Linksome commited on
Commit
44a97c5
·
verified ·
1 Parent(s): ff30b38

Upload folder using huggingface_hub

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
+ checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-180/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.50.0",
37
+ "use_cache": false,
38
+ "vocab_size": 128256
39
+ }
checkpoint-180/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.50.0"
12
+ }
checkpoint-180/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0faf0d34746af404d69c29ac5822988c2f338c31c91928ff9bf103996810cba5
3
+ size 4976698672
checkpoint-180/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d54fed3ff68d5a625147aee957ee7d2763b2d1fb38968d35323b7eff1c43652
3
+ size 4999802720
checkpoint-180/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c100e8122ad90bed2b4b91f84e1f25a2808655f311df7742756c80dcda24f4b7
3
+ size 4915916176
checkpoint-180/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:784dd7edb5422b5c2db29917bcd384500c16ddac6e130a419dad8ad9756346a3
3
+ size 1168138808
checkpoint-180/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
+ }
checkpoint-180/special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
checkpoint-180/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-180/tokenizer_config.json ADDED
@@ -0,0 +1,2069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "additional_special_tokens": [
2053
+ "<|eom_id|>"
2054
+ ],
2055
+ "bos_token": "<|begin_of_text|>",
2056
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2057
+ "clean_up_tokenization_spaces": true,
2058
+ "eos_token": "<|eot_id|>",
2059
+ "extra_special_tokens": {},
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 131072,
2065
+ "pad_token": "<|eot_id|>",
2066
+ "padding_side": "right",
2067
+ "split_special_tokens": false,
2068
+ "tokenizer_class": "PreTrainedTokenizer"
2069
+ }
checkpoint-180/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140b713838edaf6f3a96dd6bbdc90a5d1b0a1cbcbd986c0b9b69d98887cd754e
3
+ size 8017
trainer_log.jsonl ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 180, "loss": 1.8592, "lr": 1.9998476951563914e-05, "epoch": 0.02768166089965398, "percentage": 0.56, "elapsed_time": "0:00:25", "remaining_time": "1:16:29", "throughput": 10224.8, "total_tokens": 262144}
2
+ {"current_steps": 2, "total_steps": 180, "loss": 2.1203, "lr": 1.999390827019096e-05, "epoch": 0.05536332179930796, "percentage": 1.11, "elapsed_time": "0:00:50", "remaining_time": "1:14:22", "throughput": 10455.26, "total_tokens": 524288}
3
+ {"current_steps": 3, "total_steps": 180, "loss": 1.8033, "lr": 1.9986295347545738e-05, "epoch": 0.08304498269896193, "percentage": 1.67, "elapsed_time": "0:01:14", "remaining_time": "1:12:50", "throughput": 10615.83, "total_tokens": 786432}
4
+ {"current_steps": 4, "total_steps": 180, "loss": 1.6269, "lr": 1.9975640502598243e-05, "epoch": 0.11072664359861592, "percentage": 2.22, "elapsed_time": "0:01:38", "remaining_time": "1:11:54", "throughput": 10694.22, "total_tokens": 1048576}
5
+ {"current_steps": 5, "total_steps": 180, "loss": 1.5461, "lr": 1.9961946980917457e-05, "epoch": 0.1384083044982699, "percentage": 2.78, "elapsed_time": "0:02:01", "remaining_time": "1:11:09", "throughput": 10744.09, "total_tokens": 1310720}
6
+ {"current_steps": 6, "total_steps": 180, "loss": 1.4485, "lr": 1.9945218953682736e-05, "epoch": 0.16608996539792387, "percentage": 3.33, "elapsed_time": "0:02:26", "remaining_time": "1:10:34", "throughput": 10771.8, "total_tokens": 1572864}
7
+ {"current_steps": 7, "total_steps": 180, "loss": 1.3684, "lr": 1.9925461516413224e-05, "epoch": 0.19377162629757785, "percentage": 3.89, "elapsed_time": "0:02:50", "remaining_time": "1:10:01", "throughput": 10793.69, "total_tokens": 1835008}
8
+ {"current_steps": 8, "total_steps": 180, "loss": 1.2882, "lr": 1.9902680687415704e-05, "epoch": 0.22145328719723184, "percentage": 4.44, "elapsed_time": "0:03:13", "remaining_time": "1:09:30", "throughput": 10811.13, "total_tokens": 2097152}
9
+ {"current_steps": 9, "total_steps": 180, "loss": 1.2556, "lr": 1.9876883405951378e-05, "epoch": 0.2491349480968858, "percentage": 5.0, "elapsed_time": "0:03:37", "remaining_time": "1:09:01", "throughput": 10824.04, "total_tokens": 2359296}
10
+ {"current_steps": 10, "total_steps": 180, "loss": 1.2231, "lr": 1.9848077530122083e-05, "epoch": 0.2768166089965398, "percentage": 5.56, "elapsed_time": "0:04:02", "remaining_time": "1:08:34", "throughput": 10832.04, "total_tokens": 2621440}
11
+ {"current_steps": 11, "total_steps": 180, "loss": 1.1749, "lr": 1.9816271834476642e-05, "epoch": 0.3044982698961938, "percentage": 6.11, "elapsed_time": "0:04:25", "remaining_time": "1:08:06", "throughput": 10841.23, "total_tokens": 2883584}
12
+ {"current_steps": 12, "total_steps": 180, "loss": 1.139, "lr": 1.9781476007338058e-05, "epoch": 0.33217993079584773, "percentage": 6.67, "elapsed_time": "0:04:50", "remaining_time": "1:07:40", "throughput": 10847.31, "total_tokens": 3145728}
13
+ {"current_steps": 13, "total_steps": 180, "loss": 1.0982, "lr": 1.9743700647852356e-05, "epoch": 0.35986159169550175, "percentage": 7.22, "elapsed_time": "0:05:14", "remaining_time": "1:07:13", "throughput": 10853.05, "total_tokens": 3407872}
14
+ {"current_steps": 14, "total_steps": 180, "loss": 1.0773, "lr": 1.9702957262759964e-05, "epoch": 0.3875432525951557, "percentage": 7.78, "elapsed_time": "0:05:38", "remaining_time": "1:06:48", "throughput": 10855.46, "total_tokens": 3670016}
15
+ {"current_steps": 15, "total_steps": 180, "loss": 1.0514, "lr": 1.9659258262890683e-05, "epoch": 0.41522491349480967, "percentage": 8.33, "elapsed_time": "0:06:02", "remaining_time": "1:06:22", "throughput": 10861.6, "total_tokens": 3932160}
16
+ {"current_steps": 16, "total_steps": 180, "loss": 1.0428, "lr": 1.961261695938319e-05, "epoch": 0.4429065743944637, "percentage": 8.89, "elapsed_time": "0:06:25", "remaining_time": "1:05:56", "throughput": 10867.28, "total_tokens": 4194304}
17
+ {"current_steps": 17, "total_steps": 180, "loss": 1.026, "lr": 1.9563047559630356e-05, "epoch": 0.47058823529411764, "percentage": 9.44, "elapsed_time": "0:06:49", "remaining_time": "1:05:30", "throughput": 10869.97, "total_tokens": 4456448}
18
+ {"current_steps": 18, "total_steps": 180, "loss": 1.0026, "lr": 1.9510565162951538e-05, "epoch": 0.4982698961937716, "percentage": 10.0, "elapsed_time": "0:07:13", "remaining_time": "1:05:05", "throughput": 10873.84, "total_tokens": 4718592}
19
+ {"current_steps": 19, "total_steps": 180, "loss": 0.9732, "lr": 1.945518575599317e-05, "epoch": 0.5259515570934256, "percentage": 10.56, "elapsed_time": "0:07:37", "remaining_time": "1:04:40", "throughput": 10876.54, "total_tokens": 4980736}
20
+ {"current_steps": 20, "total_steps": 180, "loss": 0.9594, "lr": 1.9396926207859085e-05, "epoch": 0.5536332179930796, "percentage": 11.11, "elapsed_time": "0:08:01", "remaining_time": "1:04:15", "throughput": 10878.34, "total_tokens": 5242880}
21
+ {"current_steps": 21, "total_steps": 180, "loss": 0.9601, "lr": 1.9335804264972018e-05, "epoch": 0.5813148788927336, "percentage": 11.67, "elapsed_time": "0:08:25", "remaining_time": "1:03:51", "throughput": 10879.87, "total_tokens": 5505024}
22
+ {"current_steps": 22, "total_steps": 180, "loss": 0.9569, "lr": 1.9271838545667876e-05, "epoch": 0.6089965397923875, "percentage": 12.22, "elapsed_time": "0:08:50", "remaining_time": "1:03:26", "throughput": 10881.35, "total_tokens": 5767168}
23
+ {"current_steps": 23, "total_steps": 180, "loss": 0.9397, "lr": 1.9205048534524405e-05, "epoch": 0.6366782006920415, "percentage": 12.78, "elapsed_time": "0:09:14", "remaining_time": "1:03:01", "throughput": 10882.81, "total_tokens": 6029312}
24
+ {"current_steps": 24, "total_steps": 180, "loss": 0.9337, "lr": 1.913545457642601e-05, "epoch": 0.6643598615916955, "percentage": 13.33, "elapsed_time": "0:09:38", "remaining_time": "1:02:37", "throughput": 10884.69, "total_tokens": 6291456}
25
+ {"current_steps": 25, "total_steps": 180, "loss": 0.8997, "lr": 1.9063077870366504e-05, "epoch": 0.6920415224913494, "percentage": 13.89, "elapsed_time": "0:10:02", "remaining_time": "1:02:13", "throughput": 10884.0, "total_tokens": 6553600}
26
+ {"current_steps": 26, "total_steps": 180, "loss": 0.8547, "lr": 1.8987940462991673e-05, "epoch": 0.7197231833910035, "percentage": 14.44, "elapsed_time": "0:10:26", "remaining_time": "1:01:48", "throughput": 10885.52, "total_tokens": 6815744}
27
+ {"current_steps": 27, "total_steps": 180, "loss": 0.9092, "lr": 1.891006524188368e-05, "epoch": 0.7474048442906575, "percentage": 15.0, "elapsed_time": "0:10:50", "remaining_time": "1:01:24", "throughput": 10886.72, "total_tokens": 7077888}
28
+ {"current_steps": 28, "total_steps": 180, "loss": 0.8799, "lr": 1.8829475928589272e-05, "epoch": 0.7750865051903114, "percentage": 15.56, "elapsed_time": "0:11:14", "remaining_time": "1:00:59", "throughput": 10887.1, "total_tokens": 7340032}
29
+ {"current_steps": 29, "total_steps": 180, "loss": 0.8879, "lr": 1.874619707139396e-05, "epoch": 0.8027681660899654, "percentage": 16.11, "elapsed_time": "0:11:38", "remaining_time": "1:00:35", "throughput": 10888.43, "total_tokens": 7602176}
30
+ {"current_steps": 30, "total_steps": 180, "loss": 0.8608, "lr": 1.866025403784439e-05, "epoch": 0.8304498269896193, "percentage": 16.67, "elapsed_time": "0:12:02", "remaining_time": "1:00:11", "throughput": 10889.36, "total_tokens": 7864320}
31
+ {"current_steps": 31, "total_steps": 180, "loss": 0.879, "lr": 1.8571673007021124e-05, "epoch": 0.8581314878892734, "percentage": 17.22, "elapsed_time": "0:12:26", "remaining_time": "0:59:46", "throughput": 10889.5, "total_tokens": 8126464}
32
+ {"current_steps": 32, "total_steps": 180, "loss": 0.867, "lr": 1.848048096156426e-05, "epoch": 0.8858131487889274, "percentage": 17.78, "elapsed_time": "0:12:50", "remaining_time": "0:59:22", "throughput": 10891.41, "total_tokens": 8388608}
33
+ {"current_steps": 33, "total_steps": 180, "loss": 0.8694, "lr": 1.8386705679454243e-05, "epoch": 0.9134948096885813, "percentage": 18.33, "elapsed_time": "0:13:14", "remaining_time": "0:58:57", "throughput": 10891.98, "total_tokens": 8650752}
34
+ {"current_steps": 34, "total_steps": 180, "loss": 0.8254, "lr": 1.8290375725550417e-05, "epoch": 0.9411764705882353, "percentage": 18.89, "elapsed_time": "0:13:38", "remaining_time": "0:58:33", "throughput": 10892.19, "total_tokens": 8912896}
35
+ {"current_steps": 35, "total_steps": 180, "loss": 0.8375, "lr": 1.819152044288992e-05, "epoch": 0.9688581314878892, "percentage": 19.44, "elapsed_time": "0:14:02", "remaining_time": "0:58:09", "throughput": 10893.22, "total_tokens": 9175040}
36
+ {"current_steps": 36, "total_steps": 180, "loss": 0.8376, "lr": 1.8090169943749477e-05, "epoch": 0.9965397923875432, "percentage": 20.0, "elapsed_time": "0:14:26", "remaining_time": "0:57:45", "throughput": 10892.36, "total_tokens": 9437184}
37
+ {"current_steps": 37, "total_steps": 180, "loss": 0.8218, "lr": 1.798635510047293e-05, "epoch": 1.0, "percentage": 20.56, "elapsed_time": "0:14:29", "remaining_time": "0:56:00", "throughput": 10890.98, "total_tokens": 9469952}
38
+ {"current_steps": 38, "total_steps": 180, "loss": 0.6509, "lr": 1.788010753606722e-05, "epoch": 1.027681660899654, "percentage": 21.11, "elapsed_time": "0:14:53", "remaining_time": "0:55:39", "throughput": 10890.96, "total_tokens": 9732096}
39
+ {"current_steps": 39, "total_steps": 180, "loss": 0.6378, "lr": 1.777145961456971e-05, "epoch": 1.055363321799308, "percentage": 21.67, "elapsed_time": "0:15:17", "remaining_time": "0:55:17", "throughput": 10892.0, "total_tokens": 9994240}
40
+ {"current_steps": 40, "total_steps": 180, "loss": 0.6158, "lr": 1.766044443118978e-05, "epoch": 1.0830449826989619, "percentage": 22.22, "elapsed_time": "0:15:41", "remaining_time": "0:54:55", "throughput": 10892.99, "total_tokens": 10256384}
41
+ {"current_steps": 41, "total_steps": 180, "loss": 0.5967, "lr": 1.7547095802227723e-05, "epoch": 1.1107266435986158, "percentage": 22.78, "elapsed_time": "0:16:05", "remaining_time": "0:54:33", "throughput": 10893.85, "total_tokens": 10518528}
42
+ {"current_steps": 42, "total_steps": 180, "loss": 0.6257, "lr": 1.7431448254773943e-05, "epoch": 1.1384083044982698, "percentage": 23.33, "elapsed_time": "0:16:29", "remaining_time": "0:54:11", "throughput": 10894.32, "total_tokens": 10780672}
43
+ {"current_steps": 43, "total_steps": 180, "loss": 0.5961, "lr": 1.7313537016191706e-05, "epoch": 1.1660899653979238, "percentage": 23.89, "elapsed_time": "0:16:53", "remaining_time": "0:53:49", "throughput": 10895.25, "total_tokens": 11042816}
44
+ {"current_steps": 44, "total_steps": 180, "loss": 0.5876, "lr": 1.7193398003386514e-05, "epoch": 1.193771626297578, "percentage": 24.44, "elapsed_time": "0:17:17", "remaining_time": "0:53:26", "throughput": 10896.27, "total_tokens": 11304960}
45
+ {"current_steps": 45, "total_steps": 180, "loss": 0.5951, "lr": 1.7071067811865477e-05, "epoch": 1.221453287197232, "percentage": 25.0, "elapsed_time": "0:17:41", "remaining_time": "0:53:04", "throughput": 10896.86, "total_tokens": 11567104}
46
+ {"current_steps": 46, "total_steps": 180, "loss": 0.6005, "lr": 1.6946583704589973e-05, "epoch": 1.2491349480968859, "percentage": 25.56, "elapsed_time": "0:18:05", "remaining_time": "0:52:41", "throughput": 10898.05, "total_tokens": 11829248}
47
+ {"current_steps": 47, "total_steps": 180, "loss": 0.5808, "lr": 1.6819983600624986e-05, "epoch": 1.2768166089965398, "percentage": 26.11, "elapsed_time": "0:18:29", "remaining_time": "0:52:19", "throughput": 10898.94, "total_tokens": 12091392}
48
+ {"current_steps": 48, "total_steps": 180, "loss": 0.5859, "lr": 1.6691306063588583e-05, "epoch": 1.3044982698961938, "percentage": 26.67, "elapsed_time": "0:18:53", "remaining_time": "0:51:56", "throughput": 10899.15, "total_tokens": 12353536}
49
+ {"current_steps": 49, "total_steps": 180, "loss": 0.5691, "lr": 1.6560590289905074e-05, "epoch": 1.3321799307958477, "percentage": 27.22, "elapsed_time": "0:19:17", "remaining_time": "0:51:34", "throughput": 10899.07, "total_tokens": 12615680}
50
+ {"current_steps": 50, "total_steps": 180, "loss": 0.5608, "lr": 1.6427876096865394e-05, "epoch": 1.3598615916955017, "percentage": 27.78, "elapsed_time": "0:19:41", "remaining_time": "0:51:11", "throughput": 10900.03, "total_tokens": 12877824}
51
+ {"current_steps": 51, "total_steps": 180, "loss": 0.5701, "lr": 1.6293203910498375e-05, "epoch": 1.3875432525951557, "percentage": 28.33, "elapsed_time": "0:20:05", "remaining_time": "0:50:49", "throughput": 10900.7, "total_tokens": 13139968}
52
+ {"current_steps": 52, "total_steps": 180, "loss": 0.5736, "lr": 1.6156614753256583e-05, "epoch": 1.4152249134948096, "percentage": 28.89, "elapsed_time": "0:20:29", "remaining_time": "0:50:26", "throughput": 10901.14, "total_tokens": 13402112}
53
+ {"current_steps": 53, "total_steps": 180, "loss": 0.571, "lr": 1.6018150231520486e-05, "epoch": 1.4429065743944638, "percentage": 29.44, "elapsed_time": "0:20:53", "remaining_time": "0:50:03", "throughput": 10901.15, "total_tokens": 13664256}
54
+ {"current_steps": 54, "total_steps": 180, "loss": 0.574, "lr": 1.5877852522924733e-05, "epoch": 1.4705882352941178, "percentage": 30.0, "elapsed_time": "0:21:17", "remaining_time": "0:49:40", "throughput": 10901.23, "total_tokens": 13926400}
55
+ {"current_steps": 55, "total_steps": 180, "loss": 0.5643, "lr": 1.573576436351046e-05, "epoch": 1.4982698961937717, "percentage": 30.56, "elapsed_time": "0:21:41", "remaining_time": "0:49:18", "throughput": 10901.4, "total_tokens": 14188544}
56
+ {"current_steps": 56, "total_steps": 180, "loss": 0.5706, "lr": 1.5591929034707468e-05, "epoch": 1.5259515570934257, "percentage": 31.11, "elapsed_time": "0:22:05", "remaining_time": "0:48:55", "throughput": 10901.88, "total_tokens": 14450688}
57
+ {"current_steps": 57, "total_steps": 180, "loss": 0.5587, "lr": 1.5446390350150272e-05, "epoch": 1.5536332179930796, "percentage": 31.67, "elapsed_time": "0:22:29", "remaining_time": "0:48:32", "throughput": 10901.9, "total_tokens": 14712832}
58
+ {"current_steps": 58, "total_steps": 180, "loss": 0.5304, "lr": 1.529919264233205e-05, "epoch": 1.5813148788927336, "percentage": 32.22, "elapsed_time": "0:22:53", "remaining_time": "0:48:09", "throughput": 10902.83, "total_tokens": 14974976}
59
+ {"current_steps": 59, "total_steps": 180, "loss": 0.5462, "lr": 1.5150380749100545e-05, "epoch": 1.6089965397923875, "percentage": 32.78, "elapsed_time": "0:23:17", "remaining_time": "0:47:45", "throughput": 10903.52, "total_tokens": 15237120}
60
+ {"current_steps": 60, "total_steps": 180, "loss": 0.5554, "lr": 1.5000000000000002e-05, "epoch": 1.6366782006920415, "percentage": 33.33, "elapsed_time": "0:23:41", "remaining_time": "0:47:22", "throughput": 10904.36, "total_tokens": 15499264}
61
+ {"current_steps": 61, "total_steps": 180, "loss": 0.5347, "lr": 1.4848096202463373e-05, "epoch": 1.6643598615916955, "percentage": 33.89, "elapsed_time": "0:24:05", "remaining_time": "0:46:59", "throughput": 10905.23, "total_tokens": 15761408}
62
+ {"current_steps": 62, "total_steps": 180, "loss": 0.5615, "lr": 1.469471562785891e-05, "epoch": 1.6920415224913494, "percentage": 34.44, "elapsed_time": "0:24:29", "remaining_time": "0:46:36", "throughput": 10905.71, "total_tokens": 16023552}
63
+ {"current_steps": 63, "total_steps": 180, "loss": 0.5464, "lr": 1.4539904997395468e-05, "epoch": 1.7197231833910034, "percentage": 35.0, "elapsed_time": "0:24:53", "remaining_time": "0:46:13", "throughput": 10906.19, "total_tokens": 16285696}
64
+ {"current_steps": 64, "total_steps": 180, "loss": 0.5494, "lr": 1.4383711467890776e-05, "epoch": 1.7474048442906573, "percentage": 35.56, "elapsed_time": "0:25:17", "remaining_time": "0:45:50", "throughput": 10906.1, "total_tokens": 16547840}
65
+ {"current_steps": 65, "total_steps": 180, "loss": 0.5473, "lr": 1.4226182617406996e-05, "epoch": 1.7750865051903113, "percentage": 36.11, "elapsed_time": "0:25:41", "remaining_time": "0:45:27", "throughput": 10905.49, "total_tokens": 16809984}
66
+ {"current_steps": 66, "total_steps": 180, "loss": 0.5745, "lr": 1.4067366430758004e-05, "epoch": 1.8027681660899653, "percentage": 36.67, "elapsed_time": "0:26:05", "remaining_time": "0:45:03", "throughput": 10905.87, "total_tokens": 17072128}
67
+ {"current_steps": 67, "total_steps": 180, "loss": 0.5478, "lr": 1.3907311284892737e-05, "epoch": 1.8304498269896192, "percentage": 37.22, "elapsed_time": "0:26:29", "remaining_time": "0:44:40", "throughput": 10905.96, "total_tokens": 17334272}
68
+ {"current_steps": 68, "total_steps": 180, "loss": 0.5586, "lr": 1.3746065934159123e-05, "epoch": 1.8581314878892734, "percentage": 37.78, "elapsed_time": "0:26:53", "remaining_time": "0:44:17", "throughput": 10905.99, "total_tokens": 17596416}
69
+ {"current_steps": 69, "total_steps": 180, "loss": 0.5501, "lr": 1.3583679495453e-05, "epoch": 1.8858131487889274, "percentage": 38.33, "elapsed_time": "0:27:17", "remaining_time": "0:43:54", "throughput": 10906.09, "total_tokens": 17858560}
70
+ {"current_steps": 70, "total_steps": 180, "loss": 0.5635, "lr": 1.342020143325669e-05, "epoch": 1.9134948096885813, "percentage": 38.89, "elapsed_time": "0:27:41", "remaining_time": "0:43:30", "throughput": 10906.33, "total_tokens": 18120704}
71
+ {"current_steps": 71, "total_steps": 180, "loss": 0.5479, "lr": 1.3255681544571568e-05, "epoch": 1.9411764705882353, "percentage": 39.44, "elapsed_time": "0:28:05", "remaining_time": "0:43:07", "throughput": 10906.42, "total_tokens": 18382848}
72
+ {"current_steps": 72, "total_steps": 180, "loss": 0.5263, "lr": 1.3090169943749475e-05, "epoch": 1.9688581314878892, "percentage": 40.0, "elapsed_time": "0:28:29", "remaining_time": "0:42:44", "throughput": 10906.95, "total_tokens": 18644992}
73
+ {"current_steps": 73, "total_steps": 180, "loss": 0.534, "lr": 1.2923717047227368e-05, "epoch": 1.9965397923875432, "percentage": 40.56, "elapsed_time": "0:28:53", "remaining_time": "0:42:20", "throughput": 10907.24, "total_tokens": 18907136}
74
+ {"current_steps": 74, "total_steps": 180, "loss": 0.5051, "lr": 1.2756373558169992e-05, "epoch": 2.0, "percentage": 41.11, "elapsed_time": "0:28:56", "remaining_time": "0:41:27", "throughput": 10906.64, "total_tokens": 18939904}
75
+ {"current_steps": 75, "total_steps": 180, "loss": 0.3557, "lr": 1.2588190451025209e-05, "epoch": 2.027681660899654, "percentage": 41.67, "elapsed_time": "0:29:20", "remaining_time": "0:41:04", "throughput": 10906.75, "total_tokens": 19202048}
76
+ {"current_steps": 76, "total_steps": 180, "loss": 0.3365, "lr": 1.2419218955996677e-05, "epoch": 2.055363321799308, "percentage": 42.22, "elapsed_time": "0:29:44", "remaining_time": "0:40:42", "throughput": 10906.78, "total_tokens": 19464192}
77
+ {"current_steps": 77, "total_steps": 180, "loss": 0.3321, "lr": 1.2249510543438652e-05, "epoch": 2.083044982698962, "percentage": 42.78, "elapsed_time": "0:30:08", "remaining_time": "0:40:19", "throughput": 10906.39, "total_tokens": 19726336}
78
+ {"current_steps": 78, "total_steps": 180, "loss": 0.3188, "lr": 1.2079116908177592e-05, "epoch": 2.110726643598616, "percentage": 43.33, "elapsed_time": "0:30:32", "remaining_time": "0:39:56", "throughput": 10906.5, "total_tokens": 19988480}
79
+ {"current_steps": 79, "total_steps": 180, "loss": 0.3047, "lr": 1.190808995376545e-05, "epoch": 2.13840830449827, "percentage": 43.89, "elapsed_time": "0:30:56", "remaining_time": "0:39:33", "throughput": 10906.84, "total_tokens": 20250624}
80
+ {"current_steps": 80, "total_steps": 180, "loss": 0.3122, "lr": 1.1736481776669307e-05, "epoch": 2.1660899653979238, "percentage": 44.44, "elapsed_time": "0:31:20", "remaining_time": "0:39:10", "throughput": 10906.83, "total_tokens": 20512768}
81
+ {"current_steps": 81, "total_steps": 180, "loss": 0.2932, "lr": 1.156434465040231e-05, "epoch": 2.1937716262975777, "percentage": 45.0, "elapsed_time": "0:31:44", "remaining_time": "0:38:48", "throughput": 10906.91, "total_tokens": 20774912}
82
+ {"current_steps": 82, "total_steps": 180, "loss": 0.2965, "lr": 1.1391731009600655e-05, "epoch": 2.2214532871972317, "percentage": 45.56, "elapsed_time": "0:32:08", "remaining_time": "0:38:25", "throughput": 10906.9, "total_tokens": 21037056}
83
+ {"current_steps": 83, "total_steps": 180, "loss": 0.2984, "lr": 1.1218693434051475e-05, "epoch": 2.2491349480968856, "percentage": 46.11, "elapsed_time": "0:32:32", "remaining_time": "0:38:02", "throughput": 10906.88, "total_tokens": 21299200}
84
+ {"current_steps": 84, "total_steps": 180, "loss": 0.3062, "lr": 1.1045284632676535e-05, "epoch": 2.2768166089965396, "percentage": 46.67, "elapsed_time": "0:32:56", "remaining_time": "0:37:39", "throughput": 10906.78, "total_tokens": 21561344}
85
+ {"current_steps": 85, "total_steps": 180, "loss": 0.2817, "lr": 1.0871557427476585e-05, "epoch": 2.304498269896194, "percentage": 47.22, "elapsed_time": "0:33:20", "remaining_time": "0:37:16", "throughput": 10906.71, "total_tokens": 21823488}
86
+ {"current_steps": 86, "total_steps": 180, "loss": 0.2782, "lr": 1.0697564737441254e-05, "epoch": 2.3321799307958475, "percentage": 47.78, "elapsed_time": "0:33:44", "remaining_time": "0:36:53", "throughput": 10906.92, "total_tokens": 22085632}
87
+ {"current_steps": 87, "total_steps": 180, "loss": 0.2788, "lr": 1.0523359562429441e-05, "epoch": 2.359861591695502, "percentage": 48.33, "elapsed_time": "0:34:08", "remaining_time": "0:36:30", "throughput": 10906.97, "total_tokens": 22347776}
88
+ {"current_steps": 88, "total_steps": 180, "loss": 0.2875, "lr": 1.0348994967025012e-05, "epoch": 2.387543252595156, "percentage": 48.89, "elapsed_time": "0:34:32", "remaining_time": "0:36:07", "throughput": 10907.57, "total_tokens": 22609920}
89
+ {"current_steps": 89, "total_steps": 180, "loss": 0.2898, "lr": 1.0174524064372837e-05, "epoch": 2.41522491349481, "percentage": 49.44, "elapsed_time": "0:34:56", "remaining_time": "0:35:44", "throughput": 10907.57, "total_tokens": 22872064}
90
+ {"current_steps": 90, "total_steps": 180, "loss": 0.2814, "lr": 1e-05, "epoch": 2.442906574394464, "percentage": 50.0, "elapsed_time": "0:35:20", "remaining_time": "0:35:20", "throughput": 10907.81, "total_tokens": 23134208}
91
+ {"current_steps": 91, "total_steps": 180, "loss": 0.2962, "lr": 9.825475935627165e-06, "epoch": 2.4705882352941178, "percentage": 50.56, "elapsed_time": "0:35:44", "remaining_time": "0:34:57", "throughput": 10907.69, "total_tokens": 23396352}
92
+ {"current_steps": 92, "total_steps": 180, "loss": 0.2779, "lr": 9.651005032974994e-06, "epoch": 2.4982698961937717, "percentage": 51.11, "elapsed_time": "0:36:08", "remaining_time": "0:34:34", "throughput": 10907.76, "total_tokens": 23658496}
93
+ {"current_steps": 93, "total_steps": 180, "loss": 0.28, "lr": 9.476640437570562e-06, "epoch": 2.5259515570934257, "percentage": 51.67, "elapsed_time": "0:36:33", "remaining_time": "0:34:11", "throughput": 10907.57, "total_tokens": 23920640}
94
+ {"current_steps": 94, "total_steps": 180, "loss": 0.2632, "lr": 9.302435262558748e-06, "epoch": 2.5536332179930796, "percentage": 52.22, "elapsed_time": "0:36:57", "remaining_time": "0:33:48", "throughput": 10907.72, "total_tokens": 24182784}
95
+ {"current_steps": 95, "total_steps": 180, "loss": 0.2901, "lr": 9.128442572523418e-06, "epoch": 2.5813148788927336, "percentage": 52.78, "elapsed_time": "0:37:21", "remaining_time": "0:33:25", "throughput": 10907.83, "total_tokens": 24444928}
96
+ {"current_steps": 96, "total_steps": 180, "loss": 0.2706, "lr": 8.954715367323468e-06, "epoch": 2.6089965397923875, "percentage": 53.33, "elapsed_time": "0:37:45", "remaining_time": "0:33:01", "throughput": 10908.0, "total_tokens": 24707072}
97
+ {"current_steps": 97, "total_steps": 180, "loss": 0.2881, "lr": 8.781306565948528e-06, "epoch": 2.6366782006920415, "percentage": 53.89, "elapsed_time": "0:38:09", "remaining_time": "0:32:38", "throughput": 10908.03, "total_tokens": 24969216}
98
+ {"current_steps": 98, "total_steps": 180, "loss": 0.2758, "lr": 8.60826899039935e-06, "epoch": 2.6643598615916955, "percentage": 54.44, "elapsed_time": "0:38:33", "remaining_time": "0:32:15", "throughput": 10908.13, "total_tokens": 25231360}
99
+ {"current_steps": 99, "total_steps": 180, "loss": 0.2775, "lr": 8.43565534959769e-06, "epoch": 2.6920415224913494, "percentage": 55.0, "elapsed_time": "0:38:57", "remaining_time": "0:31:52", "throughput": 10908.35, "total_tokens": 25493504}
100
+ {"current_steps": 100, "total_steps": 180, "loss": 0.2831, "lr": 8.263518223330698e-06, "epoch": 2.7197231833910034, "percentage": 55.56, "elapsed_time": "0:39:21", "remaining_time": "0:31:28", "throughput": 10908.34, "total_tokens": 25755648}
101
+ {"current_steps": 101, "total_steps": 180, "loss": 0.2587, "lr": 8.091910046234552e-06, "epoch": 2.7474048442906573, "percentage": 56.11, "elapsed_time": "0:39:45", "remaining_time": "0:31:05", "throughput": 10908.17, "total_tokens": 26017792}
102
+ {"current_steps": 102, "total_steps": 180, "loss": 0.2791, "lr": 7.92088309182241e-06, "epoch": 2.7750865051903113, "percentage": 56.67, "elapsed_time": "0:40:09", "remaining_time": "0:30:42", "throughput": 10908.13, "total_tokens": 26279936}
103
+ {"current_steps": 103, "total_steps": 180, "loss": 0.2705, "lr": 7.750489456561351e-06, "epoch": 2.8027681660899653, "percentage": 57.22, "elapsed_time": "0:40:33", "remaining_time": "0:30:18", "throughput": 10908.32, "total_tokens": 26542080}
104
+ {"current_steps": 104, "total_steps": 180, "loss": 0.2837, "lr": 7.580781044003324e-06, "epoch": 2.830449826989619, "percentage": 57.78, "elapsed_time": "0:40:57", "remaining_time": "0:29:55", "throughput": 10908.27, "total_tokens": 26804224}
105
+ {"current_steps": 105, "total_steps": 180, "loss": 0.2569, "lr": 7.411809548974792e-06, "epoch": 2.858131487889273, "percentage": 58.33, "elapsed_time": "0:41:21", "remaining_time": "0:29:32", "throughput": 10908.03, "total_tokens": 27066368}
106
+ {"current_steps": 106, "total_steps": 180, "loss": 0.2798, "lr": 7.243626441830009e-06, "epoch": 2.8858131487889276, "percentage": 58.89, "elapsed_time": "0:41:45", "remaining_time": "0:29:08", "throughput": 10908.31, "total_tokens": 27328512}
107
+ {"current_steps": 107, "total_steps": 180, "loss": 0.2641, "lr": 7.076282952772634e-06, "epoch": 2.913494809688581, "percentage": 59.44, "elapsed_time": "0:42:09", "remaining_time": "0:28:45", "throughput": 10908.25, "total_tokens": 27590656}
108
+ {"current_steps": 108, "total_steps": 180, "loss": 0.2738, "lr": 6.909830056250527e-06, "epoch": 2.9411764705882355, "percentage": 60.0, "elapsed_time": "0:42:33", "remaining_time": "0:28:22", "throughput": 10908.0, "total_tokens": 27852800}
109
+ {"current_steps": 109, "total_steps": 180, "loss": 0.283, "lr": 6.744318455428436e-06, "epoch": 2.968858131487889, "percentage": 60.56, "elapsed_time": "0:42:57", "remaining_time": "0:27:58", "throughput": 10907.89, "total_tokens": 28114944}
110
+ {"current_steps": 110, "total_steps": 180, "loss": 0.2846, "lr": 6.579798566743314e-06, "epoch": 2.9965397923875434, "percentage": 61.11, "elapsed_time": "0:43:21", "remaining_time": "0:27:35", "throughput": 10908.14, "total_tokens": 28377088}
111
+ {"current_steps": 111, "total_steps": 180, "loss": 0.2059, "lr": 6.4163205045469975e-06, "epoch": 3.0, "percentage": 61.67, "elapsed_time": "0:43:24", "remaining_time": "0:26:59", "throughput": 10907.75, "total_tokens": 28409856}
112
+ {"current_steps": 112, "total_steps": 180, "loss": 0.1523, "lr": 6.25393406584088e-06, "epoch": 3.027681660899654, "percentage": 62.22, "elapsed_time": "0:43:48", "remaining_time": "0:26:35", "throughput": 10907.66, "total_tokens": 28672000}
113
+ {"current_steps": 113, "total_steps": 180, "loss": 0.1444, "lr": 6.092688715107265e-06, "epoch": 3.055363321799308, "percentage": 62.78, "elapsed_time": "0:44:12", "remaining_time": "0:26:12", "throughput": 10908.03, "total_tokens": 28934144}
114
+ {"current_steps": 114, "total_steps": 180, "loss": 0.1374, "lr": 5.932633569242e-06, "epoch": 3.083044982698962, "percentage": 63.33, "elapsed_time": "0:44:36", "remaining_time": "0:25:49", "throughput": 10908.12, "total_tokens": 29196288}
115
+ {"current_steps": 115, "total_steps": 180, "loss": 0.1287, "lr": 5.773817382593008e-06, "epoch": 3.110726643598616, "percentage": 63.89, "elapsed_time": "0:45:00", "remaining_time": "0:25:26", "throughput": 10908.34, "total_tokens": 29458432}
116
+ {"current_steps": 116, "total_steps": 180, "loss": 0.1238, "lr": 5.616288532109225e-06, "epoch": 3.13840830449827, "percentage": 64.44, "elapsed_time": "0:45:24", "remaining_time": "0:25:03", "throughput": 10908.4, "total_tokens": 29720576}
117
+ {"current_steps": 117, "total_steps": 180, "loss": 0.1279, "lr": 5.460095002604533e-06, "epoch": 3.1660899653979238, "percentage": 65.0, "elapsed_time": "0:45:48", "remaining_time": "0:24:40", "throughput": 10907.95, "total_tokens": 29982720}
118
+ {"current_steps": 118, "total_steps": 180, "loss": 0.1312, "lr": 5.305284372141095e-06, "epoch": 3.1937716262975777, "percentage": 65.56, "elapsed_time": "0:46:12", "remaining_time": "0:24:16", "throughput": 10908.33, "total_tokens": 30244864}
119
+ {"current_steps": 119, "total_steps": 180, "loss": 0.1295, "lr": 5.151903797536631e-06, "epoch": 3.2214532871972317, "percentage": 66.11, "elapsed_time": "0:46:36", "remaining_time": "0:23:53", "throughput": 10908.53, "total_tokens": 30507008}
120
+ {"current_steps": 120, "total_steps": 180, "loss": 0.1302, "lr": 5.000000000000003e-06, "epoch": 3.2491349480968856, "percentage": 66.67, "elapsed_time": "0:47:00", "remaining_time": "0:23:30", "throughput": 10908.35, "total_tokens": 30769152}
121
+ {"current_steps": 121, "total_steps": 180, "loss": 0.1201, "lr": 4.849619250899458e-06, "epoch": 3.2768166089965396, "percentage": 67.22, "elapsed_time": "0:47:24", "remaining_time": "0:23:07", "throughput": 10908.44, "total_tokens": 31031296}
122
+ {"current_steps": 122, "total_steps": 180, "loss": 0.1259, "lr": 4.700807357667953e-06, "epoch": 3.304498269896194, "percentage": 67.78, "elapsed_time": "0:47:48", "remaining_time": "0:22:43", "throughput": 10908.81, "total_tokens": 31293440}
123
+ {"current_steps": 123, "total_steps": 180, "loss": 0.113, "lr": 4.5536096498497295e-06, "epoch": 3.3321799307958475, "percentage": 68.33, "elapsed_time": "0:48:12", "remaining_time": "0:22:20", "throughput": 10908.82, "total_tokens": 31555584}
124
+ {"current_steps": 124, "total_steps": 180, "loss": 0.1154, "lr": 4.408070965292534e-06, "epoch": 3.359861591695502, "percentage": 68.89, "elapsed_time": "0:48:36", "remaining_time": "0:21:57", "throughput": 10908.83, "total_tokens": 31817728}
125
+ {"current_steps": 125, "total_steps": 180, "loss": 0.1208, "lr": 4.264235636489542e-06, "epoch": 3.387543252595156, "percentage": 69.44, "elapsed_time": "0:49:00", "remaining_time": "0:21:33", "throughput": 10908.89, "total_tokens": 32079872}
126
+ {"current_steps": 126, "total_steps": 180, "loss": 0.1175, "lr": 4.12214747707527e-06, "epoch": 3.41522491349481, "percentage": 70.0, "elapsed_time": "0:49:24", "remaining_time": "0:21:10", "throughput": 10908.86, "total_tokens": 32342016}
127
+ {"current_steps": 127, "total_steps": 180, "loss": 0.1223, "lr": 3.981849768479516e-06, "epoch": 3.442906574394464, "percentage": 70.56, "elapsed_time": "0:49:48", "remaining_time": "0:20:47", "throughput": 10908.89, "total_tokens": 32604160}
128
+ {"current_steps": 128, "total_steps": 180, "loss": 0.119, "lr": 3.8433852467434175e-06, "epoch": 3.4705882352941178, "percentage": 71.11, "elapsed_time": "0:50:12", "remaining_time": "0:20:23", "throughput": 10908.76, "total_tokens": 32866304}
129
+ {"current_steps": 129, "total_steps": 180, "loss": 0.1218, "lr": 3.7067960895016277e-06, "epoch": 3.4982698961937717, "percentage": 71.67, "elapsed_time": "0:50:36", "remaining_time": "0:20:00", "throughput": 10908.84, "total_tokens": 33128448}
130
+ {"current_steps": 130, "total_steps": 180, "loss": 0.1175, "lr": 3.5721239031346067e-06, "epoch": 3.5259515570934257, "percentage": 72.22, "elapsed_time": "0:51:00", "remaining_time": "0:19:37", "throughput": 10908.75, "total_tokens": 33390592}
131
+ {"current_steps": 131, "total_steps": 180, "loss": 0.1118, "lr": 3.4394097100949286e-06, "epoch": 3.5536332179930796, "percentage": 72.78, "elapsed_time": "0:51:24", "remaining_time": "0:19:13", "throughput": 10908.72, "total_tokens": 33652736}
132
+ {"current_steps": 132, "total_steps": 180, "loss": 0.1103, "lr": 3.308693936411421e-06, "epoch": 3.5813148788927336, "percentage": 73.33, "elapsed_time": "0:51:48", "remaining_time": "0:18:50", "throughput": 10908.97, "total_tokens": 33914880}
133
+ {"current_steps": 133, "total_steps": 180, "loss": 0.107, "lr": 3.1800163993750166e-06, "epoch": 3.6089965397923875, "percentage": 73.89, "elapsed_time": "0:52:12", "remaining_time": "0:18:27", "throughput": 10908.94, "total_tokens": 34177024}
134
+ {"current_steps": 134, "total_steps": 180, "loss": 0.1157, "lr": 3.0534162954100264e-06, "epoch": 3.6366782006920415, "percentage": 74.44, "elapsed_time": "0:52:36", "remaining_time": "0:18:03", "throughput": 10909.0, "total_tokens": 34439168}
135
+ {"current_steps": 135, "total_steps": 180, "loss": 0.1084, "lr": 2.9289321881345257e-06, "epoch": 3.6643598615916955, "percentage": 75.0, "elapsed_time": "0:53:00", "remaining_time": "0:17:40", "throughput": 10909.05, "total_tokens": 34701312}
136
+ {"current_steps": 136, "total_steps": 180, "loss": 0.1087, "lr": 2.8066019966134907e-06, "epoch": 3.6920415224913494, "percentage": 75.56, "elapsed_time": "0:53:24", "remaining_time": "0:17:16", "throughput": 10909.17, "total_tokens": 34963456}
137
+ {"current_steps": 137, "total_steps": 180, "loss": 0.1178, "lr": 2.6864629838082957e-06, "epoch": 3.7197231833910034, "percentage": 76.11, "elapsed_time": "0:53:48", "remaining_time": "0:16:53", "throughput": 10909.24, "total_tokens": 35225600}
138
+ {"current_steps": 138, "total_steps": 180, "loss": 0.1124, "lr": 2.5685517452260566e-06, "epoch": 3.7474048442906573, "percentage": 76.67, "elapsed_time": "0:54:12", "remaining_time": "0:16:30", "throughput": 10909.38, "total_tokens": 35487744}
139
+ {"current_steps": 139, "total_steps": 180, "loss": 0.1196, "lr": 2.45290419777228e-06, "epoch": 3.7750865051903113, "percentage": 77.22, "elapsed_time": "0:54:36", "remaining_time": "0:16:06", "throughput": 10909.35, "total_tokens": 35749888}
140
+ {"current_steps": 140, "total_steps": 180, "loss": 0.1073, "lr": 2.339555568810221e-06, "epoch": 3.8027681660899653, "percentage": 77.78, "elapsed_time": "0:55:01", "remaining_time": "0:15:43", "throughput": 10909.33, "total_tokens": 36012032}
141
+ {"current_steps": 141, "total_steps": 180, "loss": 0.1026, "lr": 2.2285403854302912e-06, "epoch": 3.830449826989619, "percentage": 78.33, "elapsed_time": "0:55:24", "remaining_time": "0:15:19", "throughput": 10909.55, "total_tokens": 36274176}
142
+ {"current_steps": 142, "total_steps": 180, "loss": 0.1104, "lr": 2.119892463932781e-06, "epoch": 3.858131487889273, "percentage": 78.89, "elapsed_time": "0:55:48", "remaining_time": "0:14:56", "throughput": 10909.81, "total_tokens": 36536320}
143
+ {"current_steps": 143, "total_steps": 180, "loss": 0.1106, "lr": 2.013644899527074e-06, "epoch": 3.8858131487889276, "percentage": 79.44, "elapsed_time": "0:56:12", "remaining_time": "0:14:32", "throughput": 10910.04, "total_tokens": 36798464}
144
+ {"current_steps": 144, "total_steps": 180, "loss": 0.1112, "lr": 1.9098300562505266e-06, "epoch": 3.913494809688581, "percentage": 80.0, "elapsed_time": "0:56:36", "remaining_time": "0:14:09", "throughput": 10910.0, "total_tokens": 37060608}
145
+ {"current_steps": 145, "total_steps": 180, "loss": 0.113, "lr": 1.808479557110081e-06, "epoch": 3.9411764705882355, "percentage": 80.56, "elapsed_time": "0:57:00", "remaining_time": "0:13:45", "throughput": 10910.13, "total_tokens": 37322752}
146
+ {"current_steps": 146, "total_steps": 180, "loss": 0.1133, "lr": 1.709624274449584e-06, "epoch": 3.968858131487889, "percentage": 81.11, "elapsed_time": "0:57:24", "remaining_time": "0:13:22", "throughput": 10910.13, "total_tokens": 37584896}
147
+ {"current_steps": 147, "total_steps": 180, "loss": 0.1101, "lr": 1.6132943205457607e-06, "epoch": 3.9965397923875434, "percentage": 81.67, "elapsed_time": "0:57:48", "remaining_time": "0:12:58", "throughput": 10910.24, "total_tokens": 37847040}
148
+ {"current_steps": 148, "total_steps": 180, "loss": 0.0868, "lr": 1.5195190384357405e-06, "epoch": 4.0, "percentage": 82.22, "elapsed_time": "0:57:52", "remaining_time": "0:12:30", "throughput": 10909.91, "total_tokens": 37879808}
149
+ {"current_steps": 149, "total_steps": 180, "loss": 0.0521, "lr": 1.4283269929788779e-06, "epoch": 4.027681660899654, "percentage": 82.78, "elapsed_time": "0:58:16", "remaining_time": "0:12:07", "throughput": 10909.79, "total_tokens": 38141952}
150
+ {"current_steps": 150, "total_steps": 180, "loss": 0.0592, "lr": 1.339745962155613e-06, "epoch": 4.055363321799308, "percentage": 83.33, "elapsed_time": "0:58:40", "remaining_time": "0:11:44", "throughput": 10909.48, "total_tokens": 38404096}
151
+ {"current_steps": 151, "total_steps": 180, "loss": 0.0547, "lr": 1.2538029286060428e-06, "epoch": 4.083044982698962, "percentage": 83.89, "elapsed_time": "0:59:04", "remaining_time": "0:11:20", "throughput": 10909.49, "total_tokens": 38666240}
152
+ {"current_steps": 152, "total_steps": 180, "loss": 0.0522, "lr": 1.1705240714107301e-06, "epoch": 4.110726643598616, "percentage": 84.44, "elapsed_time": "0:59:28", "remaining_time": "0:10:57", "throughput": 10909.58, "total_tokens": 38928384}
153
+ {"current_steps": 153, "total_steps": 180, "loss": 0.0527, "lr": 1.0899347581163222e-06, "epoch": 4.13840830449827, "percentage": 85.0, "elapsed_time": "0:59:52", "remaining_time": "0:10:33", "throughput": 10909.78, "total_tokens": 39190528}
154
+ {"current_steps": 154, "total_steps": 180, "loss": 0.0532, "lr": 1.012059537008332e-06, "epoch": 4.166089965397924, "percentage": 85.56, "elapsed_time": "1:00:16", "remaining_time": "0:10:10", "throughput": 10909.85, "total_tokens": 39452672}
155
+ {"current_steps": 155, "total_steps": 180, "loss": 0.0491, "lr": 9.369221296335007e-07, "epoch": 4.193771626297578, "percentage": 86.11, "elapsed_time": "1:00:40", "remaining_time": "0:09:47", "throughput": 10910.1, "total_tokens": 39714816}
156
+ {"current_steps": 156, "total_steps": 180, "loss": 0.0481, "lr": 8.645454235739903e-07, "epoch": 4.221453287197232, "percentage": 86.67, "elapsed_time": "1:01:04", "remaining_time": "0:09:23", "throughput": 10910.2, "total_tokens": 39976960}
157
+ {"current_steps": 157, "total_steps": 180, "loss": 0.0521, "lr": 7.949514654755963e-07, "epoch": 4.249134948096886, "percentage": 87.22, "elapsed_time": "1:01:28", "remaining_time": "0:09:00", "throughput": 10910.31, "total_tokens": 40239104}
158
+ {"current_steps": 158, "total_steps": 180, "loss": 0.0532, "lr": 7.281614543321269e-07, "epoch": 4.27681660899654, "percentage": 87.78, "elapsed_time": "1:01:52", "remaining_time": "0:08:36", "throughput": 10910.14, "total_tokens": 40501248}
159
+ {"current_steps": 159, "total_steps": 180, "loss": 0.0462, "lr": 6.641957350279838e-07, "epoch": 4.304498269896194, "percentage": 88.33, "elapsed_time": "1:02:16", "remaining_time": "0:08:13", "throughput": 10910.31, "total_tokens": 40763392}
160
+ {"current_steps": 160, "total_steps": 180, "loss": 0.0503, "lr": 6.030737921409169e-07, "epoch": 4.3321799307958475, "percentage": 88.89, "elapsed_time": "1:02:40", "remaining_time": "0:07:50", "throughput": 10910.47, "total_tokens": 41025536}
161
+ {"current_steps": 161, "total_steps": 180, "loss": 0.0471, "lr": 5.448142440068316e-07, "epoch": 4.359861591695502, "percentage": 89.44, "elapsed_time": "1:03:04", "remaining_time": "0:07:26", "throughput": 10910.47, "total_tokens": 41287680}
162
+ {"current_steps": 162, "total_steps": 180, "loss": 0.049, "lr": 4.894348370484648e-07, "epoch": 4.387543252595155, "percentage": 90.0, "elapsed_time": "1:03:28", "remaining_time": "0:07:03", "throughput": 10910.62, "total_tokens": 41549824}
163
+ {"current_steps": 163, "total_steps": 180, "loss": 0.0462, "lr": 4.3695244036964567e-07, "epoch": 4.41522491349481, "percentage": 90.56, "elapsed_time": "1:03:52", "remaining_time": "0:06:39", "throughput": 10910.61, "total_tokens": 41811968}
164
+ {"current_steps": 164, "total_steps": 180, "loss": 0.0509, "lr": 3.8738304061681107e-07, "epoch": 4.442906574394463, "percentage": 91.11, "elapsed_time": "1:04:16", "remaining_time": "0:06:16", "throughput": 10910.61, "total_tokens": 42074112}
165
+ {"current_steps": 165, "total_steps": 180, "loss": 0.0469, "lr": 3.4074173710931804e-07, "epoch": 4.470588235294118, "percentage": 91.67, "elapsed_time": "1:04:40", "remaining_time": "0:05:52", "throughput": 10910.76, "total_tokens": 42336256}
166
+ {"current_steps": 166, "total_steps": 180, "loss": 0.0479, "lr": 2.970427372400353e-07, "epoch": 4.498269896193771, "percentage": 92.22, "elapsed_time": "1:05:04", "remaining_time": "0:05:29", "throughput": 10910.92, "total_tokens": 42598400}
167
+ {"current_steps": 167, "total_steps": 180, "loss": 0.0455, "lr": 2.5629935214764866e-07, "epoch": 4.525951557093426, "percentage": 92.78, "elapsed_time": "1:05:28", "remaining_time": "0:05:05", "throughput": 10910.97, "total_tokens": 42860544}
168
+ {"current_steps": 168, "total_steps": 180, "loss": 0.0505, "lr": 2.1852399266194312e-07, "epoch": 4.553633217993079, "percentage": 93.33, "elapsed_time": "1:05:52", "remaining_time": "0:04:42", "throughput": 10910.92, "total_tokens": 43122688}
169
+ {"current_steps": 169, "total_steps": 180, "loss": 0.047, "lr": 1.8372816552336025e-07, "epoch": 4.581314878892734, "percentage": 93.89, "elapsed_time": "1:06:16", "remaining_time": "0:04:18", "throughput": 10910.92, "total_tokens": 43384832}
170
+ {"current_steps": 170, "total_steps": 180, "loss": 0.0477, "lr": 1.519224698779198e-07, "epoch": 4.608996539792388, "percentage": 94.44, "elapsed_time": "1:06:40", "remaining_time": "0:03:55", "throughput": 10910.97, "total_tokens": 43646976}
171
+ {"current_steps": 171, "total_steps": 180, "loss": 0.0468, "lr": 1.231165940486234e-07, "epoch": 4.6366782006920415, "percentage": 95.0, "elapsed_time": "1:07:04", "remaining_time": "0:03:31", "throughput": 10911.01, "total_tokens": 43909120}
172
+ {"current_steps": 172, "total_steps": 180, "loss": 0.0491, "lr": 9.731931258429638e-08, "epoch": 4.664359861591695, "percentage": 95.56, "elapsed_time": "1:07:28", "remaining_time": "0:03:08", "throughput": 10910.93, "total_tokens": 44171264}
173
+ {"current_steps": 173, "total_steps": 180, "loss": 0.0521, "lr": 7.453848358678018e-08, "epoch": 4.692041522491349, "percentage": 96.11, "elapsed_time": "1:07:52", "remaining_time": "0:02:44", "throughput": 10910.35, "total_tokens": 44433408}
174
+ {"current_steps": 174, "total_steps": 180, "loss": 0.0511, "lr": 5.4781046317267103e-08, "epoch": 4.719723183391004, "percentage": 96.67, "elapsed_time": "1:08:16", "remaining_time": "0:02:21", "throughput": 10910.18, "total_tokens": 44695552}
175
+ {"current_steps": 175, "total_steps": 180, "loss": 0.0467, "lr": 3.805301908254455e-08, "epoch": 4.747404844290657, "percentage": 97.22, "elapsed_time": "1:08:40", "remaining_time": "0:01:57", "throughput": 10910.1, "total_tokens": 44957696}
176
+ {"current_steps": 176, "total_steps": 180, "loss": 0.0442, "lr": 2.4359497401758026e-08, "epoch": 4.775086505190312, "percentage": 97.78, "elapsed_time": "1:09:04", "remaining_time": "0:01:34", "throughput": 10910.13, "total_tokens": 45219840}
177
+ {"current_steps": 177, "total_steps": 180, "loss": 0.0472, "lr": 1.370465245426167e-08, "epoch": 4.802768166089965, "percentage": 98.33, "elapsed_time": "1:09:28", "remaining_time": "0:01:10", "throughput": 10910.15, "total_tokens": 45481984}
178
+ {"current_steps": 178, "total_steps": 180, "loss": 0.0472, "lr": 6.091729809042379e-09, "epoch": 4.83044982698962, "percentage": 98.89, "elapsed_time": "1:09:52", "remaining_time": "0:00:47", "throughput": 10910.16, "total_tokens": 45744128}
179
+ {"current_steps": 179, "total_steps": 180, "loss": 0.047, "lr": 1.5230484360873043e-09, "epoch": 4.858131487889273, "percentage": 99.44, "elapsed_time": "1:10:16", "remaining_time": "0:00:23", "throughput": 10910.25, "total_tokens": 46006272}
180
+ {"current_steps": 180, "total_steps": 180, "loss": 0.0466, "lr": 0.0, "epoch": 4.885813148788928, "percentage": 100.0, "elapsed_time": "1:10:40", "remaining_time": "0:00:00", "throughput": 10910.26, "total_tokens": 46268416}