steps": 170, "total_steps": 540, "loss": 0.5031, "lr": 8.658972024843063e-06, "epoch": 0.940959409594096, "percentage": 31.48, "elapsed_time": "0:49:05", "remaining_time": "1:46:51"}
171
+ {"current_steps": 171, "total_steps": 540, "loss": 0.4904, "lr": 8.636868207865244e-06, "epoch": 0.9464944649446494, "percentage": 31.67, "elapsed_time": "0:49:23", "remaining_time": "1:46:35"}
172
+ {"current_steps": 172, "total_steps": 540, "loss": 0.486, "lr": 8.614612422498965e-06, "epoch": 0.9520295202952029, "percentage": 31.85, "elapsed_time": "0:49:41", "remaining_time": "1:46:18"}
173
+ {"current_steps": 173, "total_steps": 540, "loss": 0.4772, "lr": 8.592205598713539e-06, "epoch": 0.9575645756457565, "percentage": 32.04, "elapsed_time": "0:49:59", "remaining_time": "1:46:03"}
174
+ {"current_steps": 174, "total_steps": 540, "loss": 0.4925, "lr": 8.569648672789496e-06, "epoch": 0.9630996309963099, "percentage": 32.22, "elapsed_time": "0:50:17", "remaining_time": "1:45:47"}
175
+ {"current_steps": 175, "total_steps": 540, "loss": 0.4885, "lr": 8.546942587279465e-06, "epoch": 0.9686346863468634, "percentage": 32.41, "elapsed_time": "0:50:34", "remaining_time": "1:45:28"}
176
+ {"current_steps": 176, "total_steps": 540, "loss": 0.4944, "lr": 8.524088290968781e-06, "epoch": 0.974169741697417, "percentage": 32.59, "elapsed_time": "0:50:51", "remaining_time": "1:45:11"}
177
+ {"current_steps": 177, "total_steps": 540, "loss": 0.4855, "lr": 8.501086738835843e-06, "epoch": 0.9797047970479705, "percentage": 32.78, "elapsed_time": "0:51:08", "remaining_time": "1:44:53"}
178
+ {"current_steps": 178, "total_steps": 540, "loss": 0.4841, "lr": 8.477938892012209e-06, "epoch": 0.985239852398524, "percentage": 32.96, "elapsed_time": "0:51:26", "remaining_time": "1:44:36"}
179
+ {"current_steps": 179, "total_steps": 540, "loss": 0.5023, "lr": 8.45464571774244e-06, "epoch": 0.9907749077490775, "percentage": 33.15, "elapsed_time": "0:51:41", "remaining_time": "1:44:15"}
180
+ {"current_steps": 180, "total_steps": 540, "loss": 0.5015, "lr": 8.43120818934367e-06, "epoch": 0.996309963099631, "percentage": 33.33, "elapsed_time": "0:52:00", "remaining_time": "1:44:00"}
181
+ {"current_steps": 181, "total_steps": 540, "loss": 0.6387, "lr": 8.407627286164948e-06, "epoch": 1.0018450184501846, "percentage": 33.52, "elapsed_time": "0:53:22", "remaining_time": "1:45:51"}
182
+ {"current_steps": 182, "total_steps": 540, "loss": 0.4901, "lr": 8.38390399354631e-06, "epoch": 1.007380073800738, "percentage": 33.7, "elapsed_time": "0:53:40", "remaining_time": "1:45:35"}
183
+ {"current_steps": 183, "total_steps": 540, "loss": 0.4598, "lr": 8.360039302777614e-06, "epoch": 1.0129151291512914, "percentage": 33.89, "elapsed_time": "0:53:56", "remaining_time": "1:45:13"}
184
+ {"current_steps": 184, "total_steps": 540, "loss": 0.4684, "lr": 8.336034211057098e-06, "epoch": 1.018450184501845, "percentage": 34.07, "elapsed_time": "0:54:12", "remaining_time": "1:44:53"}
185
+ {"current_steps": 185, "total_steps": 540, "loss": 0.4677, "lr": 8.31188972144974e-06, "epoch": 1.0239852398523985, "percentage": 34.26, "elapsed_time": "0:54:30", "remaining_time": "1:44:35"}
186
+ {"current_steps": 186, "total_steps": 540, "loss": 0.4892, "lr": 8.28760684284532e-06, "epoch": 1.029520295202952, "percentage": 34.44, "elapsed_time": "0:54:48", "remaining_time": "1:44:17"}
187
+ {"current_steps": 187, "total_steps": 540, "loss": 0.4336, "lr": 8.263186589916273e-06, "epoch": 1.0350553505535056, "percentage": 34.63, "elapsed_time": "0:55:03", "remaining_time": "1:43:56"}
188
+ {"current_steps": 188, "total_steps": 540, "loss": 0.4682, "lr": 8.238629983075296e-06, "epoch": 1.040590405904059, "percentage": 34.81, "elapsed_time": "0:55:21", "remaining_time": "1:43:38"}
189
+ {"current_steps": 189, "total_steps": 540, "loss": 0.4198, "lr": 8.213938048432697e-06, "epoch": 1.0461254612546125, "percentage": 35.0, "elapsed_time": "0:55:37", "remaining_time": "1:43:17"}
190
+ {"current_steps": 190, "total_steps": 540, "loss": 0.4754, "lr": 8.18911181775353e-06, "epoch": 1.051660516605166, "percentage": 35.19, "elapsed_time": "0:55:54", "remaining_time": "1:43:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a79b40619c6669d7d6d3d4927fea5e377293289746d20e81f2e8537d1352f888
3
- size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4587bf86b20338500a6f41236d8948fd4f6e31d0c2c26a4ff347c47ba2e06c5
3
+ size 7288
vocab.json ADDED
The diff for this file is too large to render. See raw diff