Text Generation
Transformers
Safetensors
English
llama
code
text-generation-inference
Inference Endpoints
Zhuominc commited on
Commit
a509497
·
1 Parent(s): da608e1

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 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FastCoderL4-IT/checkpoint-2031",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 4,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 32.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.47.0",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
5
+ "transformers_version": "4.47.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da25242c179b8110a4731db6b66b38cb653d16a0fe6c13d245f5e6a11b182482
3
+ size 2023829752
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7070bb1a9651679ab6e6bce4cd0d71eb0ad8e9303e7d2f202699c280f338a1cd
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|finetune_right_pad_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7565ce1572c0921d8263452306eb6e64963de52db070dfaa7a5f39f5d5f8b438
3
+ size 17210199
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|finetune_right_pad_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
trainer_state.json ADDED
@@ -0,0 +1,3878 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.798653244972229,
3
+ "best_model_checkpoint": "FastCoderL4-ITX/checkpoint-500",
4
+ "epoch": 1.0,
5
+ "eval_steps": 250,
6
+ "global_step": 547,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0018281535648994515,
13
+ "grad_norm": 16.024444580078125,
14
+ "learning_rate": 1.2000000000000002e-07,
15
+ "loss": 1.6383,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.003656307129798903,
20
+ "grad_norm": 16.114477157592773,
21
+ "learning_rate": 2.4000000000000003e-07,
22
+ "loss": 1.7323,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.005484460694698354,
27
+ "grad_norm": 14.292167663574219,
28
+ "learning_rate": 3.6e-07,
29
+ "loss": 1.4207,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.007312614259597806,
34
+ "grad_norm": 15.010176658630371,
35
+ "learning_rate": 4.800000000000001e-07,
36
+ "loss": 1.5956,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.009140767824497258,
41
+ "grad_norm": 13.827630996704102,
42
+ "learning_rate": 6.000000000000001e-07,
43
+ "loss": 1.49,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.010968921389396709,
48
+ "grad_norm": 15.43071174621582,
49
+ "learning_rate": 7.2e-07,
50
+ "loss": 1.6081,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.012797074954296161,
55
+ "grad_norm": 14.97592544555664,
56
+ "learning_rate": 8.4e-07,
57
+ "loss": 1.6164,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.014625228519195612,
62
+ "grad_norm": 11.73971939086914,
63
+ "learning_rate": 9.600000000000001e-07,
64
+ "loss": 1.4299,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.016453382084095063,
69
+ "grad_norm": 12.449714660644531,
70
+ "learning_rate": 1.08e-06,
71
+ "loss": 1.3328,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.018281535648994516,
76
+ "grad_norm": 12.710100173950195,
77
+ "learning_rate": 1.2000000000000002e-06,
78
+ "loss": 1.4129,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.02010968921389397,
83
+ "grad_norm": 12.13203239440918,
84
+ "learning_rate": 1.3199999999999999e-06,
85
+ "loss": 1.3971,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.021937842778793418,
90
+ "grad_norm": 10.500185012817383,
91
+ "learning_rate": 1.44e-06,
92
+ "loss": 1.4321,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.02376599634369287,
97
+ "grad_norm": 10.064560890197754,
98
+ "learning_rate": 1.5599999999999999e-06,
99
+ "loss": 1.2872,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.025594149908592323,
104
+ "grad_norm": 7.85143518447876,
105
+ "learning_rate": 1.68e-06,
106
+ "loss": 1.2345,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.027422303473491772,
111
+ "grad_norm": 7.530126094818115,
112
+ "learning_rate": 1.8e-06,
113
+ "loss": 1.1803,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.029250457038391225,
118
+ "grad_norm": 6.091775417327881,
119
+ "learning_rate": 1.9200000000000003e-06,
120
+ "loss": 1.2247,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.031078610603290677,
125
+ "grad_norm": 4.9651384353637695,
126
+ "learning_rate": 2.0400000000000004e-06,
127
+ "loss": 1.1655,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.03290676416819013,
132
+ "grad_norm": 6.209571361541748,
133
+ "learning_rate": 2.16e-06,
134
+ "loss": 1.0649,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.03473491773308958,
139
+ "grad_norm": 4.946502208709717,
140
+ "learning_rate": 2.28e-06,
141
+ "loss": 1.1046,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.03656307129798903,
146
+ "grad_norm": 4.954932689666748,
147
+ "learning_rate": 2.4000000000000003e-06,
148
+ "loss": 1.0964,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.038391224862888484,
153
+ "grad_norm": 3.8354671001434326,
154
+ "learning_rate": 2.52e-06,
155
+ "loss": 1.2277,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.04021937842778794,
160
+ "grad_norm": 4.310220718383789,
161
+ "learning_rate": 2.6399999999999997e-06,
162
+ "loss": 1.042,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.04204753199268738,
167
+ "grad_norm": 3.9748997688293457,
168
+ "learning_rate": 2.76e-06,
169
+ "loss": 1.0234,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.043875685557586835,
174
+ "grad_norm": 3.9019360542297363,
175
+ "learning_rate": 2.88e-06,
176
+ "loss": 1.1286,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.04570383912248629,
181
+ "grad_norm": 4.246694564819336,
182
+ "learning_rate": 3e-06,
183
+ "loss": 0.9793,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.04753199268738574,
188
+ "grad_norm": 3.8797051906585693,
189
+ "learning_rate": 3.1199999999999998e-06,
190
+ "loss": 1.0747,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.04936014625228519,
195
+ "grad_norm": 4.0023908615112305,
196
+ "learning_rate": 3.24e-06,
197
+ "loss": 1.1031,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.051188299817184646,
202
+ "grad_norm": 4.26245641708374,
203
+ "learning_rate": 3.36e-06,
204
+ "loss": 1.003,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.05301645338208409,
209
+ "grad_norm": 4.6040215492248535,
210
+ "learning_rate": 3.48e-06,
211
+ "loss": 0.9311,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.054844606946983544,
216
+ "grad_norm": 4.464705467224121,
217
+ "learning_rate": 3.6e-06,
218
+ "loss": 1.0341,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.056672760511883,
223
+ "grad_norm": 3.787562608718872,
224
+ "learning_rate": 3.72e-06,
225
+ "loss": 0.984,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.05850091407678245,
230
+ "grad_norm": 3.2259016036987305,
231
+ "learning_rate": 3.8400000000000005e-06,
232
+ "loss": 0.9167,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.0603290676416819,
237
+ "grad_norm": 3.7597789764404297,
238
+ "learning_rate": 3.96e-06,
239
+ "loss": 1.0784,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.062157221206581355,
244
+ "grad_norm": 3.173090934753418,
245
+ "learning_rate": 4.080000000000001e-06,
246
+ "loss": 0.9436,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.06398537477148081,
251
+ "grad_norm": 3.336909055709839,
252
+ "learning_rate": 4.2000000000000004e-06,
253
+ "loss": 0.8013,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.06581352833638025,
258
+ "grad_norm": 2.738156318664551,
259
+ "learning_rate": 4.32e-06,
260
+ "loss": 1.1238,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.06764168190127971,
265
+ "grad_norm": 3.3270339965820312,
266
+ "learning_rate": 4.44e-06,
267
+ "loss": 0.8423,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.06946983546617916,
272
+ "grad_norm": 2.872663736343384,
273
+ "learning_rate": 4.56e-06,
274
+ "loss": 0.9931,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.0712979890310786,
279
+ "grad_norm": 3.2571451663970947,
280
+ "learning_rate": 4.68e-06,
281
+ "loss": 0.9323,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.07312614259597806,
286
+ "grad_norm": 2.999234437942505,
287
+ "learning_rate": 4.800000000000001e-06,
288
+ "loss": 0.9247,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.07495429616087751,
293
+ "grad_norm": 2.9580419063568115,
294
+ "learning_rate": 4.92e-06,
295
+ "loss": 0.8751,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.07678244972577697,
300
+ "grad_norm": 2.8437395095825195,
301
+ "learning_rate": 5.04e-06,
302
+ "loss": 0.8857,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.07861060329067641,
307
+ "grad_norm": 3.175656318664551,
308
+ "learning_rate": 5.16e-06,
309
+ "loss": 0.8942,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.08043875685557587,
314
+ "grad_norm": 2.684788703918457,
315
+ "learning_rate": 5.279999999999999e-06,
316
+ "loss": 0.8725,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.08226691042047532,
321
+ "grad_norm": 3.000286340713501,
322
+ "learning_rate": 5.4e-06,
323
+ "loss": 0.8803,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.08409506398537477,
328
+ "grad_norm": 2.856066942214966,
329
+ "learning_rate": 5.52e-06,
330
+ "loss": 0.9705,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.08592321755027423,
335
+ "grad_norm": 3.0575389862060547,
336
+ "learning_rate": 5.64e-06,
337
+ "loss": 0.8106,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.08775137111517367,
342
+ "grad_norm": 2.649608612060547,
343
+ "learning_rate": 5.76e-06,
344
+ "loss": 1.0701,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.08957952468007313,
349
+ "grad_norm": 3.1014580726623535,
350
+ "learning_rate": 5.8800000000000005e-06,
351
+ "loss": 0.9607,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.09140767824497258,
356
+ "grad_norm": 2.6570193767547607,
357
+ "learning_rate": 6e-06,
358
+ "loss": 0.9685,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.09323583180987204,
363
+ "grad_norm": 3.082258462905884,
364
+ "learning_rate": 6.12e-06,
365
+ "loss": 1.0039,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.09506398537477148,
370
+ "grad_norm": 2.4003512859344482,
371
+ "learning_rate": 6.2399999999999995e-06,
372
+ "loss": 0.8934,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.09689213893967093,
377
+ "grad_norm": 2.605583667755127,
378
+ "learning_rate": 6.36e-06,
379
+ "loss": 0.8891,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.09872029250457039,
384
+ "grad_norm": 2.541799306869507,
385
+ "learning_rate": 6.48e-06,
386
+ "loss": 0.8183,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.10054844606946983,
391
+ "grad_norm": 2.594459056854248,
392
+ "learning_rate": 6.6e-06,
393
+ "loss": 0.9906,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.10237659963436929,
398
+ "grad_norm": 2.9506289958953857,
399
+ "learning_rate": 6.72e-06,
400
+ "loss": 0.8263,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.10420475319926874,
405
+ "grad_norm": 2.8362669944763184,
406
+ "learning_rate": 6.840000000000001e-06,
407
+ "loss": 0.9,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.10603290676416818,
412
+ "grad_norm": 2.6192896366119385,
413
+ "learning_rate": 6.96e-06,
414
+ "loss": 1.05,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.10786106032906764,
419
+ "grad_norm": 2.7502949237823486,
420
+ "learning_rate": 7.08e-06,
421
+ "loss": 0.87,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.10968921389396709,
426
+ "grad_norm": 2.6745474338531494,
427
+ "learning_rate": 7.2e-06,
428
+ "loss": 0.8163,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.11151736745886655,
433
+ "grad_norm": 2.6584086418151855,
434
+ "learning_rate": 7.32e-06,
435
+ "loss": 0.8813,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.113345521023766,
440
+ "grad_norm": 2.689574956893921,
441
+ "learning_rate": 7.44e-06,
442
+ "loss": 0.9404,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.11517367458866545,
447
+ "grad_norm": 2.754441738128662,
448
+ "learning_rate": 7.5600000000000005e-06,
449
+ "loss": 0.7416,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.1170018281535649,
454
+ "grad_norm": 2.8178014755249023,
455
+ "learning_rate": 7.680000000000001e-06,
456
+ "loss": 0.8377,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.11882998171846434,
461
+ "grad_norm": 2.8821122646331787,
462
+ "learning_rate": 7.8e-06,
463
+ "loss": 0.7101,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.1206581352833638,
468
+ "grad_norm": 2.6646909713745117,
469
+ "learning_rate": 7.92e-06,
470
+ "loss": 1.0581,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.12248628884826325,
475
+ "grad_norm": 2.9155476093292236,
476
+ "learning_rate": 8.040000000000001e-06,
477
+ "loss": 0.8417,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.12431444241316271,
482
+ "grad_norm": 2.7877771854400635,
483
+ "learning_rate": 8.160000000000001e-06,
484
+ "loss": 0.9266,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.12614259597806216,
489
+ "grad_norm": 2.625126361846924,
490
+ "learning_rate": 8.28e-06,
491
+ "loss": 1.0048,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.12797074954296161,
496
+ "grad_norm": 2.7259960174560547,
497
+ "learning_rate": 8.400000000000001e-06,
498
+ "loss": 0.9485,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.12979890310786105,
503
+ "grad_norm": 2.743478536605835,
504
+ "learning_rate": 8.52e-06,
505
+ "loss": 0.9221,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.1316270566727605,
510
+ "grad_norm": 2.586174964904785,
511
+ "learning_rate": 8.64e-06,
512
+ "loss": 0.8967,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.13345521023765997,
517
+ "grad_norm": 2.817873954772949,
518
+ "learning_rate": 8.759999999999999e-06,
519
+ "loss": 0.943,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.13528336380255943,
524
+ "grad_norm": 2.692861557006836,
525
+ "learning_rate": 8.88e-06,
526
+ "loss": 0.8334,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.13711151736745886,
531
+ "grad_norm": 2.9305572509765625,
532
+ "learning_rate": 9e-06,
533
+ "loss": 0.8215,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.13893967093235832,
538
+ "grad_norm": 2.898930072784424,
539
+ "learning_rate": 9.12e-06,
540
+ "loss": 0.8979,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.14076782449725778,
545
+ "grad_norm": 2.8066327571868896,
546
+ "learning_rate": 9.24e-06,
547
+ "loss": 1.0717,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.1425959780621572,
552
+ "grad_norm": 3.126624584197998,
553
+ "learning_rate": 9.36e-06,
554
+ "loss": 0.8887,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.14442413162705667,
559
+ "grad_norm": 2.469200611114502,
560
+ "learning_rate": 9.48e-06,
561
+ "loss": 0.9542,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.14625228519195613,
566
+ "grad_norm": 2.6940770149230957,
567
+ "learning_rate": 9.600000000000001e-06,
568
+ "loss": 0.9756,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.1480804387568556,
573
+ "grad_norm": 2.847891330718994,
574
+ "learning_rate": 9.72e-06,
575
+ "loss": 0.8966,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.14990859232175502,
580
+ "grad_norm": 2.9159109592437744,
581
+ "learning_rate": 9.84e-06,
582
+ "loss": 0.8055,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.15173674588665448,
587
+ "grad_norm": 2.9693570137023926,
588
+ "learning_rate": 9.960000000000001e-06,
589
+ "loss": 0.8913,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.15356489945155394,
594
+ "grad_norm": 2.6382272243499756,
595
+ "learning_rate": 1.008e-05,
596
+ "loss": 0.8565,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.15539305301645337,
601
+ "grad_norm": 2.7299423217773438,
602
+ "learning_rate": 1.02e-05,
603
+ "loss": 0.8096,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.15722120658135283,
608
+ "grad_norm": 2.7661237716674805,
609
+ "learning_rate": 1.032e-05,
610
+ "loss": 0.9193,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.1590493601462523,
615
+ "grad_norm": 3.0896854400634766,
616
+ "learning_rate": 1.044e-05,
617
+ "loss": 0.7745,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.16087751371115175,
622
+ "grad_norm": 2.6443893909454346,
623
+ "learning_rate": 1.0559999999999999e-05,
624
+ "loss": 0.8674,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.16270566727605118,
629
+ "grad_norm": 3.047353506088257,
630
+ "learning_rate": 1.068e-05,
631
+ "loss": 0.9062,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.16453382084095064,
636
+ "grad_norm": 2.7751214504241943,
637
+ "learning_rate": 1.08e-05,
638
+ "loss": 0.8222,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.1663619744058501,
643
+ "grad_norm": 2.5556681156158447,
644
+ "learning_rate": 1.092e-05,
645
+ "loss": 0.7737,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.16819012797074953,
650
+ "grad_norm": 2.840104103088379,
651
+ "learning_rate": 1.104e-05,
652
+ "loss": 0.9967,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.170018281535649,
657
+ "grad_norm": 2.784130811691284,
658
+ "learning_rate": 1.116e-05,
659
+ "loss": 0.8571,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.17184643510054845,
664
+ "grad_norm": 2.5982677936553955,
665
+ "learning_rate": 1.128e-05,
666
+ "loss": 0.7934,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.1736745886654479,
671
+ "grad_norm": 3.1838393211364746,
672
+ "learning_rate": 1.1400000000000001e-05,
673
+ "loss": 0.8569,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.17550274223034734,
678
+ "grad_norm": 2.793653726577759,
679
+ "learning_rate": 1.152e-05,
680
+ "loss": 0.9144,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.1773308957952468,
685
+ "grad_norm": 2.6756796836853027,
686
+ "learning_rate": 1.164e-05,
687
+ "loss": 0.8517,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.17915904936014626,
692
+ "grad_norm": 2.6979010105133057,
693
+ "learning_rate": 1.1760000000000001e-05,
694
+ "loss": 0.7551,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.1809872029250457,
699
+ "grad_norm": 2.9032483100891113,
700
+ "learning_rate": 1.1880000000000001e-05,
701
+ "loss": 0.777,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.18281535648994515,
706
+ "grad_norm": 2.555727243423462,
707
+ "learning_rate": 1.2e-05,
708
+ "loss": 0.7583,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.1846435100548446,
713
+ "grad_norm": 2.7780463695526123,
714
+ "learning_rate": 1.2120000000000001e-05,
715
+ "loss": 1.0916,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.18647166361974407,
720
+ "grad_norm": 2.791424512863159,
721
+ "learning_rate": 1.224e-05,
722
+ "loss": 0.9344,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.1882998171846435,
727
+ "grad_norm": 2.590106248855591,
728
+ "learning_rate": 1.236e-05,
729
+ "loss": 0.8391,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.19012797074954296,
734
+ "grad_norm": 2.7519073486328125,
735
+ "learning_rate": 1.2479999999999999e-05,
736
+ "loss": 0.7809,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.19195612431444242,
741
+ "grad_norm": 2.8074002265930176,
742
+ "learning_rate": 1.26e-05,
743
+ "loss": 0.8258,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.19378427787934185,
748
+ "grad_norm": 2.6220719814300537,
749
+ "learning_rate": 1.272e-05,
750
+ "loss": 0.7542,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.1956124314442413,
755
+ "grad_norm": 2.8143625259399414,
756
+ "learning_rate": 1.284e-05,
757
+ "loss": 0.8587,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.19744058500914077,
762
+ "grad_norm": 2.4876911640167236,
763
+ "learning_rate": 1.296e-05,
764
+ "loss": 0.8425,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.19926873857404023,
769
+ "grad_norm": 2.7102651596069336,
770
+ "learning_rate": 1.308e-05,
771
+ "loss": 0.9726,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.20109689213893966,
776
+ "grad_norm": 2.375572919845581,
777
+ "learning_rate": 1.32e-05,
778
+ "loss": 0.8122,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.20292504570383912,
783
+ "grad_norm": 2.485874652862549,
784
+ "learning_rate": 1.3320000000000001e-05,
785
+ "loss": 0.7726,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.20475319926873858,
790
+ "grad_norm": 2.5263822078704834,
791
+ "learning_rate": 1.344e-05,
792
+ "loss": 0.9219,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.20658135283363802,
797
+ "grad_norm": 2.5467567443847656,
798
+ "learning_rate": 1.356e-05,
799
+ "loss": 0.8116,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.20840950639853748,
804
+ "grad_norm": 2.3540358543395996,
805
+ "learning_rate": 1.3680000000000001e-05,
806
+ "loss": 1.0343,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.21023765996343693,
811
+ "grad_norm": 2.6379354000091553,
812
+ "learning_rate": 1.3800000000000002e-05,
813
+ "loss": 0.8242,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.21206581352833637,
818
+ "grad_norm": 2.5178139209747314,
819
+ "learning_rate": 1.392e-05,
820
+ "loss": 0.8899,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.21389396709323583,
825
+ "grad_norm": 2.802619695663452,
826
+ "learning_rate": 1.4040000000000001e-05,
827
+ "loss": 0.8031,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.21572212065813529,
832
+ "grad_norm": 2.7448935508728027,
833
+ "learning_rate": 1.416e-05,
834
+ "loss": 0.8676,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.21755027422303475,
839
+ "grad_norm": 2.626340627670288,
840
+ "learning_rate": 1.428e-05,
841
+ "loss": 0.9465,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.21937842778793418,
846
+ "grad_norm": 2.5691044330596924,
847
+ "learning_rate": 1.44e-05,
848
+ "loss": 0.712,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.22120658135283364,
853
+ "grad_norm": 2.877453565597534,
854
+ "learning_rate": 1.452e-05,
855
+ "loss": 0.8605,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.2230347349177331,
860
+ "grad_norm": 2.409876585006714,
861
+ "learning_rate": 1.464e-05,
862
+ "loss": 0.8972,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.22486288848263253,
867
+ "grad_norm": 2.517220973968506,
868
+ "learning_rate": 1.4760000000000001e-05,
869
+ "loss": 0.822,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.226691042047532,
874
+ "grad_norm": 2.53521728515625,
875
+ "learning_rate": 1.488e-05,
876
+ "loss": 0.7721,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.22851919561243145,
881
+ "grad_norm": 2.533579111099243,
882
+ "learning_rate": 1.5e-05,
883
+ "loss": 0.7182,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.2303473491773309,
888
+ "grad_norm": 2.8807780742645264,
889
+ "learning_rate": 1.5120000000000001e-05,
890
+ "loss": 0.8755,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.23217550274223034,
895
+ "grad_norm": 2.8886823654174805,
896
+ "learning_rate": 1.524e-05,
897
+ "loss": 0.8119,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.2340036563071298,
902
+ "grad_norm": 2.710432529449463,
903
+ "learning_rate": 1.5360000000000002e-05,
904
+ "loss": 0.7054,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.23583180987202926,
909
+ "grad_norm": 2.3780925273895264,
910
+ "learning_rate": 1.548e-05,
911
+ "loss": 0.9101,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.2376599634369287,
916
+ "grad_norm": 2.6293869018554688,
917
+ "learning_rate": 1.56e-05,
918
+ "loss": 0.7895,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.23948811700182815,
923
+ "grad_norm": 2.584303617477417,
924
+ "learning_rate": 1.5720000000000002e-05,
925
+ "loss": 1.0317,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.2413162705667276,
930
+ "grad_norm": 2.4637179374694824,
931
+ "learning_rate": 1.584e-05,
932
+ "loss": 0.7805,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.24314442413162707,
937
+ "grad_norm": 2.4105379581451416,
938
+ "learning_rate": 1.596e-05,
939
+ "loss": 0.8044,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.2449725776965265,
944
+ "grad_norm": 2.476205825805664,
945
+ "learning_rate": 1.6080000000000002e-05,
946
+ "loss": 0.7283,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.24680073126142596,
951
+ "grad_norm": 2.620548725128174,
952
+ "learning_rate": 1.62e-05,
953
+ "loss": 0.8035,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.24862888482632542,
958
+ "grad_norm": 2.4662225246429443,
959
+ "learning_rate": 1.6320000000000003e-05,
960
+ "loss": 0.8235,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.25045703839122485,
965
+ "grad_norm": 2.405362367630005,
966
+ "learning_rate": 1.6440000000000002e-05,
967
+ "loss": 0.8681,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.2522851919561243,
972
+ "grad_norm": 2.331638813018799,
973
+ "learning_rate": 1.656e-05,
974
+ "loss": 0.8784,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.25411334552102377,
979
+ "grad_norm": 2.796093463897705,
980
+ "learning_rate": 1.6680000000000003e-05,
981
+ "loss": 0.9942,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.25594149908592323,
986
+ "grad_norm": 2.3736331462860107,
987
+ "learning_rate": 1.6800000000000002e-05,
988
+ "loss": 0.7229,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.2577696526508227,
993
+ "grad_norm": 2.4110031127929688,
994
+ "learning_rate": 1.6919999999999997e-05,
995
+ "loss": 0.8202,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.2595978062157221,
1000
+ "grad_norm": 2.3349928855895996,
1001
+ "learning_rate": 1.704e-05,
1002
+ "loss": 0.7966,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.26142595978062155,
1007
+ "grad_norm": 2.4862008094787598,
1008
+ "learning_rate": 1.716e-05,
1009
+ "loss": 0.8141,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.263254113345521,
1014
+ "grad_norm": 2.787587881088257,
1015
+ "learning_rate": 1.728e-05,
1016
+ "loss": 0.7861,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.26508226691042047,
1021
+ "grad_norm": 2.687865972518921,
1022
+ "learning_rate": 1.74e-05,
1023
+ "loss": 0.9085,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.26691042047531993,
1028
+ "grad_norm": 2.517024278640747,
1029
+ "learning_rate": 1.7519999999999998e-05,
1030
+ "loss": 0.8719,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.2687385740402194,
1035
+ "grad_norm": 2.4157791137695312,
1036
+ "learning_rate": 1.764e-05,
1037
+ "loss": 0.8469,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.27056672760511885,
1042
+ "grad_norm": 2.647015333175659,
1043
+ "learning_rate": 1.776e-05,
1044
+ "loss": 0.8133,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.27239488117001825,
1049
+ "grad_norm": 2.7705986499786377,
1050
+ "learning_rate": 1.7879999999999998e-05,
1051
+ "loss": 0.8819,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.2742230347349177,
1056
+ "grad_norm": 2.2369964122772217,
1057
+ "learning_rate": 1.8e-05,
1058
+ "loss": 0.88,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.2760511882998172,
1063
+ "grad_norm": 2.239433765411377,
1064
+ "learning_rate": 1.812e-05,
1065
+ "loss": 0.7873,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.27787934186471663,
1070
+ "grad_norm": 2.493117332458496,
1071
+ "learning_rate": 1.824e-05,
1072
+ "loss": 0.8111,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.2797074954296161,
1077
+ "grad_norm": 2.5309877395629883,
1078
+ "learning_rate": 1.836e-05,
1079
+ "loss": 0.7235,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.28153564899451555,
1084
+ "grad_norm": 2.403522491455078,
1085
+ "learning_rate": 1.848e-05,
1086
+ "loss": 0.816,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.283363802559415,
1091
+ "grad_norm": 2.8262531757354736,
1092
+ "learning_rate": 1.86e-05,
1093
+ "loss": 0.9069,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.2851919561243144,
1098
+ "grad_norm": 2.51188588142395,
1099
+ "learning_rate": 1.872e-05,
1100
+ "loss": 0.8979,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.2870201096892139,
1105
+ "grad_norm": 2.493990659713745,
1106
+ "learning_rate": 1.884e-05,
1107
+ "loss": 0.798,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.28884826325411334,
1112
+ "grad_norm": 2.5412824153900146,
1113
+ "learning_rate": 1.896e-05,
1114
+ "loss": 0.7898,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.2906764168190128,
1119
+ "grad_norm": 2.4731011390686035,
1120
+ "learning_rate": 1.908e-05,
1121
+ "loss": 0.8854,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.29250457038391225,
1126
+ "grad_norm": 2.6185050010681152,
1127
+ "learning_rate": 1.9200000000000003e-05,
1128
+ "loss": 0.8163,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.2943327239488117,
1133
+ "grad_norm": 2.384073495864868,
1134
+ "learning_rate": 1.932e-05,
1135
+ "loss": 0.7888,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.2961608775137112,
1140
+ "grad_norm": 2.566452741622925,
1141
+ "learning_rate": 1.944e-05,
1142
+ "loss": 0.8344,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.2979890310786106,
1147
+ "grad_norm": 2.4498672485351562,
1148
+ "learning_rate": 1.9560000000000002e-05,
1149
+ "loss": 0.8288,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.29981718464351004,
1154
+ "grad_norm": 2.7561299800872803,
1155
+ "learning_rate": 1.968e-05,
1156
+ "loss": 0.8321,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.3016453382084095,
1161
+ "grad_norm": 2.5148916244506836,
1162
+ "learning_rate": 1.98e-05,
1163
+ "loss": 0.8343,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.30347349177330896,
1168
+ "grad_norm": 2.444960594177246,
1169
+ "learning_rate": 1.9920000000000002e-05,
1170
+ "loss": 0.6833,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.3053016453382084,
1175
+ "grad_norm": 2.5153768062591553,
1176
+ "learning_rate": 2.004e-05,
1177
+ "loss": 0.9192,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.3071297989031079,
1182
+ "grad_norm": 2.301560640335083,
1183
+ "learning_rate": 2.016e-05,
1184
+ "loss": 0.7864,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.30895795246800734,
1189
+ "grad_norm": 2.628103733062744,
1190
+ "learning_rate": 2.0280000000000002e-05,
1191
+ "loss": 0.8426,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.31078610603290674,
1196
+ "grad_norm": 2.4587066173553467,
1197
+ "learning_rate": 2.04e-05,
1198
+ "loss": 0.8344,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.3126142595978062,
1203
+ "grad_norm": 2.4356703758239746,
1204
+ "learning_rate": 2.0520000000000003e-05,
1205
+ "loss": 0.7558,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.31444241316270566,
1210
+ "grad_norm": 2.531304121017456,
1211
+ "learning_rate": 2.064e-05,
1212
+ "loss": 0.855,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.3162705667276051,
1217
+ "grad_norm": 2.2168610095977783,
1218
+ "learning_rate": 2.0759999999999998e-05,
1219
+ "loss": 0.8551,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.3180987202925046,
1224
+ "grad_norm": 2.4772465229034424,
1225
+ "learning_rate": 2.088e-05,
1226
+ "loss": 0.8782,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.31992687385740404,
1231
+ "grad_norm": 2.4406375885009766,
1232
+ "learning_rate": 2.1e-05,
1233
+ "loss": 0.775,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.3217550274223035,
1238
+ "grad_norm": 2.638505697250366,
1239
+ "learning_rate": 2.1119999999999998e-05,
1240
+ "loss": 0.9181,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.3235831809872029,
1245
+ "grad_norm": 2.452930212020874,
1246
+ "learning_rate": 2.124e-05,
1247
+ "loss": 0.8452,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.32541133455210236,
1252
+ "grad_norm": 2.370314836502075,
1253
+ "learning_rate": 2.136e-05,
1254
+ "loss": 1.0293,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.3272394881170018,
1259
+ "grad_norm": 2.4259750843048096,
1260
+ "learning_rate": 2.148e-05,
1261
+ "loss": 0.7744,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.3290676416819013,
1266
+ "grad_norm": 2.374286413192749,
1267
+ "learning_rate": 2.16e-05,
1268
+ "loss": 0.8336,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.33089579524680074,
1273
+ "grad_norm": 2.4372458457946777,
1274
+ "learning_rate": 2.172e-05,
1275
+ "loss": 0.9673,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.3327239488117002,
1280
+ "grad_norm": 2.6595754623413086,
1281
+ "learning_rate": 2.184e-05,
1282
+ "loss": 0.8805,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.33455210237659966,
1287
+ "grad_norm": 2.521261692047119,
1288
+ "learning_rate": 2.196e-05,
1289
+ "loss": 0.962,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.33638025594149906,
1294
+ "grad_norm": 2.559983015060425,
1295
+ "learning_rate": 2.208e-05,
1296
+ "loss": 0.8236,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.3382084095063985,
1301
+ "grad_norm": 2.5021865367889404,
1302
+ "learning_rate": 2.22e-05,
1303
+ "loss": 0.7696,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.340036563071298,
1308
+ "grad_norm": 2.389669418334961,
1309
+ "learning_rate": 2.232e-05,
1310
+ "loss": 0.9296,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.34186471663619744,
1315
+ "grad_norm": 2.8006410598754883,
1316
+ "learning_rate": 2.2440000000000002e-05,
1317
+ "loss": 1.1051,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.3436928702010969,
1322
+ "grad_norm": 2.246638774871826,
1323
+ "learning_rate": 2.256e-05,
1324
+ "loss": 0.67,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.34552102376599636,
1329
+ "grad_norm": 2.3323843479156494,
1330
+ "learning_rate": 2.268e-05,
1331
+ "loss": 0.7483,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.3473491773308958,
1336
+ "grad_norm": 2.599168539047241,
1337
+ "learning_rate": 2.2800000000000002e-05,
1338
+ "loss": 0.7095,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.3491773308957952,
1343
+ "grad_norm": 2.5335357189178467,
1344
+ "learning_rate": 2.292e-05,
1345
+ "loss": 0.7943,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.3510054844606947,
1350
+ "grad_norm": 2.523808717727661,
1351
+ "learning_rate": 2.304e-05,
1352
+ "loss": 0.8714,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.35283363802559414,
1357
+ "grad_norm": 2.3433940410614014,
1358
+ "learning_rate": 2.3160000000000002e-05,
1359
+ "loss": 0.7879,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.3546617915904936,
1364
+ "grad_norm": 2.5101304054260254,
1365
+ "learning_rate": 2.328e-05,
1366
+ "loss": 0.9299,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.35648994515539306,
1371
+ "grad_norm": 2.652029275894165,
1372
+ "learning_rate": 2.3400000000000003e-05,
1373
+ "loss": 0.813,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.3583180987202925,
1378
+ "grad_norm": 2.250645160675049,
1379
+ "learning_rate": 2.3520000000000002e-05,
1380
+ "loss": 0.9784,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.360146252285192,
1385
+ "grad_norm": 2.2848877906799316,
1386
+ "learning_rate": 2.364e-05,
1387
+ "loss": 0.9483,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.3619744058500914,
1392
+ "grad_norm": 2.4996519088745117,
1393
+ "learning_rate": 2.3760000000000003e-05,
1394
+ "loss": 0.8746,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.36380255941499084,
1399
+ "grad_norm": 2.451387882232666,
1400
+ "learning_rate": 2.3880000000000002e-05,
1401
+ "loss": 0.8514,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.3656307129798903,
1406
+ "grad_norm": 2.382949113845825,
1407
+ "learning_rate": 2.4e-05,
1408
+ "loss": 1.0895,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.36745886654478976,
1413
+ "grad_norm": 2.407252788543701,
1414
+ "learning_rate": 2.4120000000000003e-05,
1415
+ "loss": 0.9273,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.3692870201096892,
1420
+ "grad_norm": 2.554053544998169,
1421
+ "learning_rate": 2.4240000000000002e-05,
1422
+ "loss": 0.8187,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.3711151736745887,
1427
+ "grad_norm": 2.1548268795013428,
1428
+ "learning_rate": 2.4360000000000004e-05,
1429
+ "loss": 0.9683,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.37294332723948814,
1434
+ "grad_norm": 2.419849395751953,
1435
+ "learning_rate": 2.448e-05,
1436
+ "loss": 0.8276,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.37477148080438755,
1441
+ "grad_norm": 2.300262451171875,
1442
+ "learning_rate": 2.4599999999999998e-05,
1443
+ "loss": 0.8748,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.376599634369287,
1448
+ "grad_norm": 2.4870543479919434,
1449
+ "learning_rate": 2.472e-05,
1450
+ "loss": 0.8901,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.37842778793418647,
1455
+ "grad_norm": 2.703481435775757,
1456
+ "learning_rate": 2.484e-05,
1457
+ "loss": 0.871,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.3802559414990859,
1462
+ "grad_norm": 2.597571611404419,
1463
+ "learning_rate": 2.4959999999999998e-05,
1464
+ "loss": 0.747,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.3820840950639854,
1469
+ "grad_norm": 2.4933812618255615,
1470
+ "learning_rate": 2.508e-05,
1471
+ "loss": 0.7869,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.38391224862888484,
1476
+ "grad_norm": 2.566986322402954,
1477
+ "learning_rate": 2.52e-05,
1478
+ "loss": 0.9081,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.3857404021937843,
1483
+ "grad_norm": 2.4893436431884766,
1484
+ "learning_rate": 2.5319999999999998e-05,
1485
+ "loss": 0.866,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.3875685557586837,
1490
+ "grad_norm": 2.5950074195861816,
1491
+ "learning_rate": 2.544e-05,
1492
+ "loss": 0.8783,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.38939670932358317,
1497
+ "grad_norm": 2.3816328048706055,
1498
+ "learning_rate": 2.556e-05,
1499
+ "loss": 0.8963,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.3912248628884826,
1504
+ "grad_norm": 2.064539670944214,
1505
+ "learning_rate": 2.568e-05,
1506
+ "loss": 0.8979,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.3930530164533821,
1511
+ "grad_norm": 2.43748140335083,
1512
+ "learning_rate": 2.58e-05,
1513
+ "loss": 0.8466,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.39488117001828155,
1518
+ "grad_norm": 2.2571210861206055,
1519
+ "learning_rate": 2.592e-05,
1520
+ "loss": 0.8433,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.396709323583181,
1525
+ "grad_norm": 2.3223443031311035,
1526
+ "learning_rate": 2.604e-05,
1527
+ "loss": 0.7485,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.39853747714808047,
1532
+ "grad_norm": 2.435385227203369,
1533
+ "learning_rate": 2.616e-05,
1534
+ "loss": 0.8868,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.40036563071297987,
1539
+ "grad_norm": 2.4609930515289307,
1540
+ "learning_rate": 2.628e-05,
1541
+ "loss": 0.7649,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.40219378427787933,
1546
+ "grad_norm": 2.3334007263183594,
1547
+ "learning_rate": 2.64e-05,
1548
+ "loss": 0.8722,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.4040219378427788,
1553
+ "grad_norm": 2.4103660583496094,
1554
+ "learning_rate": 2.652e-05,
1555
+ "loss": 0.8687,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.40585009140767825,
1560
+ "grad_norm": 2.386665105819702,
1561
+ "learning_rate": 2.6640000000000002e-05,
1562
+ "loss": 0.9062,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.4076782449725777,
1567
+ "grad_norm": 2.420870065689087,
1568
+ "learning_rate": 2.676e-05,
1569
+ "loss": 0.9941,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.40950639853747717,
1574
+ "grad_norm": 2.643944025039673,
1575
+ "learning_rate": 2.688e-05,
1576
+ "loss": 0.8953,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.4113345521023766,
1581
+ "grad_norm": 2.400880813598633,
1582
+ "learning_rate": 2.7000000000000002e-05,
1583
+ "loss": 0.8583,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.41316270566727603,
1588
+ "grad_norm": 2.415785312652588,
1589
+ "learning_rate": 2.712e-05,
1590
+ "loss": 0.7549,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.4149908592321755,
1595
+ "grad_norm": 2.6550943851470947,
1596
+ "learning_rate": 2.724e-05,
1597
+ "loss": 0.9005,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.41681901279707495,
1602
+ "grad_norm": 2.31974720954895,
1603
+ "learning_rate": 2.7360000000000002e-05,
1604
+ "loss": 0.9962,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.4186471663619744,
1609
+ "grad_norm": 2.463061571121216,
1610
+ "learning_rate": 2.748e-05,
1611
+ "loss": 0.7754,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.42047531992687387,
1616
+ "grad_norm": 2.5701842308044434,
1617
+ "learning_rate": 2.7600000000000003e-05,
1618
+ "loss": 0.772,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.42230347349177333,
1623
+ "grad_norm": 2.3573224544525146,
1624
+ "learning_rate": 2.7720000000000002e-05,
1625
+ "loss": 0.8872,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.42413162705667273,
1630
+ "grad_norm": 2.345667600631714,
1631
+ "learning_rate": 2.784e-05,
1632
+ "loss": 0.7977,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.4259597806215722,
1637
+ "grad_norm": 2.583740234375,
1638
+ "learning_rate": 2.7960000000000003e-05,
1639
+ "loss": 0.9406,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.42778793418647165,
1644
+ "grad_norm": 2.51877760887146,
1645
+ "learning_rate": 2.8080000000000002e-05,
1646
+ "loss": 0.8245,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.4296160877513711,
1651
+ "grad_norm": 2.6624832153320312,
1652
+ "learning_rate": 2.8199999999999998e-05,
1653
+ "loss": 0.8747,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.43144424131627057,
1658
+ "grad_norm": 2.6126315593719482,
1659
+ "learning_rate": 2.832e-05,
1660
+ "loss": 0.881,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.43327239488117003,
1665
+ "grad_norm": 2.533567428588867,
1666
+ "learning_rate": 2.844e-05,
1667
+ "loss": 0.9505,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.4351005484460695,
1672
+ "grad_norm": 2.4115335941314697,
1673
+ "learning_rate": 2.856e-05,
1674
+ "loss": 0.9703,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.4369287020109689,
1679
+ "grad_norm": 2.2946977615356445,
1680
+ "learning_rate": 2.868e-05,
1681
+ "loss": 0.8025,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.43875685557586835,
1686
+ "grad_norm": 2.7821929454803467,
1687
+ "learning_rate": 2.88e-05,
1688
+ "loss": 0.8108,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.4405850091407678,
1693
+ "grad_norm": 2.5924153327941895,
1694
+ "learning_rate": 2.892e-05,
1695
+ "loss": 0.7716,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.4424131627056673,
1700
+ "grad_norm": 2.484504222869873,
1701
+ "learning_rate": 2.904e-05,
1702
+ "loss": 0.8917,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.44424131627056673,
1707
+ "grad_norm": 2.4044761657714844,
1708
+ "learning_rate": 2.916e-05,
1709
+ "loss": 0.9806,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.4460694698354662,
1714
+ "grad_norm": 2.3332765102386475,
1715
+ "learning_rate": 2.928e-05,
1716
+ "loss": 0.7616,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.44789762340036565,
1721
+ "grad_norm": 2.3703112602233887,
1722
+ "learning_rate": 2.94e-05,
1723
+ "loss": 0.8937,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.44972577696526506,
1728
+ "grad_norm": 2.3351054191589355,
1729
+ "learning_rate": 2.9520000000000002e-05,
1730
+ "loss": 0.83,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.4515539305301645,
1735
+ "grad_norm": 2.3738510608673096,
1736
+ "learning_rate": 2.964e-05,
1737
+ "loss": 0.904,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.453382084095064,
1742
+ "grad_norm": 2.5012619495391846,
1743
+ "learning_rate": 2.976e-05,
1744
+ "loss": 0.8809,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.45521023765996343,
1749
+ "grad_norm": 2.5719287395477295,
1750
+ "learning_rate": 2.9880000000000002e-05,
1751
+ "loss": 0.773,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.4570383912248629,
1756
+ "grad_norm": 2.3036999702453613,
1757
+ "learning_rate": 3e-05,
1758
+ "loss": 0.7487,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.4570383912248629,
1763
+ "eval_loss": 0.8340924382209778,
1764
+ "eval_runtime": 11.3221,
1765
+ "eval_samples_per_second": 98.215,
1766
+ "eval_steps_per_second": 3.091,
1767
+ "step": 250
1768
+ },
1769
+ {
1770
+ "epoch": 0.45886654478976235,
1771
+ "grad_norm": 2.355015754699707,
1772
+ "learning_rate": 2.9999160841378727e-05,
1773
+ "loss": 0.7973,
1774
+ "step": 251
1775
+ },
1776
+ {
1777
+ "epoch": 0.4606946983546618,
1778
+ "grad_norm": 2.296038866043091,
1779
+ "learning_rate": 2.9996643459406528e-05,
1780
+ "loss": 0.8632,
1781
+ "step": 252
1782
+ },
1783
+ {
1784
+ "epoch": 0.4625228519195612,
1785
+ "grad_norm": 2.2504048347473145,
1786
+ "learning_rate": 2.999244813574778e-05,
1787
+ "loss": 0.704,
1788
+ "step": 253
1789
+ },
1790
+ {
1791
+ "epoch": 0.4643510054844607,
1792
+ "grad_norm": 2.4145545959472656,
1793
+ "learning_rate": 2.9986575339808077e-05,
1794
+ "loss": 0.7892,
1795
+ "step": 254
1796
+ },
1797
+ {
1798
+ "epoch": 0.46617915904936014,
1799
+ "grad_norm": 2.3196182250976562,
1800
+ "learning_rate": 2.997902572868174e-05,
1801
+ "loss": 0.9237,
1802
+ "step": 255
1803
+ },
1804
+ {
1805
+ "epoch": 0.4680073126142596,
1806
+ "grad_norm": 2.5195236206054688,
1807
+ "learning_rate": 2.9969800147078265e-05,
1808
+ "loss": 0.8632,
1809
+ "step": 256
1810
+ },
1811
+ {
1812
+ "epoch": 0.46983546617915906,
1813
+ "grad_norm": 2.3776962757110596,
1814
+ "learning_rate": 2.995889962722784e-05,
1815
+ "loss": 0.8948,
1816
+ "step": 257
1817
+ },
1818
+ {
1819
+ "epoch": 0.4716636197440585,
1820
+ "grad_norm": 2.3582563400268555,
1821
+ "learning_rate": 2.9946325388765812e-05,
1822
+ "loss": 0.8258,
1823
+ "step": 258
1824
+ },
1825
+ {
1826
+ "epoch": 0.473491773308958,
1827
+ "grad_norm": 2.4774725437164307,
1828
+ "learning_rate": 2.993207883859627e-05,
1829
+ "loss": 0.8687,
1830
+ "step": 259
1831
+ },
1832
+ {
1833
+ "epoch": 0.4753199268738574,
1834
+ "grad_norm": 2.2049193382263184,
1835
+ "learning_rate": 2.99161615707346e-05,
1836
+ "loss": 0.9289,
1837
+ "step": 260
1838
+ },
1839
+ {
1840
+ "epoch": 0.47714808043875684,
1841
+ "grad_norm": 2.2471542358398438,
1842
+ "learning_rate": 2.9898575366129145e-05,
1843
+ "loss": 0.8769,
1844
+ "step": 261
1845
+ },
1846
+ {
1847
+ "epoch": 0.4789762340036563,
1848
+ "grad_norm": 2.2609918117523193,
1849
+ "learning_rate": 2.9879322192461932e-05,
1850
+ "loss": 1.0632,
1851
+ "step": 262
1852
+ },
1853
+ {
1854
+ "epoch": 0.48080438756855576,
1855
+ "grad_norm": 2.3569087982177734,
1856
+ "learning_rate": 2.985840420392851e-05,
1857
+ "loss": 0.854,
1858
+ "step": 263
1859
+ },
1860
+ {
1861
+ "epoch": 0.4826325411334552,
1862
+ "grad_norm": 2.398346185684204,
1863
+ "learning_rate": 2.9835823740996944e-05,
1864
+ "loss": 0.7765,
1865
+ "step": 264
1866
+ },
1867
+ {
1868
+ "epoch": 0.4844606946983547,
1869
+ "grad_norm": 2.251390218734741,
1870
+ "learning_rate": 2.9811583330145915e-05,
1871
+ "loss": 0.8045,
1872
+ "step": 265
1873
+ },
1874
+ {
1875
+ "epoch": 0.48628884826325414,
1876
+ "grad_norm": 2.3630456924438477,
1877
+ "learning_rate": 2.9785685683582057e-05,
1878
+ "loss": 0.8945,
1879
+ "step": 266
1880
+ },
1881
+ {
1882
+ "epoch": 0.48811700182815354,
1883
+ "grad_norm": 2.259655714035034,
1884
+ "learning_rate": 2.975813369893649e-05,
1885
+ "loss": 0.7409,
1886
+ "step": 267
1887
+ },
1888
+ {
1889
+ "epoch": 0.489945155393053,
1890
+ "grad_norm": 2.4072036743164062,
1891
+ "learning_rate": 2.97289304589406e-05,
1892
+ "loss": 0.8358,
1893
+ "step": 268
1894
+ },
1895
+ {
1896
+ "epoch": 0.49177330895795246,
1897
+ "grad_norm": 2.3019490242004395,
1898
+ "learning_rate": 2.9698079231081144e-05,
1899
+ "loss": 0.8837,
1900
+ "step": 269
1901
+ },
1902
+ {
1903
+ "epoch": 0.4936014625228519,
1904
+ "grad_norm": 2.3812527656555176,
1905
+ "learning_rate": 2.966558346723463e-05,
1906
+ "loss": 0.8772,
1907
+ "step": 270
1908
+ },
1909
+ {
1910
+ "epoch": 0.4954296160877514,
1911
+ "grad_norm": 2.3249640464782715,
1912
+ "learning_rate": 2.963144680328111e-05,
1913
+ "loss": 0.7369,
1914
+ "step": 271
1915
+ },
1916
+ {
1917
+ "epoch": 0.49725776965265084,
1918
+ "grad_norm": 2.431414842605591,
1919
+ "learning_rate": 2.959567305869736e-05,
1920
+ "loss": 0.8207,
1921
+ "step": 272
1922
+ },
1923
+ {
1924
+ "epoch": 0.4990859232175503,
1925
+ "grad_norm": 2.3795621395111084,
1926
+ "learning_rate": 2.955826623612954e-05,
1927
+ "loss": 0.73,
1928
+ "step": 273
1929
+ },
1930
+ {
1931
+ "epoch": 0.5009140767824497,
1932
+ "grad_norm": 2.426405906677246,
1933
+ "learning_rate": 2.9519230520945346e-05,
1934
+ "loss": 0.9324,
1935
+ "step": 274
1936
+ },
1937
+ {
1938
+ "epoch": 0.5027422303473492,
1939
+ "grad_norm": 2.2649593353271484,
1940
+ "learning_rate": 2.947857028076569e-05,
1941
+ "loss": 0.8003,
1942
+ "step": 275
1943
+ },
1944
+ {
1945
+ "epoch": 0.5045703839122486,
1946
+ "grad_norm": 2.481842041015625,
1947
+ "learning_rate": 2.943629006497606e-05,
1948
+ "loss": 0.7915,
1949
+ "step": 276
1950
+ },
1951
+ {
1952
+ "epoch": 0.506398537477148,
1953
+ "grad_norm": 2.5210118293762207,
1954
+ "learning_rate": 2.939239460421746e-05,
1955
+ "loss": 0.7953,
1956
+ "step": 277
1957
+ },
1958
+ {
1959
+ "epoch": 0.5082266910420475,
1960
+ "grad_norm": 2.3630707263946533,
1961
+ "learning_rate": 2.934688880985714e-05,
1962
+ "loss": 0.8232,
1963
+ "step": 278
1964
+ },
1965
+ {
1966
+ "epoch": 0.5100548446069469,
1967
+ "grad_norm": 2.3418996334075928,
1968
+ "learning_rate": 2.9299777773439056e-05,
1969
+ "loss": 0.909,
1970
+ "step": 279
1971
+ },
1972
+ {
1973
+ "epoch": 0.5118829981718465,
1974
+ "grad_norm": 2.34122633934021,
1975
+ "learning_rate": 2.925106676611418e-05,
1976
+ "loss": 0.7633,
1977
+ "step": 280
1978
+ },
1979
+ {
1980
+ "epoch": 0.5137111517367459,
1981
+ "grad_norm": 2.499547243118286,
1982
+ "learning_rate": 2.9200761238050756e-05,
1983
+ "loss": 0.851,
1984
+ "step": 281
1985
+ },
1986
+ {
1987
+ "epoch": 0.5155393053016454,
1988
+ "grad_norm": 2.456969738006592,
1989
+ "learning_rate": 2.9148866817824454e-05,
1990
+ "loss": 0.8803,
1991
+ "step": 282
1992
+ },
1993
+ {
1994
+ "epoch": 0.5173674588665448,
1995
+ "grad_norm": 2.2602295875549316,
1996
+ "learning_rate": 2.9095389311788626e-05,
1997
+ "loss": 0.8049,
1998
+ "step": 283
1999
+ },
2000
+ {
2001
+ "epoch": 0.5191956124314442,
2002
+ "grad_norm": 2.1520049571990967,
2003
+ "learning_rate": 2.9040334703424637e-05,
2004
+ "loss": 0.7233,
2005
+ "step": 284
2006
+ },
2007
+ {
2008
+ "epoch": 0.5210237659963437,
2009
+ "grad_norm": 2.4685440063476562,
2010
+ "learning_rate": 2.8983709152672386e-05,
2011
+ "loss": 0.9514,
2012
+ "step": 285
2013
+ },
2014
+ {
2015
+ "epoch": 0.5228519195612431,
2016
+ "grad_norm": 2.296013593673706,
2017
+ "learning_rate": 2.892551899524109e-05,
2018
+ "loss": 0.7938,
2019
+ "step": 286
2020
+ },
2021
+ {
2022
+ "epoch": 0.5246800731261426,
2023
+ "grad_norm": 2.3713924884796143,
2024
+ "learning_rate": 2.8865770741900382e-05,
2025
+ "loss": 0.93,
2026
+ "step": 287
2027
+ },
2028
+ {
2029
+ "epoch": 0.526508226691042,
2030
+ "grad_norm": 2.6389975547790527,
2031
+ "learning_rate": 2.8804471077751847e-05,
2032
+ "loss": 0.9036,
2033
+ "step": 288
2034
+ },
2035
+ {
2036
+ "epoch": 0.5283363802559415,
2037
+ "grad_norm": 2.4582440853118896,
2038
+ "learning_rate": 2.8741626861481043e-05,
2039
+ "loss": 0.9437,
2040
+ "step": 289
2041
+ },
2042
+ {
2043
+ "epoch": 0.5301645338208409,
2044
+ "grad_norm": 2.3008275032043457,
2045
+ "learning_rate": 2.8677245124590087e-05,
2046
+ "loss": 0.7939,
2047
+ "step": 290
2048
+ },
2049
+ {
2050
+ "epoch": 0.5319926873857403,
2051
+ "grad_norm": 2.319469928741455,
2052
+ "learning_rate": 2.8611333070610918e-05,
2053
+ "loss": 0.8535,
2054
+ "step": 291
2055
+ },
2056
+ {
2057
+ "epoch": 0.5338208409506399,
2058
+ "grad_norm": 2.295746088027954,
2059
+ "learning_rate": 2.8543898074299322e-05,
2060
+ "loss": 0.736,
2061
+ "step": 292
2062
+ },
2063
+ {
2064
+ "epoch": 0.5356489945155393,
2065
+ "grad_norm": 2.5527262687683105,
2066
+ "learning_rate": 2.8474947680809754e-05,
2067
+ "loss": 0.8192,
2068
+ "step": 293
2069
+ },
2070
+ {
2071
+ "epoch": 0.5374771480804388,
2072
+ "grad_norm": 2.308958053588867,
2073
+ "learning_rate": 2.8404489604851186e-05,
2074
+ "loss": 0.9077,
2075
+ "step": 294
2076
+ },
2077
+ {
2078
+ "epoch": 0.5393053016453382,
2079
+ "grad_norm": 2.524796724319458,
2080
+ "learning_rate": 2.8332531729823853e-05,
2081
+ "loss": 0.8038,
2082
+ "step": 295
2083
+ },
2084
+ {
2085
+ "epoch": 0.5411334552102377,
2086
+ "grad_norm": 2.420640468597412,
2087
+ "learning_rate": 2.8259082106937255e-05,
2088
+ "loss": 0.7417,
2089
+ "step": 296
2090
+ },
2091
+ {
2092
+ "epoch": 0.5429616087751371,
2093
+ "grad_norm": 2.364328384399414,
2094
+ "learning_rate": 2.8184148954309295e-05,
2095
+ "loss": 0.8791,
2096
+ "step": 297
2097
+ },
2098
+ {
2099
+ "epoch": 0.5447897623400365,
2100
+ "grad_norm": 2.412336587905884,
2101
+ "learning_rate": 2.8107740656046775e-05,
2102
+ "loss": 0.83,
2103
+ "step": 298
2104
+ },
2105
+ {
2106
+ "epoch": 0.546617915904936,
2107
+ "grad_norm": 2.5241622924804688,
2108
+ "learning_rate": 2.802986576130733e-05,
2109
+ "loss": 0.8886,
2110
+ "step": 299
2111
+ },
2112
+ {
2113
+ "epoch": 0.5484460694698354,
2114
+ "grad_norm": 2.330146074295044,
2115
+ "learning_rate": 2.7950532983342863e-05,
2116
+ "loss": 0.8117,
2117
+ "step": 300
2118
+ },
2119
+ {
2120
+ "epoch": 0.5502742230347349,
2121
+ "grad_norm": 2.1738884449005127,
2122
+ "learning_rate": 2.7869751198524656e-05,
2123
+ "loss": 0.8588,
2124
+ "step": 301
2125
+ },
2126
+ {
2127
+ "epoch": 0.5521023765996343,
2128
+ "grad_norm": 2.343388319015503,
2129
+ "learning_rate": 2.7787529445350192e-05,
2130
+ "loss": 0.7355,
2131
+ "step": 302
2132
+ },
2133
+ {
2134
+ "epoch": 0.5539305301645339,
2135
+ "grad_norm": 2.2163190841674805,
2136
+ "learning_rate": 2.7703876923431882e-05,
2137
+ "loss": 0.8508,
2138
+ "step": 303
2139
+ },
2140
+ {
2141
+ "epoch": 0.5557586837294333,
2142
+ "grad_norm": 2.1025807857513428,
2143
+ "learning_rate": 2.7618802992467718e-05,
2144
+ "loss": 0.7909,
2145
+ "step": 304
2146
+ },
2147
+ {
2148
+ "epoch": 0.5575868372943327,
2149
+ "grad_norm": 2.4115538597106934,
2150
+ "learning_rate": 2.753231717119405e-05,
2151
+ "loss": 0.7964,
2152
+ "step": 305
2153
+ },
2154
+ {
2155
+ "epoch": 0.5594149908592322,
2156
+ "grad_norm": 2.2953007221221924,
2157
+ "learning_rate": 2.744442913632054e-05,
2158
+ "loss": 0.8284,
2159
+ "step": 306
2160
+ },
2161
+ {
2162
+ "epoch": 0.5612431444241316,
2163
+ "grad_norm": 2.4674270153045654,
2164
+ "learning_rate": 2.7355148721447492e-05,
2165
+ "loss": 0.9302,
2166
+ "step": 307
2167
+ },
2168
+ {
2169
+ "epoch": 0.5630712979890311,
2170
+ "grad_norm": 2.447037935256958,
2171
+ "learning_rate": 2.7264485915965548e-05,
2172
+ "loss": 0.9281,
2173
+ "step": 308
2174
+ },
2175
+ {
2176
+ "epoch": 0.5648994515539305,
2177
+ "grad_norm": 2.1784889698028564,
2178
+ "learning_rate": 2.717245086393801e-05,
2179
+ "loss": 0.7989,
2180
+ "step": 309
2181
+ },
2182
+ {
2183
+ "epoch": 0.56672760511883,
2184
+ "grad_norm": 2.2562270164489746,
2185
+ "learning_rate": 2.707905386296588e-05,
2186
+ "loss": 0.8856,
2187
+ "step": 310
2188
+ },
2189
+ {
2190
+ "epoch": 0.5685557586837294,
2191
+ "grad_norm": 2.272416591644287,
2192
+ "learning_rate": 2.6984305363035616e-05,
2193
+ "loss": 1.0322,
2194
+ "step": 311
2195
+ },
2196
+ {
2197
+ "epoch": 0.5703839122486288,
2198
+ "grad_norm": 2.2202160358428955,
2199
+ "learning_rate": 2.6888215965349974e-05,
2200
+ "loss": 0.9454,
2201
+ "step": 312
2202
+ },
2203
+ {
2204
+ "epoch": 0.5722120658135283,
2205
+ "grad_norm": 2.4724793434143066,
2206
+ "learning_rate": 2.6790796421141813e-05,
2207
+ "loss": 0.8584,
2208
+ "step": 313
2209
+ },
2210
+ {
2211
+ "epoch": 0.5740402193784278,
2212
+ "grad_norm": 2.3383536338806152,
2213
+ "learning_rate": 2.6692057630471184e-05,
2214
+ "loss": 0.978,
2215
+ "step": 314
2216
+ },
2217
+ {
2218
+ "epoch": 0.5758683729433273,
2219
+ "grad_norm": 2.173809766769409,
2220
+ "learning_rate": 2.6592010641005745e-05,
2221
+ "loss": 0.8318,
2222
+ "step": 315
2223
+ },
2224
+ {
2225
+ "epoch": 0.5776965265082267,
2226
+ "grad_norm": 2.306762456893921,
2227
+ "learning_rate": 2.649066664678467e-05,
2228
+ "loss": 0.841,
2229
+ "step": 316
2230
+ },
2231
+ {
2232
+ "epoch": 0.5795246800731262,
2233
+ "grad_norm": 2.038734197616577,
2234
+ "learning_rate": 2.638803698696615e-05,
2235
+ "loss": 0.8219,
2236
+ "step": 317
2237
+ },
2238
+ {
2239
+ "epoch": 0.5813528336380256,
2240
+ "grad_norm": 2.2740612030029297,
2241
+ "learning_rate": 2.6284133144558697e-05,
2242
+ "loss": 0.8945,
2243
+ "step": 318
2244
+ },
2245
+ {
2246
+ "epoch": 0.583180987202925,
2247
+ "grad_norm": 2.338181972503662,
2248
+ "learning_rate": 2.6178966745136322e-05,
2249
+ "loss": 1.0114,
2250
+ "step": 319
2251
+ },
2252
+ {
2253
+ "epoch": 0.5850091407678245,
2254
+ "grad_norm": 2.357879877090454,
2255
+ "learning_rate": 2.60725495555378e-05,
2256
+ "loss": 0.7024,
2257
+ "step": 320
2258
+ },
2259
+ {
2260
+ "epoch": 0.5868372943327239,
2261
+ "grad_norm": 2.271117925643921,
2262
+ "learning_rate": 2.5964893482550076e-05,
2263
+ "loss": 0.8802,
2264
+ "step": 321
2265
+ },
2266
+ {
2267
+ "epoch": 0.5886654478976234,
2268
+ "grad_norm": 2.092961072921753,
2269
+ "learning_rate": 2.5856010571576052e-05,
2270
+ "loss": 0.8343,
2271
+ "step": 322
2272
+ },
2273
+ {
2274
+ "epoch": 0.5904936014625228,
2275
+ "grad_norm": 2.297849655151367,
2276
+ "learning_rate": 2.574591300528686e-05,
2277
+ "loss": 0.8124,
2278
+ "step": 323
2279
+ },
2280
+ {
2281
+ "epoch": 0.5923217550274223,
2282
+ "grad_norm": 2.293593645095825,
2283
+ "learning_rate": 2.563461310225875e-05,
2284
+ "loss": 0.7819,
2285
+ "step": 324
2286
+ },
2287
+ {
2288
+ "epoch": 0.5941499085923218,
2289
+ "grad_norm": 2.2364585399627686,
2290
+ "learning_rate": 2.552212331559482e-05,
2291
+ "loss": 0.9649,
2292
+ "step": 325
2293
+ },
2294
+ {
2295
+ "epoch": 0.5959780621572212,
2296
+ "grad_norm": 2.2145204544067383,
2297
+ "learning_rate": 2.5408456231531634e-05,
2298
+ "loss": 0.8959,
2299
+ "step": 326
2300
+ },
2301
+ {
2302
+ "epoch": 0.5978062157221207,
2303
+ "grad_norm": 2.4612884521484375,
2304
+ "learning_rate": 2.5293624568031008e-05,
2305
+ "loss": 0.929,
2306
+ "step": 327
2307
+ },
2308
+ {
2309
+ "epoch": 0.5996343692870201,
2310
+ "grad_norm": 2.4367892742156982,
2311
+ "learning_rate": 2.5177641173356985e-05,
2312
+ "loss": 0.7942,
2313
+ "step": 328
2314
+ },
2315
+ {
2316
+ "epoch": 0.6014625228519196,
2317
+ "grad_norm": 2.5621209144592285,
2318
+ "learning_rate": 2.5060519024638312e-05,
2319
+ "loss": 0.9107,
2320
+ "step": 329
2321
+ },
2322
+ {
2323
+ "epoch": 0.603290676416819,
2324
+ "grad_norm": 2.2086422443389893,
2325
+ "learning_rate": 2.4942271226416444e-05,
2326
+ "loss": 0.7485,
2327
+ "step": 330
2328
+ },
2329
+ {
2330
+ "epoch": 0.6051188299817185,
2331
+ "grad_norm": 2.4878604412078857,
2332
+ "learning_rate": 2.482291100917928e-05,
2333
+ "loss": 0.8663,
2334
+ "step": 331
2335
+ },
2336
+ {
2337
+ "epoch": 0.6069469835466179,
2338
+ "grad_norm": 2.4622035026550293,
2339
+ "learning_rate": 2.4702451727880862e-05,
2340
+ "loss": 0.9976,
2341
+ "step": 332
2342
+ },
2343
+ {
2344
+ "epoch": 0.6087751371115173,
2345
+ "grad_norm": 2.313488245010376,
2346
+ "learning_rate": 2.458090686044712e-05,
2347
+ "loss": 0.86,
2348
+ "step": 333
2349
+ },
2350
+ {
2351
+ "epoch": 0.6106032906764168,
2352
+ "grad_norm": 2.495249032974243,
2353
+ "learning_rate": 2.445829000626784e-05,
2354
+ "loss": 0.7586,
2355
+ "step": 334
2356
+ },
2357
+ {
2358
+ "epoch": 0.6124314442413162,
2359
+ "grad_norm": 2.2994625568389893,
2360
+ "learning_rate": 2.433461488467505e-05,
2361
+ "loss": 0.9011,
2362
+ "step": 335
2363
+ },
2364
+ {
2365
+ "epoch": 0.6142595978062158,
2366
+ "grad_norm": 2.410585403442383,
2367
+ "learning_rate": 2.4209895333408028e-05,
2368
+ "loss": 0.7784,
2369
+ "step": 336
2370
+ },
2371
+ {
2372
+ "epoch": 0.6160877513711152,
2373
+ "grad_norm": 2.371408462524414,
2374
+ "learning_rate": 2.4084145307065e-05,
2375
+ "loss": 0.9034,
2376
+ "step": 337
2377
+ },
2378
+ {
2379
+ "epoch": 0.6179159049360147,
2380
+ "grad_norm": 2.2253592014312744,
2381
+ "learning_rate": 2.3957378875541795e-05,
2382
+ "loss": 0.8581,
2383
+ "step": 338
2384
+ },
2385
+ {
2386
+ "epoch": 0.6197440585009141,
2387
+ "grad_norm": 2.18859601020813,
2388
+ "learning_rate": 2.382961022245759e-05,
2389
+ "loss": 0.8338,
2390
+ "step": 339
2391
+ },
2392
+ {
2393
+ "epoch": 0.6215722120658135,
2394
+ "grad_norm": 2.1277389526367188,
2395
+ "learning_rate": 2.3700853643567973e-05,
2396
+ "loss": 0.7985,
2397
+ "step": 340
2398
+ },
2399
+ {
2400
+ "epoch": 0.623400365630713,
2401
+ "grad_norm": 2.2631025314331055,
2402
+ "learning_rate": 2.3571123545165362e-05,
2403
+ "loss": 0.865,
2404
+ "step": 341
2405
+ },
2406
+ {
2407
+ "epoch": 0.6252285191956124,
2408
+ "grad_norm": 2.4531781673431396,
2409
+ "learning_rate": 2.3440434442467155e-05,
2410
+ "loss": 0.8673,
2411
+ "step": 342
2412
+ },
2413
+ {
2414
+ "epoch": 0.6270566727605119,
2415
+ "grad_norm": 2.3396685123443604,
2416
+ "learning_rate": 2.3308800957991657e-05,
2417
+ "loss": 0.868,
2418
+ "step": 343
2419
+ },
2420
+ {
2421
+ "epoch": 0.6288848263254113,
2422
+ "grad_norm": 2.2110092639923096,
2423
+ "learning_rate": 2.3176237819921975e-05,
2424
+ "loss": 0.7553,
2425
+ "step": 344
2426
+ },
2427
+ {
2428
+ "epoch": 0.6307129798903108,
2429
+ "grad_norm": 2.3857622146606445,
2430
+ "learning_rate": 2.3042759860458142e-05,
2431
+ "loss": 0.7463,
2432
+ "step": 345
2433
+ },
2434
+ {
2435
+ "epoch": 0.6325411334552102,
2436
+ "grad_norm": 2.304614782333374,
2437
+ "learning_rate": 2.2908382014157536e-05,
2438
+ "loss": 0.939,
2439
+ "step": 346
2440
+ },
2441
+ {
2442
+ "epoch": 0.6343692870201096,
2443
+ "grad_norm": 2.360813617706299,
2444
+ "learning_rate": 2.2773119316263935e-05,
2445
+ "loss": 0.7792,
2446
+ "step": 347
2447
+ },
2448
+ {
2449
+ "epoch": 0.6361974405850092,
2450
+ "grad_norm": 2.41550612449646,
2451
+ "learning_rate": 2.2636986901025208e-05,
2452
+ "loss": 0.8776,
2453
+ "step": 348
2454
+ },
2455
+ {
2456
+ "epoch": 0.6380255941499086,
2457
+ "grad_norm": 2.514841318130493,
2458
+ "learning_rate": 2.25e-05,
2459
+ "loss": 0.8356,
2460
+ "step": 349
2461
+ },
2462
+ {
2463
+ "epoch": 0.6398537477148081,
2464
+ "grad_norm": 2.2054624557495117,
2465
+ "learning_rate": 2.2362173940353522e-05,
2466
+ "loss": 0.7899,
2467
+ "step": 350
2468
+ },
2469
+ {
2470
+ "epoch": 0.6416819012797075,
2471
+ "grad_norm": 2.144213914871216,
2472
+ "learning_rate": 2.2223524143142595e-05,
2473
+ "loss": 0.8054,
2474
+ "step": 351
2475
+ },
2476
+ {
2477
+ "epoch": 0.643510054844607,
2478
+ "grad_norm": 2.340751886367798,
2479
+ "learning_rate": 2.2084066121590242e-05,
2480
+ "loss": 0.8224,
2481
+ "step": 352
2482
+ },
2483
+ {
2484
+ "epoch": 0.6453382084095064,
2485
+ "grad_norm": 2.3917925357818604,
2486
+ "learning_rate": 2.194381547934994e-05,
2487
+ "loss": 0.8739,
2488
+ "step": 353
2489
+ },
2490
+ {
2491
+ "epoch": 0.6471663619744058,
2492
+ "grad_norm": 2.30846905708313,
2493
+ "learning_rate": 2.1802787908759767e-05,
2494
+ "loss": 0.866,
2495
+ "step": 354
2496
+ },
2497
+ {
2498
+ "epoch": 0.6489945155393053,
2499
+ "grad_norm": 2.0527448654174805,
2500
+ "learning_rate": 2.1660999189086613e-05,
2501
+ "loss": 0.8253,
2502
+ "step": 355
2503
+ },
2504
+ {
2505
+ "epoch": 0.6508226691042047,
2506
+ "grad_norm": 2.263025999069214,
2507
+ "learning_rate": 2.1518465184760686e-05,
2508
+ "loss": 0.8838,
2509
+ "step": 356
2510
+ },
2511
+ {
2512
+ "epoch": 0.6526508226691042,
2513
+ "grad_norm": 2.3904080390930176,
2514
+ "learning_rate": 2.1375201843600452e-05,
2515
+ "loss": 0.9442,
2516
+ "step": 357
2517
+ },
2518
+ {
2519
+ "epoch": 0.6544789762340036,
2520
+ "grad_norm": 2.1965222358703613,
2521
+ "learning_rate": 2.12312251950283e-05,
2522
+ "loss": 0.6803,
2523
+ "step": 358
2524
+ },
2525
+ {
2526
+ "epoch": 0.6563071297989032,
2527
+ "grad_norm": 2.2777087688446045,
2528
+ "learning_rate": 2.108655134827701e-05,
2529
+ "loss": 0.8077,
2530
+ "step": 359
2531
+ },
2532
+ {
2533
+ "epoch": 0.6581352833638026,
2534
+ "grad_norm": 2.2738406658172607,
2535
+ "learning_rate": 2.0941196490587352e-05,
2536
+ "loss": 0.855,
2537
+ "step": 360
2538
+ },
2539
+ {
2540
+ "epoch": 0.659963436928702,
2541
+ "grad_norm": 2.04484486579895,
2542
+ "learning_rate": 2.0795176885396928e-05,
2543
+ "loss": 0.8816,
2544
+ "step": 361
2545
+ },
2546
+ {
2547
+ "epoch": 0.6617915904936015,
2548
+ "grad_norm": 2.364666223526001,
2549
+ "learning_rate": 2.064850887052048e-05,
2550
+ "loss": 0.9707,
2551
+ "step": 362
2552
+ },
2553
+ {
2554
+ "epoch": 0.6636197440585009,
2555
+ "grad_norm": 2.2735183238983154,
2556
+ "learning_rate": 2.0501208856321895e-05,
2557
+ "loss": 0.8226,
2558
+ "step": 363
2559
+ },
2560
+ {
2561
+ "epoch": 0.6654478976234004,
2562
+ "grad_norm": 2.370248794555664,
2563
+ "learning_rate": 2.035329332387808e-05,
2564
+ "loss": 0.797,
2565
+ "step": 364
2566
+ },
2567
+ {
2568
+ "epoch": 0.6672760511882998,
2569
+ "grad_norm": 2.614694595336914,
2570
+ "learning_rate": 2.0204778823134936e-05,
2571
+ "loss": 0.8665,
2572
+ "step": 365
2573
+ },
2574
+ {
2575
+ "epoch": 0.6691042047531993,
2576
+ "grad_norm": 2.3441321849823,
2577
+ "learning_rate": 2.0055681971055626e-05,
2578
+ "loss": 0.8658,
2579
+ "step": 366
2580
+ },
2581
+ {
2582
+ "epoch": 0.6709323583180987,
2583
+ "grad_norm": 2.3217623233795166,
2584
+ "learning_rate": 1.990601944976133e-05,
2585
+ "loss": 0.8256,
2586
+ "step": 367
2587
+ },
2588
+ {
2589
+ "epoch": 0.6727605118829981,
2590
+ "grad_norm": 2.209233522415161,
2591
+ "learning_rate": 1.9755808004664702e-05,
2592
+ "loss": 0.7482,
2593
+ "step": 368
2594
+ },
2595
+ {
2596
+ "epoch": 0.6745886654478976,
2597
+ "grad_norm": 2.4364049434661865,
2598
+ "learning_rate": 1.9605064442596316e-05,
2599
+ "loss": 0.8031,
2600
+ "step": 369
2601
+ },
2602
+ {
2603
+ "epoch": 0.676416819012797,
2604
+ "grad_norm": 2.168339967727661,
2605
+ "learning_rate": 1.9453805629924126e-05,
2606
+ "loss": 0.8416,
2607
+ "step": 370
2608
+ },
2609
+ {
2610
+ "epoch": 0.6782449725776966,
2611
+ "grad_norm": 2.428342580795288,
2612
+ "learning_rate": 1.9302048490666356e-05,
2613
+ "loss": 0.8554,
2614
+ "step": 371
2615
+ },
2616
+ {
2617
+ "epoch": 0.680073126142596,
2618
+ "grad_norm": 1.9630411863327026,
2619
+ "learning_rate": 1.9149810004597906e-05,
2620
+ "loss": 0.7988,
2621
+ "step": 372
2622
+ },
2623
+ {
2624
+ "epoch": 0.6819012797074955,
2625
+ "grad_norm": 2.591010570526123,
2626
+ "learning_rate": 1.8997107205350525e-05,
2627
+ "loss": 1.048,
2628
+ "step": 373
2629
+ },
2630
+ {
2631
+ "epoch": 0.6837294332723949,
2632
+ "grad_norm": 2.476414442062378,
2633
+ "learning_rate": 1.884395717850694e-05,
2634
+ "loss": 0.8041,
2635
+ "step": 374
2636
+ },
2637
+ {
2638
+ "epoch": 0.6855575868372943,
2639
+ "grad_norm": 2.514333486557007,
2640
+ "learning_rate": 1.8690377059689202e-05,
2641
+ "loss": 0.8906,
2642
+ "step": 375
2643
+ },
2644
+ {
2645
+ "epoch": 0.6873857404021938,
2646
+ "grad_norm": 2.299752712249756,
2647
+ "learning_rate": 1.853638403264141e-05,
2648
+ "loss": 0.9203,
2649
+ "step": 376
2650
+ },
2651
+ {
2652
+ "epoch": 0.6892138939670932,
2653
+ "grad_norm": 2.3039369583129883,
2654
+ "learning_rate": 1.8381995327307067e-05,
2655
+ "loss": 0.8833,
2656
+ "step": 377
2657
+ },
2658
+ {
2659
+ "epoch": 0.6910420475319927,
2660
+ "grad_norm": 2.3373348712921143,
2661
+ "learning_rate": 1.822722821790126e-05,
2662
+ "loss": 0.7324,
2663
+ "step": 378
2664
+ },
2665
+ {
2666
+ "epoch": 0.6928702010968921,
2667
+ "grad_norm": 2.774083137512207,
2668
+ "learning_rate": 1.807210002097786e-05,
2669
+ "loss": 0.8778,
2670
+ "step": 379
2671
+ },
2672
+ {
2673
+ "epoch": 0.6946983546617916,
2674
+ "grad_norm": 2.214552402496338,
2675
+ "learning_rate": 1.791662809349206e-05,
2676
+ "loss": 0.8044,
2677
+ "step": 380
2678
+ },
2679
+ {
2680
+ "epoch": 0.696526508226691,
2681
+ "grad_norm": 2.298497438430786,
2682
+ "learning_rate": 1.7760829830858305e-05,
2683
+ "loss": 0.8667,
2684
+ "step": 381
2685
+ },
2686
+ {
2687
+ "epoch": 0.6983546617915904,
2688
+ "grad_norm": 2.23805570602417,
2689
+ "learning_rate": 1.760472266500396e-05,
2690
+ "loss": 0.7938,
2691
+ "step": 382
2692
+ },
2693
+ {
2694
+ "epoch": 0.70018281535649,
2695
+ "grad_norm": 2.18110990524292,
2696
+ "learning_rate": 1.744832406241889e-05,
2697
+ "loss": 0.8147,
2698
+ "step": 383
2699
+ },
2700
+ {
2701
+ "epoch": 0.7020109689213894,
2702
+ "grad_norm": 2.2718112468719482,
2703
+ "learning_rate": 1.7291651522201208e-05,
2704
+ "loss": 0.973,
2705
+ "step": 384
2706
+ },
2707
+ {
2708
+ "epoch": 0.7038391224862889,
2709
+ "grad_norm": 2.254279375076294,
2710
+ "learning_rate": 1.713472257409928e-05,
2711
+ "loss": 0.7439,
2712
+ "step": 385
2713
+ },
2714
+ {
2715
+ "epoch": 0.7056672760511883,
2716
+ "grad_norm": 2.268983840942383,
2717
+ "learning_rate": 1.6977554776550403e-05,
2718
+ "loss": 0.8309,
2719
+ "step": 386
2720
+ },
2721
+ {
2722
+ "epoch": 0.7074954296160878,
2723
+ "grad_norm": 2.189608097076416,
2724
+ "learning_rate": 1.682016571471623e-05,
2725
+ "loss": 0.8748,
2726
+ "step": 387
2727
+ },
2728
+ {
2729
+ "epoch": 0.7093235831809872,
2730
+ "grad_norm": 2.231454610824585,
2731
+ "learning_rate": 1.6662572998515166e-05,
2732
+ "loss": 0.8759,
2733
+ "step": 388
2734
+ },
2735
+ {
2736
+ "epoch": 0.7111517367458866,
2737
+ "grad_norm": 2.324653148651123,
2738
+ "learning_rate": 1.6504794260652077e-05,
2739
+ "loss": 0.7731,
2740
+ "step": 389
2741
+ },
2742
+ {
2743
+ "epoch": 0.7129798903107861,
2744
+ "grad_norm": 2.113718271255493,
2745
+ "learning_rate": 1.6346847154645376e-05,
2746
+ "loss": 0.7961,
2747
+ "step": 390
2748
+ },
2749
+ {
2750
+ "epoch": 0.7148080438756855,
2751
+ "grad_norm": 2.413463830947876,
2752
+ "learning_rate": 1.6188749352851825e-05,
2753
+ "loss": 0.9315,
2754
+ "step": 391
2755
+ },
2756
+ {
2757
+ "epoch": 0.716636197440585,
2758
+ "grad_norm": 2.175915002822876,
2759
+ "learning_rate": 1.6030518544489215e-05,
2760
+ "loss": 0.7061,
2761
+ "step": 392
2762
+ },
2763
+ {
2764
+ "epoch": 0.7184643510054844,
2765
+ "grad_norm": 2.2238268852233887,
2766
+ "learning_rate": 1.587217243365714e-05,
2767
+ "loss": 0.8585,
2768
+ "step": 393
2769
+ },
2770
+ {
2771
+ "epoch": 0.720292504570384,
2772
+ "grad_norm": 2.3010525703430176,
2773
+ "learning_rate": 1.5713728737356138e-05,
2774
+ "loss": 0.8064,
2775
+ "step": 394
2776
+ },
2777
+ {
2778
+ "epoch": 0.7221206581352834,
2779
+ "grad_norm": 2.2713418006896973,
2780
+ "learning_rate": 1.555520518350537e-05,
2781
+ "loss": 0.8125,
2782
+ "step": 395
2783
+ },
2784
+ {
2785
+ "epoch": 0.7239488117001828,
2786
+ "grad_norm": 2.311316967010498,
2787
+ "learning_rate": 1.5396619508959102e-05,
2788
+ "loss": 0.7494,
2789
+ "step": 396
2790
+ },
2791
+ {
2792
+ "epoch": 0.7257769652650823,
2793
+ "grad_norm": 2.3094563484191895,
2794
+ "learning_rate": 1.523798945752212e-05,
2795
+ "loss": 0.8135,
2796
+ "step": 397
2797
+ },
2798
+ {
2799
+ "epoch": 0.7276051188299817,
2800
+ "grad_norm": 2.1408050060272217,
2801
+ "learning_rate": 1.5079332777964467e-05,
2802
+ "loss": 0.8519,
2803
+ "step": 398
2804
+ },
2805
+ {
2806
+ "epoch": 0.7294332723948812,
2807
+ "grad_norm": 2.196596622467041,
2808
+ "learning_rate": 1.4920667222035532e-05,
2809
+ "loss": 0.9019,
2810
+ "step": 399
2811
+ },
2812
+ {
2813
+ "epoch": 0.7312614259597806,
2814
+ "grad_norm": 2.4077069759368896,
2815
+ "learning_rate": 1.4762010542477881e-05,
2816
+ "loss": 0.8437,
2817
+ "step": 400
2818
+ },
2819
+ {
2820
+ "epoch": 0.7330895795246801,
2821
+ "grad_norm": 2.138925075531006,
2822
+ "learning_rate": 1.46033804910409e-05,
2823
+ "loss": 0.7867,
2824
+ "step": 401
2825
+ },
2826
+ {
2827
+ "epoch": 0.7349177330895795,
2828
+ "grad_norm": 2.280134439468384,
2829
+ "learning_rate": 1.4444794816494629e-05,
2830
+ "loss": 1.0417,
2831
+ "step": 402
2832
+ },
2833
+ {
2834
+ "epoch": 0.7367458866544789,
2835
+ "grad_norm": 2.484534502029419,
2836
+ "learning_rate": 1.4286271262643866e-05,
2837
+ "loss": 0.7929,
2838
+ "step": 403
2839
+ },
2840
+ {
2841
+ "epoch": 0.7385740402193784,
2842
+ "grad_norm": 2.2009499073028564,
2843
+ "learning_rate": 1.4127827566342864e-05,
2844
+ "loss": 0.7963,
2845
+ "step": 404
2846
+ },
2847
+ {
2848
+ "epoch": 0.7404021937842779,
2849
+ "grad_norm": 2.313990831375122,
2850
+ "learning_rate": 1.3969481455510787e-05,
2851
+ "loss": 0.9538,
2852
+ "step": 405
2853
+ },
2854
+ {
2855
+ "epoch": 0.7422303473491774,
2856
+ "grad_norm": 2.1209707260131836,
2857
+ "learning_rate": 1.3811250647148172e-05,
2858
+ "loss": 0.8327,
2859
+ "step": 406
2860
+ },
2861
+ {
2862
+ "epoch": 0.7440585009140768,
2863
+ "grad_norm": 2.3821375370025635,
2864
+ "learning_rate": 1.3653152845354625e-05,
2865
+ "loss": 0.8677,
2866
+ "step": 407
2867
+ },
2868
+ {
2869
+ "epoch": 0.7458866544789763,
2870
+ "grad_norm": 2.179967164993286,
2871
+ "learning_rate": 1.3495205739347925e-05,
2872
+ "loss": 0.8095,
2873
+ "step": 408
2874
+ },
2875
+ {
2876
+ "epoch": 0.7477148080438757,
2877
+ "grad_norm": 2.5116395950317383,
2878
+ "learning_rate": 1.3337427001484836e-05,
2879
+ "loss": 0.9218,
2880
+ "step": 409
2881
+ },
2882
+ {
2883
+ "epoch": 0.7495429616087751,
2884
+ "grad_norm": 2.173802375793457,
2885
+ "learning_rate": 1.3179834285283773e-05,
2886
+ "loss": 0.7475,
2887
+ "step": 410
2888
+ },
2889
+ {
2890
+ "epoch": 0.7513711151736746,
2891
+ "grad_norm": 2.0795040130615234,
2892
+ "learning_rate": 1.3022445223449596e-05,
2893
+ "loss": 0.8749,
2894
+ "step": 411
2895
+ },
2896
+ {
2897
+ "epoch": 0.753199268738574,
2898
+ "grad_norm": 2.1474385261535645,
2899
+ "learning_rate": 1.2865277425900725e-05,
2900
+ "loss": 0.8277,
2901
+ "step": 412
2902
+ },
2903
+ {
2904
+ "epoch": 0.7550274223034735,
2905
+ "grad_norm": 2.243417978286743,
2906
+ "learning_rate": 1.2708348477798795e-05,
2907
+ "loss": 0.8147,
2908
+ "step": 413
2909
+ },
2910
+ {
2911
+ "epoch": 0.7568555758683729,
2912
+ "grad_norm": 2.3106589317321777,
2913
+ "learning_rate": 1.255167593758111e-05,
2914
+ "loss": 0.7848,
2915
+ "step": 414
2916
+ },
2917
+ {
2918
+ "epoch": 0.7586837294332724,
2919
+ "grad_norm": 2.397627830505371,
2920
+ "learning_rate": 1.2395277334996045e-05,
2921
+ "loss": 0.9778,
2922
+ "step": 415
2923
+ },
2924
+ {
2925
+ "epoch": 0.7605118829981719,
2926
+ "grad_norm": 2.3535757064819336,
2927
+ "learning_rate": 1.2239170169141696e-05,
2928
+ "loss": 0.7996,
2929
+ "step": 416
2930
+ },
2931
+ {
2932
+ "epoch": 0.7623400365630713,
2933
+ "grad_norm": 2.224731922149658,
2934
+ "learning_rate": 1.2083371906507939e-05,
2935
+ "loss": 0.8442,
2936
+ "step": 417
2937
+ },
2938
+ {
2939
+ "epoch": 0.7641681901279708,
2940
+ "grad_norm": 2.4303503036499023,
2941
+ "learning_rate": 1.1927899979022143e-05,
2942
+ "loss": 0.8317,
2943
+ "step": 418
2944
+ },
2945
+ {
2946
+ "epoch": 0.7659963436928702,
2947
+ "grad_norm": 2.4696667194366455,
2948
+ "learning_rate": 1.1772771782098748e-05,
2949
+ "loss": 0.8581,
2950
+ "step": 419
2951
+ },
2952
+ {
2953
+ "epoch": 0.7678244972577697,
2954
+ "grad_norm": 2.2766096591949463,
2955
+ "learning_rate": 1.1618004672692937e-05,
2956
+ "loss": 0.781,
2957
+ "step": 420
2958
+ },
2959
+ {
2960
+ "epoch": 0.7696526508226691,
2961
+ "grad_norm": 2.2170205116271973,
2962
+ "learning_rate": 1.146361596735859e-05,
2963
+ "loss": 0.6847,
2964
+ "step": 421
2965
+ },
2966
+ {
2967
+ "epoch": 0.7714808043875686,
2968
+ "grad_norm": 2.301888942718506,
2969
+ "learning_rate": 1.1309622940310798e-05,
2970
+ "loss": 0.9334,
2971
+ "step": 422
2972
+ },
2973
+ {
2974
+ "epoch": 0.773308957952468,
2975
+ "grad_norm": 2.0786006450653076,
2976
+ "learning_rate": 1.1156042821493062e-05,
2977
+ "loss": 0.8339,
2978
+ "step": 423
2979
+ },
2980
+ {
2981
+ "epoch": 0.7751371115173674,
2982
+ "grad_norm": 2.1867787837982178,
2983
+ "learning_rate": 1.1002892794649478e-05,
2984
+ "loss": 0.8398,
2985
+ "step": 424
2986
+ },
2987
+ {
2988
+ "epoch": 0.7769652650822669,
2989
+ "grad_norm": 2.1924829483032227,
2990
+ "learning_rate": 1.0850189995402096e-05,
2991
+ "loss": 0.8241,
2992
+ "step": 425
2993
+ },
2994
+ {
2995
+ "epoch": 0.7787934186471663,
2996
+ "grad_norm": 2.104240655899048,
2997
+ "learning_rate": 1.069795150933365e-05,
2998
+ "loss": 0.83,
2999
+ "step": 426
3000
+ },
3001
+ {
3002
+ "epoch": 0.7806215722120659,
3003
+ "grad_norm": 2.301518201828003,
3004
+ "learning_rate": 1.0546194370075882e-05,
3005
+ "loss": 0.7494,
3006
+ "step": 427
3007
+ },
3008
+ {
3009
+ "epoch": 0.7824497257769653,
3010
+ "grad_norm": 2.3547585010528564,
3011
+ "learning_rate": 1.0394935557403684e-05,
3012
+ "loss": 0.7907,
3013
+ "step": 428
3014
+ },
3015
+ {
3016
+ "epoch": 0.7842778793418648,
3017
+ "grad_norm": 2.225034713745117,
3018
+ "learning_rate": 1.0244191995335299e-05,
3019
+ "loss": 0.8484,
3020
+ "step": 429
3021
+ },
3022
+ {
3023
+ "epoch": 0.7861060329067642,
3024
+ "grad_norm": 2.3130884170532227,
3025
+ "learning_rate": 1.0093980550238676e-05,
3026
+ "loss": 0.8425,
3027
+ "step": 430
3028
+ },
3029
+ {
3030
+ "epoch": 0.7879341864716636,
3031
+ "grad_norm": 2.425241708755493,
3032
+ "learning_rate": 9.944318028944374e-06,
3033
+ "loss": 0.9269,
3034
+ "step": 431
3035
+ },
3036
+ {
3037
+ "epoch": 0.7897623400365631,
3038
+ "grad_norm": 2.1149165630340576,
3039
+ "learning_rate": 9.795221176865065e-06,
3040
+ "loss": 0.7503,
3041
+ "step": 432
3042
+ },
3043
+ {
3044
+ "epoch": 0.7915904936014625,
3045
+ "grad_norm": 2.3856897354125977,
3046
+ "learning_rate": 9.646706676121924e-06,
3047
+ "loss": 0.8628,
3048
+ "step": 433
3049
+ },
3050
+ {
3051
+ "epoch": 0.793418647166362,
3052
+ "grad_norm": 2.1912615299224854,
3053
+ "learning_rate": 9.49879114367811e-06,
3054
+ "loss": 0.8198,
3055
+ "step": 434
3056
+ },
3057
+ {
3058
+ "epoch": 0.7952468007312614,
3059
+ "grad_norm": 2.1112685203552246,
3060
+ "learning_rate": 9.351491129479519e-06,
3061
+ "loss": 0.8933,
3062
+ "step": 435
3063
+ },
3064
+ {
3065
+ "epoch": 0.7970749542961609,
3066
+ "grad_norm": 2.3817248344421387,
3067
+ "learning_rate": 9.20482311460307e-06,
3068
+ "loss": 0.8212,
3069
+ "step": 436
3070
+ },
3071
+ {
3072
+ "epoch": 0.7989031078610603,
3073
+ "grad_norm": 2.216339349746704,
3074
+ "learning_rate": 9.058803509412647e-06,
3075
+ "loss": 0.7964,
3076
+ "step": 437
3077
+ },
3078
+ {
3079
+ "epoch": 0.8007312614259597,
3080
+ "grad_norm": 2.2197396755218506,
3081
+ "learning_rate": 8.913448651722994e-06,
3082
+ "loss": 0.7535,
3083
+ "step": 438
3084
+ },
3085
+ {
3086
+ "epoch": 0.8025594149908593,
3087
+ "grad_norm": 2.083980083465576,
3088
+ "learning_rate": 8.768774804971705e-06,
3089
+ "loss": 0.9009,
3090
+ "step": 439
3091
+ },
3092
+ {
3093
+ "epoch": 0.8043875685557587,
3094
+ "grad_norm": 2.0909934043884277,
3095
+ "learning_rate": 8.624798156399554e-06,
3096
+ "loss": 0.8016,
3097
+ "step": 440
3098
+ },
3099
+ {
3100
+ "epoch": 0.8062157221206582,
3101
+ "grad_norm": 2.4581222534179688,
3102
+ "learning_rate": 8.481534815239323e-06,
3103
+ "loss": 0.9227,
3104
+ "step": 441
3105
+ },
3106
+ {
3107
+ "epoch": 0.8080438756855576,
3108
+ "grad_norm": 2.1503217220306396,
3109
+ "learning_rate": 8.339000810913388e-06,
3110
+ "loss": 0.7305,
3111
+ "step": 442
3112
+ },
3113
+ {
3114
+ "epoch": 0.8098720292504571,
3115
+ "grad_norm": 1.9855475425720215,
3116
+ "learning_rate": 8.197212091240237e-06,
3117
+ "loss": 0.7195,
3118
+ "step": 443
3119
+ },
3120
+ {
3121
+ "epoch": 0.8117001828153565,
3122
+ "grad_norm": 2.25361967086792,
3123
+ "learning_rate": 8.056184520650064e-06,
3124
+ "loss": 0.7594,
3125
+ "step": 444
3126
+ },
3127
+ {
3128
+ "epoch": 0.8135283363802559,
3129
+ "grad_norm": 2.2054708003997803,
3130
+ "learning_rate": 7.915933878409762e-06,
3131
+ "loss": 0.7931,
3132
+ "step": 445
3133
+ },
3134
+ {
3135
+ "epoch": 0.8153564899451554,
3136
+ "grad_norm": 2.134115219116211,
3137
+ "learning_rate": 7.776475856857409e-06,
3138
+ "loss": 0.7195,
3139
+ "step": 446
3140
+ },
3141
+ {
3142
+ "epoch": 0.8171846435100548,
3143
+ "grad_norm": 1.9758131504058838,
3144
+ "learning_rate": 7.63782605964648e-06,
3145
+ "loss": 0.872,
3146
+ "step": 447
3147
+ },
3148
+ {
3149
+ "epoch": 0.8190127970749543,
3150
+ "grad_norm": 2.291642904281616,
3151
+ "learning_rate": 7.500000000000004e-06,
3152
+ "loss": 0.8467,
3153
+ "step": 448
3154
+ },
3155
+ {
3156
+ "epoch": 0.8208409506398537,
3157
+ "grad_norm": 2.2243387699127197,
3158
+ "learning_rate": 7.3630130989748e-06,
3159
+ "loss": 0.9038,
3160
+ "step": 449
3161
+ },
3162
+ {
3163
+ "epoch": 0.8226691042047533,
3164
+ "grad_norm": 2.283393383026123,
3165
+ "learning_rate": 7.226880683736066e-06,
3166
+ "loss": 0.8102,
3167
+ "step": 450
3168
+ },
3169
+ {
3170
+ "epoch": 0.8244972577696527,
3171
+ "grad_norm": 2.078200101852417,
3172
+ "learning_rate": 7.091617985842463e-06,
3173
+ "loss": 0.761,
3174
+ "step": 451
3175
+ },
3176
+ {
3177
+ "epoch": 0.8263254113345521,
3178
+ "grad_norm": 2.3057701587677,
3179
+ "learning_rate": 6.9572401395418615e-06,
3180
+ "loss": 0.8682,
3181
+ "step": 452
3182
+ },
3183
+ {
3184
+ "epoch": 0.8281535648994516,
3185
+ "grad_norm": 2.171827793121338,
3186
+ "learning_rate": 6.8237621800780255e-06,
3187
+ "loss": 0.7561,
3188
+ "step": 453
3189
+ },
3190
+ {
3191
+ "epoch": 0.829981718464351,
3192
+ "grad_norm": 2.3417348861694336,
3193
+ "learning_rate": 6.691199042008346e-06,
3194
+ "loss": 0.8277,
3195
+ "step": 454
3196
+ },
3197
+ {
3198
+ "epoch": 0.8318098720292505,
3199
+ "grad_norm": 2.1309165954589844,
3200
+ "learning_rate": 6.559565557532847e-06,
3201
+ "loss": 0.8441,
3202
+ "step": 455
3203
+ },
3204
+ {
3205
+ "epoch": 0.8336380255941499,
3206
+ "grad_norm": 2.3415029048919678,
3207
+ "learning_rate": 6.428876454834643e-06,
3208
+ "loss": 0.787,
3209
+ "step": 456
3210
+ },
3211
+ {
3212
+ "epoch": 0.8354661791590493,
3213
+ "grad_norm": 2.2141568660736084,
3214
+ "learning_rate": 6.2991463564320296e-06,
3215
+ "loss": 0.8158,
3216
+ "step": 457
3217
+ },
3218
+ {
3219
+ "epoch": 0.8372943327239488,
3220
+ "grad_norm": 2.0096514225006104,
3221
+ "learning_rate": 6.170389777542409e-06,
3222
+ "loss": 0.7489,
3223
+ "step": 458
3224
+ },
3225
+ {
3226
+ "epoch": 0.8391224862888482,
3227
+ "grad_norm": 2.125929355621338,
3228
+ "learning_rate": 6.0426211244582105e-06,
3229
+ "loss": 0.8803,
3230
+ "step": 459
3231
+ },
3232
+ {
3233
+ "epoch": 0.8409506398537477,
3234
+ "grad_norm": 2.0805740356445312,
3235
+ "learning_rate": 5.915854692935002e-06,
3236
+ "loss": 0.773,
3237
+ "step": 460
3238
+ },
3239
+ {
3240
+ "epoch": 0.8427787934186471,
3241
+ "grad_norm": 2.357139825820923,
3242
+ "learning_rate": 5.790104666591974e-06,
3243
+ "loss": 0.7609,
3244
+ "step": 461
3245
+ },
3246
+ {
3247
+ "epoch": 0.8446069469835467,
3248
+ "grad_norm": 2.277031898498535,
3249
+ "learning_rate": 5.665385115324954e-06,
3250
+ "loss": 0.8573,
3251
+ "step": 462
3252
+ },
3253
+ {
3254
+ "epoch": 0.8464351005484461,
3255
+ "grad_norm": 2.2020912170410156,
3256
+ "learning_rate": 5.541709993732168e-06,
3257
+ "loss": 0.9261,
3258
+ "step": 463
3259
+ },
3260
+ {
3261
+ "epoch": 0.8482632541133455,
3262
+ "grad_norm": 2.294649362564087,
3263
+ "learning_rate": 5.419093139552878e-06,
3264
+ "loss": 0.8164,
3265
+ "step": 464
3266
+ },
3267
+ {
3268
+ "epoch": 0.850091407678245,
3269
+ "grad_norm": 2.047896385192871,
3270
+ "learning_rate": 5.297548272119138e-06,
3271
+ "loss": 0.8419,
3272
+ "step": 465
3273
+ },
3274
+ {
3275
+ "epoch": 0.8519195612431444,
3276
+ "grad_norm": 2.4558777809143066,
3277
+ "learning_rate": 5.177088990820725e-06,
3278
+ "loss": 0.8319,
3279
+ "step": 466
3280
+ },
3281
+ {
3282
+ "epoch": 0.8537477148080439,
3283
+ "grad_norm": 2.008725643157959,
3284
+ "learning_rate": 5.05772877358356e-06,
3285
+ "loss": 0.7503,
3286
+ "step": 467
3287
+ },
3288
+ {
3289
+ "epoch": 0.8555758683729433,
3290
+ "grad_norm": 2.16011643409729,
3291
+ "learning_rate": 4.939480975361687e-06,
3292
+ "loss": 0.7007,
3293
+ "step": 468
3294
+ },
3295
+ {
3296
+ "epoch": 0.8574040219378428,
3297
+ "grad_norm": 2.166571855545044,
3298
+ "learning_rate": 4.822358826643019e-06,
3299
+ "loss": 0.7383,
3300
+ "step": 469
3301
+ },
3302
+ {
3303
+ "epoch": 0.8592321755027422,
3304
+ "grad_norm": 2.3428239822387695,
3305
+ "learning_rate": 4.706375431968998e-06,
3306
+ "loss": 0.792,
3307
+ "step": 470
3308
+ },
3309
+ {
3310
+ "epoch": 0.8610603290676416,
3311
+ "grad_norm": 2.3133058547973633,
3312
+ "learning_rate": 4.591543768468364e-06,
3313
+ "loss": 0.7791,
3314
+ "step": 471
3315
+ },
3316
+ {
3317
+ "epoch": 0.8628884826325411,
3318
+ "grad_norm": 2.227383852005005,
3319
+ "learning_rate": 4.4778766844051795e-06,
3320
+ "loss": 0.8838,
3321
+ "step": 472
3322
+ },
3323
+ {
3324
+ "epoch": 0.8647166361974405,
3325
+ "grad_norm": 1.9852975606918335,
3326
+ "learning_rate": 4.365386897741249e-06,
3327
+ "loss": 0.8375,
3328
+ "step": 473
3329
+ },
3330
+ {
3331
+ "epoch": 0.8665447897623401,
3332
+ "grad_norm": 2.151278018951416,
3333
+ "learning_rate": 4.254086994713141e-06,
3334
+ "loss": 0.7966,
3335
+ "step": 474
3336
+ },
3337
+ {
3338
+ "epoch": 0.8683729433272395,
3339
+ "grad_norm": 2.355102777481079,
3340
+ "learning_rate": 4.1439894284239474e-06,
3341
+ "loss": 0.8264,
3342
+ "step": 475
3343
+ },
3344
+ {
3345
+ "epoch": 0.870201096892139,
3346
+ "grad_norm": 2.390646457672119,
3347
+ "learning_rate": 4.035106517449926e-06,
3348
+ "loss": 0.8292,
3349
+ "step": 476
3350
+ },
3351
+ {
3352
+ "epoch": 0.8720292504570384,
3353
+ "grad_norm": 2.1484568119049072,
3354
+ "learning_rate": 3.9274504444622025e-06,
3355
+ "loss": 0.8624,
3356
+ "step": 477
3357
+ },
3358
+ {
3359
+ "epoch": 0.8738574040219378,
3360
+ "grad_norm": 2.134361505508423,
3361
+ "learning_rate": 3.82103325486368e-06,
3362
+ "loss": 0.8226,
3363
+ "step": 478
3364
+ },
3365
+ {
3366
+ "epoch": 0.8756855575868373,
3367
+ "grad_norm": 2.1799209117889404,
3368
+ "learning_rate": 3.715866855441309e-06,
3369
+ "loss": 0.7563,
3370
+ "step": 479
3371
+ },
3372
+ {
3373
+ "epoch": 0.8775137111517367,
3374
+ "grad_norm": 2.338834285736084,
3375
+ "learning_rate": 3.6119630130338537e-06,
3376
+ "loss": 0.8319,
3377
+ "step": 480
3378
+ },
3379
+ {
3380
+ "epoch": 0.8793418647166362,
3381
+ "grad_norm": 2.032010555267334,
3382
+ "learning_rate": 3.5093333532153316e-06,
3383
+ "loss": 0.7693,
3384
+ "step": 481
3385
+ },
3386
+ {
3387
+ "epoch": 0.8811700182815356,
3388
+ "grad_norm": 2.1978771686553955,
3389
+ "learning_rate": 3.4079893589942544e-06,
3390
+ "loss": 0.7642,
3391
+ "step": 482
3392
+ },
3393
+ {
3394
+ "epoch": 0.8829981718464351,
3395
+ "grad_norm": 2.5220754146575928,
3396
+ "learning_rate": 3.3079423695288204e-06,
3397
+ "loss": 0.9182,
3398
+ "step": 483
3399
+ },
3400
+ {
3401
+ "epoch": 0.8848263254113345,
3402
+ "grad_norm": 2.1148622035980225,
3403
+ "learning_rate": 3.2092035788581907e-06,
3404
+ "loss": 0.8411,
3405
+ "step": 484
3406
+ },
3407
+ {
3408
+ "epoch": 0.886654478976234,
3409
+ "grad_norm": 2.1336936950683594,
3410
+ "learning_rate": 3.1117840346500287e-06,
3411
+ "loss": 0.7711,
3412
+ "step": 485
3413
+ },
3414
+ {
3415
+ "epoch": 0.8884826325411335,
3416
+ "grad_norm": 2.175741672515869,
3417
+ "learning_rate": 3.0156946369643803e-06,
3418
+ "loss": 0.9526,
3419
+ "step": 486
3420
+ },
3421
+ {
3422
+ "epoch": 0.8903107861060329,
3423
+ "grad_norm": 2.207550525665283,
3424
+ "learning_rate": 2.9209461370341204e-06,
3425
+ "loss": 0.7538,
3426
+ "step": 487
3427
+ },
3428
+ {
3429
+ "epoch": 0.8921389396709324,
3430
+ "grad_norm": 2.0048232078552246,
3431
+ "learning_rate": 2.8275491360619875e-06,
3432
+ "loss": 0.8079,
3433
+ "step": 488
3434
+ },
3435
+ {
3436
+ "epoch": 0.8939670932358318,
3437
+ "grad_norm": 2.2302756309509277,
3438
+ "learning_rate": 2.735514084034457e-06,
3439
+ "loss": 0.8385,
3440
+ "step": 489
3441
+ },
3442
+ {
3443
+ "epoch": 0.8957952468007313,
3444
+ "grad_norm": 2.7533788681030273,
3445
+ "learning_rate": 2.64485127855251e-06,
3446
+ "loss": 0.7718,
3447
+ "step": 490
3448
+ },
3449
+ {
3450
+ "epoch": 0.8976234003656307,
3451
+ "grad_norm": 2.3614344596862793,
3452
+ "learning_rate": 2.5555708636794594e-06,
3453
+ "loss": 0.7767,
3454
+ "step": 491
3455
+ },
3456
+ {
3457
+ "epoch": 0.8994515539305301,
3458
+ "grad_norm": 2.726402521133423,
3459
+ "learning_rate": 2.467682828805956e-06,
3460
+ "loss": 0.7917,
3461
+ "step": 492
3462
+ },
3463
+ {
3464
+ "epoch": 0.9012797074954296,
3465
+ "grad_norm": 2.2285687923431396,
3466
+ "learning_rate": 2.38119700753228e-06,
3467
+ "loss": 0.8958,
3468
+ "step": 493
3469
+ },
3470
+ {
3471
+ "epoch": 0.903107861060329,
3472
+ "grad_norm": 2.1934146881103516,
3473
+ "learning_rate": 2.2961230765681158e-06,
3474
+ "loss": 0.7796,
3475
+ "step": 494
3476
+ },
3477
+ {
3478
+ "epoch": 0.9049360146252285,
3479
+ "grad_norm": 2.349043607711792,
3480
+ "learning_rate": 2.212470554649805e-06,
3481
+ "loss": 0.8538,
3482
+ "step": 495
3483
+ },
3484
+ {
3485
+ "epoch": 0.906764168190128,
3486
+ "grad_norm": 1.995997667312622,
3487
+ "learning_rate": 2.130248801475344e-06,
3488
+ "loss": 0.8433,
3489
+ "step": 496
3490
+ },
3491
+ {
3492
+ "epoch": 0.9085923217550275,
3493
+ "grad_norm": 2.1767685413360596,
3494
+ "learning_rate": 2.0494670166571356e-06,
3495
+ "loss": 0.8276,
3496
+ "step": 497
3497
+ },
3498
+ {
3499
+ "epoch": 0.9104204753199269,
3500
+ "grad_norm": 2.255619525909424,
3501
+ "learning_rate": 1.9701342386926712e-06,
3502
+ "loss": 0.7797,
3503
+ "step": 498
3504
+ },
3505
+ {
3506
+ "epoch": 0.9122486288848263,
3507
+ "grad_norm": 2.3576643466949463,
3508
+ "learning_rate": 1.892259343953226e-06,
3509
+ "loss": 0.9015,
3510
+ "step": 499
3511
+ },
3512
+ {
3513
+ "epoch": 0.9140767824497258,
3514
+ "grad_norm": 1.9980827569961548,
3515
+ "learning_rate": 1.815851045690708e-06,
3516
+ "loss": 0.6846,
3517
+ "step": 500
3518
+ },
3519
+ {
3520
+ "epoch": 0.9140767824497258,
3521
+ "eval_loss": 0.798653244972229,
3522
+ "eval_runtime": 11.4055,
3523
+ "eval_samples_per_second": 97.497,
3524
+ "eval_steps_per_second": 3.069,
3525
+ "step": 500
3526
+ },
3527
+ {
3528
+ "epoch": 0.9159049360146252,
3529
+ "grad_norm": 2.24575138092041,
3530
+ "learning_rate": 1.7409178930627473e-06,
3531
+ "loss": 0.8362,
3532
+ "step": 501
3533
+ },
3534
+ {
3535
+ "epoch": 0.9177330895795247,
3536
+ "grad_norm": 2.058715343475342,
3537
+ "learning_rate": 1.6674682701761496e-06,
3538
+ "loss": 0.8225,
3539
+ "step": 502
3540
+ },
3541
+ {
3542
+ "epoch": 0.9195612431444241,
3543
+ "grad_norm": 2.0738391876220703,
3544
+ "learning_rate": 1.5955103951488177e-06,
3545
+ "loss": 0.7747,
3546
+ "step": 503
3547
+ },
3548
+ {
3549
+ "epoch": 0.9213893967093236,
3550
+ "grad_norm": 2.142606735229492,
3551
+ "learning_rate": 1.5250523191902455e-06,
3552
+ "loss": 0.8331,
3553
+ "step": 504
3554
+ },
3555
+ {
3556
+ "epoch": 0.923217550274223,
3557
+ "grad_norm": 2.2022759914398193,
3558
+ "learning_rate": 1.456101925700684e-06,
3559
+ "loss": 0.8037,
3560
+ "step": 505
3561
+ },
3562
+ {
3563
+ "epoch": 0.9250457038391224,
3564
+ "grad_norm": 2.1481759548187256,
3565
+ "learning_rate": 1.3886669293890837e-06,
3566
+ "loss": 0.7431,
3567
+ "step": 506
3568
+ },
3569
+ {
3570
+ "epoch": 0.926873857404022,
3571
+ "grad_norm": 2.3185274600982666,
3572
+ "learning_rate": 1.322754875409915e-06,
3573
+ "loss": 0.7726,
3574
+ "step": 507
3575
+ },
3576
+ {
3577
+ "epoch": 0.9287020109689214,
3578
+ "grad_norm": 2.315138816833496,
3579
+ "learning_rate": 1.2583731385189562e-06,
3580
+ "loss": 0.7026,
3581
+ "step": 508
3582
+ },
3583
+ {
3584
+ "epoch": 0.9305301645338209,
3585
+ "grad_norm": 2.050353527069092,
3586
+ "learning_rate": 1.1955289222481513e-06,
3587
+ "loss": 0.7373,
3588
+ "step": 509
3589
+ },
3590
+ {
3591
+ "epoch": 0.9323583180987203,
3592
+ "grad_norm": 2.3529744148254395,
3593
+ "learning_rate": 1.1342292580996195e-06,
3594
+ "loss": 0.8461,
3595
+ "step": 510
3596
+ },
3597
+ {
3598
+ "epoch": 0.9341864716636198,
3599
+ "grad_norm": 2.264411687850952,
3600
+ "learning_rate": 1.0744810047589116e-06,
3601
+ "loss": 1.05,
3602
+ "step": 511
3603
+ },
3604
+ {
3605
+ "epoch": 0.9360146252285192,
3606
+ "grad_norm": 2.2528390884399414,
3607
+ "learning_rate": 1.0162908473276133e-06,
3608
+ "loss": 0.8218,
3609
+ "step": 512
3610
+ },
3611
+ {
3612
+ "epoch": 0.9378427787934186,
3613
+ "grad_norm": 2.23812198638916,
3614
+ "learning_rate": 9.596652965753632e-07,
3615
+ "loss": 0.8533,
3616
+ "step": 513
3617
+ },
3618
+ {
3619
+ "epoch": 0.9396709323583181,
3620
+ "grad_norm": 2.4503235816955566,
3621
+ "learning_rate": 9.046106882113753e-07,
3622
+ "loss": 0.8821,
3623
+ "step": 514
3624
+ },
3625
+ {
3626
+ "epoch": 0.9414990859232175,
3627
+ "grad_norm": 2.152954578399658,
3628
+ "learning_rate": 8.511331821755459e-07,
3629
+ "loss": 0.7932,
3630
+ "step": 515
3631
+ },
3632
+ {
3633
+ "epoch": 0.943327239488117,
3634
+ "grad_norm": 2.1594455242156982,
3635
+ "learning_rate": 7.992387619492436e-07,
3636
+ "loss": 0.7988,
3637
+ "step": 516
3638
+ },
3639
+ {
3640
+ "epoch": 0.9451553930530164,
3641
+ "grad_norm": 2.086651086807251,
3642
+ "learning_rate": 7.489332338858202e-07,
3643
+ "loss": 0.8552,
3644
+ "step": 517
3645
+ },
3646
+ {
3647
+ "epoch": 0.946983546617916,
3648
+ "grad_norm": 2.134727954864502,
3649
+ "learning_rate": 7.002222265609476e-07,
3650
+ "loss": 0.8825,
3651
+ "step": 518
3652
+ },
3653
+ {
3654
+ "epoch": 0.9488117001828154,
3655
+ "grad_norm": 2.169853448867798,
3656
+ "learning_rate": 6.53111190142861e-07,
3657
+ "loss": 0.8105,
3658
+ "step": 519
3659
+ },
3660
+ {
3661
+ "epoch": 0.9506398537477148,
3662
+ "grad_norm": 2.000743865966797,
3663
+ "learning_rate": 6.076053957825411e-07,
3664
+ "loss": 0.6882,
3665
+ "step": 520
3666
+ },
3667
+ {
3668
+ "epoch": 0.9524680073126143,
3669
+ "grad_norm": 2.1314992904663086,
3670
+ "learning_rate": 5.637099350239427e-07,
3671
+ "loss": 0.7354,
3672
+ "step": 521
3673
+ },
3674
+ {
3675
+ "epoch": 0.9542961608775137,
3676
+ "grad_norm": 2.3546230792999268,
3677
+ "learning_rate": 5.214297192343104e-07,
3678
+ "loss": 0.8793,
3679
+ "step": 522
3680
+ },
3681
+ {
3682
+ "epoch": 0.9561243144424132,
3683
+ "grad_norm": 2.054684638977051,
3684
+ "learning_rate": 4.807694790546563e-07,
3685
+ "loss": 0.8644,
3686
+ "step": 523
3687
+ },
3688
+ {
3689
+ "epoch": 0.9579524680073126,
3690
+ "grad_norm": 2.0605905055999756,
3691
+ "learning_rate": 4.417337638704588e-07,
3692
+ "loss": 0.675,
3693
+ "step": 524
3694
+ },
3695
+ {
3696
+ "epoch": 0.9597806215722121,
3697
+ "grad_norm": 2.196253776550293,
3698
+ "learning_rate": 4.043269413026429e-07,
3699
+ "loss": 0.8171,
3700
+ "step": 525
3701
+ },
3702
+ {
3703
+ "epoch": 0.9616087751371115,
3704
+ "grad_norm": 2.239720582962036,
3705
+ "learning_rate": 3.6855319671889433e-07,
3706
+ "loss": 0.7863,
3707
+ "step": 526
3708
+ },
3709
+ {
3710
+ "epoch": 0.9634369287020109,
3711
+ "grad_norm": 2.3303980827331543,
3712
+ "learning_rate": 3.3441653276537253e-07,
3713
+ "loss": 0.7169,
3714
+ "step": 527
3715
+ },
3716
+ {
3717
+ "epoch": 0.9652650822669104,
3718
+ "grad_norm": 2.10151743888855,
3719
+ "learning_rate": 3.0192076891885745e-07,
3720
+ "loss": 0.8925,
3721
+ "step": 528
3722
+ },
3723
+ {
3724
+ "epoch": 0.9670932358318098,
3725
+ "grad_norm": 2.475900411605835,
3726
+ "learning_rate": 2.710695410593994e-07,
3727
+ "loss": 0.8043,
3728
+ "step": 529
3729
+ },
3730
+ {
3731
+ "epoch": 0.9689213893967094,
3732
+ "grad_norm": 2.0351574420928955,
3733
+ "learning_rate": 2.418663010635114e-07,
3734
+ "loss": 0.6677,
3735
+ "step": 530
3736
+ },
3737
+ {
3738
+ "epoch": 0.9707495429616088,
3739
+ "grad_norm": 2.2573163509368896,
3740
+ "learning_rate": 2.1431431641794287e-07,
3741
+ "loss": 0.8685,
3742
+ "step": 531
3743
+ },
3744
+ {
3745
+ "epoch": 0.9725776965265083,
3746
+ "grad_norm": 2.2806551456451416,
3747
+ "learning_rate": 1.8841666985408566e-07,
3748
+ "loss": 1.0264,
3749
+ "step": 532
3750
+ },
3751
+ {
3752
+ "epoch": 0.9744058500914077,
3753
+ "grad_norm": 2.0971100330352783,
3754
+ "learning_rate": 1.6417625900305656e-07,
3755
+ "loss": 0.663,
3756
+ "step": 533
3757
+ },
3758
+ {
3759
+ "epoch": 0.9762340036563071,
3760
+ "grad_norm": 2.1479334831237793,
3761
+ "learning_rate": 1.4159579607148976e-07,
3762
+ "loss": 0.7461,
3763
+ "step": 534
3764
+ },
3765
+ {
3766
+ "epoch": 0.9780621572212066,
3767
+ "grad_norm": 2.1846601963043213,
3768
+ "learning_rate": 1.206778075380699e-07,
3769
+ "loss": 0.7843,
3770
+ "step": 535
3771
+ },
3772
+ {
3773
+ "epoch": 0.979890310786106,
3774
+ "grad_norm": 2.18355131149292,
3775
+ "learning_rate": 1.0142463387085465e-07,
3776
+ "loss": 0.8233,
3777
+ "step": 536
3778
+ },
3779
+ {
3780
+ "epoch": 0.9817184643510055,
3781
+ "grad_norm": 1.9972505569458008,
3782
+ "learning_rate": 8.38384292653993e-08,
3783
+ "loss": 0.6412,
3784
+ "step": 537
3785
+ },
3786
+ {
3787
+ "epoch": 0.9835466179159049,
3788
+ "grad_norm": 2.2325432300567627,
3789
+ "learning_rate": 6.792116140373117e-08,
3790
+ "loss": 0.7315,
3791
+ "step": 538
3792
+ },
3793
+ {
3794
+ "epoch": 0.9853747714808044,
3795
+ "grad_norm": 2.270096778869629,
3796
+ "learning_rate": 5.367461123419071e-08,
3797
+ "loss": 0.7166,
3798
+ "step": 539
3799
+ },
3800
+ {
3801
+ "epoch": 0.9872029250457038,
3802
+ "grad_norm": 2.084451675415039,
3803
+ "learning_rate": 4.110037277216427e-08,
3804
+ "loss": 0.7703,
3805
+ "step": 540
3806
+ },
3807
+ {
3808
+ "epoch": 0.9890310786106032,
3809
+ "grad_norm": 2.1931207180023193,
3810
+ "learning_rate": 3.0199852921735104e-08,
3811
+ "loss": 0.9388,
3812
+ "step": 541
3813
+ },
3814
+ {
3815
+ "epoch": 0.9908592321755028,
3816
+ "grad_norm": 2.08048939704895,
3817
+ "learning_rate": 2.0974271318260907e-08,
3818
+ "loss": 0.669,
3819
+ "step": 542
3820
+ },
3821
+ {
3822
+ "epoch": 0.9926873857404022,
3823
+ "grad_norm": 2.402120351791382,
3824
+ "learning_rate": 1.342466019192301e-08,
3825
+ "loss": 0.8257,
3826
+ "step": 543
3827
+ },
3828
+ {
3829
+ "epoch": 0.9945155393053017,
3830
+ "grad_norm": 2.3177034854888916,
3831
+ "learning_rate": 7.551864252223762e-09,
3832
+ "loss": 0.8117,
3833
+ "step": 544
3834
+ },
3835
+ {
3836
+ "epoch": 0.9963436928702011,
3837
+ "grad_norm": 2.3477089405059814,
3838
+ "learning_rate": 3.3565405934721237e-09,
3839
+ "loss": 0.8285,
3840
+ "step": 545
3841
+ },
3842
+ {
3843
+ "epoch": 0.9981718464351006,
3844
+ "grad_norm": 2.4188199043273926,
3845
+ "learning_rate": 8.391586212741498e-10,
3846
+ "loss": 0.8643,
3847
+ "step": 546
3848
+ },
3849
+ {
3850
+ "epoch": 1.0,
3851
+ "grad_norm": 2.4587948322296143,
3852
+ "learning_rate": 0.0,
3853
+ "loss": 0.8511,
3854
+ "step": 547
3855
+ }
3856
+ ],
3857
+ "logging_steps": 1,
3858
+ "max_steps": 547,
3859
+ "num_input_tokens_seen": 0,
3860
+ "num_train_epochs": 1,
3861
+ "save_steps": 250,
3862
+ "stateful_callbacks": {
3863
+ "TrainerControl": {
3864
+ "args": {
3865
+ "should_epoch_stop": false,
3866
+ "should_evaluate": false,
3867
+ "should_log": false,
3868
+ "should_save": true,
3869
+ "should_training_stop": true
3870
+ },
3871
+ "attributes": {}
3872
+ }
3873
+ },
3874
+ "total_flos": 2.615833264128e+16,
3875
+ "train_batch_size": 32,
3876
+ "trial_name": null,
3877
+ "trial_params": null
3878
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43092a7457a9b1b2e3566452c8d766810852f564c0e2b282b0443762c085373
3
+ size 5240