yujianll commited on
Commit
b94f677
·
verified ·
1 Parent(s): 49888eb

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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
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": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 24,
22
+ "num_hidden_layers": 28,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 32.0,
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": true,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.51.0",
37
+ "use_cache": false,
38
+ "vocab_size": 128256
39
+ }
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": "4.51.0"
12
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757fd61ae707751201fe377e162c900995284e87b731eec7c1292ba65339815b
3
+ size 4965799096
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f27d355d66cb095162d6ff4f42c4a2a3186b7606f590437db4e016c3723fc99
3
+ size 2247734992
model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7213504512
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.norm.weight": "model-00002-of-00002.safetensors"
261
+ }
262
+ }
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
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 {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\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 #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\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 {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\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
+ }
trainer_state.json ADDED
@@ -0,0 +1,1714 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 7.361963190184049,
6
+ "eval_steps": 500,
7
+ "global_step": 1200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03067484662576687,
14
+ "grad_norm": 2.916747570037842,
15
+ "learning_rate": 1.6326530612244901e-07,
16
+ "loss": 1.2014,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.06134969325153374,
21
+ "grad_norm": 2.8873817920684814,
22
+ "learning_rate": 3.6734693877551025e-07,
23
+ "loss": 1.1968,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.09202453987730061,
28
+ "grad_norm": 2.65090012550354,
29
+ "learning_rate": 5.714285714285715e-07,
30
+ "loss": 1.1791,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.12269938650306748,
35
+ "grad_norm": 2.3519155979156494,
36
+ "learning_rate": 7.755102040816327e-07,
37
+ "loss": 1.1753,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.15337423312883436,
42
+ "grad_norm": 1.5954474210739136,
43
+ "learning_rate": 9.795918367346939e-07,
44
+ "loss": 1.1336,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.18404907975460122,
49
+ "grad_norm": 1.1593321561813354,
50
+ "learning_rate": 1.1836734693877552e-06,
51
+ "loss": 1.1015,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.2147239263803681,
56
+ "grad_norm": 1.082676887512207,
57
+ "learning_rate": 1.3877551020408165e-06,
58
+ "loss": 1.054,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.24539877300613497,
63
+ "grad_norm": 1.2616770267486572,
64
+ "learning_rate": 1.5918367346938775e-06,
65
+ "loss": 1.0152,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.27607361963190186,
70
+ "grad_norm": 0.7849059700965881,
71
+ "learning_rate": 1.7959183673469388e-06,
72
+ "loss": 0.9693,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.3067484662576687,
77
+ "grad_norm": 0.5774770379066467,
78
+ "learning_rate": 2.0000000000000003e-06,
79
+ "loss": 0.9483,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.3374233128834356,
84
+ "grad_norm": 0.5419191718101501,
85
+ "learning_rate": 2.2040816326530616e-06,
86
+ "loss": 0.928,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.36809815950920244,
91
+ "grad_norm": 0.5010412931442261,
92
+ "learning_rate": 2.4081632653061225e-06,
93
+ "loss": 0.8946,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.3987730061349693,
98
+ "grad_norm": 0.45867446064949036,
99
+ "learning_rate": 2.6122448979591842e-06,
100
+ "loss": 0.8818,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.4294478527607362,
105
+ "grad_norm": 0.41711899638175964,
106
+ "learning_rate": 2.816326530612245e-06,
107
+ "loss": 0.8657,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.4601226993865031,
112
+ "grad_norm": 0.3863469362258911,
113
+ "learning_rate": 3.0204081632653064e-06,
114
+ "loss": 0.8518,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.49079754601226994,
119
+ "grad_norm": 0.3639077842235565,
120
+ "learning_rate": 3.2244897959183672e-06,
121
+ "loss": 0.8378,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.5214723926380368,
126
+ "grad_norm": 0.3680429458618164,
127
+ "learning_rate": 3.428571428571429e-06,
128
+ "loss": 0.8328,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.5521472392638037,
133
+ "grad_norm": 0.3493054211139679,
134
+ "learning_rate": 3.6326530612244903e-06,
135
+ "loss": 0.8278,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.5828220858895705,
140
+ "grad_norm": 0.35972270369529724,
141
+ "learning_rate": 3.836734693877551e-06,
142
+ "loss": 0.8177,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.6134969325153374,
147
+ "grad_norm": 0.3597475588321686,
148
+ "learning_rate": 4.040816326530612e-06,
149
+ "loss": 0.8045,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.6441717791411042,
154
+ "grad_norm": 0.3763820230960846,
155
+ "learning_rate": 4.244897959183674e-06,
156
+ "loss": 0.8003,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.6748466257668712,
161
+ "grad_norm": 0.4080606997013092,
162
+ "learning_rate": 4.448979591836735e-06,
163
+ "loss": 0.7961,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.7055214723926381,
168
+ "grad_norm": 0.3602585196495056,
169
+ "learning_rate": 4.653061224489796e-06,
170
+ "loss": 0.7918,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.7361963190184049,
175
+ "grad_norm": 0.3696184456348419,
176
+ "learning_rate": 4.857142857142858e-06,
177
+ "loss": 0.7875,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.7668711656441718,
182
+ "grad_norm": 0.37600934505462646,
183
+ "learning_rate": 5.061224489795918e-06,
184
+ "loss": 0.7875,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.7975460122699386,
189
+ "grad_norm": 0.38016051054000854,
190
+ "learning_rate": 5.26530612244898e-06,
191
+ "loss": 0.7748,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.8282208588957055,
196
+ "grad_norm": 0.3912647068500519,
197
+ "learning_rate": 5.4693877551020415e-06,
198
+ "loss": 0.772,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.8588957055214724,
203
+ "grad_norm": 0.3811889886856079,
204
+ "learning_rate": 5.673469387755103e-06,
205
+ "loss": 0.7678,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.8895705521472392,
210
+ "grad_norm": 0.38242849707603455,
211
+ "learning_rate": 5.877551020408164e-06,
212
+ "loss": 0.761,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.9202453987730062,
217
+ "grad_norm": 0.4102751910686493,
218
+ "learning_rate": 6.0816326530612245e-06,
219
+ "loss": 0.763,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.950920245398773,
224
+ "grad_norm": 0.38672712445259094,
225
+ "learning_rate": 6.285714285714286e-06,
226
+ "loss": 0.7576,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.9815950920245399,
231
+ "grad_norm": 0.3906507194042206,
232
+ "learning_rate": 6.489795918367348e-06,
233
+ "loss": 0.751,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 1.0122699386503067,
238
+ "grad_norm": 0.4010821580886841,
239
+ "learning_rate": 6.693877551020409e-06,
240
+ "loss": 0.7451,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 1.0429447852760736,
245
+ "grad_norm": 0.454095721244812,
246
+ "learning_rate": 6.8979591836734705e-06,
247
+ "loss": 0.7373,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 1.0736196319018405,
252
+ "grad_norm": 0.44405630230903625,
253
+ "learning_rate": 7.102040816326531e-06,
254
+ "loss": 0.7361,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 1.1042944785276074,
259
+ "grad_norm": 0.42133402824401855,
260
+ "learning_rate": 7.306122448979592e-06,
261
+ "loss": 0.7309,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 1.1349693251533743,
266
+ "grad_norm": 0.4115142226219177,
267
+ "learning_rate": 7.5102040816326536e-06,
268
+ "loss": 0.7213,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 1.165644171779141,
273
+ "grad_norm": 0.48450756072998047,
274
+ "learning_rate": 7.714285714285716e-06,
275
+ "loss": 0.7311,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 1.196319018404908,
280
+ "grad_norm": 0.44604143500328064,
281
+ "learning_rate": 7.918367346938776e-06,
282
+ "loss": 0.7265,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 1.2269938650306749,
287
+ "grad_norm": 0.4400920271873474,
288
+ "learning_rate": 8.122448979591837e-06,
289
+ "loss": 0.7231,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 1.2576687116564418,
294
+ "grad_norm": 0.4529883861541748,
295
+ "learning_rate": 8.326530612244899e-06,
296
+ "loss": 0.7177,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 1.2883435582822087,
301
+ "grad_norm": 0.4646182954311371,
302
+ "learning_rate": 8.530612244897961e-06,
303
+ "loss": 0.7119,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 1.3190184049079754,
308
+ "grad_norm": 0.45873209834098816,
309
+ "learning_rate": 8.734693877551021e-06,
310
+ "loss": 0.7131,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 1.3496932515337423,
315
+ "grad_norm": 0.45401182770729065,
316
+ "learning_rate": 8.938775510204082e-06,
317
+ "loss": 0.7136,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 1.3803680981595092,
322
+ "grad_norm": 0.4406537711620331,
323
+ "learning_rate": 9.142857142857144e-06,
324
+ "loss": 0.7148,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 1.4110429447852761,
329
+ "grad_norm": 0.5117276310920715,
330
+ "learning_rate": 9.346938775510204e-06,
331
+ "loss": 0.7112,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 1.441717791411043,
336
+ "grad_norm": 0.4318268895149231,
337
+ "learning_rate": 9.551020408163266e-06,
338
+ "loss": 0.7065,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 1.4723926380368098,
343
+ "grad_norm": 0.4682416617870331,
344
+ "learning_rate": 9.755102040816327e-06,
345
+ "loss": 0.7019,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 1.5030674846625767,
350
+ "grad_norm": 0.48544424772262573,
351
+ "learning_rate": 9.959183673469387e-06,
352
+ "loss": 0.7084,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 1.5337423312883436,
357
+ "grad_norm": 0.45956820249557495,
358
+ "learning_rate": 9.999918433243253e-06,
359
+ "loss": 0.7045,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 1.5644171779141103,
364
+ "grad_norm": 0.4829379618167877,
365
+ "learning_rate": 9.999587072854989e-06,
366
+ "loss": 0.6992,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 1.5950920245398774,
371
+ "grad_norm": 0.4817286431789398,
372
+ "learning_rate": 9.99900083779239e-06,
373
+ "loss": 0.6949,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 1.6257668711656441,
378
+ "grad_norm": 0.41464245319366455,
379
+ "learning_rate": 9.998159757941219e-06,
380
+ "loss": 0.6943,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 1.656441717791411,
385
+ "grad_norm": 0.45459651947021484,
386
+ "learning_rate": 9.997063876179007e-06,
387
+ "loss": 0.6978,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 1.687116564417178,
392
+ "grad_norm": 0.4576292335987091,
393
+ "learning_rate": 9.99571324837287e-06,
394
+ "loss": 0.6944,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 1.7177914110429446,
399
+ "grad_norm": 0.4427788555622101,
400
+ "learning_rate": 9.994107943376654e-06,
401
+ "loss": 0.6914,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 1.7484662576687118,
406
+ "grad_norm": 0.4589153528213501,
407
+ "learning_rate": 9.992248043027441e-06,
408
+ "loss": 0.6818,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 1.7791411042944785,
413
+ "grad_norm": 0.4295940399169922,
414
+ "learning_rate": 9.990133642141359e-06,
415
+ "loss": 0.6902,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 1.8098159509202454,
420
+ "grad_norm": 0.4209536910057068,
421
+ "learning_rate": 9.987764848508756e-06,
422
+ "loss": 0.6856,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 1.8404907975460123,
427
+ "grad_norm": 0.4128643870353699,
428
+ "learning_rate": 9.985141782888705e-06,
429
+ "loss": 0.683,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 1.871165644171779,
434
+ "grad_norm": 0.44537627696990967,
435
+ "learning_rate": 9.982264579002853e-06,
436
+ "loss": 0.6837,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 1.9018404907975461,
441
+ "grad_norm": 0.40354472398757935,
442
+ "learning_rate": 9.979133383528591e-06,
443
+ "loss": 0.686,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 1.9325153374233128,
448
+ "grad_norm": 0.43714097142219543,
449
+ "learning_rate": 9.975748356091589e-06,
450
+ "loss": 0.6809,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 1.9631901840490797,
455
+ "grad_norm": 0.4338328540325165,
456
+ "learning_rate": 9.972109669257645e-06,
457
+ "loss": 0.6787,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 1.9938650306748467,
462
+ "grad_norm": 0.4852101802825928,
463
+ "learning_rate": 9.968217508523913e-06,
464
+ "loss": 0.6696,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 2.0245398773006134,
469
+ "grad_norm": 0.49633219838142395,
470
+ "learning_rate": 9.964072072309412e-06,
471
+ "loss": 0.652,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 2.0552147239263805,
476
+ "grad_norm": 0.48235881328582764,
477
+ "learning_rate": 9.959673571944939e-06,
478
+ "loss": 0.6525,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 2.085889570552147,
483
+ "grad_norm": 0.47604846954345703,
484
+ "learning_rate": 9.955022231662282e-06,
485
+ "loss": 0.6445,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 2.116564417177914,
490
+ "grad_norm": 0.4336640238761902,
491
+ "learning_rate": 9.95011828858279e-06,
492
+ "loss": 0.6557,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 2.147239263803681,
497
+ "grad_norm": 0.4802437722682953,
498
+ "learning_rate": 9.944961992705288e-06,
499
+ "loss": 0.6467,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 2.1779141104294477,
504
+ "grad_norm": 0.476906955242157,
505
+ "learning_rate": 9.939553606893334e-06,
506
+ "loss": 0.6463,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 2.208588957055215,
511
+ "grad_norm": 0.49822670221328735,
512
+ "learning_rate": 9.933893406861808e-06,
513
+ "loss": 0.6483,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 2.2392638036809815,
518
+ "grad_norm": 0.49377647042274475,
519
+ "learning_rate": 9.927981681162873e-06,
520
+ "loss": 0.6413,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 2.2699386503067487,
525
+ "grad_norm": 0.4360464811325073,
526
+ "learning_rate": 9.921818731171249e-06,
527
+ "loss": 0.6478,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 2.3006134969325154,
532
+ "grad_norm": 0.5180469155311584,
533
+ "learning_rate": 9.915404871068855e-06,
534
+ "loss": 0.6458,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 2.331288343558282,
539
+ "grad_norm": 0.5449960231781006,
540
+ "learning_rate": 9.9087404278288e-06,
541
+ "loss": 0.6445,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 2.361963190184049,
546
+ "grad_norm": 0.4497530460357666,
547
+ "learning_rate": 9.901825741198697e-06,
548
+ "loss": 0.6403,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 2.392638036809816,
553
+ "grad_norm": 0.4317333698272705,
554
+ "learning_rate": 9.894661163683361e-06,
555
+ "loss": 0.6434,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 2.4233128834355826,
560
+ "grad_norm": 0.47986018657684326,
561
+ "learning_rate": 9.887247060526827e-06,
562
+ "loss": 0.6422,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 2.4539877300613497,
567
+ "grad_norm": 0.4332720637321472,
568
+ "learning_rate": 9.879583809693737e-06,
569
+ "loss": 0.6438,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 2.4846625766871164,
574
+ "grad_norm": 0.4776013493537903,
575
+ "learning_rate": 9.871671801850065e-06,
576
+ "loss": 0.6393,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 2.5153374233128836,
581
+ "grad_norm": 0.48002681136131287,
582
+ "learning_rate": 9.863511440343206e-06,
583
+ "loss": 0.6385,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 2.5460122699386503,
588
+ "grad_norm": 0.4508747458457947,
589
+ "learning_rate": 9.855103141181412e-06,
590
+ "loss": 0.6362,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 2.5766871165644174,
595
+ "grad_norm": 0.5055172443389893,
596
+ "learning_rate": 9.846447333012587e-06,
597
+ "loss": 0.6388,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 2.607361963190184,
602
+ "grad_norm": 0.4450007975101471,
603
+ "learning_rate": 9.837544457102428e-06,
604
+ "loss": 0.6377,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 2.638036809815951,
609
+ "grad_norm": 0.4479919970035553,
610
+ "learning_rate": 9.82839496731194e-06,
611
+ "loss": 0.6372,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 2.668711656441718,
616
+ "grad_norm": 0.45310866832733154,
617
+ "learning_rate": 9.818999330074288e-06,
618
+ "loss": 0.6336,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 2.6993865030674846,
623
+ "grad_norm": 0.4643765091896057,
624
+ "learning_rate": 9.809358024371025e-06,
625
+ "loss": 0.6363,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 2.7300613496932513,
630
+ "grad_norm": 0.48741263151168823,
631
+ "learning_rate": 9.799471541707672e-06,
632
+ "loss": 0.6382,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 2.7607361963190185,
637
+ "grad_norm": 0.45080405473709106,
638
+ "learning_rate": 9.789340386088663e-06,
639
+ "loss": 0.6357,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 2.791411042944785,
644
+ "grad_norm": 0.5053460597991943,
645
+ "learning_rate": 9.778965073991652e-06,
646
+ "loss": 0.6315,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 2.8220858895705523,
651
+ "grad_norm": 0.523303747177124,
652
+ "learning_rate": 9.768346134341174e-06,
653
+ "loss": 0.6336,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 2.852760736196319,
658
+ "grad_norm": 0.4880037307739258,
659
+ "learning_rate": 9.757484108481695e-06,
660
+ "loss": 0.63,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 2.883435582822086,
665
+ "grad_norm": 0.4551119804382324,
666
+ "learning_rate": 9.74637955015001e-06,
667
+ "loss": 0.6315,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 2.914110429447853,
672
+ "grad_norm": 0.529259204864502,
673
+ "learning_rate": 9.735033025447e-06,
674
+ "loss": 0.6346,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 2.9447852760736195,
679
+ "grad_norm": 0.44139307737350464,
680
+ "learning_rate": 9.723445112808802e-06,
681
+ "loss": 0.6284,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 2.9754601226993866,
686
+ "grad_norm": 0.44775474071502686,
687
+ "learning_rate": 9.71161640297729e-06,
688
+ "loss": 0.6316,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 3.0061349693251533,
693
+ "grad_norm": 0.5552355051040649,
694
+ "learning_rate": 9.699547498969978e-06,
695
+ "loss": 0.6217,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 3.03680981595092,
700
+ "grad_norm": 0.5540191531181335,
701
+ "learning_rate": 9.687239016049275e-06,
702
+ "loss": 0.5991,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 3.067484662576687,
707
+ "grad_norm": 0.5161706209182739,
708
+ "learning_rate": 9.674691581691114e-06,
709
+ "loss": 0.5983,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 3.098159509202454,
714
+ "grad_norm": 0.564895510673523,
715
+ "learning_rate": 9.661905835552974e-06,
716
+ "loss": 0.599,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 3.128834355828221,
721
+ "grad_norm": 0.5886032581329346,
722
+ "learning_rate": 9.648882429441258e-06,
723
+ "loss": 0.5958,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 3.1595092024539877,
728
+ "grad_norm": 0.5232917666435242,
729
+ "learning_rate": 9.635622027278076e-06,
730
+ "loss": 0.5981,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 3.190184049079755,
735
+ "grad_norm": 0.5367550849914551,
736
+ "learning_rate": 9.622125305067394e-06,
737
+ "loss": 0.6009,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 3.2208588957055215,
742
+ "grad_norm": 0.5145596861839294,
743
+ "learning_rate": 9.608392950860568e-06,
744
+ "loss": 0.5964,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 3.2515337423312882,
749
+ "grad_norm": 0.48504817485809326,
750
+ "learning_rate": 9.594425664721275e-06,
751
+ "loss": 0.5954,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 3.2822085889570554,
756
+ "grad_norm": 0.44789251685142517,
757
+ "learning_rate": 9.580224158689821e-06,
758
+ "loss": 0.5963,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 3.312883435582822,
763
+ "grad_norm": 0.44385582208633423,
764
+ "learning_rate": 9.565789156746843e-06,
765
+ "loss": 0.5953,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 3.3435582822085887,
770
+ "grad_norm": 0.46638399362564087,
771
+ "learning_rate": 9.551121394776395e-06,
772
+ "loss": 0.5953,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 3.374233128834356,
777
+ "grad_norm": 0.47886648774147034,
778
+ "learning_rate": 9.536221620528442e-06,
779
+ "loss": 0.5984,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 3.4049079754601226,
784
+ "grad_norm": 0.43750545382499695,
785
+ "learning_rate": 9.521090593580737e-06,
786
+ "loss": 0.5966,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 3.4355828220858897,
791
+ "grad_norm": 0.4883286654949188,
792
+ "learning_rate": 9.505729085300098e-06,
793
+ "loss": 0.5976,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 3.4662576687116564,
798
+ "grad_norm": 0.5246576070785522,
799
+ "learning_rate": 9.490137878803078e-06,
800
+ "loss": 0.596,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 3.4969325153374236,
805
+ "grad_norm": 0.47524797916412354,
806
+ "learning_rate": 9.47431776891606e-06,
807
+ "loss": 0.5991,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 3.5276073619631902,
812
+ "grad_norm": 0.4653734266757965,
813
+ "learning_rate": 9.458269562134717e-06,
814
+ "loss": 0.594,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 3.558282208588957,
819
+ "grad_norm": 0.5341756343841553,
820
+ "learning_rate": 9.441994076582907e-06,
821
+ "loss": 0.5985,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 3.588957055214724,
826
+ "grad_norm": 0.5514233708381653,
827
+ "learning_rate": 9.425492141970973e-06,
828
+ "loss": 0.5992,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 3.6196319018404908,
833
+ "grad_norm": 0.4911518096923828,
834
+ "learning_rate": 9.408764599553429e-06,
835
+ "loss": 0.5935,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 3.6503067484662575,
840
+ "grad_norm": 0.4620342552661896,
841
+ "learning_rate": 9.391812302086088e-06,
842
+ "loss": 0.5977,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 3.6809815950920246,
847
+ "grad_norm": 0.44591575860977173,
848
+ "learning_rate": 9.374636113782576e-06,
849
+ "loss": 0.5928,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 3.7116564417177913,
854
+ "grad_norm": 0.40037840604782104,
855
+ "learning_rate": 9.357236910270292e-06,
856
+ "loss": 0.5883,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 3.7423312883435584,
861
+ "grad_norm": 0.4316963255405426,
862
+ "learning_rate": 9.339615578545753e-06,
863
+ "loss": 0.5916,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 3.773006134969325,
868
+ "grad_norm": 0.47416016459465027,
869
+ "learning_rate": 9.321773016929382e-06,
870
+ "loss": 0.5935,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 3.8036809815950923,
875
+ "grad_norm": 0.486749529838562,
876
+ "learning_rate": 9.30371013501972e-06,
877
+ "loss": 0.5976,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 3.834355828220859,
882
+ "grad_norm": 0.46578896045684814,
883
+ "learning_rate": 9.285427853647038e-06,
884
+ "loss": 0.5964,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 3.8650306748466257,
889
+ "grad_norm": 0.4229313135147095,
890
+ "learning_rate": 9.26692710482641e-06,
891
+ "loss": 0.5941,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 3.895705521472393,
896
+ "grad_norm": 0.45090341567993164,
897
+ "learning_rate": 9.248208831710195e-06,
898
+ "loss": 0.5922,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 3.9263803680981595,
903
+ "grad_norm": 0.4940469264984131,
904
+ "learning_rate": 9.229273988539951e-06,
905
+ "loss": 0.5957,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 3.957055214723926,
910
+ "grad_norm": 0.45583370327949524,
911
+ "learning_rate": 9.210123540597792e-06,
912
+ "loss": 0.592,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 3.9877300613496933,
917
+ "grad_norm": 0.43879297375679016,
918
+ "learning_rate": 9.190758464157184e-06,
919
+ "loss": 0.5936,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 4.0184049079754605,
924
+ "grad_norm": 0.5458897948265076,
925
+ "learning_rate": 9.171179746433164e-06,
926
+ "loss": 0.5735,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 4.049079754601227,
931
+ "grad_norm": 0.5021305084228516,
932
+ "learning_rate": 9.151388385532022e-06,
933
+ "loss": 0.5571,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 4.079754601226994,
938
+ "grad_norm": 0.47301429510116577,
939
+ "learning_rate": 9.131385390400417e-06,
940
+ "loss": 0.5594,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 4.110429447852761,
945
+ "grad_norm": 0.46195101737976074,
946
+ "learning_rate": 9.111171780773938e-06,
947
+ "loss": 0.556,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 4.141104294478527,
952
+ "grad_norm": 0.4663168489933014,
953
+ "learning_rate": 9.090748587125118e-06,
954
+ "loss": 0.5576,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 4.171779141104294,
959
+ "grad_norm": 0.5041781067848206,
960
+ "learning_rate": 9.070116850610911e-06,
961
+ "loss": 0.5546,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 4.2024539877300615,
966
+ "grad_norm": 0.571372389793396,
967
+ "learning_rate": 9.049277623019603e-06,
968
+ "loss": 0.5609,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 4.233128834355828,
973
+ "grad_norm": 0.4924178421497345,
974
+ "learning_rate": 9.0282319667172e-06,
975
+ "loss": 0.5569,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 4.263803680981595,
980
+ "grad_norm": 0.4700438678264618,
981
+ "learning_rate": 9.006980954593262e-06,
982
+ "loss": 0.5622,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 4.294478527607362,
987
+ "grad_norm": 0.46645787358283997,
988
+ "learning_rate": 8.985525670006225e-06,
989
+ "loss": 0.5561,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 4.325153374233129,
994
+ "grad_norm": 0.47866857051849365,
995
+ "learning_rate": 8.963867206728147e-06,
996
+ "loss": 0.5594,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 4.355828220858895,
1001
+ "grad_norm": 0.4613681733608246,
1002
+ "learning_rate": 8.942006668888972e-06,
1003
+ "loss": 0.5556,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 4.386503067484663,
1008
+ "grad_norm": 0.451261043548584,
1009
+ "learning_rate": 8.919945170920224e-06,
1010
+ "loss": 0.558,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 4.41717791411043,
1015
+ "grad_norm": 0.5014335513114929,
1016
+ "learning_rate": 8.89768383749821e-06,
1017
+ "loss": 0.5622,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 4.447852760736196,
1022
+ "grad_norm": 0.5099634528160095,
1023
+ "learning_rate": 8.875223803486674e-06,
1024
+ "loss": 0.566,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 4.478527607361963,
1029
+ "grad_norm": 0.5409094095230103,
1030
+ "learning_rate": 8.852566213878947e-06,
1031
+ "loss": 0.5562,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 4.50920245398773,
1036
+ "grad_norm": 0.5168077945709229,
1037
+ "learning_rate": 8.829712223739574e-06,
1038
+ "loss": 0.5589,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 4.539877300613497,
1043
+ "grad_norm": 0.5725398063659668,
1044
+ "learning_rate": 8.80666299814543e-06,
1045
+ "loss": 0.5567,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 4.570552147239264,
1050
+ "grad_norm": 0.45501619577407837,
1051
+ "learning_rate": 8.783419712126335e-06,
1052
+ "loss": 0.5615,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 4.601226993865031,
1057
+ "grad_norm": 0.5540989637374878,
1058
+ "learning_rate": 8.759983550605132e-06,
1059
+ "loss": 0.5578,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 4.631901840490798,
1064
+ "grad_norm": 0.5188400745391846,
1065
+ "learning_rate": 8.736355708337298e-06,
1066
+ "loss": 0.5605,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 4.662576687116564,
1071
+ "grad_norm": 0.48551928997039795,
1072
+ "learning_rate": 8.71253738985003e-06,
1073
+ "loss": 0.5579,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 4.693251533742331,
1078
+ "grad_norm": 0.44432246685028076,
1079
+ "learning_rate": 8.688529809380843e-06,
1080
+ "loss": 0.5595,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 4.723926380368098,
1085
+ "grad_norm": 0.45983144640922546,
1086
+ "learning_rate": 8.66433419081566e-06,
1087
+ "loss": 0.5611,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 4.754601226993865,
1092
+ "grad_norm": 0.48174920678138733,
1093
+ "learning_rate": 8.639951767626429e-06,
1094
+ "loss": 0.5637,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 4.785276073619632,
1099
+ "grad_norm": 0.4685279130935669,
1100
+ "learning_rate": 8.615383782808238e-06,
1101
+ "loss": 0.5608,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 4.815950920245399,
1106
+ "grad_norm": 0.5617627501487732,
1107
+ "learning_rate": 8.590631488815945e-06,
1108
+ "loss": 0.5596,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 4.846625766871165,
1113
+ "grad_norm": 0.5751484036445618,
1114
+ "learning_rate": 8.565696147500338e-06,
1115
+ "loss": 0.5596,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 4.877300613496932,
1120
+ "grad_norm": 0.6005717515945435,
1121
+ "learning_rate": 8.540579030043795e-06,
1122
+ "loss": 0.5614,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 4.9079754601226995,
1127
+ "grad_norm": 0.5048331022262573,
1128
+ "learning_rate": 8.515281416895489e-06,
1129
+ "loss": 0.5585,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 4.938650306748467,
1134
+ "grad_norm": 0.4952603578567505,
1135
+ "learning_rate": 8.48980459770611e-06,
1136
+ "loss": 0.5599,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 4.969325153374233,
1141
+ "grad_norm": 0.49712324142456055,
1142
+ "learning_rate": 8.464149871262118e-06,
1143
+ "loss": 0.5614,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 5.0,
1148
+ "grad_norm": 0.5496305227279663,
1149
+ "learning_rate": 8.43831854541953e-06,
1150
+ "loss": 0.559,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 5.030674846625767,
1155
+ "grad_norm": 0.565785825252533,
1156
+ "learning_rate": 8.412311937037255e-06,
1157
+ "loss": 0.5256,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 5.061349693251533,
1162
+ "grad_norm": 0.5519700050354004,
1163
+ "learning_rate": 8.386131371909948e-06,
1164
+ "loss": 0.5198,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 5.0920245398773005,
1169
+ "grad_norm": 0.5226123332977295,
1170
+ "learning_rate": 8.35977818470044e-06,
1171
+ "loss": 0.5235,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 5.122699386503068,
1176
+ "grad_norm": 0.5327089428901672,
1177
+ "learning_rate": 8.33325371887168e-06,
1178
+ "loss": 0.5267,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 5.153374233128835,
1183
+ "grad_norm": 0.5217044949531555,
1184
+ "learning_rate": 8.30655932661826e-06,
1185
+ "loss": 0.5215,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 5.184049079754601,
1190
+ "grad_norm": 0.5113396048545837,
1191
+ "learning_rate": 8.279696368797471e-06,
1192
+ "loss": 0.5227,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 5.214723926380368,
1197
+ "grad_norm": 0.5224789977073669,
1198
+ "learning_rate": 8.252666214859936e-06,
1199
+ "loss": 0.5211,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 5.245398773006135,
1204
+ "grad_norm": 0.47648775577545166,
1205
+ "learning_rate": 8.225470242779791e-06,
1206
+ "loss": 0.5262,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 5.276073619631902,
1211
+ "grad_norm": 0.5127813816070557,
1212
+ "learning_rate": 8.19810983898444e-06,
1213
+ "loss": 0.5256,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 5.306748466257669,
1218
+ "grad_norm": 0.5499957799911499,
1219
+ "learning_rate": 8.170586398283878e-06,
1220
+ "loss": 0.5267,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 5.337423312883436,
1225
+ "grad_norm": 0.5156161189079285,
1226
+ "learning_rate": 8.142901323799578e-06,
1227
+ "loss": 0.5252,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 5.368098159509202,
1232
+ "grad_norm": 0.4825647175312042,
1233
+ "learning_rate": 8.115056026892965e-06,
1234
+ "loss": 0.5266,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 5.398773006134969,
1239
+ "grad_norm": 0.5043969750404358,
1240
+ "learning_rate": 8.08705192709347e-06,
1241
+ "loss": 0.5241,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 5.429447852760736,
1246
+ "grad_norm": 0.47043198347091675,
1247
+ "learning_rate": 8.058890452026155e-06,
1248
+ "loss": 0.5272,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 5.460122699386503,
1253
+ "grad_norm": 0.471513956785202,
1254
+ "learning_rate": 8.030573037338942e-06,
1255
+ "loss": 0.5321,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 5.49079754601227,
1260
+ "grad_norm": 0.48654860258102417,
1261
+ "learning_rate": 8.002101126629422e-06,
1262
+ "loss": 0.5267,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 5.521472392638037,
1267
+ "grad_norm": 0.4844699501991272,
1268
+ "learning_rate": 7.973476171371255e-06,
1269
+ "loss": 0.5301,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 5.552147239263804,
1274
+ "grad_norm": 0.4706033170223236,
1275
+ "learning_rate": 7.94469963084019e-06,
1276
+ "loss": 0.5276,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 5.58282208588957,
1281
+ "grad_norm": 0.47882503271102905,
1282
+ "learning_rate": 7.91577297203966e-06,
1283
+ "loss": 0.5267,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 5.613496932515337,
1288
+ "grad_norm": 0.5027369856834412,
1289
+ "learning_rate": 7.886697669625995e-06,
1290
+ "loss": 0.5313,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 5.644171779141105,
1295
+ "grad_norm": 0.4971833825111389,
1296
+ "learning_rate": 7.857475205833255e-06,
1297
+ "loss": 0.5219,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 5.674846625766871,
1302
+ "grad_norm": 0.488737016916275,
1303
+ "learning_rate": 7.828107070397657e-06,
1304
+ "loss": 0.5233,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 5.705521472392638,
1309
+ "grad_norm": 0.49035337567329407,
1310
+ "learning_rate": 7.798594760481639e-06,
1311
+ "loss": 0.5254,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 5.736196319018405,
1316
+ "grad_norm": 0.5278029441833496,
1317
+ "learning_rate": 7.768939780597523e-06,
1318
+ "loss": 0.5246,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 5.766871165644172,
1323
+ "grad_norm": 0.4724002480506897,
1324
+ "learning_rate": 7.739143642530833e-06,
1325
+ "loss": 0.5218,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 5.7975460122699385,
1330
+ "grad_norm": 0.5203721523284912,
1331
+ "learning_rate": 7.70920786526321e-06,
1332
+ "loss": 0.5256,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 5.828220858895706,
1337
+ "grad_norm": 0.5066553950309753,
1338
+ "learning_rate": 7.679133974894984e-06,
1339
+ "loss": 0.5272,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 5.858895705521473,
1344
+ "grad_norm": 0.5213795304298401,
1345
+ "learning_rate": 7.648923504567374e-06,
1346
+ "loss": 0.5293,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 5.889570552147239,
1351
+ "grad_norm": 0.5189357399940491,
1352
+ "learning_rate": 7.618577994384324e-06,
1353
+ "loss": 0.525,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 5.920245398773006,
1358
+ "grad_norm": 0.45614001154899597,
1359
+ "learning_rate": 7.588098991334001e-06,
1360
+ "loss": 0.5254,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 5.950920245398773,
1365
+ "grad_norm": 0.5392826199531555,
1366
+ "learning_rate": 7.557488049209921e-06,
1367
+ "loss": 0.5215,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 5.9815950920245395,
1372
+ "grad_norm": 0.5028013586997986,
1373
+ "learning_rate": 7.52674672853174e-06,
1374
+ "loss": 0.5249,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 6.012269938650307,
1379
+ "grad_norm": 0.5520371198654175,
1380
+ "learning_rate": 7.495876596465703e-06,
1381
+ "loss": 0.5087,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 6.042944785276074,
1386
+ "grad_norm": 0.6230819225311279,
1387
+ "learning_rate": 7.464879226744748e-06,
1388
+ "loss": 0.4881,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 6.07361963190184,
1393
+ "grad_norm": 0.581471860408783,
1394
+ "learning_rate": 7.433756199588282e-06,
1395
+ "loss": 0.4891,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 6.104294478527607,
1400
+ "grad_norm": 0.6113958358764648,
1401
+ "learning_rate": 7.402509101621618e-06,
1402
+ "loss": 0.4848,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 6.134969325153374,
1407
+ "grad_norm": 0.5332604050636292,
1408
+ "learning_rate": 7.371139525795094e-06,
1409
+ "loss": 0.488,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 6.1656441717791415,
1414
+ "grad_norm": 0.538058340549469,
1415
+ "learning_rate": 7.3396490713028674e-06,
1416
+ "loss": 0.4904,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 6.196319018404908,
1421
+ "grad_norm": 0.5761954188346863,
1422
+ "learning_rate": 7.308039343501381e-06,
1423
+ "loss": 0.4907,
1424
+ "step": 1010
1425
+ },
1426
+ {
1427
+ "epoch": 6.226993865030675,
1428
+ "grad_norm": 0.5636390447616577,
1429
+ "learning_rate": 7.276311953827533e-06,
1430
+ "loss": 0.4872,
1431
+ "step": 1015
1432
+ },
1433
+ {
1434
+ "epoch": 6.257668711656442,
1435
+ "grad_norm": 0.5386704802513123,
1436
+ "learning_rate": 7.244468519716521e-06,
1437
+ "loss": 0.4946,
1438
+ "step": 1020
1439
+ },
1440
+ {
1441
+ "epoch": 6.288343558282208,
1442
+ "grad_norm": 0.585161566734314,
1443
+ "learning_rate": 7.212510664519391e-06,
1444
+ "loss": 0.4934,
1445
+ "step": 1025
1446
+ },
1447
+ {
1448
+ "epoch": 6.319018404907975,
1449
+ "grad_norm": 0.5781230330467224,
1450
+ "learning_rate": 7.180440017420277e-06,
1451
+ "loss": 0.494,
1452
+ "step": 1030
1453
+ },
1454
+ {
1455
+ "epoch": 6.3496932515337425,
1456
+ "grad_norm": 0.5272154211997986,
1457
+ "learning_rate": 7.148258213353347e-06,
1458
+ "loss": 0.4944,
1459
+ "step": 1035
1460
+ },
1461
+ {
1462
+ "epoch": 6.38036809815951,
1463
+ "grad_norm": 0.5416070222854614,
1464
+ "learning_rate": 7.115966892919459e-06,
1465
+ "loss": 0.4936,
1466
+ "step": 1040
1467
+ },
1468
+ {
1469
+ "epoch": 6.411042944785276,
1470
+ "grad_norm": 0.5524059534072876,
1471
+ "learning_rate": 7.083567702302517e-06,
1472
+ "loss": 0.4901,
1473
+ "step": 1045
1474
+ },
1475
+ {
1476
+ "epoch": 6.441717791411043,
1477
+ "grad_norm": 0.5226433277130127,
1478
+ "learning_rate": 7.05106229318556e-06,
1479
+ "loss": 0.4931,
1480
+ "step": 1050
1481
+ },
1482
+ {
1483
+ "epoch": 6.47239263803681,
1484
+ "grad_norm": 0.5324561595916748,
1485
+ "learning_rate": 7.018452322666549e-06,
1486
+ "loss": 0.4906,
1487
+ "step": 1055
1488
+ },
1489
+ {
1490
+ "epoch": 6.5030674846625764,
1491
+ "grad_norm": 0.5099997520446777,
1492
+ "learning_rate": 6.985739453173903e-06,
1493
+ "loss": 0.4909,
1494
+ "step": 1060
1495
+ },
1496
+ {
1497
+ "epoch": 6.533742331288344,
1498
+ "grad_norm": 0.5172037482261658,
1499
+ "learning_rate": 6.9529253523817396e-06,
1500
+ "loss": 0.4936,
1501
+ "step": 1065
1502
+ },
1503
+ {
1504
+ "epoch": 6.564417177914111,
1505
+ "grad_norm": 0.5281527638435364,
1506
+ "learning_rate": 6.9200116931248575e-06,
1507
+ "loss": 0.4949,
1508
+ "step": 1070
1509
+ },
1510
+ {
1511
+ "epoch": 6.595092024539877,
1512
+ "grad_norm": 0.5232874751091003,
1513
+ "learning_rate": 6.887000153313468e-06,
1514
+ "loss": 0.493,
1515
+ "step": 1075
1516
+ },
1517
+ {
1518
+ "epoch": 6.625766871165644,
1519
+ "grad_norm": 0.5422880053520203,
1520
+ "learning_rate": 6.853892415847645e-06,
1521
+ "loss": 0.4944,
1522
+ "step": 1080
1523
+ },
1524
+ {
1525
+ "epoch": 6.656441717791411,
1526
+ "grad_norm": 0.5587918758392334,
1527
+ "learning_rate": 6.8206901685315366e-06,
1528
+ "loss": 0.4974,
1529
+ "step": 1085
1530
+ },
1531
+ {
1532
+ "epoch": 6.6871165644171775,
1533
+ "grad_norm": 0.5716516971588135,
1534
+ "learning_rate": 6.787395103987323e-06,
1535
+ "loss": 0.4959,
1536
+ "step": 1090
1537
+ },
1538
+ {
1539
+ "epoch": 6.717791411042945,
1540
+ "grad_norm": 0.5290241837501526,
1541
+ "learning_rate": 6.754008919568927e-06,
1542
+ "loss": 0.49,
1543
+ "step": 1095
1544
+ },
1545
+ {
1546
+ "epoch": 6.748466257668712,
1547
+ "grad_norm": 0.545229971408844,
1548
+ "learning_rate": 6.72053331727549e-06,
1549
+ "loss": 0.4913,
1550
+ "step": 1100
1551
+ },
1552
+ {
1553
+ "epoch": 6.779141104294479,
1554
+ "grad_norm": 0.5339862108230591,
1555
+ "learning_rate": 6.686970003664588e-06,
1556
+ "loss": 0.4933,
1557
+ "step": 1105
1558
+ },
1559
+ {
1560
+ "epoch": 6.809815950920245,
1561
+ "grad_norm": 0.5517235398292542,
1562
+ "learning_rate": 6.653320689765257e-06,
1563
+ "loss": 0.4957,
1564
+ "step": 1110
1565
+ },
1566
+ {
1567
+ "epoch": 6.840490797546012,
1568
+ "grad_norm": 0.5221419334411621,
1569
+ "learning_rate": 6.619587090990748e-06,
1570
+ "loss": 0.4938,
1571
+ "step": 1115
1572
+ },
1573
+ {
1574
+ "epoch": 6.871165644171779,
1575
+ "grad_norm": 0.5578407049179077,
1576
+ "learning_rate": 6.585770927051085e-06,
1577
+ "loss": 0.4992,
1578
+ "step": 1120
1579
+ },
1580
+ {
1581
+ "epoch": 6.901840490797546,
1582
+ "grad_norm": 0.5061231255531311,
1583
+ "learning_rate": 6.551873921865393e-06,
1584
+ "loss": 0.4968,
1585
+ "step": 1125
1586
+ },
1587
+ {
1588
+ "epoch": 6.932515337423313,
1589
+ "grad_norm": 0.5198781490325928,
1590
+ "learning_rate": 6.517897803474011e-06,
1591
+ "loss": 0.4982,
1592
+ "step": 1130
1593
+ },
1594
+ {
1595
+ "epoch": 6.96319018404908,
1596
+ "grad_norm": 0.5066606998443604,
1597
+ "learning_rate": 6.483844303950411e-06,
1598
+ "loss": 0.4975,
1599
+ "step": 1135
1600
+ },
1601
+ {
1602
+ "epoch": 6.993865030674847,
1603
+ "grad_norm": 0.5105178952217102,
1604
+ "learning_rate": 6.4497151593128795e-06,
1605
+ "loss": 0.5015,
1606
+ "step": 1140
1607
+ },
1608
+ {
1609
+ "epoch": 7.024539877300613,
1610
+ "grad_norm": 0.6838037967681885,
1611
+ "learning_rate": 6.415512109436031e-06,
1612
+ "loss": 0.4634,
1613
+ "step": 1145
1614
+ },
1615
+ {
1616
+ "epoch": 7.0552147239263805,
1617
+ "grad_norm": 0.6098262667655945,
1618
+ "learning_rate": 6.381236897962102e-06,
1619
+ "loss": 0.4616,
1620
+ "step": 1150
1621
+ },
1622
+ {
1623
+ "epoch": 7.085889570552148,
1624
+ "grad_norm": 0.5857096314430237,
1625
+ "learning_rate": 6.3468912722120715e-06,
1626
+ "loss": 0.4557,
1627
+ "step": 1155
1628
+ },
1629
+ {
1630
+ "epoch": 7.116564417177914,
1631
+ "grad_norm": 0.5579211115837097,
1632
+ "learning_rate": 6.312476983096573e-06,
1633
+ "loss": 0.454,
1634
+ "step": 1160
1635
+ },
1636
+ {
1637
+ "epoch": 7.147239263803681,
1638
+ "grad_norm": 0.5579200387001038,
1639
+ "learning_rate": 6.277995785026642e-06,
1640
+ "loss": 0.4606,
1641
+ "step": 1165
1642
+ },
1643
+ {
1644
+ "epoch": 7.177914110429448,
1645
+ "grad_norm": 0.5602801442146301,
1646
+ "learning_rate": 6.243449435824276e-06,
1647
+ "loss": 0.4557,
1648
+ "step": 1170
1649
+ },
1650
+ {
1651
+ "epoch": 7.208588957055214,
1652
+ "grad_norm": 0.5627221465110779,
1653
+ "learning_rate": 6.2088396966328155e-06,
1654
+ "loss": 0.4564,
1655
+ "step": 1175
1656
+ },
1657
+ {
1658
+ "epoch": 7.2392638036809815,
1659
+ "grad_norm": 0.5709859728813171,
1660
+ "learning_rate": 6.174168331827179e-06,
1661
+ "loss": 0.4596,
1662
+ "step": 1180
1663
+ },
1664
+ {
1665
+ "epoch": 7.269938650306749,
1666
+ "grad_norm": 0.554961621761322,
1667
+ "learning_rate": 6.139437108923898e-06,
1668
+ "loss": 0.4583,
1669
+ "step": 1185
1670
+ },
1671
+ {
1672
+ "epoch": 7.300613496932515,
1673
+ "grad_norm": 0.5725740790367126,
1674
+ "learning_rate": 6.1046477984910215e-06,
1675
+ "loss": 0.458,
1676
+ "step": 1190
1677
+ },
1678
+ {
1679
+ "epoch": 7.331288343558282,
1680
+ "grad_norm": 0.5590230226516724,
1681
+ "learning_rate": 6.069802174057849e-06,
1682
+ "loss": 0.4604,
1683
+ "step": 1195
1684
+ },
1685
+ {
1686
+ "epoch": 7.361963190184049,
1687
+ "grad_norm": 0.5823590159416199,
1688
+ "learning_rate": 6.034902012024521e-06,
1689
+ "loss": 0.4575,
1690
+ "step": 1200
1691
+ }
1692
+ ],
1693
+ "logging_steps": 5,
1694
+ "max_steps": 2445,
1695
+ "num_input_tokens_seen": 0,
1696
+ "num_train_epochs": 15,
1697
+ "save_steps": 400,
1698
+ "stateful_callbacks": {
1699
+ "TrainerControl": {
1700
+ "args": {
1701
+ "should_epoch_stop": false,
1702
+ "should_evaluate": false,
1703
+ "should_log": false,
1704
+ "should_save": true,
1705
+ "should_training_stop": false
1706
+ },
1707
+ "attributes": {}
1708
+ }
1709
+ },
1710
+ "total_flos": 1.6846057011425575e+19,
1711
+ "train_batch_size": 2,
1712
+ "trial_name": null,
1713
+ "trial_params": null
1714
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c578589ffc6d135437c0d6e87c09596d92cd05e36f817324e1117854c8d50519
3
+ size 7544