gsmyrnis commited on
Commit
21eb828
·
verified ·
1 Parent(s): 507389f

Training in progress, epoch 1

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 sha256:233d90ff3fc03b1f34b6371af665e12f9af2b1a611854c0a97588886e3ddc9e5
3
- size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652c76fb302abb8017e0669d2a0ddc4219270310309166e060d3e32c00f40883
3
+ size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a7c49b63828ab136e75116e39ad427f224b2fa9c2f3f37683dccc7964a738f9
3
- size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9155effecbb67cc8bdd8ed4fd8ea658367461ba8880817260bdf8e0c8ebc8229
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:bd6bd937733fb3ce0c62dc5d70a97c5ca08907579c9311aca6ca281710a6ab86
3
- size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c9b8d597d77a79e1437b56c6babad84612ec588474057fae17b5a4070230d90
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:d9c7546ca2ffe13afdac1e2b24b34ce3800e43d1f8fe1ad63e2a40b821909a68
3
- size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c8a4a11963291f8677e2b658d9df583c3cff179d5ed5a754da09ee83cc5eca
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
@@ -1,9 +1,273 @@
1
- {"current_steps": 10, "total_steps": 51, "loss": 0.8804, "lr": 5e-06, "epoch": 0.5882352941176471, "percentage": 19.61, "elapsed_time": "0:00:59", "remaining_time": "0:04:04"}
2
- {"current_steps": 17, "total_steps": 51, "eval_loss": 0.7954549193382263, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:01:42", "remaining_time": "0:03:24"}
3
- {"current_steps": 20, "total_steps": 51, "loss": 0.7874, "lr": 5e-06, "epoch": 1.1764705882352942, "percentage": 39.22, "elapsed_time": "0:03:16", "remaining_time": "0:05:04"}
4
- {"current_steps": 30, "total_steps": 51, "loss": 0.7508, "lr": 5e-06, "epoch": 1.7647058823529411, "percentage": 58.82, "elapsed_time": "0:04:15", "remaining_time": "0:02:58"}
5
- {"current_steps": 34, "total_steps": 51, "eval_loss": 0.7634365558624268, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:04:40", "remaining_time": "0:02:20"}
6
- {"current_steps": 40, "total_steps": 51, "loss": 0.7209, "lr": 5e-06, "epoch": 2.3529411764705883, "percentage": 78.43, "elapsed_time": "0:06:38", "remaining_time": "0:01:49"}
7
- {"current_steps": 50, "total_steps": 51, "loss": 0.7022, "lr": 5e-06, "epoch": 2.9411764705882355, "percentage": 98.04, "elapsed_time": "0:07:36", "remaining_time": "0:00:09"}
8
- {"current_steps": 51, "total_steps": 51, "eval_loss": 0.7526352405548096, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:09:13", "remaining_time": "0:00:00"}
9
- {"current_steps": 51, "total_steps": 51, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:10:36", "remaining_time": "0:00:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 543, "loss": 0.882, "lr": 1.8181818181818183e-07, "epoch": 0.0055248618784530384, "percentage": 0.18, "elapsed_time": "0:00:02", "remaining_time": "0:23:39"}
2
+ {"current_steps": 2, "total_steps": 543, "loss": 0.9499, "lr": 3.6363636363636366e-07, "epoch": 0.011049723756906077, "percentage": 0.37, "elapsed_time": "0:00:04", "remaining_time": "0:20:29"}
3
+ {"current_steps": 3, "total_steps": 543, "loss": 0.8375, "lr": 5.454545454545455e-07, "epoch": 0.016574585635359115, "percentage": 0.55, "elapsed_time": "0:00:05", "remaining_time": "0:17:39"}
4
+ {"current_steps": 4, "total_steps": 543, "loss": 0.8694, "lr": 7.272727272727273e-07, "epoch": 0.022099447513812154, "percentage": 0.74, "elapsed_time": "0:00:07", "remaining_time": "0:16:15"}
5
+ {"current_steps": 5, "total_steps": 543, "loss": 0.7922, "lr": 9.090909090909091e-07, "epoch": 0.027624309392265192, "percentage": 0.92, "elapsed_time": "0:00:08", "remaining_time": "0:16:06"}
6
+ {"current_steps": 6, "total_steps": 543, "loss": 0.8158, "lr": 1.090909090909091e-06, "epoch": 0.03314917127071823, "percentage": 1.1, "elapsed_time": "0:00:10", "remaining_time": "0:15:22"}
7
+ {"current_steps": 7, "total_steps": 543, "loss": 0.8463, "lr": 1.2727272727272728e-06, "epoch": 0.03867403314917127, "percentage": 1.29, "elapsed_time": "0:00:11", "remaining_time": "0:15:14"}
8
+ {"current_steps": 8, "total_steps": 543, "loss": 0.7804, "lr": 1.4545454545454546e-06, "epoch": 0.04419889502762431, "percentage": 1.47, "elapsed_time": "0:00:14", "remaining_time": "0:15:56"}
9
+ {"current_steps": 9, "total_steps": 543, "loss": 0.8386, "lr": 1.6363636363636365e-06, "epoch": 0.049723756906077346, "percentage": 1.66, "elapsed_time": "0:00:15", "remaining_time": "0:15:24"}
10
+ {"current_steps": 10, "total_steps": 543, "loss": 0.7804, "lr": 1.8181818181818183e-06, "epoch": 0.055248618784530384, "percentage": 1.84, "elapsed_time": "0:00:17", "remaining_time": "0:15:15"}
11
+ {"current_steps": 11, "total_steps": 543, "loss": 0.7536, "lr": 2.0000000000000003e-06, "epoch": 0.06077348066298342, "percentage": 2.03, "elapsed_time": "0:00:18", "remaining_time": "0:15:00"}
12
+ {"current_steps": 12, "total_steps": 543, "loss": 0.8003, "lr": 2.181818181818182e-06, "epoch": 0.06629834254143646, "percentage": 2.21, "elapsed_time": "0:00:20", "remaining_time": "0:14:47"}
13
+ {"current_steps": 13, "total_steps": 543, "loss": 0.7728, "lr": 2.363636363636364e-06, "epoch": 0.0718232044198895, "percentage": 2.39, "elapsed_time": "0:00:21", "remaining_time": "0:14:39"}
14
+ {"current_steps": 14, "total_steps": 543, "loss": 0.7816, "lr": 2.5454545454545456e-06, "epoch": 0.07734806629834254, "percentage": 2.58, "elapsed_time": "0:00:23", "remaining_time": "0:14:32"}
15
+ {"current_steps": 15, "total_steps": 543, "loss": 0.7138, "lr": 2.7272727272727272e-06, "epoch": 0.08287292817679558, "percentage": 2.76, "elapsed_time": "0:00:24", "remaining_time": "0:14:23"}
16
+ {"current_steps": 16, "total_steps": 543, "loss": 0.7254, "lr": 2.9090909090909093e-06, "epoch": 0.08839779005524862, "percentage": 2.95, "elapsed_time": "0:00:25", "remaining_time": "0:14:12"}
17
+ {"current_steps": 17, "total_steps": 543, "loss": 0.7294, "lr": 3.090909090909091e-06, "epoch": 0.09392265193370165, "percentage": 3.13, "elapsed_time": "0:00:28", "remaining_time": "0:14:43"}
18
+ {"current_steps": 18, "total_steps": 543, "loss": 0.711, "lr": 3.272727272727273e-06, "epoch": 0.09944751381215469, "percentage": 3.31, "elapsed_time": "0:00:29", "remaining_time": "0:14:31"}
19
+ {"current_steps": 19, "total_steps": 543, "loss": 0.6706, "lr": 3.454545454545455e-06, "epoch": 0.10497237569060773, "percentage": 3.5, "elapsed_time": "0:00:31", "remaining_time": "0:14:37"}
20
+ {"current_steps": 20, "total_steps": 543, "loss": 0.714, "lr": 3.6363636363636366e-06, "epoch": 0.11049723756906077, "percentage": 3.68, "elapsed_time": "0:00:33", "remaining_time": "0:14:30"}
21
+ {"current_steps": 21, "total_steps": 543, "loss": 0.6221, "lr": 3.818181818181819e-06, "epoch": 0.11602209944751381, "percentage": 3.87, "elapsed_time": "0:00:34", "remaining_time": "0:14:27"}
22
+ {"current_steps": 22, "total_steps": 543, "loss": 0.6874, "lr": 4.000000000000001e-06, "epoch": 0.12154696132596685, "percentage": 4.05, "elapsed_time": "0:00:36", "remaining_time": "0:14:23"}
23
+ {"current_steps": 23, "total_steps": 543, "loss": 0.6741, "lr": 4.181818181818182e-06, "epoch": 0.1270718232044199, "percentage": 4.24, "elapsed_time": "0:00:37", "remaining_time": "0:14:16"}
24
+ {"current_steps": 24, "total_steps": 543, "loss": 0.8114, "lr": 4.363636363636364e-06, "epoch": 0.13259668508287292, "percentage": 4.42, "elapsed_time": "0:00:39", "remaining_time": "0:14:08"}
25
+ {"current_steps": 25, "total_steps": 543, "loss": 0.6904, "lr": 4.5454545454545455e-06, "epoch": 0.13812154696132597, "percentage": 4.6, "elapsed_time": "0:00:40", "remaining_time": "0:14:04"}
26
+ {"current_steps": 26, "total_steps": 543, "loss": 0.6887, "lr": 4.727272727272728e-06, "epoch": 0.143646408839779, "percentage": 4.79, "elapsed_time": "0:00:42", "remaining_time": "0:14:02"}
27
+ {"current_steps": 27, "total_steps": 543, "loss": 0.7305, "lr": 4.90909090909091e-06, "epoch": 0.14917127071823205, "percentage": 4.97, "elapsed_time": "0:00:44", "remaining_time": "0:14:03"}
28
+ {"current_steps": 28, "total_steps": 543, "loss": 0.7216, "lr": 5.090909090909091e-06, "epoch": 0.15469613259668508, "percentage": 5.16, "elapsed_time": "0:00:45", "remaining_time": "0:13:55"}
29
+ {"current_steps": 29, "total_steps": 543, "loss": 0.7262, "lr": 5.272727272727273e-06, "epoch": 0.16022099447513813, "percentage": 5.34, "elapsed_time": "0:00:46", "remaining_time": "0:13:48"}
30
+ {"current_steps": 30, "total_steps": 543, "loss": 0.6818, "lr": 5.4545454545454545e-06, "epoch": 0.16574585635359115, "percentage": 5.52, "elapsed_time": "0:00:52", "remaining_time": "0:15:05"}
31
+ {"current_steps": 31, "total_steps": 543, "loss": 0.6709, "lr": 5.636363636363636e-06, "epoch": 0.1712707182320442, "percentage": 5.71, "elapsed_time": "0:00:54", "remaining_time": "0:15:02"}
32
+ {"current_steps": 32, "total_steps": 543, "loss": 0.7056, "lr": 5.8181818181818185e-06, "epoch": 0.17679558011049723, "percentage": 5.89, "elapsed_time": "0:00:56", "remaining_time": "0:14:55"}
33
+ {"current_steps": 33, "total_steps": 543, "loss": 0.7321, "lr": 6e-06, "epoch": 0.18232044198895028, "percentage": 6.08, "elapsed_time": "0:00:57", "remaining_time": "0:14:48"}
34
+ {"current_steps": 34, "total_steps": 543, "loss": 0.6943, "lr": 6.181818181818182e-06, "epoch": 0.1878453038674033, "percentage": 6.26, "elapsed_time": "0:00:58", "remaining_time": "0:14:42"}
35
+ {"current_steps": 35, "total_steps": 543, "loss": 0.7474, "lr": 6.363636363636364e-06, "epoch": 0.19337016574585636, "percentage": 6.45, "elapsed_time": "0:01:00", "remaining_time": "0:14:39"}
36
+ {"current_steps": 36, "total_steps": 543, "loss": 0.7448, "lr": 6.545454545454546e-06, "epoch": 0.19889502762430938, "percentage": 6.63, "elapsed_time": "0:01:02", "remaining_time": "0:14:35"}
37
+ {"current_steps": 37, "total_steps": 543, "loss": 0.6026, "lr": 6.7272727272727275e-06, "epoch": 0.20441988950276244, "percentage": 6.81, "elapsed_time": "0:01:03", "remaining_time": "0:14:32"}
38
+ {"current_steps": 38, "total_steps": 543, "loss": 0.686, "lr": 6.90909090909091e-06, "epoch": 0.20994475138121546, "percentage": 7.0, "elapsed_time": "0:01:05", "remaining_time": "0:14:27"}
39
+ {"current_steps": 39, "total_steps": 543, "loss": 0.6863, "lr": 7.0909090909090916e-06, "epoch": 0.2154696132596685, "percentage": 7.18, "elapsed_time": "0:01:06", "remaining_time": "0:14:24"}
40
+ {"current_steps": 40, "total_steps": 543, "loss": 0.6495, "lr": 7.272727272727273e-06, "epoch": 0.22099447513812154, "percentage": 7.37, "elapsed_time": "0:01:08", "remaining_time": "0:14:17"}
41
+ {"current_steps": 41, "total_steps": 543, "loss": 0.6903, "lr": 7.454545454545456e-06, "epoch": 0.2265193370165746, "percentage": 7.55, "elapsed_time": "0:01:09", "remaining_time": "0:14:14"}
42
+ {"current_steps": 42, "total_steps": 543, "loss": 0.6681, "lr": 7.636363636363638e-06, "epoch": 0.23204419889502761, "percentage": 7.73, "elapsed_time": "0:01:11", "remaining_time": "0:14:11"}
43
+ {"current_steps": 43, "total_steps": 543, "loss": 0.6454, "lr": 7.81818181818182e-06, "epoch": 0.23756906077348067, "percentage": 7.92, "elapsed_time": "0:01:12", "remaining_time": "0:14:05"}
44
+ {"current_steps": 44, "total_steps": 543, "loss": 0.6943, "lr": 8.000000000000001e-06, "epoch": 0.2430939226519337, "percentage": 8.1, "elapsed_time": "0:01:14", "remaining_time": "0:14:03"}
45
+ {"current_steps": 45, "total_steps": 543, "loss": 0.6376, "lr": 8.181818181818183e-06, "epoch": 0.24861878453038674, "percentage": 8.29, "elapsed_time": "0:01:15", "remaining_time": "0:13:57"}
46
+ {"current_steps": 46, "total_steps": 543, "loss": 0.6873, "lr": 8.363636363636365e-06, "epoch": 0.2541436464088398, "percentage": 8.47, "elapsed_time": "0:01:17", "remaining_time": "0:13:53"}
47
+ {"current_steps": 47, "total_steps": 543, "loss": 0.6275, "lr": 8.545454545454546e-06, "epoch": 0.2596685082872928, "percentage": 8.66, "elapsed_time": "0:01:18", "remaining_time": "0:13:49"}
48
+ {"current_steps": 48, "total_steps": 543, "loss": 0.7049, "lr": 8.727272727272728e-06, "epoch": 0.26519337016574585, "percentage": 8.84, "elapsed_time": "0:01:20", "remaining_time": "0:13:45"}
49
+ {"current_steps": 49, "total_steps": 543, "loss": 0.6914, "lr": 8.90909090909091e-06, "epoch": 0.27071823204419887, "percentage": 9.02, "elapsed_time": "0:01:21", "remaining_time": "0:13:40"}
50
+ {"current_steps": 50, "total_steps": 543, "loss": 0.6982, "lr": 9.090909090909091e-06, "epoch": 0.27624309392265195, "percentage": 9.21, "elapsed_time": "0:01:22", "remaining_time": "0:13:37"}
51
+ {"current_steps": 51, "total_steps": 543, "loss": 0.7023, "lr": 9.272727272727273e-06, "epoch": 0.281767955801105, "percentage": 9.39, "elapsed_time": "0:01:24", "remaining_time": "0:13:38"}
52
+ {"current_steps": 52, "total_steps": 543, "loss": 0.695, "lr": 9.454545454545456e-06, "epoch": 0.287292817679558, "percentage": 9.58, "elapsed_time": "0:01:26", "remaining_time": "0:13:35"}
53
+ {"current_steps": 53, "total_steps": 543, "loss": 0.7185, "lr": 9.636363636363638e-06, "epoch": 0.292817679558011, "percentage": 9.76, "elapsed_time": "0:01:27", "remaining_time": "0:13:30"}
54
+ {"current_steps": 54, "total_steps": 543, "loss": 0.6864, "lr": 9.81818181818182e-06, "epoch": 0.2983425414364641, "percentage": 9.94, "elapsed_time": "0:01:29", "remaining_time": "0:13:26"}
55
+ {"current_steps": 55, "total_steps": 543, "loss": 0.6191, "lr": 1e-05, "epoch": 0.30386740331491713, "percentage": 10.13, "elapsed_time": "0:01:31", "remaining_time": "0:13:28"}
56
+ {"current_steps": 56, "total_steps": 543, "loss": 0.6469, "lr": 9.999896390730872e-06, "epoch": 0.30939226519337015, "percentage": 10.31, "elapsed_time": "0:01:32", "remaining_time": "0:13:24"}
57
+ {"current_steps": 57, "total_steps": 543, "loss": 0.7147, "lr": 9.99958556721744e-06, "epoch": 0.3149171270718232, "percentage": 10.5, "elapsed_time": "0:01:33", "remaining_time": "0:13:19"}
58
+ {"current_steps": 58, "total_steps": 543, "loss": 0.6935, "lr": 9.99906754234138e-06, "epoch": 0.32044198895027626, "percentage": 10.68, "elapsed_time": "0:01:36", "remaining_time": "0:13:23"}
59
+ {"current_steps": 59, "total_steps": 543, "loss": 0.6852, "lr": 9.998342337571566e-06, "epoch": 0.3259668508287293, "percentage": 10.87, "elapsed_time": "0:01:37", "remaining_time": "0:13:21"}
60
+ {"current_steps": 60, "total_steps": 543, "loss": 0.594, "lr": 9.997409982963173e-06, "epoch": 0.3314917127071823, "percentage": 11.05, "elapsed_time": "0:01:39", "remaining_time": "0:13:20"}
61
+ {"current_steps": 61, "total_steps": 543, "loss": 0.6359, "lr": 9.996270517156431e-06, "epoch": 0.3370165745856354, "percentage": 11.23, "elapsed_time": "0:01:41", "remaining_time": "0:13:21"}
62
+ {"current_steps": 62, "total_steps": 543, "loss": 0.6948, "lr": 9.994923987375029e-06, "epoch": 0.3425414364640884, "percentage": 11.42, "elapsed_time": "0:01:42", "remaining_time": "0:13:18"}
63
+ {"current_steps": 63, "total_steps": 543, "loss": 0.73, "lr": 9.993370449424153e-06, "epoch": 0.34806629834254144, "percentage": 11.6, "elapsed_time": "0:01:44", "remaining_time": "0:13:14"}
64
+ {"current_steps": 64, "total_steps": 543, "loss": 0.7042, "lr": 9.991609967688177e-06, "epoch": 0.35359116022099446, "percentage": 11.79, "elapsed_time": "0:01:45", "remaining_time": "0:13:09"}
65
+ {"current_steps": 65, "total_steps": 543, "loss": 0.7034, "lr": 9.98964261512799e-06, "epoch": 0.35911602209944754, "percentage": 11.97, "elapsed_time": "0:01:46", "remaining_time": "0:13:05"}
66
+ {"current_steps": 66, "total_steps": 543, "loss": 0.6368, "lr": 9.987468473277975e-06, "epoch": 0.36464088397790057, "percentage": 12.15, "elapsed_time": "0:01:48", "remaining_time": "0:13:00"}
67
+ {"current_steps": 67, "total_steps": 543, "loss": 0.7059, "lr": 9.985087632242634e-06, "epoch": 0.3701657458563536, "percentage": 12.34, "elapsed_time": "0:01:49", "remaining_time": "0:12:57"}
68
+ {"current_steps": 68, "total_steps": 543, "loss": 0.7011, "lr": 9.982500190692846e-06, "epoch": 0.3756906077348066, "percentage": 12.52, "elapsed_time": "0:01:50", "remaining_time": "0:12:53"}
69
+ {"current_steps": 69, "total_steps": 543, "loss": 0.7038, "lr": 9.97970625586178e-06, "epoch": 0.3812154696132597, "percentage": 12.71, "elapsed_time": "0:01:52", "remaining_time": "0:12:53"}
70
+ {"current_steps": 70, "total_steps": 543, "loss": 0.7167, "lr": 9.976705943540458e-06, "epoch": 0.3867403314917127, "percentage": 12.89, "elapsed_time": "0:01:54", "remaining_time": "0:12:51"}
71
+ {"current_steps": 71, "total_steps": 543, "loss": 0.6383, "lr": 9.973499378072947e-06, "epoch": 0.39226519337016574, "percentage": 13.08, "elapsed_time": "0:01:55", "remaining_time": "0:12:48"}
72
+ {"current_steps": 72, "total_steps": 543, "loss": 0.6711, "lr": 9.970086692351204e-06, "epoch": 0.39779005524861877, "percentage": 13.26, "elapsed_time": "0:01:56", "remaining_time": "0:12:44"}
73
+ {"current_steps": 73, "total_steps": 543, "loss": 0.6631, "lr": 9.966468027809582e-06, "epoch": 0.40331491712707185, "percentage": 13.44, "elapsed_time": "0:01:58", "remaining_time": "0:12:42"}
74
+ {"current_steps": 74, "total_steps": 543, "loss": 0.7296, "lr": 9.962643534418954e-06, "epoch": 0.4088397790055249, "percentage": 13.63, "elapsed_time": "0:01:59", "remaining_time": "0:12:40"}
75
+ {"current_steps": 75, "total_steps": 543, "loss": 0.6619, "lr": 9.958613370680507e-06, "epoch": 0.4143646408839779, "percentage": 13.81, "elapsed_time": "0:02:01", "remaining_time": "0:12:36"}
76
+ {"current_steps": 76, "total_steps": 543, "loss": 0.6449, "lr": 9.954377703619171e-06, "epoch": 0.4198895027624309, "percentage": 14.0, "elapsed_time": "0:02:02", "remaining_time": "0:12:34"}
77
+ {"current_steps": 77, "total_steps": 543, "loss": 0.761, "lr": 9.949936708776692e-06, "epoch": 0.425414364640884, "percentage": 14.18, "elapsed_time": "0:02:04", "remaining_time": "0:12:32"}
78
+ {"current_steps": 78, "total_steps": 543, "loss": 0.6456, "lr": 9.945290570204361e-06, "epoch": 0.430939226519337, "percentage": 14.36, "elapsed_time": "0:02:05", "remaining_time": "0:12:29"}
79
+ {"current_steps": 79, "total_steps": 543, "loss": 0.6883, "lr": 9.940439480455386e-06, "epoch": 0.43646408839779005, "percentage": 14.55, "elapsed_time": "0:02:07", "remaining_time": "0:12:27"}
80
+ {"current_steps": 80, "total_steps": 543, "loss": 0.7192, "lr": 9.935383640576915e-06, "epoch": 0.4419889502762431, "percentage": 14.73, "elapsed_time": "0:02:08", "remaining_time": "0:12:23"}
81
+ {"current_steps": 81, "total_steps": 543, "loss": 0.7022, "lr": 9.930123260101697e-06, "epoch": 0.44751381215469616, "percentage": 14.92, "elapsed_time": "0:02:09", "remaining_time": "0:12:21"}
82
+ {"current_steps": 82, "total_steps": 543, "loss": 0.653, "lr": 9.9246585570394e-06, "epoch": 0.4530386740331492, "percentage": 15.1, "elapsed_time": "0:02:11", "remaining_time": "0:12:18"}
83
+ {"current_steps": 83, "total_steps": 543, "loss": 0.7316, "lr": 9.918989757867584e-06, "epoch": 0.4585635359116022, "percentage": 15.29, "elapsed_time": "0:02:12", "remaining_time": "0:12:16"}
84
+ {"current_steps": 84, "total_steps": 543, "loss": 0.632, "lr": 9.9131170975223e-06, "epoch": 0.46408839779005523, "percentage": 15.47, "elapsed_time": "0:02:14", "remaining_time": "0:12:14"}
85
+ {"current_steps": 85, "total_steps": 543, "loss": 0.7125, "lr": 9.907040819388372e-06, "epoch": 0.4696132596685083, "percentage": 15.65, "elapsed_time": "0:02:15", "remaining_time": "0:12:12"}
86
+ {"current_steps": 86, "total_steps": 543, "loss": 0.7054, "lr": 9.90076117528929e-06, "epoch": 0.47513812154696133, "percentage": 15.84, "elapsed_time": "0:02:17", "remaining_time": "0:12:10"}
87
+ {"current_steps": 87, "total_steps": 543, "loss": 0.6908, "lr": 9.89427842547679e-06, "epoch": 0.48066298342541436, "percentage": 16.02, "elapsed_time": "0:02:19", "remaining_time": "0:12:08"}
88
+ {"current_steps": 88, "total_steps": 543, "loss": 0.6951, "lr": 9.88759283862006e-06, "epoch": 0.4861878453038674, "percentage": 16.21, "elapsed_time": "0:02:20", "remaining_time": "0:12:05"}
89
+ {"current_steps": 89, "total_steps": 543, "loss": 0.6829, "lr": 9.880704691794608e-06, "epoch": 0.49171270718232046, "percentage": 16.39, "elapsed_time": "0:02:22", "remaining_time": "0:12:05"}
90
+ {"current_steps": 90, "total_steps": 543, "loss": 0.704, "lr": 9.873614270470778e-06, "epoch": 0.4972375690607735, "percentage": 16.57, "elapsed_time": "0:02:23", "remaining_time": "0:12:04"}
91
+ {"current_steps": 91, "total_steps": 543, "loss": 0.7535, "lr": 9.866321868501914e-06, "epoch": 0.5027624309392266, "percentage": 16.76, "elapsed_time": "0:02:25", "remaining_time": "0:12:03"}
92
+ {"current_steps": 92, "total_steps": 543, "loss": 0.6771, "lr": 9.858827788112195e-06, "epoch": 0.5082872928176796, "percentage": 16.94, "elapsed_time": "0:02:27", "remaining_time": "0:12:00"}
93
+ {"current_steps": 93, "total_steps": 543, "loss": 0.6821, "lr": 9.851132339884097e-06, "epoch": 0.5138121546961326, "percentage": 17.13, "elapsed_time": "0:02:28", "remaining_time": "0:11:58"}
94
+ {"current_steps": 94, "total_steps": 543, "loss": 0.6985, "lr": 9.843235842745527e-06, "epoch": 0.5193370165745856, "percentage": 17.31, "elapsed_time": "0:02:30", "remaining_time": "0:11:57"}
95
+ {"current_steps": 95, "total_steps": 543, "loss": 0.6875, "lr": 9.835138623956603e-06, "epoch": 0.5248618784530387, "percentage": 17.5, "elapsed_time": "0:02:32", "remaining_time": "0:11:57"}
96
+ {"current_steps": 96, "total_steps": 543, "loss": 0.6488, "lr": 9.826841019096095e-06, "epoch": 0.5303867403314917, "percentage": 17.68, "elapsed_time": "0:02:33", "remaining_time": "0:11:56"}
97
+ {"current_steps": 97, "total_steps": 543, "loss": 0.6749, "lr": 9.818343372047509e-06, "epoch": 0.5359116022099447, "percentage": 17.86, "elapsed_time": "0:02:35", "remaining_time": "0:11:54"}
98
+ {"current_steps": 98, "total_steps": 543, "loss": 0.6468, "lr": 9.80964603498485e-06, "epoch": 0.5414364640883977, "percentage": 18.05, "elapsed_time": "0:02:36", "remaining_time": "0:11:51"}
99
+ {"current_steps": 99, "total_steps": 543, "loss": 0.7068, "lr": 9.80074936835801e-06, "epoch": 0.5469613259668509, "percentage": 18.23, "elapsed_time": "0:02:38", "remaining_time": "0:11:49"}
100
+ {"current_steps": 100, "total_steps": 543, "loss": 0.7422, "lr": 9.79165374087784e-06, "epoch": 0.5524861878453039, "percentage": 18.42, "elapsed_time": "0:02:39", "remaining_time": "0:11:48"}
101
+ {"current_steps": 101, "total_steps": 543, "loss": 0.6541, "lr": 9.782359529500867e-06, "epoch": 0.5580110497237569, "percentage": 18.6, "elapsed_time": "0:02:41", "remaining_time": "0:11:45"}
102
+ {"current_steps": 102, "total_steps": 543, "loss": 0.6509, "lr": 9.772867119413667e-06, "epoch": 0.56353591160221, "percentage": 18.78, "elapsed_time": "0:02:42", "remaining_time": "0:11:43"}
103
+ {"current_steps": 103, "total_steps": 543, "loss": 0.7281, "lr": 9.763176904016914e-06, "epoch": 0.569060773480663, "percentage": 18.97, "elapsed_time": "0:02:44", "remaining_time": "0:11:41"}
104
+ {"current_steps": 104, "total_steps": 543, "loss": 0.6853, "lr": 9.753289284909058e-06, "epoch": 0.574585635359116, "percentage": 19.15, "elapsed_time": "0:02:45", "remaining_time": "0:11:38"}
105
+ {"current_steps": 105, "total_steps": 543, "loss": 0.7378, "lr": 9.743204671869694e-06, "epoch": 0.580110497237569, "percentage": 19.34, "elapsed_time": "0:02:46", "remaining_time": "0:11:36"}
106
+ {"current_steps": 106, "total_steps": 543, "loss": 0.6548, "lr": 9.73292348284258e-06, "epoch": 0.585635359116022, "percentage": 19.52, "elapsed_time": "0:02:48", "remaining_time": "0:11:34"}
107
+ {"current_steps": 107, "total_steps": 543, "loss": 0.7006, "lr": 9.722446143918307e-06, "epoch": 0.5911602209944752, "percentage": 19.71, "elapsed_time": "0:02:49", "remaining_time": "0:11:32"}
108
+ {"current_steps": 108, "total_steps": 543, "loss": 0.6197, "lr": 9.711773089316645e-06, "epoch": 0.5966850828729282, "percentage": 19.89, "elapsed_time": "0:02:51", "remaining_time": "0:11:29"}
109
+ {"current_steps": 109, "total_steps": 543, "loss": 0.7452, "lr": 9.70090476136855e-06, "epoch": 0.6022099447513812, "percentage": 20.07, "elapsed_time": "0:02:52", "remaining_time": "0:11:26"}
110
+ {"current_steps": 110, "total_steps": 543, "loss": 0.687, "lr": 9.689841610497828e-06, "epoch": 0.6077348066298343, "percentage": 20.26, "elapsed_time": "0:02:53", "remaining_time": "0:11:24"}
111
+ {"current_steps": 111, "total_steps": 543, "loss": 0.7223, "lr": 9.678584095202468e-06, "epoch": 0.6132596685082873, "percentage": 20.44, "elapsed_time": "0:02:55", "remaining_time": "0:11:22"}
112
+ {"current_steps": 112, "total_steps": 543, "loss": 0.6301, "lr": 9.667132682035646e-06, "epoch": 0.6187845303867403, "percentage": 20.63, "elapsed_time": "0:02:56", "remaining_time": "0:11:20"}
113
+ {"current_steps": 113, "total_steps": 543, "loss": 0.6117, "lr": 9.655487845586378e-06, "epoch": 0.6243093922651933, "percentage": 20.81, "elapsed_time": "0:02:58", "remaining_time": "0:11:18"}
114
+ {"current_steps": 114, "total_steps": 543, "loss": 0.5902, "lr": 9.643650068459863e-06, "epoch": 0.6298342541436464, "percentage": 20.99, "elapsed_time": "0:03:01", "remaining_time": "0:11:22"}
115
+ {"current_steps": 115, "total_steps": 543, "loss": 0.6144, "lr": 9.631619841257477e-06, "epoch": 0.6353591160220995, "percentage": 21.18, "elapsed_time": "0:03:02", "remaining_time": "0:11:19"}
116
+ {"current_steps": 116, "total_steps": 543, "loss": 0.6444, "lr": 9.619397662556434e-06, "epoch": 0.6408839779005525, "percentage": 21.36, "elapsed_time": "0:03:04", "remaining_time": "0:11:19"}
117
+ {"current_steps": 117, "total_steps": 543, "loss": 0.6478, "lr": 9.606984038889142e-06, "epoch": 0.6464088397790055, "percentage": 21.55, "elapsed_time": "0:03:06", "remaining_time": "0:11:17"}
118
+ {"current_steps": 118, "total_steps": 543, "loss": 0.6368, "lr": 9.594379484722185e-06, "epoch": 0.6519337016574586, "percentage": 21.73, "elapsed_time": "0:03:07", "remaining_time": "0:11:15"}
119
+ {"current_steps": 119, "total_steps": 543, "loss": 0.6971, "lr": 9.581584522435025e-06, "epoch": 0.6574585635359116, "percentage": 21.92, "elapsed_time": "0:03:09", "remaining_time": "0:11:14"}
120
+ {"current_steps": 120, "total_steps": 543, "loss": 0.6323, "lr": 9.568599682298337e-06, "epoch": 0.6629834254143646, "percentage": 22.1, "elapsed_time": "0:03:10", "remaining_time": "0:11:12"}
121
+ {"current_steps": 121, "total_steps": 543, "loss": 0.7068, "lr": 9.555425502452038e-06, "epoch": 0.6685082872928176, "percentage": 22.28, "elapsed_time": "0:03:16", "remaining_time": "0:11:26"}
122
+ {"current_steps": 122, "total_steps": 543, "loss": 0.6758, "lr": 9.542062528882989e-06, "epoch": 0.6740331491712708, "percentage": 22.47, "elapsed_time": "0:03:18", "remaining_time": "0:11:24"}
123
+ {"current_steps": 123, "total_steps": 543, "loss": 0.6844, "lr": 9.528511315402358e-06, "epoch": 0.6795580110497238, "percentage": 22.65, "elapsed_time": "0:03:20", "remaining_time": "0:11:25"}
124
+ {"current_steps": 124, "total_steps": 543, "loss": 0.7468, "lr": 9.514772423622675e-06, "epoch": 0.6850828729281768, "percentage": 22.84, "elapsed_time": "0:03:22", "remaining_time": "0:11:23"}
125
+ {"current_steps": 125, "total_steps": 543, "loss": 0.6884, "lr": 9.500846422934557e-06, "epoch": 0.6906077348066298, "percentage": 23.02, "elapsed_time": "0:03:24", "remaining_time": "0:11:22"}
126
+ {"current_steps": 126, "total_steps": 543, "loss": 0.6807, "lr": 9.4867338904831e-06, "epoch": 0.6961325966850829, "percentage": 23.2, "elapsed_time": "0:03:25", "remaining_time": "0:11:20"}
127
+ {"current_steps": 127, "total_steps": 543, "loss": 0.631, "lr": 9.472435411143979e-06, "epoch": 0.7016574585635359, "percentage": 23.39, "elapsed_time": "0:03:27", "remaining_time": "0:11:18"}
128
+ {"current_steps": 128, "total_steps": 543, "loss": 0.6678, "lr": 9.457951577499187e-06, "epoch": 0.7071823204419889, "percentage": 23.57, "elapsed_time": "0:03:28", "remaining_time": "0:11:16"}
129
+ {"current_steps": 129, "total_steps": 543, "loss": 0.6413, "lr": 9.443282989812494e-06, "epoch": 0.712707182320442, "percentage": 23.76, "elapsed_time": "0:03:30", "remaining_time": "0:11:15"}
130
+ {"current_steps": 130, "total_steps": 543, "loss": 0.6523, "lr": 9.428430256004558e-06, "epoch": 0.7182320441988951, "percentage": 23.94, "elapsed_time": "0:03:31", "remaining_time": "0:11:12"}
131
+ {"current_steps": 131, "total_steps": 543, "loss": 0.6826, "lr": 9.413393991627737e-06, "epoch": 0.7237569060773481, "percentage": 24.13, "elapsed_time": "0:03:33", "remaining_time": "0:11:11"}
132
+ {"current_steps": 132, "total_steps": 543, "loss": 0.6405, "lr": 9.398174819840577e-06, "epoch": 0.7292817679558011, "percentage": 24.31, "elapsed_time": "0:03:35", "remaining_time": "0:11:09"}
133
+ {"current_steps": 133, "total_steps": 543, "loss": 0.6689, "lr": 9.382773371381986e-06, "epoch": 0.7348066298342542, "percentage": 24.49, "elapsed_time": "0:03:36", "remaining_time": "0:11:06"}
134
+ {"current_steps": 134, "total_steps": 543, "loss": 0.7109, "lr": 9.367190284545087e-06, "epoch": 0.7403314917127072, "percentage": 24.68, "elapsed_time": "0:03:37", "remaining_time": "0:11:04"}
135
+ {"current_steps": 135, "total_steps": 543, "loss": 0.66, "lr": 9.351426205150778e-06, "epoch": 0.7458563535911602, "percentage": 24.86, "elapsed_time": "0:03:39", "remaining_time": "0:11:02"}
136
+ {"current_steps": 136, "total_steps": 543, "loss": 0.7216, "lr": 9.335481786520955e-06, "epoch": 0.7513812154696132, "percentage": 25.05, "elapsed_time": "0:03:40", "remaining_time": "0:11:00"}
137
+ {"current_steps": 137, "total_steps": 543, "loss": 0.6562, "lr": 9.319357689451444e-06, "epoch": 0.7569060773480663, "percentage": 25.23, "elapsed_time": "0:03:42", "remaining_time": "0:10:58"}
138
+ {"current_steps": 138, "total_steps": 543, "loss": 0.6882, "lr": 9.30305458218461e-06, "epoch": 0.7624309392265194, "percentage": 25.41, "elapsed_time": "0:03:43", "remaining_time": "0:10:56"}
139
+ {"current_steps": 139, "total_steps": 543, "loss": 0.6541, "lr": 9.286573140381663e-06, "epoch": 0.7679558011049724, "percentage": 25.6, "elapsed_time": "0:03:45", "remaining_time": "0:10:54"}
140
+ {"current_steps": 140, "total_steps": 543, "loss": 0.6289, "lr": 9.26991404709466e-06, "epoch": 0.7734806629834254, "percentage": 25.78, "elapsed_time": "0:03:46", "remaining_time": "0:10:52"}
141
+ {"current_steps": 141, "total_steps": 543, "loss": 0.73, "lr": 9.253077992738193e-06, "epoch": 0.7790055248618785, "percentage": 25.97, "elapsed_time": "0:03:48", "remaining_time": "0:10:50"}
142
+ {"current_steps": 142, "total_steps": 543, "loss": 0.693, "lr": 9.236065675060775e-06, "epoch": 0.7845303867403315, "percentage": 26.15, "elapsed_time": "0:03:49", "remaining_time": "0:10:49"}
143
+ {"current_steps": 143, "total_steps": 543, "loss": 0.7252, "lr": 9.218877799115929e-06, "epoch": 0.7900552486187845, "percentage": 26.34, "elapsed_time": "0:03:51", "remaining_time": "0:10:46"}
144
+ {"current_steps": 144, "total_steps": 543, "loss": 0.703, "lr": 9.201515077232958e-06, "epoch": 0.7955801104972375, "percentage": 26.52, "elapsed_time": "0:03:52", "remaining_time": "0:10:44"}
145
+ {"current_steps": 145, "total_steps": 543, "loss": 0.6511, "lr": 9.183978228987436e-06, "epoch": 0.8011049723756906, "percentage": 26.7, "elapsed_time": "0:03:54", "remaining_time": "0:10:44"}
146
+ {"current_steps": 146, "total_steps": 543, "loss": 0.6477, "lr": 9.166267981171369e-06, "epoch": 0.8066298342541437, "percentage": 26.89, "elapsed_time": "0:03:56", "remaining_time": "0:10:42"}
147
+ {"current_steps": 147, "total_steps": 543, "loss": 0.6407, "lr": 9.148385067763094e-06, "epoch": 0.8121546961325967, "percentage": 27.07, "elapsed_time": "0:03:57", "remaining_time": "0:10:40"}
148
+ {"current_steps": 148, "total_steps": 543, "loss": 0.6096, "lr": 9.130330229896846e-06, "epoch": 0.8176795580110497, "percentage": 27.26, "elapsed_time": "0:03:59", "remaining_time": "0:10:38"}
149
+ {"current_steps": 149, "total_steps": 543, "loss": 0.658, "lr": 9.112104215832047e-06, "epoch": 0.8232044198895028, "percentage": 27.44, "elapsed_time": "0:04:00", "remaining_time": "0:10:36"}
150
+ {"current_steps": 150, "total_steps": 543, "loss": 0.6985, "lr": 9.093707780922293e-06, "epoch": 0.8287292817679558, "percentage": 27.62, "elapsed_time": "0:04:02", "remaining_time": "0:10:34"}
151
+ {"current_steps": 151, "total_steps": 543, "loss": 0.6801, "lr": 9.075141687584056e-06, "epoch": 0.8342541436464088, "percentage": 27.81, "elapsed_time": "0:04:03", "remaining_time": "0:10:32"}
152
+ {"current_steps": 152, "total_steps": 543, "loss": 0.6442, "lr": 9.056406705265084e-06, "epoch": 0.8397790055248618, "percentage": 27.99, "elapsed_time": "0:04:05", "remaining_time": "0:10:30"}
153
+ {"current_steps": 153, "total_steps": 543, "loss": 0.6446, "lr": 9.037503610412502e-06, "epoch": 0.8453038674033149, "percentage": 28.18, "elapsed_time": "0:04:06", "remaining_time": "0:10:28"}
154
+ {"current_steps": 154, "total_steps": 543, "loss": 0.7106, "lr": 9.018433186440648e-06, "epoch": 0.850828729281768, "percentage": 28.36, "elapsed_time": "0:04:08", "remaining_time": "0:10:26"}
155
+ {"current_steps": 155, "total_steps": 543, "loss": 0.7418, "lr": 8.999196223698599e-06, "epoch": 0.856353591160221, "percentage": 28.55, "elapsed_time": "0:04:12", "remaining_time": "0:10:33"}
156
+ {"current_steps": 156, "total_steps": 543, "loss": 0.7064, "lr": 8.979793519437413e-06, "epoch": 0.861878453038674, "percentage": 28.73, "elapsed_time": "0:04:14", "remaining_time": "0:10:30"}
157
+ {"current_steps": 157, "total_steps": 543, "loss": 0.7153, "lr": 8.960225877777095e-06, "epoch": 0.8674033149171271, "percentage": 28.91, "elapsed_time": "0:04:15", "remaining_time": "0:10:28"}
158
+ {"current_steps": 158, "total_steps": 543, "loss": 0.6121, "lr": 8.940494109673266e-06, "epoch": 0.8729281767955801, "percentage": 29.1, "elapsed_time": "0:04:17", "remaining_time": "0:10:27"}
159
+ {"current_steps": 159, "total_steps": 543, "loss": 0.6781, "lr": 8.920599032883553e-06, "epoch": 0.8784530386740331, "percentage": 29.28, "elapsed_time": "0:04:19", "remaining_time": "0:10:25"}
160
+ {"current_steps": 160, "total_steps": 543, "loss": 0.6979, "lr": 8.900541471933703e-06, "epoch": 0.8839779005524862, "percentage": 29.47, "elapsed_time": "0:04:20", "remaining_time": "0:10:23"}
161
+ {"current_steps": 161, "total_steps": 543, "loss": 0.6557, "lr": 8.880322258083408e-06, "epoch": 0.8895027624309392, "percentage": 29.65, "elapsed_time": "0:04:22", "remaining_time": "0:10:21"}
162
+ {"current_steps": 162, "total_steps": 543, "loss": 0.662, "lr": 8.859942229291856e-06, "epoch": 0.8950276243093923, "percentage": 29.83, "elapsed_time": "0:04:23", "remaining_time": "0:10:20"}
163
+ {"current_steps": 163, "total_steps": 543, "loss": 0.662, "lr": 8.839402230183e-06, "epoch": 0.9005524861878453, "percentage": 30.02, "elapsed_time": "0:04:24", "remaining_time": "0:10:17"}
164
+ {"current_steps": 164, "total_steps": 543, "loss": 0.6935, "lr": 8.818703112010562e-06, "epoch": 0.9060773480662984, "percentage": 30.2, "elapsed_time": "0:04:26", "remaining_time": "0:10:16"}
165
+ {"current_steps": 165, "total_steps": 543, "loss": 0.7031, "lr": 8.797845732622742e-06, "epoch": 0.9116022099447514, "percentage": 30.39, "elapsed_time": "0:04:28", "remaining_time": "0:10:14"}
166
+ {"current_steps": 166, "total_steps": 543, "loss": 0.708, "lr": 8.776830956426674e-06, "epoch": 0.9171270718232044, "percentage": 30.57, "elapsed_time": "0:04:29", "remaining_time": "0:10:12"}
167
+ {"current_steps": 167, "total_steps": 543, "loss": 0.7169, "lr": 8.755659654352599e-06, "epoch": 0.9226519337016574, "percentage": 30.76, "elapsed_time": "0:04:31", "remaining_time": "0:10:11"}
168
+ {"current_steps": 168, "total_steps": 543, "loss": 0.6991, "lr": 8.734332703817771e-06, "epoch": 0.9281767955801105, "percentage": 30.94, "elapsed_time": "0:04:32", "remaining_time": "0:10:09"}
169
+ {"current_steps": 169, "total_steps": 543, "loss": 0.7032, "lr": 8.712850988690094e-06, "epoch": 0.9337016574585635, "percentage": 31.12, "elapsed_time": "0:04:34", "remaining_time": "0:10:06"}
170
+ {"current_steps": 170, "total_steps": 543, "loss": 0.6439, "lr": 8.691215399251489e-06, "epoch": 0.9392265193370166, "percentage": 31.31, "elapsed_time": "0:04:35", "remaining_time": "0:10:04"}
171
+ {"current_steps": 171, "total_steps": 543, "loss": 0.6193, "lr": 8.669426832160997e-06, "epoch": 0.9447513812154696, "percentage": 31.49, "elapsed_time": "0:04:37", "remaining_time": "0:10:02"}
172
+ {"current_steps": 172, "total_steps": 543, "loss": 0.6929, "lr": 8.647486190417624e-06, "epoch": 0.9502762430939227, "percentage": 31.68, "elapsed_time": "0:04:38", "remaining_time": "0:10:00"}
173
+ {"current_steps": 173, "total_steps": 543, "loss": 0.6779, "lr": 8.625394383322914e-06, "epoch": 0.9558011049723757, "percentage": 31.86, "elapsed_time": "0:04:40", "remaining_time": "0:09:58"}
174
+ {"current_steps": 174, "total_steps": 543, "loss": 0.6412, "lr": 8.603152326443262e-06, "epoch": 0.9613259668508287, "percentage": 32.04, "elapsed_time": "0:04:41", "remaining_time": "0:09:56"}
175
+ {"current_steps": 175, "total_steps": 543, "loss": 0.7249, "lr": 8.580760941571968e-06, "epoch": 0.9668508287292817, "percentage": 32.23, "elapsed_time": "0:04:42", "remaining_time": "0:09:54"}
176
+ {"current_steps": 176, "total_steps": 543, "loss": 0.6725, "lr": 8.55822115669104e-06, "epoch": 0.9723756906077348, "percentage": 32.41, "elapsed_time": "0:04:44", "remaining_time": "0:09:53"}
177
+ {"current_steps": 177, "total_steps": 543, "loss": 0.6778, "lr": 8.535533905932739e-06, "epoch": 0.9779005524861878, "percentage": 32.6, "elapsed_time": "0:04:46", "remaining_time": "0:09:51"}
178
+ {"current_steps": 178, "total_steps": 543, "loss": 0.646, "lr": 8.512700129540847e-06, "epoch": 0.9834254143646409, "percentage": 32.78, "elapsed_time": "0:04:47", "remaining_time": "0:09:49"}
179
+ {"current_steps": 179, "total_steps": 543, "loss": 0.6742, "lr": 8.489720773831717e-06, "epoch": 0.988950276243094, "percentage": 32.97, "elapsed_time": "0:04:49", "remaining_time": "0:09:48"}
180
+ {"current_steps": 180, "total_steps": 543, "loss": 0.6745, "lr": 8.466596791155055e-06, "epoch": 0.994475138121547, "percentage": 33.15, "elapsed_time": "0:04:50", "remaining_time": "0:09:46"}
181
+ {"current_steps": 181, "total_steps": 543, "loss": 0.635, "lr": 8.443329139854434e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:04:52", "remaining_time": "0:09:44"}
182
+ {"current_steps": 182, "total_steps": 543, "loss": 0.6638, "lr": 8.419918784227592e-06, "epoch": 1.0055248618784531, "percentage": 33.52, "elapsed_time": "0:06:01", "remaining_time": "0:11:57"}
183
+ {"current_steps": 183, "total_steps": 543, "loss": 0.6176, "lr": 8.396366694486466e-06, "epoch": 1.011049723756906, "percentage": 33.7, "elapsed_time": "0:06:03", "remaining_time": "0:11:54"}
184
+ {"current_steps": 184, "total_steps": 543, "loss": 0.5742, "lr": 8.372673846716977e-06, "epoch": 1.0165745856353592, "percentage": 33.89, "elapsed_time": "0:06:04", "remaining_time": "0:11:51"}
185
+ {"current_steps": 185, "total_steps": 543, "loss": 0.5965, "lr": 8.348841222838579e-06, "epoch": 1.022099447513812, "percentage": 34.07, "elapsed_time": "0:06:06", "remaining_time": "0:11:48"}
186
+ {"current_steps": 186, "total_steps": 543, "loss": 0.6031, "lr": 8.324869810563573e-06, "epoch": 1.0276243093922652, "percentage": 34.25, "elapsed_time": "0:06:07", "remaining_time": "0:11:45"}
187
+ {"current_steps": 187, "total_steps": 543, "loss": 0.6378, "lr": 8.30076060335616e-06, "epoch": 1.0331491712707181, "percentage": 34.44, "elapsed_time": "0:06:09", "remaining_time": "0:11:43"}
188
+ {"current_steps": 188, "total_steps": 543, "loss": 0.5828, "lr": 8.276514600391272e-06, "epoch": 1.0386740331491713, "percentage": 34.62, "elapsed_time": "0:06:10", "remaining_time": "0:11:40"}
189
+ {"current_steps": 189, "total_steps": 543, "loss": 0.5991, "lr": 8.25213280651317e-06, "epoch": 1.0441988950276242, "percentage": 34.81, "elapsed_time": "0:06:12", "remaining_time": "0:11:37"}
190
+ {"current_steps": 190, "total_steps": 543, "loss": 0.5877, "lr": 8.227616232193794e-06, "epoch": 1.0497237569060773, "percentage": 34.99, "elapsed_time": "0:06:13", "remaining_time": "0:11:34"}
191
+ {"current_steps": 191, "total_steps": 543, "loss": 0.6476, "lr": 8.202965893490877e-06, "epoch": 1.0552486187845305, "percentage": 35.17, "elapsed_time": "0:06:15", "remaining_time": "0:11:32"}
192
+ {"current_steps": 192, "total_steps": 543, "loss": 0.5147, "lr": 8.178182812005853e-06, "epoch": 1.0607734806629834, "percentage": 35.36, "elapsed_time": "0:06:17", "remaining_time": "0:11:29"}
193
+ {"current_steps": 193, "total_steps": 543, "loss": 0.6128, "lr": 8.153268014841507e-06, "epoch": 1.0662983425414365, "percentage": 35.54, "elapsed_time": "0:06:18", "remaining_time": "0:11:26"}
194
+ {"current_steps": 194, "total_steps": 543, "loss": 0.5743, "lr": 8.128222534559406e-06, "epoch": 1.0718232044198894, "percentage": 35.73, "elapsed_time": "0:06:20", "remaining_time": "0:11:24"}
195
+ {"current_steps": 195, "total_steps": 543, "loss": 0.6736, "lr": 8.103047409137114e-06, "epoch": 1.0773480662983426, "percentage": 35.91, "elapsed_time": "0:06:21", "remaining_time": "0:11:21"}
196
+ {"current_steps": 196, "total_steps": 543, "loss": 0.6658, "lr": 8.07774368192517e-06, "epoch": 1.0828729281767955, "percentage": 36.1, "elapsed_time": "0:06:23", "remaining_time": "0:11:18"}
197
+ {"current_steps": 197, "total_steps": 543, "loss": 0.5765, "lr": 8.052312401603848e-06, "epoch": 1.0883977900552486, "percentage": 36.28, "elapsed_time": "0:06:24", "remaining_time": "0:11:15"}
198
+ {"current_steps": 198, "total_steps": 543, "loss": 0.5903, "lr": 8.026754622139691e-06, "epoch": 1.0939226519337018, "percentage": 36.46, "elapsed_time": "0:06:26", "remaining_time": "0:11:12"}
199
+ {"current_steps": 199, "total_steps": 543, "loss": 0.6027, "lr": 8.001071402741843e-06, "epoch": 1.0994475138121547, "percentage": 36.65, "elapsed_time": "0:06:27", "remaining_time": "0:11:09"}
200
+ {"current_steps": 200, "total_steps": 543, "loss": 0.6428, "lr": 7.975263807818136e-06, "epoch": 1.1049723756906078, "percentage": 36.83, "elapsed_time": "0:06:28", "remaining_time": "0:11:07"}
201
+ {"current_steps": 201, "total_steps": 543, "loss": 0.6502, "lr": 7.949332906930995e-06, "epoch": 1.1104972375690607, "percentage": 37.02, "elapsed_time": "0:06:30", "remaining_time": "0:11:04"}
202
+ {"current_steps": 202, "total_steps": 543, "loss": 0.5865, "lr": 7.923279774753092e-06, "epoch": 1.1160220994475138, "percentage": 37.2, "elapsed_time": "0:06:31", "remaining_time": "0:11:01"}
203
+ {"current_steps": 203, "total_steps": 543, "loss": 0.5737, "lr": 7.897105491022819e-06, "epoch": 1.1215469613259668, "percentage": 37.38, "elapsed_time": "0:06:33", "remaining_time": "0:10:58"}
204
+ {"current_steps": 204, "total_steps": 543, "loss": 0.5916, "lr": 7.870811140499543e-06, "epoch": 1.12707182320442, "percentage": 37.57, "elapsed_time": "0:06:34", "remaining_time": "0:10:55"}
205
+ {"current_steps": 205, "total_steps": 543, "loss": 0.5629, "lr": 7.844397812918637e-06, "epoch": 1.132596685082873, "percentage": 37.75, "elapsed_time": "0:06:35", "remaining_time": "0:10:52"}
206
+ {"current_steps": 206, "total_steps": 543, "loss": 0.6174, "lr": 7.817866602946326e-06, "epoch": 1.138121546961326, "percentage": 37.94, "elapsed_time": "0:06:37", "remaining_time": "0:10:49"}
207
+ {"current_steps": 207, "total_steps": 543, "loss": 0.5891, "lr": 7.791218610134324e-06, "epoch": 1.143646408839779, "percentage": 38.12, "elapsed_time": "0:06:38", "remaining_time": "0:10:47"}
208
+ {"current_steps": 208, "total_steps": 543, "loss": 0.5973, "lr": 7.764454938874252e-06, "epoch": 1.149171270718232, "percentage": 38.31, "elapsed_time": "0:06:44", "remaining_time": "0:10:52"}
209
+ {"current_steps": 209, "total_steps": 543, "loss": 0.6368, "lr": 7.737576698351878e-06, "epoch": 1.1546961325966851, "percentage": 38.49, "elapsed_time": "0:06:46", "remaining_time": "0:10:49"}
210
+ {"current_steps": 210, "total_steps": 543, "loss": 0.6458, "lr": 7.710585002501145e-06, "epoch": 1.160220994475138, "percentage": 38.67, "elapsed_time": "0:06:47", "remaining_time": "0:10:46"}
211
+ {"current_steps": 211, "total_steps": 543, "loss": 0.5674, "lr": 7.683480969958005e-06, "epoch": 1.1657458563535912, "percentage": 38.86, "elapsed_time": "0:06:49", "remaining_time": "0:10:43"}
212
+ {"current_steps": 212, "total_steps": 543, "loss": 0.6039, "lr": 7.656265724014054e-06, "epoch": 1.1712707182320443, "percentage": 39.04, "elapsed_time": "0:06:50", "remaining_time": "0:10:40"}
213
+ {"current_steps": 213, "total_steps": 543, "loss": 0.6395, "lr": 7.628940392569995e-06, "epoch": 1.1767955801104972, "percentage": 39.23, "elapsed_time": "0:06:52", "remaining_time": "0:10:38"}
214
+ {"current_steps": 214, "total_steps": 543, "loss": 0.5882, "lr": 7.601506108088874e-06, "epoch": 1.1823204419889504, "percentage": 39.41, "elapsed_time": "0:06:53", "remaining_time": "0:10:36"}
215
+ {"current_steps": 215, "total_steps": 543, "loss": 0.6184, "lr": 7.5739640075491546e-06, "epoch": 1.1878453038674033, "percentage": 39.59, "elapsed_time": "0:06:55", "remaining_time": "0:10:33"}
216
+ {"current_steps": 216, "total_steps": 543, "loss": 0.6138, "lr": 7.546315232397601e-06, "epoch": 1.1933701657458564, "percentage": 39.78, "elapsed_time": "0:06:57", "remaining_time": "0:10:31"}
217
+ {"current_steps": 217, "total_steps": 543, "loss": 0.6252, "lr": 7.518560928501969e-06, "epoch": 1.1988950276243093, "percentage": 39.96, "elapsed_time": "0:06:58", "remaining_time": "0:10:28"}
218
+ {"current_steps": 218, "total_steps": 543, "loss": 0.6002, "lr": 7.4907022461035125e-06, "epoch": 1.2044198895027625, "percentage": 40.15, "elapsed_time": "0:06:59", "remaining_time": "0:10:26"}
219
+ {"current_steps": 219, "total_steps": 543, "loss": 0.5868, "lr": 7.462740339769323e-06, "epoch": 1.2099447513812154, "percentage": 40.33, "elapsed_time": "0:07:01", "remaining_time": "0:10:24"}
220
+ {"current_steps": 220, "total_steps": 543, "loss": 0.655, "lr": 7.434676368344469e-06, "epoch": 1.2154696132596685, "percentage": 40.52, "elapsed_time": "0:07:03", "remaining_time": "0:10:22"}
221
+ {"current_steps": 221, "total_steps": 543, "loss": 0.5975, "lr": 7.406511494903982e-06, "epoch": 1.2209944751381214, "percentage": 40.7, "elapsed_time": "0:07:05", "remaining_time": "0:10:20"}
222
+ {"current_steps": 222, "total_steps": 543, "loss": 0.6729, "lr": 7.378246886704638e-06, "epoch": 1.2265193370165746, "percentage": 40.88, "elapsed_time": "0:07:07", "remaining_time": "0:10:17"}
223
+ {"current_steps": 223, "total_steps": 543, "loss": 0.6123, "lr": 7.349883715136601e-06, "epoch": 1.2320441988950277, "percentage": 41.07, "elapsed_time": "0:07:08", "remaining_time": "0:10:15"}
224
+ {"current_steps": 224, "total_steps": 543, "loss": 0.5287, "lr": 7.321423155674858e-06, "epoch": 1.2375690607734806, "percentage": 41.25, "elapsed_time": "0:07:10", "remaining_time": "0:10:12"}
225
+ {"current_steps": 225, "total_steps": 543, "loss": 0.5927, "lr": 7.292866387830515e-06, "epoch": 1.2430939226519337, "percentage": 41.44, "elapsed_time": "0:07:11", "remaining_time": "0:10:10"}
226
+ {"current_steps": 226, "total_steps": 543, "loss": 0.6321, "lr": 7.264214595101913e-06, "epoch": 1.2486187845303867, "percentage": 41.62, "elapsed_time": "0:07:13", "remaining_time": "0:10:07"}
227
+ {"current_steps": 227, "total_steps": 543, "loss": 0.5794, "lr": 7.235468964925571e-06, "epoch": 1.2541436464088398, "percentage": 41.8, "elapsed_time": "0:07:14", "remaining_time": "0:10:04"}
228
+ {"current_steps": 228, "total_steps": 543, "loss": 0.6563, "lr": 7.206630688626981e-06, "epoch": 1.2596685082872927, "percentage": 41.99, "elapsed_time": "0:07:15", "remaining_time": "0:10:01"}
229
+ {"current_steps": 229, "total_steps": 543, "loss": 0.6075, "lr": 7.177700961371239e-06, "epoch": 1.2651933701657458, "percentage": 42.17, "elapsed_time": "0:07:17", "remaining_time": "0:09:59"}
230
+ {"current_steps": 230, "total_steps": 543, "loss": 0.6422, "lr": 7.148680982113502e-06, "epoch": 1.270718232044199, "percentage": 42.36, "elapsed_time": "0:07:18", "remaining_time": "0:09:56"}
231
+ {"current_steps": 231, "total_steps": 543, "loss": 0.645, "lr": 7.119571953549305e-06, "epoch": 1.276243093922652, "percentage": 42.54, "elapsed_time": "0:07:20", "remaining_time": "0:09:54"}
232
+ {"current_steps": 232, "total_steps": 543, "loss": 0.6046, "lr": 7.0903750820647175e-06, "epoch": 1.281767955801105, "percentage": 42.73, "elapsed_time": "0:07:21", "remaining_time": "0:09:52"}
233
+ {"current_steps": 233, "total_steps": 543, "loss": 0.5663, "lr": 7.061091577686349e-06, "epoch": 1.287292817679558, "percentage": 42.91, "elapsed_time": "0:07:23", "remaining_time": "0:09:49"}
234
+ {"current_steps": 234, "total_steps": 543, "loss": 0.5901, "lr": 7.031722654031192e-06, "epoch": 1.292817679558011, "percentage": 43.09, "elapsed_time": "0:07:24", "remaining_time": "0:09:47"}
235
+ {"current_steps": 235, "total_steps": 543, "loss": 0.6084, "lr": 7.002269528256334e-06, "epoch": 1.298342541436464, "percentage": 43.28, "elapsed_time": "0:07:26", "remaining_time": "0:09:45"}
236
+ {"current_steps": 236, "total_steps": 543, "loss": 0.5938, "lr": 6.972733421008505e-06, "epoch": 1.3038674033149171, "percentage": 43.46, "elapsed_time": "0:07:28", "remaining_time": "0:09:43"}
237
+ {"current_steps": 237, "total_steps": 543, "loss": 0.606, "lr": 6.943115556373503e-06, "epoch": 1.3093922651933703, "percentage": 43.65, "elapsed_time": "0:07:30", "remaining_time": "0:09:41"}
238
+ {"current_steps": 238, "total_steps": 543, "loss": 0.6491, "lr": 6.913417161825449e-06, "epoch": 1.3149171270718232, "percentage": 43.83, "elapsed_time": "0:07:31", "remaining_time": "0:09:38"}
239
+ {"current_steps": 239, "total_steps": 543, "loss": 0.6072, "lr": 6.883639468175926e-06, "epoch": 1.3204419889502763, "percentage": 44.01, "elapsed_time": "0:07:32", "remaining_time": "0:09:36"}
240
+ {"current_steps": 240, "total_steps": 543, "loss": 0.6018, "lr": 6.853783709522963e-06, "epoch": 1.3259668508287292, "percentage": 44.2, "elapsed_time": "0:07:34", "remaining_time": "0:09:33"}
241
+ {"current_steps": 241, "total_steps": 543, "loss": 0.6434, "lr": 6.823851123199894e-06, "epoch": 1.3314917127071824, "percentage": 44.38, "elapsed_time": "0:07:35", "remaining_time": "0:09:31"}
242
+ {"current_steps": 242, "total_steps": 543, "loss": 0.6225, "lr": 6.793842949724074e-06, "epoch": 1.3370165745856353, "percentage": 44.57, "elapsed_time": "0:07:37", "remaining_time": "0:09:28"}
243
+ {"current_steps": 243, "total_steps": 543, "loss": 0.6131, "lr": 6.763760432745475e-06, "epoch": 1.3425414364640884, "percentage": 44.75, "elapsed_time": "0:07:38", "remaining_time": "0:09:26"}
244
+ {"current_steps": 244, "total_steps": 543, "loss": 0.6366, "lr": 6.733604818995133e-06, "epoch": 1.3480662983425415, "percentage": 44.94, "elapsed_time": "0:07:40", "remaining_time": "0:09:23"}
245
+ {"current_steps": 245, "total_steps": 543, "loss": 0.595, "lr": 6.703377358233489e-06, "epoch": 1.3535911602209945, "percentage": 45.12, "elapsed_time": "0:07:41", "remaining_time": "0:09:21"}
246
+ {"current_steps": 246, "total_steps": 543, "loss": 0.5941, "lr": 6.673079303198591e-06, "epoch": 1.3591160220994476, "percentage": 45.3, "elapsed_time": "0:07:42", "remaining_time": "0:09:18"}
247
+ {"current_steps": 247, "total_steps": 543, "loss": 0.5967, "lr": 6.6427119095541745e-06, "epoch": 1.3646408839779005, "percentage": 45.49, "elapsed_time": "0:07:44", "remaining_time": "0:09:16"}
248
+ {"current_steps": 248, "total_steps": 543, "loss": 0.5917, "lr": 6.612276435837622e-06, "epoch": 1.3701657458563536, "percentage": 45.67, "elapsed_time": "0:07:45", "remaining_time": "0:09:14"}
249
+ {"current_steps": 249, "total_steps": 543, "loss": 0.6342, "lr": 6.58177414340781e-06, "epoch": 1.3756906077348066, "percentage": 45.86, "elapsed_time": "0:07:48", "remaining_time": "0:09:12"}
250
+ {"current_steps": 250, "total_steps": 543, "loss": 0.5791, "lr": 6.551206296392827e-06, "epoch": 1.3812154696132597, "percentage": 46.04, "elapsed_time": "0:07:49", "remaining_time": "0:09:10"}
251
+ {"current_steps": 251, "total_steps": 543, "loss": 0.6555, "lr": 6.520574161637591e-06, "epoch": 1.3867403314917128, "percentage": 46.22, "elapsed_time": "0:07:51", "remaining_time": "0:09:08"}
252
+ {"current_steps": 252, "total_steps": 543, "loss": 0.6002, "lr": 6.4898790086513366e-06, "epoch": 1.3922651933701657, "percentage": 46.41, "elapsed_time": "0:07:52", "remaining_time": "0:09:05"}
253
+ {"current_steps": 253, "total_steps": 543, "loss": 0.5968, "lr": 6.459122109555011e-06, "epoch": 1.3977900552486187, "percentage": 46.59, "elapsed_time": "0:07:54", "remaining_time": "0:09:03"}
254
+ {"current_steps": 254, "total_steps": 543, "loss": 0.5915, "lr": 6.42830473902855e-06, "epoch": 1.4033149171270718, "percentage": 46.78, "elapsed_time": "0:07:55", "remaining_time": "0:09:00"}
255
+ {"current_steps": 255, "total_steps": 543, "loss": 0.6129, "lr": 6.397428174258048e-06, "epoch": 1.408839779005525, "percentage": 46.96, "elapsed_time": "0:07:57", "remaining_time": "0:08:58"}
256
+ {"current_steps": 256, "total_steps": 543, "loss": 0.618, "lr": 6.3664936948828296e-06, "epoch": 1.4143646408839778, "percentage": 47.15, "elapsed_time": "0:08:01", "remaining_time": "0:09:00"}
257
+ {"current_steps": 257, "total_steps": 543, "loss": 0.58, "lr": 6.335502582942409e-06, "epoch": 1.419889502762431, "percentage": 47.33, "elapsed_time": "0:08:03", "remaining_time": "0:08:57"}
258
+ {"current_steps": 258, "total_steps": 543, "loss": 0.6284, "lr": 6.304456122823377e-06, "epoch": 1.4254143646408841, "percentage": 47.51, "elapsed_time": "0:08:06", "remaining_time": "0:08:56"}
259
+ {"current_steps": 259, "total_steps": 543, "loss": 0.628, "lr": 6.273355601206143e-06, "epoch": 1.430939226519337, "percentage": 47.7, "elapsed_time": "0:08:07", "remaining_time": "0:08:54"}
260
+ {"current_steps": 260, "total_steps": 543, "loss": 0.6601, "lr": 6.24220230701164e-06, "epoch": 1.43646408839779, "percentage": 47.88, "elapsed_time": "0:08:08", "remaining_time": "0:08:52"}
261
+ {"current_steps": 261, "total_steps": 543, "loss": 0.5342, "lr": 6.210997531347879e-06, "epoch": 1.441988950276243, "percentage": 48.07, "elapsed_time": "0:08:10", "remaining_time": "0:08:49"}
262
+ {"current_steps": 262, "total_steps": 543, "loss": 0.6339, "lr": 6.179742567456464e-06, "epoch": 1.4475138121546962, "percentage": 48.25, "elapsed_time": "0:08:12", "remaining_time": "0:08:48"}
263
+ {"current_steps": 263, "total_steps": 543, "loss": 0.5782, "lr": 6.148438710658979e-06, "epoch": 1.4530386740331491, "percentage": 48.43, "elapsed_time": "0:08:14", "remaining_time": "0:08:46"}
264
+ {"current_steps": 264, "total_steps": 543, "loss": 0.6392, "lr": 6.117087258303314e-06, "epoch": 1.4585635359116023, "percentage": 48.62, "elapsed_time": "0:08:15", "remaining_time": "0:08:44"}
265
+ {"current_steps": 265, "total_steps": 543, "loss": 0.5848, "lr": 6.085689509709893e-06, "epoch": 1.4640883977900552, "percentage": 48.8, "elapsed_time": "0:08:17", "remaining_time": "0:08:41"}
266
+ {"current_steps": 266, "total_steps": 543, "loss": 0.6243, "lr": 6.0542467661178325e-06, "epoch": 1.4696132596685083, "percentage": 48.99, "elapsed_time": "0:08:19", "remaining_time": "0:08:39"}
267
+ {"current_steps": 267, "total_steps": 543, "loss": 0.6081, "lr": 6.022760330631006e-06, "epoch": 1.4751381215469612, "percentage": 49.17, "elapsed_time": "0:08:20", "remaining_time": "0:08:37"}
268
+ {"current_steps": 268, "total_steps": 543, "loss": 0.6315, "lr": 5.991231508164037e-06, "epoch": 1.4806629834254144, "percentage": 49.36, "elapsed_time": "0:08:22", "remaining_time": "0:08:35"}
269
+ {"current_steps": 269, "total_steps": 543, "loss": 0.5479, "lr": 5.959661605388229e-06, "epoch": 1.4861878453038675, "percentage": 49.54, "elapsed_time": "0:08:23", "remaining_time": "0:08:33"}
270
+ {"current_steps": 270, "total_steps": 543, "loss": 0.6074, "lr": 5.928051930677404e-06, "epoch": 1.4917127071823204, "percentage": 49.72, "elapsed_time": "0:08:25", "remaining_time": "0:08:30"}
271
+ {"current_steps": 271, "total_steps": 543, "loss": 0.6117, "lr": 5.896403794053679e-06, "epoch": 1.4972375690607735, "percentage": 49.91, "elapsed_time": "0:08:26", "remaining_time": "0:08:28"}
272
+ {"current_steps": 272, "total_steps": 543, "loss": 0.6015, "lr": 5.864718507133176e-06, "epoch": 1.5027624309392267, "percentage": 50.09, "elapsed_time": "0:08:28", "remaining_time": "0:08:26"}
273
+ {"current_steps": 273, "total_steps": 543, "loss": 0.6491, "lr": 5.83299738307166e-06, "epoch": 1.5082872928176796, "percentage": 50.28, "elapsed_time": "0:08:29", "remaining_time": "0:08:24"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85ff94a63d6f8a6bdba4e7e23ca2743b33370af437032cc30c119f84d4359807
3
- size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b51e25a6c24f1db7f9d2ee1f91890c08c6b039b010df16a89db12294fd3ec25
3
+ size 7288
vocab.json ADDED
The diff for this file is too large to render. See raw diff