sedrickkeh commited on
Commit
6b431b7
·
verified ·
1 Parent(s): 98bd7bf

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B",
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": 8192,
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": null,
24
+ "rope_theta": 500000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.46.1",
28
+ "use_cache": false,
29
+ "vocab_size": 128256
30
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fcb302cd4dcef405d2eb5f5d8554c2683a085d1927ba4461e4f3a545ced323e
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:784d6ff55eab8e66be4c7731417d74f42630b78f91ca806a34911001cabc700d
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded72949bc0ddbdfc105859bebb772d42c277ba2055d2f4d3b2827b5971702a5
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a50be0b77f7c94e41bf0345b1f41e61678c55de2274a6e23c86dc007fabf029
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{ '<|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": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 1235, "loss": 3.4051, "lr": 3.2258064516129035e-07, "epoch": 0.004048582995951417, "percentage": 0.08, "elapsed_time": "0:01:07", "remaining_time": "23:13:48"}
2
+ {"current_steps": 2, "total_steps": 1235, "loss": 3.3621, "lr": 6.451612903225807e-07, "epoch": 0.008097165991902834, "percentage": 0.16, "elapsed_time": "0:02:09", "remaining_time": "22:06:03"}
3
+ {"current_steps": 3, "total_steps": 1235, "loss": 3.5526, "lr": 9.67741935483871e-07, "epoch": 0.012145748987854251, "percentage": 0.24, "elapsed_time": "0:03:12", "remaining_time": "21:54:48"}
4
+ {"current_steps": 4, "total_steps": 1235, "loss": 3.4076, "lr": 1.2903225806451614e-06, "epoch": 0.016194331983805668, "percentage": 0.32, "elapsed_time": "0:04:15", "remaining_time": "21:49:06"}
5
+ {"current_steps": 5, "total_steps": 1235, "loss": 3.3798, "lr": 1.6129032258064516e-06, "epoch": 0.020242914979757085, "percentage": 0.4, "elapsed_time": "0:05:17", "remaining_time": "21:41:06"}
6
+ {"current_steps": 6, "total_steps": 1235, "loss": 3.0998, "lr": 1.935483870967742e-06, "epoch": 0.024291497975708502, "percentage": 0.49, "elapsed_time": "0:06:20", "remaining_time": "21:39:19"}
7
+ {"current_steps": 7, "total_steps": 1235, "loss": 2.9039, "lr": 2.2580645161290324e-06, "epoch": 0.02834008097165992, "percentage": 0.57, "elapsed_time": "0:07:22", "remaining_time": "21:35:09"}
8
+ {"current_steps": 8, "total_steps": 1235, "loss": 2.7937, "lr": 2.580645161290323e-06, "epoch": 0.032388663967611336, "percentage": 0.65, "elapsed_time": "0:08:24", "remaining_time": "21:29:50"}
9
+ {"current_steps": 9, "total_steps": 1235, "loss": 2.6497, "lr": 2.903225806451613e-06, "epoch": 0.03643724696356275, "percentage": 0.73, "elapsed_time": "0:09:25", "remaining_time": "21:24:15"}
10
+ {"current_steps": 10, "total_steps": 1235, "loss": 2.5071, "lr": 3.225806451612903e-06, "epoch": 0.04048582995951417, "percentage": 0.81, "elapsed_time": "0:10:26", "remaining_time": "21:18:35"}
11
+ {"current_steps": 11, "total_steps": 1235, "loss": 2.404, "lr": 3.548387096774194e-06, "epoch": 0.044534412955465584, "percentage": 0.89, "elapsed_time": "0:11:27", "remaining_time": "21:14:29"}
12
+ {"current_steps": 12, "total_steps": 1235, "loss": 2.2667, "lr": 3.870967741935484e-06, "epoch": 0.048582995951417005, "percentage": 0.97, "elapsed_time": "0:12:27", "remaining_time": "21:10:27"}
13
+ {"current_steps": 13, "total_steps": 1235, "loss": 2.1906, "lr": 4.193548387096774e-06, "epoch": 0.05263157894736842, "percentage": 1.05, "elapsed_time": "0:13:29", "remaining_time": "21:08:06"}
14
+ {"current_steps": 14, "total_steps": 1235, "loss": 2.1105, "lr": 4.516129032258065e-06, "epoch": 0.05668016194331984, "percentage": 1.13, "elapsed_time": "0:14:32", "remaining_time": "21:07:49"}
15
+ {"current_steps": 15, "total_steps": 1235, "loss": 2.0655, "lr": 4.838709677419355e-06, "epoch": 0.06072874493927125, "percentage": 1.21, "elapsed_time": "0:15:32", "remaining_time": "21:04:39"}
16
+ {"current_steps": 16, "total_steps": 1235, "loss": 2.064, "lr": 5.161290322580646e-06, "epoch": 0.06477732793522267, "percentage": 1.3, "elapsed_time": "0:16:36", "remaining_time": "21:04:50"}
17
+ {"current_steps": 17, "total_steps": 1235, "loss": 1.9681, "lr": 5.483870967741935e-06, "epoch": 0.06882591093117409, "percentage": 1.38, "elapsed_time": "0:17:36", "remaining_time": "21:01:43"}
18
+ {"current_steps": 18, "total_steps": 1235, "loss": 1.8934, "lr": 5.806451612903226e-06, "epoch": 0.0728744939271255, "percentage": 1.46, "elapsed_time": "0:18:38", "remaining_time": "20:59:54"}
19
+ {"current_steps": 19, "total_steps": 1235, "loss": 1.8139, "lr": 6.129032258064517e-06, "epoch": 0.07692307692307693, "percentage": 1.54, "elapsed_time": "0:19:38", "remaining_time": "20:56:40"}
20
+ {"current_steps": 20, "total_steps": 1235, "loss": 1.8037, "lr": 6.451612903225806e-06, "epoch": 0.08097165991902834, "percentage": 1.62, "elapsed_time": "0:20:39", "remaining_time": "20:55:15"}
21
+ {"current_steps": 21, "total_steps": 1235, "loss": 1.781, "lr": 6.774193548387097e-06, "epoch": 0.08502024291497975, "percentage": 1.7, "elapsed_time": "0:21:40", "remaining_time": "20:52:59"}
22
+ {"current_steps": 22, "total_steps": 1235, "loss": 1.7082, "lr": 7.096774193548388e-06, "epoch": 0.08906882591093117, "percentage": 1.78, "elapsed_time": "0:22:42", "remaining_time": "20:51:45"}
23
+ {"current_steps": 23, "total_steps": 1235, "loss": 1.7057, "lr": 7.4193548387096784e-06, "epoch": 0.0931174089068826, "percentage": 1.86, "elapsed_time": "0:23:42", "remaining_time": "20:49:03"}
24
+ {"current_steps": 24, "total_steps": 1235, "loss": 1.6431, "lr": 7.741935483870968e-06, "epoch": 0.09716599190283401, "percentage": 1.94, "elapsed_time": "0:24:41", "remaining_time": "20:46:11"}
25
+ {"current_steps": 25, "total_steps": 1235, "loss": 1.6176, "lr": 8.064516129032258e-06, "epoch": 0.10121457489878542, "percentage": 2.02, "elapsed_time": "0:25:42", "remaining_time": "20:43:59"}
26
+ {"current_steps": 26, "total_steps": 1235, "loss": 1.6033, "lr": 8.387096774193549e-06, "epoch": 0.10526315789473684, "percentage": 2.11, "elapsed_time": "0:26:43", "remaining_time": "20:42:28"}
27
+ {"current_steps": 27, "total_steps": 1235, "loss": 1.5937, "lr": 8.70967741935484e-06, "epoch": 0.10931174089068826, "percentage": 2.19, "elapsed_time": "0:27:43", "remaining_time": "20:40:30"}
28
+ {"current_steps": 28, "total_steps": 1235, "loss": 1.6327, "lr": 9.03225806451613e-06, "epoch": 0.11336032388663968, "percentage": 2.27, "elapsed_time": "0:28:43", "remaining_time": "20:38:00"}
29
+ {"current_steps": 29, "total_steps": 1235, "loss": 1.6315, "lr": 9.35483870967742e-06, "epoch": 0.11740890688259109, "percentage": 2.35, "elapsed_time": "0:29:45", "remaining_time": "20:37:24"}
30
+ {"current_steps": 30, "total_steps": 1235, "loss": 1.596, "lr": 9.67741935483871e-06, "epoch": 0.1214574898785425, "percentage": 2.43, "elapsed_time": "0:30:46", "remaining_time": "20:36:26"}
31
+ {"current_steps": 31, "total_steps": 1235, "loss": 1.5881, "lr": 1e-05, "epoch": 0.12550607287449392, "percentage": 2.51, "elapsed_time": "0:31:47", "remaining_time": "20:34:57"}
32
+ {"current_steps": 32, "total_steps": 1235, "loss": 1.5409, "lr": 1.0322580645161291e-05, "epoch": 0.12955465587044535, "percentage": 2.59, "elapsed_time": "0:32:47", "remaining_time": "20:33:02"}
33
+ {"current_steps": 33, "total_steps": 1235, "loss": 1.5356, "lr": 1.0645161290322582e-05, "epoch": 0.13360323886639677, "percentage": 2.67, "elapsed_time": "0:33:48", "remaining_time": "20:31:40"}
34
+ {"current_steps": 34, "total_steps": 1235, "loss": 1.4527, "lr": 1.096774193548387e-05, "epoch": 0.13765182186234817, "percentage": 2.75, "elapsed_time": "0:34:50", "remaining_time": "20:30:38"}
35
+ {"current_steps": 35, "total_steps": 1235, "loss": 1.4964, "lr": 1.1290322580645164e-05, "epoch": 0.1417004048582996, "percentage": 2.83, "elapsed_time": "0:35:50", "remaining_time": "20:29:01"}
36
+ {"current_steps": 36, "total_steps": 1235, "loss": 1.4683, "lr": 1.1612903225806453e-05, "epoch": 0.145748987854251, "percentage": 2.91, "elapsed_time": "0:36:52", "remaining_time": "20:28:02"}
37
+ {"current_steps": 37, "total_steps": 1235, "loss": 1.442, "lr": 1.1935483870967743e-05, "epoch": 0.14979757085020243, "percentage": 3.0, "elapsed_time": "0:37:54", "remaining_time": "20:27:12"}
38
+ {"current_steps": 38, "total_steps": 1235, "loss": 1.4702, "lr": 1.2258064516129034e-05, "epoch": 0.15384615384615385, "percentage": 3.08, "elapsed_time": "0:38:54", "remaining_time": "20:25:45"}
39
+ {"current_steps": 39, "total_steps": 1235, "loss": 1.4688, "lr": 1.2580645161290324e-05, "epoch": 0.15789473684210525, "percentage": 3.16, "elapsed_time": "0:39:55", "remaining_time": "20:24:10"}
40
+ {"current_steps": 40, "total_steps": 1235, "loss": 1.4209, "lr": 1.2903225806451613e-05, "epoch": 0.16194331983805668, "percentage": 3.24, "elapsed_time": "0:40:55", "remaining_time": "20:22:47"}
41
+ {"current_steps": 41, "total_steps": 1235, "loss": 1.3777, "lr": 1.3225806451612903e-05, "epoch": 0.1659919028340081, "percentage": 3.32, "elapsed_time": "0:41:55", "remaining_time": "20:20:55"}
42
+ {"current_steps": 42, "total_steps": 1235, "loss": 1.3551, "lr": 1.3548387096774194e-05, "epoch": 0.1700404858299595, "percentage": 3.4, "elapsed_time": "0:42:56", "remaining_time": "20:19:40"}
43
+ {"current_steps": 43, "total_steps": 1235, "loss": 1.3709, "lr": 1.3870967741935486e-05, "epoch": 0.17408906882591094, "percentage": 3.48, "elapsed_time": "0:43:56", "remaining_time": "20:18:13"}
44
+ {"current_steps": 44, "total_steps": 1235, "loss": 1.3396, "lr": 1.4193548387096776e-05, "epoch": 0.17813765182186234, "percentage": 3.56, "elapsed_time": "0:44:57", "remaining_time": "20:16:56"}
45
+ {"current_steps": 45, "total_steps": 1235, "loss": 1.3827, "lr": 1.4516129032258066e-05, "epoch": 0.18218623481781376, "percentage": 3.64, "elapsed_time": "0:45:58", "remaining_time": "20:15:34"}
46
+ {"current_steps": 46, "total_steps": 1235, "loss": 1.3422, "lr": 1.4838709677419357e-05, "epoch": 0.1862348178137652, "percentage": 3.72, "elapsed_time": "0:46:57", "remaining_time": "20:13:58"}
47
+ {"current_steps": 47, "total_steps": 1235, "loss": 1.4188, "lr": 1.5161290322580646e-05, "epoch": 0.1902834008097166, "percentage": 3.81, "elapsed_time": "0:47:58", "remaining_time": "20:12:36"}
48
+ {"current_steps": 48, "total_steps": 1235, "loss": 1.4783, "lr": 1.5483870967741936e-05, "epoch": 0.19433198380566802, "percentage": 3.89, "elapsed_time": "0:48:58", "remaining_time": "20:11:12"}
49
+ {"current_steps": 49, "total_steps": 1235, "loss": 1.4304, "lr": 1.5806451612903226e-05, "epoch": 0.19838056680161945, "percentage": 3.97, "elapsed_time": "0:49:58", "remaining_time": "20:09:43"}
50
+ {"current_steps": 50, "total_steps": 1235, "loss": 1.3672, "lr": 1.6129032258064517e-05, "epoch": 0.20242914979757085, "percentage": 4.05, "elapsed_time": "0:50:58", "remaining_time": "20:08:10"}
51
+ {"current_steps": 51, "total_steps": 1235, "loss": 1.3423, "lr": 1.6451612903225807e-05, "epoch": 0.20647773279352227, "percentage": 4.13, "elapsed_time": "0:51:59", "remaining_time": "20:06:50"}
52
+ {"current_steps": 52, "total_steps": 1235, "loss": 1.3921, "lr": 1.6774193548387098e-05, "epoch": 0.21052631578947367, "percentage": 4.21, "elapsed_time": "0:52:59", "remaining_time": "20:05:24"}
53
+ {"current_steps": 53, "total_steps": 1235, "loss": 1.3472, "lr": 1.7096774193548388e-05, "epoch": 0.2145748987854251, "percentage": 4.29, "elapsed_time": "0:53:59", "remaining_time": "20:04:10"}
54
+ {"current_steps": 54, "total_steps": 1235, "loss": 1.3374, "lr": 1.741935483870968e-05, "epoch": 0.21862348178137653, "percentage": 4.37, "elapsed_time": "0:54:59", "remaining_time": "20:02:48"}
55
+ {"current_steps": 55, "total_steps": 1235, "loss": 1.3607, "lr": 1.774193548387097e-05, "epoch": 0.22267206477732793, "percentage": 4.45, "elapsed_time": "0:56:00", "remaining_time": "20:01:30"}
56
+ {"current_steps": 56, "total_steps": 1235, "loss": 1.3177, "lr": 1.806451612903226e-05, "epoch": 0.22672064777327935, "percentage": 4.53, "elapsed_time": "0:57:00", "remaining_time": "20:00:03"}
57
+ {"current_steps": 57, "total_steps": 1235, "loss": 1.3228, "lr": 1.838709677419355e-05, "epoch": 0.23076923076923078, "percentage": 4.62, "elapsed_time": "0:58:00", "remaining_time": "19:58:46"}
58
+ {"current_steps": 58, "total_steps": 1235, "loss": 1.3736, "lr": 1.870967741935484e-05, "epoch": 0.23481781376518218, "percentage": 4.7, "elapsed_time": "0:59:01", "remaining_time": "19:57:38"}
59
+ {"current_steps": 59, "total_steps": 1235, "loss": 1.2494, "lr": 1.903225806451613e-05, "epoch": 0.2388663967611336, "percentage": 4.78, "elapsed_time": "1:00:00", "remaining_time": "19:56:14"}
60
+ {"current_steps": 60, "total_steps": 1235, "loss": 1.3123, "lr": 1.935483870967742e-05, "epoch": 0.242914979757085, "percentage": 4.86, "elapsed_time": "1:01:01", "remaining_time": "19:54:57"}
61
+ {"current_steps": 61, "total_steps": 1235, "loss": 1.2758, "lr": 1.967741935483871e-05, "epoch": 0.24696356275303644, "percentage": 4.94, "elapsed_time": "1:02:00", "remaining_time": "19:53:26"}
62
+ {"current_steps": 62, "total_steps": 1235, "loss": 1.3466, "lr": 2e-05, "epoch": 0.25101214574898784, "percentage": 5.02, "elapsed_time": "1:03:00", "remaining_time": "19:52:10"}
63
+ {"current_steps": 63, "total_steps": 1235, "loss": 1.3001, "lr": 2.0322580645161292e-05, "epoch": 0.2550607287449393, "percentage": 5.1, "elapsed_time": "1:04:01", "remaining_time": "19:50:59"}
64
+ {"current_steps": 64, "total_steps": 1235, "loss": 1.2652, "lr": 2.0645161290322582e-05, "epoch": 0.2591093117408907, "percentage": 5.18, "elapsed_time": "1:05:00", "remaining_time": "19:49:30"}
65
+ {"current_steps": 65, "total_steps": 1235, "loss": 1.2335, "lr": 2.0967741935483873e-05, "epoch": 0.2631578947368421, "percentage": 5.26, "elapsed_time": "1:06:00", "remaining_time": "19:48:13"}
66
+ {"current_steps": 66, "total_steps": 1235, "loss": 1.2518, "lr": 2.1290322580645163e-05, "epoch": 0.26720647773279355, "percentage": 5.34, "elapsed_time": "1:07:01", "remaining_time": "19:47:07"}
67
+ {"current_steps": 67, "total_steps": 1235, "loss": 1.283, "lr": 2.161290322580645e-05, "epoch": 0.27125506072874495, "percentage": 5.43, "elapsed_time": "1:08:02", "remaining_time": "19:46:05"}
68
+ {"current_steps": 68, "total_steps": 1235, "loss": 1.2817, "lr": 2.193548387096774e-05, "epoch": 0.27530364372469635, "percentage": 5.51, "elapsed_time": "1:09:02", "remaining_time": "19:44:57"}
69
+ {"current_steps": 69, "total_steps": 1235, "loss": 1.2674, "lr": 2.225806451612903e-05, "epoch": 0.2793522267206478, "percentage": 5.59, "elapsed_time": "1:10:03", "remaining_time": "19:43:49"}
70
+ {"current_steps": 70, "total_steps": 1235, "loss": 1.2571, "lr": 2.2580645161290328e-05, "epoch": 0.2834008097165992, "percentage": 5.67, "elapsed_time": "1:11:03", "remaining_time": "19:42:40"}
71
+ {"current_steps": 71, "total_steps": 1235, "loss": 1.2306, "lr": 2.2903225806451615e-05, "epoch": 0.2874493927125506, "percentage": 5.75, "elapsed_time": "1:12:03", "remaining_time": "19:41:28"}
72
+ {"current_steps": 72, "total_steps": 1235, "loss": 1.2576, "lr": 2.3225806451612906e-05, "epoch": 0.291497975708502, "percentage": 5.83, "elapsed_time": "1:13:04", "remaining_time": "19:40:25"}
73
+ {"current_steps": 73, "total_steps": 1235, "loss": 1.2126, "lr": 2.3548387096774196e-05, "epoch": 0.29554655870445345, "percentage": 5.91, "elapsed_time": "1:14:06", "remaining_time": "19:39:42"}
74
+ {"current_steps": 74, "total_steps": 1235, "loss": 1.2392, "lr": 2.3870967741935486e-05, "epoch": 0.29959514170040485, "percentage": 5.99, "elapsed_time": "1:15:06", "remaining_time": "19:38:24"}
75
+ {"current_steps": 75, "total_steps": 1235, "loss": 1.2299, "lr": 2.4193548387096777e-05, "epoch": 0.30364372469635625, "percentage": 6.07, "elapsed_time": "1:16:06", "remaining_time": "19:37:15"}
76
+ {"current_steps": 76, "total_steps": 1235, "loss": 1.2553, "lr": 2.4516129032258067e-05, "epoch": 0.3076923076923077, "percentage": 6.15, "elapsed_time": "1:17:06", "remaining_time": "19:35:59"}
77
+ {"current_steps": 77, "total_steps": 1235, "loss": 1.2274, "lr": 2.4838709677419358e-05, "epoch": 0.3117408906882591, "percentage": 6.23, "elapsed_time": "1:18:07", "remaining_time": "19:34:50"}
78
+ {"current_steps": 78, "total_steps": 1235, "loss": 1.27, "lr": 2.5161290322580648e-05, "epoch": 0.3157894736842105, "percentage": 6.32, "elapsed_time": "1:19:08", "remaining_time": "19:33:54"}
79
+ {"current_steps": 79, "total_steps": 1235, "loss": 1.2661, "lr": 2.548387096774194e-05, "epoch": 0.31983805668016196, "percentage": 6.4, "elapsed_time": "1:20:08", "remaining_time": "19:32:44"}
80
+ {"current_steps": 80, "total_steps": 1235, "loss": 1.2396, "lr": 2.5806451612903226e-05, "epoch": 0.32388663967611336, "percentage": 6.48, "elapsed_time": "1:21:09", "remaining_time": "19:31:38"}
81
+ {"current_steps": 81, "total_steps": 1235, "loss": 1.2577, "lr": 2.6129032258064516e-05, "epoch": 0.32793522267206476, "percentage": 6.56, "elapsed_time": "1:22:08", "remaining_time": "19:30:22"}
82
+ {"current_steps": 82, "total_steps": 1235, "loss": 1.2659, "lr": 2.6451612903225806e-05, "epoch": 0.3319838056680162, "percentage": 6.64, "elapsed_time": "1:23:09", "remaining_time": "19:29:11"}
83
+ {"current_steps": 83, "total_steps": 1235, "loss": 1.2175, "lr": 2.6774193548387097e-05, "epoch": 0.3360323886639676, "percentage": 6.72, "elapsed_time": "1:24:09", "remaining_time": "19:28:05"}
84
+ {"current_steps": 84, "total_steps": 1235, "loss": 1.1957, "lr": 2.7096774193548387e-05, "epoch": 0.340080971659919, "percentage": 6.8, "elapsed_time": "1:25:11", "remaining_time": "19:27:15"}
85
+ {"current_steps": 85, "total_steps": 1235, "loss": 1.2014, "lr": 2.7419354838709678e-05, "epoch": 0.3441295546558704, "percentage": 6.88, "elapsed_time": "1:26:11", "remaining_time": "19:26:12"}
86
+ {"current_steps": 86, "total_steps": 1235, "loss": 1.1962, "lr": 2.774193548387097e-05, "epoch": 0.3481781376518219, "percentage": 6.96, "elapsed_time": "1:27:12", "remaining_time": "19:25:06"}
87
+ {"current_steps": 87, "total_steps": 1235, "loss": 1.207, "lr": 2.8064516129032262e-05, "epoch": 0.3522267206477733, "percentage": 7.04, "elapsed_time": "1:28:12", "remaining_time": "19:24:00"}
88
+ {"current_steps": 88, "total_steps": 1235, "loss": 1.1884, "lr": 2.8387096774193552e-05, "epoch": 0.3562753036437247, "percentage": 7.13, "elapsed_time": "1:29:13", "remaining_time": "19:22:58"}
89
+ {"current_steps": 89, "total_steps": 1235, "loss": 1.2091, "lr": 2.8709677419354843e-05, "epoch": 0.3603238866396761, "percentage": 7.21, "elapsed_time": "1:30:14", "remaining_time": "19:21:58"}
90
+ {"current_steps": 90, "total_steps": 1235, "loss": 1.2292, "lr": 2.9032258064516133e-05, "epoch": 0.3643724696356275, "percentage": 7.29, "elapsed_time": "1:31:14", "remaining_time": "19:20:52"}
91
+ {"current_steps": 91, "total_steps": 1235, "loss": 1.1778, "lr": 2.9354838709677423e-05, "epoch": 0.3684210526315789, "percentage": 7.37, "elapsed_time": "1:32:15", "remaining_time": "19:19:49"}
92
+ {"current_steps": 92, "total_steps": 1235, "loss": 1.2239, "lr": 2.9677419354838714e-05, "epoch": 0.3724696356275304, "percentage": 7.45, "elapsed_time": "1:33:15", "remaining_time": "19:18:36"}
93
+ {"current_steps": 93, "total_steps": 1235, "loss": 1.227, "lr": 3.0000000000000004e-05, "epoch": 0.3765182186234818, "percentage": 7.53, "elapsed_time": "1:34:16", "remaining_time": "19:17:34"}
94
+ {"current_steps": 94, "total_steps": 1235, "loss": 1.2175, "lr": 3.032258064516129e-05, "epoch": 0.3805668016194332, "percentage": 7.61, "elapsed_time": "1:35:16", "remaining_time": "19:16:29"}
95
+ {"current_steps": 95, "total_steps": 1235, "loss": 1.2091, "lr": 3.0645161290322585e-05, "epoch": 0.38461538461538464, "percentage": 7.69, "elapsed_time": "1:36:19", "remaining_time": "19:15:48"}
96
+ {"current_steps": 96, "total_steps": 1235, "loss": 1.1938, "lr": 3.096774193548387e-05, "epoch": 0.38866396761133604, "percentage": 7.77, "elapsed_time": "1:37:19", "remaining_time": "19:14:48"}
97
+ {"current_steps": 97, "total_steps": 1235, "loss": 1.1939, "lr": 3.1290322580645166e-05, "epoch": 0.39271255060728744, "percentage": 7.85, "elapsed_time": "1:38:20", "remaining_time": "19:13:39"}
98
+ {"current_steps": 98, "total_steps": 1235, "loss": 1.1746, "lr": 3.161290322580645e-05, "epoch": 0.3967611336032389, "percentage": 7.94, "elapsed_time": "1:39:20", "remaining_time": "19:12:30"}
99
+ {"current_steps": 99, "total_steps": 1235, "loss": 1.1875, "lr": 3.193548387096774e-05, "epoch": 0.4008097165991903, "percentage": 8.02, "elapsed_time": "1:40:20", "remaining_time": "19:11:24"}
100
+ {"current_steps": 100, "total_steps": 1235, "loss": 1.2147, "lr": 3.2258064516129034e-05, "epoch": 0.4048582995951417, "percentage": 8.1, "elapsed_time": "1:41:20", "remaining_time": "19:10:12"}
101
+ {"current_steps": 101, "total_steps": 1235, "loss": 1.2029, "lr": 3.258064516129033e-05, "epoch": 0.4089068825910931, "percentage": 8.18, "elapsed_time": "1:42:20", "remaining_time": "19:09:06"}
102
+ {"current_steps": 102, "total_steps": 1235, "loss": 1.2185, "lr": 3.2903225806451614e-05, "epoch": 0.41295546558704455, "percentage": 8.26, "elapsed_time": "1:43:21", "remaining_time": "19:08:01"}
103
+ {"current_steps": 103, "total_steps": 1235, "loss": 1.1434, "lr": 3.322580645161291e-05, "epoch": 0.41700404858299595, "percentage": 8.34, "elapsed_time": "1:44:22", "remaining_time": "19:07:01"}
104
+ {"current_steps": 104, "total_steps": 1235, "loss": 1.1559, "lr": 3.3548387096774195e-05, "epoch": 0.42105263157894735, "percentage": 8.42, "elapsed_time": "1:45:22", "remaining_time": "19:06:02"}
105
+ {"current_steps": 105, "total_steps": 1235, "loss": 1.1291, "lr": 3.387096774193549e-05, "epoch": 0.4251012145748988, "percentage": 8.5, "elapsed_time": "1:46:23", "remaining_time": "19:04:56"}
106
+ {"current_steps": 106, "total_steps": 1235, "loss": 1.17, "lr": 3.4193548387096776e-05, "epoch": 0.4291497975708502, "percentage": 8.58, "elapsed_time": "1:47:23", "remaining_time": "19:03:52"}
107
+ {"current_steps": 107, "total_steps": 1235, "loss": 1.1625, "lr": 3.451612903225807e-05, "epoch": 0.4331983805668016, "percentage": 8.66, "elapsed_time": "1:48:24", "remaining_time": "19:02:49"}
108
+ {"current_steps": 108, "total_steps": 1235, "loss": 1.1441, "lr": 3.483870967741936e-05, "epoch": 0.43724696356275305, "percentage": 8.74, "elapsed_time": "1:49:24", "remaining_time": "19:01:46"}
109
+ {"current_steps": 109, "total_steps": 1235, "loss": 1.1805, "lr": 3.516129032258065e-05, "epoch": 0.44129554655870445, "percentage": 8.83, "elapsed_time": "1:50:24", "remaining_time": "19:00:30"}
110
+ {"current_steps": 110, "total_steps": 1235, "loss": 1.1975, "lr": 3.548387096774194e-05, "epoch": 0.44534412955465585, "percentage": 8.91, "elapsed_time": "1:51:24", "remaining_time": "18:59:24"}
111
+ {"current_steps": 111, "total_steps": 1235, "loss": 1.1737, "lr": 3.5806451612903225e-05, "epoch": 0.4493927125506073, "percentage": 8.99, "elapsed_time": "1:52:25", "remaining_time": "18:58:29"}
112
+ {"current_steps": 112, "total_steps": 1235, "loss": 1.1966, "lr": 3.612903225806452e-05, "epoch": 0.4534412955465587, "percentage": 9.07, "elapsed_time": "1:53:25", "remaining_time": "18:57:19"}
113
+ {"current_steps": 113, "total_steps": 1235, "loss": 1.1534, "lr": 3.6451612903225805e-05, "epoch": 0.4574898785425101, "percentage": 9.15, "elapsed_time": "1:54:26", "remaining_time": "18:56:14"}
114
+ {"current_steps": 114, "total_steps": 1235, "loss": 1.1642, "lr": 3.67741935483871e-05, "epoch": 0.46153846153846156, "percentage": 9.23, "elapsed_time": "1:55:26", "remaining_time": "18:55:07"}
115
+ {"current_steps": 115, "total_steps": 1235, "loss": 1.1698, "lr": 3.7096774193548386e-05, "epoch": 0.46558704453441296, "percentage": 9.31, "elapsed_time": "1:56:26", "remaining_time": "18:54:04"}
116
+ {"current_steps": 116, "total_steps": 1235, "loss": 1.1652, "lr": 3.741935483870968e-05, "epoch": 0.46963562753036436, "percentage": 9.39, "elapsed_time": "1:57:26", "remaining_time": "18:52:59"}
117
+ {"current_steps": 117, "total_steps": 1235, "loss": 1.1466, "lr": 3.7741935483870974e-05, "epoch": 0.47368421052631576, "percentage": 9.47, "elapsed_time": "1:58:27", "remaining_time": "18:51:52"}
118
+ {"current_steps": 118, "total_steps": 1235, "loss": 1.097, "lr": 3.806451612903226e-05, "epoch": 0.4777327935222672, "percentage": 9.55, "elapsed_time": "1:59:28", "remaining_time": "18:50:57"}
119
+ {"current_steps": 119, "total_steps": 1235, "loss": 1.1377, "lr": 3.8387096774193555e-05, "epoch": 0.4817813765182186, "percentage": 9.64, "elapsed_time": "2:00:28", "remaining_time": "18:49:47"}
120
+ {"current_steps": 120, "total_steps": 1235, "loss": 1.148, "lr": 3.870967741935484e-05, "epoch": 0.48582995951417, "percentage": 9.72, "elapsed_time": "2:01:28", "remaining_time": "18:48:40"}
121
+ {"current_steps": 121, "total_steps": 1235, "loss": 1.182, "lr": 3.9032258064516135e-05, "epoch": 0.4898785425101215, "percentage": 9.8, "elapsed_time": "2:02:28", "remaining_time": "18:47:36"}
122
+ {"current_steps": 122, "total_steps": 1235, "loss": 1.1406, "lr": 3.935483870967742e-05, "epoch": 0.4939271255060729, "percentage": 9.88, "elapsed_time": "2:03:29", "remaining_time": "18:46:34"}
123
+ {"current_steps": 123, "total_steps": 1235, "loss": 1.152, "lr": 3.9677419354838716e-05, "epoch": 0.4979757085020243, "percentage": 9.96, "elapsed_time": "2:04:30", "remaining_time": "18:45:35"}
124
+ {"current_steps": 124, "total_steps": 1235, "loss": 1.1669, "lr": 4e-05, "epoch": 0.5020242914979757, "percentage": 10.04, "elapsed_time": "2:05:30", "remaining_time": "18:44:33"}
125
+ {"current_steps": 125, "total_steps": 1235, "loss": 1.1228, "lr": 3.9999920040266474e-05, "epoch": 0.5060728744939271, "percentage": 10.12, "elapsed_time": "2:06:31", "remaining_time": "18:43:28"}
126
+ {"current_steps": 126, "total_steps": 1235, "loss": 1.1584, "lr": 3.999968016170525e-05, "epoch": 0.5101214574898786, "percentage": 10.2, "elapsed_time": "2:07:30", "remaining_time": "18:42:19"}
127
+ {"current_steps": 127, "total_steps": 1235, "loss": 1.1931, "lr": 3.9999280366234394e-05, "epoch": 0.5141700404858299, "percentage": 10.28, "elapsed_time": "2:08:31", "remaining_time": "18:41:15"}
128
+ {"current_steps": 128, "total_steps": 1235, "loss": 1.1227, "lr": 3.999872065705065e-05, "epoch": 0.5182186234817814, "percentage": 10.36, "elapsed_time": "2:09:31", "remaining_time": "18:40:12"}
129
+ {"current_steps": 129, "total_steps": 1235, "loss": 1.1454, "lr": 3.999800103862945e-05, "epoch": 0.5222672064777328, "percentage": 10.45, "elapsed_time": "2:10:32", "remaining_time": "18:39:09"}
130
+ {"current_steps": 130, "total_steps": 1235, "loss": 1.1921, "lr": 3.9997121516724834e-05, "epoch": 0.5263157894736842, "percentage": 10.53, "elapsed_time": "2:11:34", "remaining_time": "18:38:20"}
131
+ {"current_steps": 131, "total_steps": 1235, "loss": 1.1754, "lr": 3.999608209836944e-05, "epoch": 0.5303643724696356, "percentage": 10.61, "elapsed_time": "2:12:34", "remaining_time": "18:37:16"}
132
+ {"current_steps": 132, "total_steps": 1235, "loss": 1.1661, "lr": 3.999488279187443e-05, "epoch": 0.5344129554655871, "percentage": 10.69, "elapsed_time": "2:13:34", "remaining_time": "18:36:12"}
133
+ {"current_steps": 133, "total_steps": 1235, "loss": 1.1073, "lr": 3.9993523606829425e-05, "epoch": 0.5384615384615384, "percentage": 10.77, "elapsed_time": "2:14:35", "remaining_time": "18:35:11"}
134
+ {"current_steps": 134, "total_steps": 1235, "loss": 1.1561, "lr": 3.9992004554102435e-05, "epoch": 0.5425101214574899, "percentage": 10.85, "elapsed_time": "2:15:35", "remaining_time": "18:34:05"}
135
+ {"current_steps": 135, "total_steps": 1235, "loss": 1.0863, "lr": 3.999032564583976e-05, "epoch": 0.5465587044534413, "percentage": 10.93, "elapsed_time": "2:16:36", "remaining_time": "18:33:02"}
136
+ {"current_steps": 136, "total_steps": 1235, "loss": 1.1508, "lr": 3.998848689546591e-05, "epoch": 0.5506072874493927, "percentage": 11.01, "elapsed_time": "2:17:36", "remaining_time": "18:31:58"}
137
+ {"current_steps": 137, "total_steps": 1235, "loss": 1.1056, "lr": 3.9986488317683496e-05, "epoch": 0.5546558704453441, "percentage": 11.09, "elapsed_time": "2:18:35", "remaining_time": "18:30:48"}
138
+ {"current_steps": 138, "total_steps": 1235, "loss": 1.1388, "lr": 3.9984329928473067e-05, "epoch": 0.5587044534412956, "percentage": 11.17, "elapsed_time": "2:19:36", "remaining_time": "18:29:46"}
139
+ {"current_steps": 139, "total_steps": 1235, "loss": 1.0908, "lr": 3.998201174509306e-05, "epoch": 0.562753036437247, "percentage": 11.26, "elapsed_time": "2:20:36", "remaining_time": "18:28:44"}
140
+ {"current_steps": 140, "total_steps": 1235, "loss": 1.1655, "lr": 3.997953378607961e-05, "epoch": 0.5668016194331984, "percentage": 11.34, "elapsed_time": "2:21:36", "remaining_time": "18:27:37"}
141
+ {"current_steps": 141, "total_steps": 1235, "loss": 1.1484, "lr": 3.9976896071246403e-05, "epoch": 0.5708502024291497, "percentage": 11.42, "elapsed_time": "2:22:37", "remaining_time": "18:26:33"}
142
+ {"current_steps": 142, "total_steps": 1235, "loss": 1.2187, "lr": 3.997409862168454e-05, "epoch": 0.5748987854251012, "percentage": 11.5, "elapsed_time": "2:23:37", "remaining_time": "18:25:30"}
143
+ {"current_steps": 143, "total_steps": 1235, "loss": 1.1452, "lr": 3.997114145976237e-05, "epoch": 0.5789473684210527, "percentage": 11.58, "elapsed_time": "2:24:37", "remaining_time": "18:24:26"}
144
+ {"current_steps": 144, "total_steps": 1235, "loss": 1.153, "lr": 3.9968024609125245e-05, "epoch": 0.582995951417004, "percentage": 11.66, "elapsed_time": "2:25:38", "remaining_time": "18:23:25"}
145
+ {"current_steps": 145, "total_steps": 1235, "loss": 1.0823, "lr": 3.996474809469545e-05, "epoch": 0.5870445344129555, "percentage": 11.74, "elapsed_time": "2:26:38", "remaining_time": "18:22:21"}
146
+ {"current_steps": 146, "total_steps": 1235, "loss": 1.153, "lr": 3.996131194267189e-05, "epoch": 0.5910931174089069, "percentage": 11.82, "elapsed_time": "2:27:38", "remaining_time": "18:21:15"}
147
+ {"current_steps": 147, "total_steps": 1235, "loss": 1.1641, "lr": 3.995771618052995e-05, "epoch": 0.5951417004048583, "percentage": 11.9, "elapsed_time": "2:28:38", "remaining_time": "18:20:12"}
148
+ {"current_steps": 148, "total_steps": 1235, "loss": 1.1322, "lr": 3.9953960837021256e-05, "epoch": 0.5991902834008097, "percentage": 11.98, "elapsed_time": "2:29:39", "remaining_time": "18:19:11"}
149
+ {"current_steps": 149, "total_steps": 1235, "loss": 1.1439, "lr": 3.995004594217343e-05, "epoch": 0.6032388663967612, "percentage": 12.06, "elapsed_time": "2:30:40", "remaining_time": "18:18:09"}
150
+ {"current_steps": 150, "total_steps": 1235, "loss": 1.1254, "lr": 3.994597152728987e-05, "epoch": 0.6072874493927125, "percentage": 12.15, "elapsed_time": "2:31:40", "remaining_time": "18:17:07"}
151
+ {"current_steps": 151, "total_steps": 1235, "loss": 1.1564, "lr": 3.994173762494947e-05, "epoch": 0.611336032388664, "percentage": 12.23, "elapsed_time": "2:32:40", "remaining_time": "18:16:03"}
152
+ {"current_steps": 152, "total_steps": 1235, "loss": 1.1391, "lr": 3.9937344269006424e-05, "epoch": 0.6153846153846154, "percentage": 12.31, "elapsed_time": "2:33:41", "remaining_time": "18:15:01"}
153
+ {"current_steps": 153, "total_steps": 1235, "loss": 1.1637, "lr": 3.993279149458988e-05, "epoch": 0.6194331983805668, "percentage": 12.39, "elapsed_time": "2:34:41", "remaining_time": "18:14:01"}
154
+ {"current_steps": 154, "total_steps": 1235, "loss": 1.1546, "lr": 3.9928079338103695e-05, "epoch": 0.6234817813765182, "percentage": 12.47, "elapsed_time": "2:35:42", "remaining_time": "18:12:57"}
155
+ {"current_steps": 155, "total_steps": 1235, "loss": 1.1051, "lr": 3.992320783722616e-05, "epoch": 0.6275303643724697, "percentage": 12.55, "elapsed_time": "2:36:42", "remaining_time": "18:11:52"}
156
+ {"current_steps": 156, "total_steps": 1235, "loss": 1.069, "lr": 3.991817703090965e-05, "epoch": 0.631578947368421, "percentage": 12.63, "elapsed_time": "2:37:43", "remaining_time": "18:10:52"}
157
+ {"current_steps": 157, "total_steps": 1235, "loss": 1.1032, "lr": 3.991298695938038e-05, "epoch": 0.6356275303643725, "percentage": 12.71, "elapsed_time": "2:38:43", "remaining_time": "18:09:50"}
158
+ {"current_steps": 158, "total_steps": 1235, "loss": 1.1173, "lr": 3.9907637664138e-05, "epoch": 0.6396761133603239, "percentage": 12.79, "elapsed_time": "2:39:44", "remaining_time": "18:08:51"}
159
+ {"current_steps": 159, "total_steps": 1235, "loss": 1.1558, "lr": 3.990212918795534e-05, "epoch": 0.6437246963562753, "percentage": 12.87, "elapsed_time": "2:40:44", "remaining_time": "18:07:49"}
160
+ {"current_steps": 160, "total_steps": 1235, "loss": 1.1304, "lr": 3.9896461574878036e-05, "epoch": 0.6477732793522267, "percentage": 12.96, "elapsed_time": "2:41:46", "remaining_time": "18:06:52"}
161
+ {"current_steps": 161, "total_steps": 1235, "loss": 1.1357, "lr": 3.989063487022416e-05, "epoch": 0.6518218623481782, "percentage": 13.04, "elapsed_time": "2:42:46", "remaining_time": "18:05:48"}
162
+ {"current_steps": 162, "total_steps": 1235, "loss": 1.071, "lr": 3.9884649120583903e-05, "epoch": 0.6558704453441295, "percentage": 13.12, "elapsed_time": "2:43:47", "remaining_time": "18:04:51"}
163
+ {"current_steps": 163, "total_steps": 1235, "loss": 1.0931, "lr": 3.987850437381915e-05, "epoch": 0.659919028340081, "percentage": 13.2, "elapsed_time": "2:44:47", "remaining_time": "18:03:47"}
164
+ {"current_steps": 164, "total_steps": 1235, "loss": 1.1105, "lr": 3.987220067906313e-05, "epoch": 0.6639676113360324, "percentage": 13.28, "elapsed_time": "2:45:48", "remaining_time": "18:02:46"}
165
+ {"current_steps": 165, "total_steps": 1235, "loss": 1.1565, "lr": 3.986573808672002e-05, "epoch": 0.6680161943319838, "percentage": 13.36, "elapsed_time": "2:46:48", "remaining_time": "18:01:42"}
166
+ {"current_steps": 166, "total_steps": 1235, "loss": 1.1708, "lr": 3.9859116648464534e-05, "epoch": 0.6720647773279352, "percentage": 13.44, "elapsed_time": "2:47:49", "remaining_time": "18:00:43"}
167
+ {"current_steps": 167, "total_steps": 1235, "loss": 1.1464, "lr": 3.985233641724152e-05, "epoch": 0.6761133603238867, "percentage": 13.52, "elapsed_time": "2:48:49", "remaining_time": "17:59:39"}
168
+ {"current_steps": 168, "total_steps": 1235, "loss": 1.1287, "lr": 3.984539744726554e-05, "epoch": 0.680161943319838, "percentage": 13.6, "elapsed_time": "2:49:49", "remaining_time": "17:58:38"}
169
+ {"current_steps": 169, "total_steps": 1235, "loss": 1.1339, "lr": 3.983829979402038e-05, "epoch": 0.6842105263157895, "percentage": 13.68, "elapsed_time": "2:50:50", "remaining_time": "17:57:37"}
170
+ {"current_steps": 170, "total_steps": 1235, "loss": 1.1649, "lr": 3.983104351425871e-05, "epoch": 0.6882591093117408, "percentage": 13.77, "elapsed_time": "2:51:50", "remaining_time": "17:56:32"}
171
+ {"current_steps": 171, "total_steps": 1235, "loss": 1.1259, "lr": 3.982362866600154e-05, "epoch": 0.6923076923076923, "percentage": 13.85, "elapsed_time": "2:52:50", "remaining_time": "17:55:29"}
172
+ {"current_steps": 172, "total_steps": 1235, "loss": 1.1404, "lr": 3.9816055308537806e-05, "epoch": 0.6963562753036437, "percentage": 13.93, "elapsed_time": "2:53:50", "remaining_time": "17:54:23"}
173
+ {"current_steps": 173, "total_steps": 1235, "loss": 1.1116, "lr": 3.980832350242388e-05, "epoch": 0.7004048582995951, "percentage": 14.01, "elapsed_time": "2:54:51", "remaining_time": "17:53:22"}
174
+ {"current_steps": 174, "total_steps": 1235, "loss": 1.0959, "lr": 3.980043330948306e-05, "epoch": 0.7044534412955465, "percentage": 14.09, "elapsed_time": "2:55:51", "remaining_time": "17:52:20"}
175
+ {"current_steps": 175, "total_steps": 1235, "loss": 1.1465, "lr": 3.9792384792805124e-05, "epoch": 0.708502024291498, "percentage": 14.17, "elapsed_time": "2:56:51", "remaining_time": "17:51:16"}
176
+ {"current_steps": 176, "total_steps": 1235, "loss": 1.0984, "lr": 3.978417801674579e-05, "epoch": 0.7125506072874493, "percentage": 14.25, "elapsed_time": "2:57:52", "remaining_time": "17:50:15"}
177
+ {"current_steps": 177, "total_steps": 1235, "loss": 1.1253, "lr": 3.9775813046926244e-05, "epoch": 0.7165991902834008, "percentage": 14.33, "elapsed_time": "2:58:52", "remaining_time": "17:49:11"}
178
+ {"current_steps": 178, "total_steps": 1235, "loss": 1.1296, "lr": 3.976728995023254e-05, "epoch": 0.7206477732793523, "percentage": 14.41, "elapsed_time": "2:59:52", "remaining_time": "17:48:10"}
179
+ {"current_steps": 179, "total_steps": 1235, "loss": 1.1068, "lr": 3.975860879481514e-05, "epoch": 0.7246963562753036, "percentage": 14.49, "elapsed_time": "3:00:53", "remaining_time": "17:47:12"}
180
+ {"current_steps": 180, "total_steps": 1235, "loss": 1.1408, "lr": 3.974976965008833e-05, "epoch": 0.728744939271255, "percentage": 14.57, "elapsed_time": "3:01:54", "remaining_time": "17:46:10"}
181
+ {"current_steps": 181, "total_steps": 1235, "loss": 1.1237, "lr": 3.9740772586729674e-05, "epoch": 0.7327935222672065, "percentage": 14.66, "elapsed_time": "3:02:55", "remaining_time": "17:45:09"}
182
+ {"current_steps": 182, "total_steps": 1235, "loss": 1.1299, "lr": 3.973161767667946e-05, "epoch": 0.7368421052631579, "percentage": 14.74, "elapsed_time": "3:03:55", "remaining_time": "17:44:06"}
183
+ {"current_steps": 183, "total_steps": 1235, "loss": 1.1251, "lr": 3.972230499314009e-05, "epoch": 0.7408906882591093, "percentage": 14.82, "elapsed_time": "3:04:55", "remaining_time": "17:43:03"}
184
+ {"current_steps": 184, "total_steps": 1235, "loss": 1.0596, "lr": 3.9712834610575545e-05, "epoch": 0.7449392712550608, "percentage": 14.9, "elapsed_time": "3:05:55", "remaining_time": "17:42:01"}
185
+ {"current_steps": 185, "total_steps": 1235, "loss": 1.1473, "lr": 3.9703206604710746e-05, "epoch": 0.7489878542510121, "percentage": 14.98, "elapsed_time": "3:06:56", "remaining_time": "17:41:01"}
186
+ {"current_steps": 186, "total_steps": 1235, "loss": 1.0998, "lr": 3.969342105253098e-05, "epoch": 0.7530364372469636, "percentage": 15.06, "elapsed_time": "3:07:57", "remaining_time": "17:40:00"}
187
+ {"current_steps": 187, "total_steps": 1235, "loss": 1.1439, "lr": 3.9683478032281246e-05, "epoch": 0.757085020242915, "percentage": 15.14, "elapsed_time": "3:08:57", "remaining_time": "17:38:57"}
188
+ {"current_steps": 188, "total_steps": 1235, "loss": 1.0833, "lr": 3.967337762346568e-05, "epoch": 0.7611336032388664, "percentage": 15.22, "elapsed_time": "3:09:57", "remaining_time": "17:37:53"}
189
+ {"current_steps": 189, "total_steps": 1235, "loss": 1.1117, "lr": 3.9663119906846885e-05, "epoch": 0.7651821862348178, "percentage": 15.3, "elapsed_time": "3:10:57", "remaining_time": "17:36:49"}
190
+ {"current_steps": 190, "total_steps": 1235, "loss": 1.0639, "lr": 3.965270496444528e-05, "epoch": 0.7692307692307693, "percentage": 15.38, "elapsed_time": "3:11:57", "remaining_time": "17:35:48"}
191
+ {"current_steps": 191, "total_steps": 1235, "loss": 1.1002, "lr": 3.9642132879538465e-05, "epoch": 0.7732793522267206, "percentage": 15.47, "elapsed_time": "3:12:58", "remaining_time": "17:34:45"}
192
+ {"current_steps": 192, "total_steps": 1235, "loss": 1.0961, "lr": 3.9631403736660566e-05, "epoch": 0.7773279352226721, "percentage": 15.55, "elapsed_time": "3:13:58", "remaining_time": "17:33:44"}
193
+ {"current_steps": 193, "total_steps": 1235, "loss": 1.1088, "lr": 3.962051762160151e-05, "epoch": 0.7813765182186235, "percentage": 15.63, "elapsed_time": "3:14:59", "remaining_time": "17:32:43"}
194
+ {"current_steps": 194, "total_steps": 1235, "loss": 1.0506, "lr": 3.960947462140638e-05, "epoch": 0.7854251012145749, "percentage": 15.71, "elapsed_time": "3:15:59", "remaining_time": "17:31:43"}
195
+ {"current_steps": 195, "total_steps": 1235, "loss": 1.0767, "lr": 3.959827482437472e-05, "epoch": 0.7894736842105263, "percentage": 15.79, "elapsed_time": "3:17:00", "remaining_time": "17:30:43"}
196
+ {"current_steps": 196, "total_steps": 1235, "loss": 1.1475, "lr": 3.958691832005981e-05, "epoch": 0.7935222672064778, "percentage": 15.87, "elapsed_time": "3:18:01", "remaining_time": "17:29:43"}
197
+ {"current_steps": 197, "total_steps": 1235, "loss": 1.0918, "lr": 3.9575405199267944e-05, "epoch": 0.7975708502024291, "percentage": 15.95, "elapsed_time": "3:19:02", "remaining_time": "17:28:46"}
198
+ {"current_steps": 198, "total_steps": 1235, "loss": 1.127, "lr": 3.956373555405774e-05, "epoch": 0.8016194331983806, "percentage": 16.03, "elapsed_time": "3:20:02", "remaining_time": "17:27:42"}
199
+ {"current_steps": 199, "total_steps": 1235, "loss": 1.1027, "lr": 3.955190947773937e-05, "epoch": 0.805668016194332, "percentage": 16.11, "elapsed_time": "3:21:03", "remaining_time": "17:26:42"}
200
+ {"current_steps": 200, "total_steps": 1235, "loss": 1.1552, "lr": 3.9539927064873824e-05, "epoch": 0.8097165991902834, "percentage": 16.19, "elapsed_time": "3:22:03", "remaining_time": "17:25:38"}
201
+ {"current_steps": 201, "total_steps": 1235, "loss": 1.114, "lr": 3.952778841127214e-05, "epoch": 0.8137651821862348, "percentage": 16.28, "elapsed_time": "3:23:03", "remaining_time": "17:24:37"}
202
+ {"current_steps": 202, "total_steps": 1235, "loss": 1.0884, "lr": 3.95154936139947e-05, "epoch": 0.8178137651821862, "percentage": 16.36, "elapsed_time": "3:24:03", "remaining_time": "17:23:29"}
203
+ {"current_steps": 203, "total_steps": 1235, "loss": 1.0743, "lr": 3.950304277135034e-05, "epoch": 0.8218623481781376, "percentage": 16.44, "elapsed_time": "3:25:02", "remaining_time": "17:22:23"}
204
+ {"current_steps": 204, "total_steps": 1235, "loss": 1.1475, "lr": 3.94904359828957e-05, "epoch": 0.8259109311740891, "percentage": 16.52, "elapsed_time": "3:26:02", "remaining_time": "17:21:21"}
205
+ {"current_steps": 205, "total_steps": 1235, "loss": 1.1091, "lr": 3.94776733494343e-05, "epoch": 0.8299595141700404, "percentage": 16.6, "elapsed_time": "3:27:03", "remaining_time": "17:20:20"}
206
+ {"current_steps": 206, "total_steps": 1235, "loss": 1.1003, "lr": 3.9464754973015826e-05, "epoch": 0.8340080971659919, "percentage": 16.68, "elapsed_time": "3:28:03", "remaining_time": "17:19:16"}
207
+ {"current_steps": 207, "total_steps": 1235, "loss": 1.0717, "lr": 3.9451680956935275e-05, "epoch": 0.8380566801619433, "percentage": 16.76, "elapsed_time": "3:29:04", "remaining_time": "17:18:18"}
208
+ {"current_steps": 208, "total_steps": 1235, "loss": 1.0818, "lr": 3.943845140573213e-05, "epoch": 0.8421052631578947, "percentage": 16.84, "elapsed_time": "3:30:05", "remaining_time": "17:17:19"}
209
+ {"current_steps": 209, "total_steps": 1235, "loss": 1.091, "lr": 3.942506642518952e-05, "epoch": 0.8461538461538461, "percentage": 16.92, "elapsed_time": "3:31:05", "remaining_time": "17:16:15"}
210
+ {"current_steps": 210, "total_steps": 1235, "loss": 1.072, "lr": 3.9411526122333396e-05, "epoch": 0.8502024291497976, "percentage": 17.0, "elapsed_time": "3:32:06", "remaining_time": "17:15:18"}
211
+ {"current_steps": 211, "total_steps": 1235, "loss": 1.0768, "lr": 3.939783060543167e-05, "epoch": 0.854251012145749, "percentage": 17.09, "elapsed_time": "3:33:06", "remaining_time": "17:14:15"}
212
+ {"current_steps": 212, "total_steps": 1235, "loss": 1.057, "lr": 3.938397998399333e-05, "epoch": 0.8582995951417004, "percentage": 17.17, "elapsed_time": "3:34:07", "remaining_time": "17:13:16"}
213
+ {"current_steps": 213, "total_steps": 1235, "loss": 1.0888, "lr": 3.936997436876756e-05, "epoch": 0.8623481781376519, "percentage": 17.25, "elapsed_time": "3:35:07", "remaining_time": "17:12:12"}
214
+ {"current_steps": 214, "total_steps": 1235, "loss": 1.088, "lr": 3.935581387174289e-05, "epoch": 0.8663967611336032, "percentage": 17.33, "elapsed_time": "3:36:07", "remaining_time": "17:11:10"}
215
+ {"current_steps": 215, "total_steps": 1235, "loss": 1.1216, "lr": 3.9341498606146295e-05, "epoch": 0.8704453441295547, "percentage": 17.41, "elapsed_time": "3:37:08", "remaining_time": "17:10:08"}
216
+ {"current_steps": 216, "total_steps": 1235, "loss": 1.0607, "lr": 3.932702868644224e-05, "epoch": 0.8744939271255061, "percentage": 17.49, "elapsed_time": "3:38:09", "remaining_time": "17:09:09"}
217
+ {"current_steps": 217, "total_steps": 1235, "loss": 1.0977, "lr": 3.931240422833181e-05, "epoch": 0.8785425101214575, "percentage": 17.57, "elapsed_time": "3:39:09", "remaining_time": "17:08:07"}
218
+ {"current_steps": 218, "total_steps": 1235, "loss": 1.0937, "lr": 3.9297625348751806e-05, "epoch": 0.8825910931174089, "percentage": 17.65, "elapsed_time": "3:40:09", "remaining_time": "17:07:06"}
219
+ {"current_steps": 219, "total_steps": 1235, "loss": 1.0804, "lr": 3.9282692165873744e-05, "epoch": 0.8866396761133604, "percentage": 17.73, "elapsed_time": "3:41:10", "remaining_time": "17:06:06"}
220
+ {"current_steps": 220, "total_steps": 1235, "loss": 1.1184, "lr": 3.9267604799102945e-05, "epoch": 0.8906882591093117, "percentage": 17.81, "elapsed_time": "3:42:10", "remaining_time": "17:05:01"}
221
+ {"current_steps": 221, "total_steps": 1235, "loss": 1.0918, "lr": 3.9252363369077615e-05, "epoch": 0.8947368421052632, "percentage": 17.89, "elapsed_time": "3:43:11", "remaining_time": "17:04:05"}
222
+ {"current_steps": 222, "total_steps": 1235, "loss": 1.1098, "lr": 3.9236967997667796e-05, "epoch": 0.8987854251012146, "percentage": 17.98, "elapsed_time": "3:44:12", "remaining_time": "17:03:04"}
223
+ {"current_steps": 223, "total_steps": 1235, "loss": 1.1341, "lr": 3.9221418807974496e-05, "epoch": 0.902834008097166, "percentage": 18.06, "elapsed_time": "3:45:12", "remaining_time": "17:01:59"}
224
+ {"current_steps": 224, "total_steps": 1235, "loss": 1.0833, "lr": 3.92057159243286e-05, "epoch": 0.9068825910931174, "percentage": 18.14, "elapsed_time": "3:46:12", "remaining_time": "17:00:56"}
225
+ {"current_steps": 225, "total_steps": 1235, "loss": 1.087, "lr": 3.9189859472289956e-05, "epoch": 0.9109311740890689, "percentage": 18.22, "elapsed_time": "3:47:12", "remaining_time": "16:59:55"}
226
+ {"current_steps": 226, "total_steps": 1235, "loss": 1.0873, "lr": 3.9173849578646324e-05, "epoch": 0.9149797570850202, "percentage": 18.3, "elapsed_time": "3:48:13", "remaining_time": "16:58:54"}
227
+ {"current_steps": 227, "total_steps": 1235, "loss": 1.0678, "lr": 3.9157686371412395e-05, "epoch": 0.9190283400809717, "percentage": 18.38, "elapsed_time": "3:49:13", "remaining_time": "16:57:51"}
228
+ {"current_steps": 228, "total_steps": 1235, "loss": 1.0894, "lr": 3.914136997982874e-05, "epoch": 0.9230769230769231, "percentage": 18.46, "elapsed_time": "3:50:13", "remaining_time": "16:56:49"}
229
+ {"current_steps": 229, "total_steps": 1235, "loss": 1.0862, "lr": 3.912490053436079e-05, "epoch": 0.9271255060728745, "percentage": 18.54, "elapsed_time": "3:51:13", "remaining_time": "16:55:48"}
230
+ {"current_steps": 230, "total_steps": 1235, "loss": 1.1167, "lr": 3.9108278166697805e-05, "epoch": 0.9311740890688259, "percentage": 18.62, "elapsed_time": "3:52:14", "remaining_time": "16:54:46"}
231
+ {"current_steps": 231, "total_steps": 1235, "loss": 1.0372, "lr": 3.909150300975178e-05, "epoch": 0.9352226720647774, "percentage": 18.7, "elapsed_time": "3:53:14", "remaining_time": "16:53:46"}
232
+ {"current_steps": 232, "total_steps": 1235, "loss": 1.1427, "lr": 3.907457519765642e-05, "epoch": 0.9392712550607287, "percentage": 18.79, "elapsed_time": "3:54:15", "remaining_time": "16:52:43"}
233
+ {"current_steps": 233, "total_steps": 1235, "loss": 1.0559, "lr": 3.905749486576607e-05, "epoch": 0.9433198380566802, "percentage": 18.87, "elapsed_time": "3:55:15", "remaining_time": "16:51:43"}
234
+ {"current_steps": 234, "total_steps": 1235, "loss": 1.1228, "lr": 3.90402621506546e-05, "epoch": 0.9473684210526315, "percentage": 18.95, "elapsed_time": "3:56:16", "remaining_time": "16:50:42"}
235
+ {"current_steps": 235, "total_steps": 1235, "loss": 1.0954, "lr": 3.902287719011435e-05, "epoch": 0.951417004048583, "percentage": 19.03, "elapsed_time": "3:57:17", "remaining_time": "16:49:43"}
236
+ {"current_steps": 236, "total_steps": 1235, "loss": 1.0742, "lr": 3.900534012315499e-05, "epoch": 0.9554655870445344, "percentage": 19.11, "elapsed_time": "3:58:17", "remaining_time": "16:48:41"}
237
+ {"current_steps": 237, "total_steps": 1235, "loss": 1.0861, "lr": 3.8987651090002454e-05, "epoch": 0.9595141700404858, "percentage": 19.19, "elapsed_time": "3:59:17", "remaining_time": "16:47:39"}
238
+ {"current_steps": 238, "total_steps": 1235, "loss": 1.1021, "lr": 3.896981023209777e-05, "epoch": 0.9635627530364372, "percentage": 19.27, "elapsed_time": "4:00:17", "remaining_time": "16:46:36"}
239
+ {"current_steps": 239, "total_steps": 1235, "loss": 1.0665, "lr": 3.8951817692095966e-05, "epoch": 0.9676113360323887, "percentage": 19.35, "elapsed_time": "4:01:17", "remaining_time": "16:45:34"}
240
+ {"current_steps": 240, "total_steps": 1235, "loss": 1.0595, "lr": 3.893367361386491e-05, "epoch": 0.97165991902834, "percentage": 19.43, "elapsed_time": "4:02:18", "remaining_time": "16:44:32"}
241
+ {"current_steps": 241, "total_steps": 1235, "loss": 1.0709, "lr": 3.891537814248417e-05, "epoch": 0.9757085020242915, "percentage": 19.51, "elapsed_time": "4:03:18", "remaining_time": "16:43:31"}
242
+ {"current_steps": 242, "total_steps": 1235, "loss": 1.0652, "lr": 3.889693142424384e-05, "epoch": 0.979757085020243, "percentage": 19.6, "elapsed_time": "4:04:19", "remaining_time": "16:42:33"}
243
+ {"current_steps": 243, "total_steps": 1235, "loss": 1.101, "lr": 3.8878333606643405e-05, "epoch": 0.9838056680161943, "percentage": 19.68, "elapsed_time": "4:05:20", "remaining_time": "16:41:31"}
244
+ {"current_steps": 244, "total_steps": 1235, "loss": 1.087, "lr": 3.885958483839049e-05, "epoch": 0.9878542510121457, "percentage": 19.76, "elapsed_time": "4:06:20", "remaining_time": "16:40:31"}
245
+ {"current_steps": 245, "total_steps": 1235, "loss": 1.1126, "lr": 3.8840685269399786e-05, "epoch": 0.9919028340080972, "percentage": 19.84, "elapsed_time": "4:07:20", "remaining_time": "16:39:29"}
246
+ {"current_steps": 246, "total_steps": 1235, "loss": 1.1316, "lr": 3.882163505079171e-05, "epoch": 0.9959514170040485, "percentage": 19.92, "elapsed_time": "4:08:21", "remaining_time": "16:38:27"}
247
+ {"current_steps": 247, "total_steps": 1235, "loss": 1.0673, "lr": 3.880243433489132e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "4:09:21", "remaining_time": "16:37:27"}
248
+ {"current_steps": 248, "total_steps": 1235, "loss": 1.0415, "lr": 3.878308327522702e-05, "epoch": 1.0040485829959513, "percentage": 20.08, "elapsed_time": "4:11:10", "remaining_time": "16:39:39"}
249
+ {"current_steps": 249, "total_steps": 1235, "loss": 1.0844, "lr": 3.876358202652936e-05, "epoch": 1.008097165991903, "percentage": 20.16, "elapsed_time": "4:12:10", "remaining_time": "16:38:35"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859b1cfd68c79fbf225ac7dac8fd1c90e02557efd123d64ec5cfaa0b802ef8f7
3
+ size 7160