Junhoee commited on
Commit
96f8d79
1 Parent(s): 200a1fb

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoints/jeju_checkpoint_146000_0524",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "author": "Heewon Jeon(madjakarta@gmail.com)",
12
+ "bos_token_id": 1,
13
+ "classif_dropout": 0.1,
14
+ "classifier_dropout": 0.1,
15
+ "d_model": 768,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 3072,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 6,
20
+ "decoder_start_token_id": 1,
21
+ "do_blenderbot_90_layernorm": false,
22
+ "dropout": 0.1,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 1,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 1,
31
+ "gradient_checkpointing": false,
32
+ "id2label": {
33
+ "0": "NEGATIVE",
34
+ "1": "POSITIVE"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "kobart_version": 2.0,
39
+ "label2id": {
40
+ "NEGATIVE": 0,
41
+ "POSITIVE": 1
42
+ },
43
+ "max_position_embeddings": 1026,
44
+ "model_type": "bart",
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 3,
49
+ "scale_embedding": false,
50
+ "static_position_embeddings": false,
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.41.1",
54
+ "use_cache": true,
55
+ "vocab_size": 30000
56
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 1,
5
+ "eos_token_id": 1,
6
+ "forced_eos_token_id": 1,
7
+ "pad_token_id": 3,
8
+ "transformers_version": "4.41.1"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5033a2e53f03b59bb6cefece28d63a122276720d92ccd799d8ffed99d805ce3d
3
+ size 495589768
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4cbe2f0b0c4223dc95bd1c7acd22e541c772bf3c14a7744a67f2db58421b4e
3
+ size 991096314
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478607ae38c9dca117fbd0cb3e8fda388da64bab3615e993ad541872c5f8a0e7
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca6c6f1d56354c2b1b816d3cc6da1a04e0330d9d8183476ffbea2bbb6bb8574
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,1851 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<usr>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<sys>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<unk>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mask>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<unused0>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<unused1>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<unused2>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<unused3>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<unused4>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<unused5>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<unused6>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "<unused7>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "<unused8>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "<unused9>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "<unused10>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "<unused11>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "<unused12>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "<unused13>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "<unused14>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "<unused15>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "23": {
188
+ "content": "<unused16>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "24": {
196
+ "content": "<unused17>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "25": {
204
+ "content": "<unused18>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "26": {
212
+ "content": "<unused19>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "27": {
220
+ "content": "<unused20>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "28": {
228
+ "content": "<unused21>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "29": {
236
+ "content": "<unused22>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "30": {
244
+ "content": "<unused23>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "31": {
252
+ "content": "<unused24>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "<unused25>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "<unused26>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "<unused27>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "<unused28>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "36": {
292
+ "content": "<unused29>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "37": {
300
+ "content": "<unused30>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "38": {
308
+ "content": "<unused31>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "39": {
316
+ "content": "<unused32>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "40": {
324
+ "content": "<unused33>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "41": {
332
+ "content": "<unused34>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "42": {
340
+ "content": "<unused35>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "43": {
348
+ "content": "<unused36>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "44": {
356
+ "content": "<unused37>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "45": {
364
+ "content": "<unused38>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "46": {
372
+ "content": "<unused39>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "47": {
380
+ "content": "<unused40>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "48": {
388
+ "content": "<unused41>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "49": {
396
+ "content": "<unused42>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<unused43>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<unused44>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<unused45>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<unused46>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<unused47>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<unused48>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<unused49>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<unused50>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<unused51>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<unused52>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "60": {
484
+ "content": "<unused53>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "61": {
492
+ "content": "<unused54>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "62": {
500
+ "content": "<unused55>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "63": {
508
+ "content": "<unused56>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "64": {
516
+ "content": "<unused57>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "65": {
524
+ "content": "<unused58>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "66": {
532
+ "content": "<unused59>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "67": {
540
+ "content": "<unused60>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "68": {
548
+ "content": "<unused61>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "69": {
556
+ "content": "<unused62>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "70": {
564
+ "content": "<unused63>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "71": {
572
+ "content": "<unused64>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "72": {
580
+ "content": "<unused65>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "73": {
588
+ "content": "<unused66>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "74": {
596
+ "content": "<unused67>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "75": {
604
+ "content": "<unused68>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "76": {
612
+ "content": "<unused69>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "77": {
620
+ "content": "<unused70>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "78": {
628
+ "content": "<unused71>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "79": {
636
+ "content": "<unused72>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "80": {
644
+ "content": "<unused73>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "81": {
652
+ "content": "<unused74>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "82": {
660
+ "content": "<unused75>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "83": {
668
+ "content": "<unused76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "84": {
676
+ "content": "<unused77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "85": {
684
+ "content": "<unused78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "86": {
692
+ "content": "<unused79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "87": {
700
+ "content": "<unused80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "88": {
708
+ "content": "<unused81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "89": {
716
+ "content": "<unused82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "90": {
724
+ "content": "<unused83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "91": {
732
+ "content": "<unused84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "92": {
740
+ "content": "<unused85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "93": {
748
+ "content": "<unused86>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "94": {
756
+ "content": "<unused87>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "95": {
764
+ "content": "<unused88>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "96": {
772
+ "content": "<unused89>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "97": {
780
+ "content": "<unused90>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "98": {
788
+ "content": "<unused91>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "99": {
796
+ "content": "<unused92>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "100": {
804
+ "content": "<unused93>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "101": {
812
+ "content": "<unused94>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "102": {
820
+ "content": "<unused95>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "103": {
828
+ "content": "<unused96>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "104": {
836
+ "content": "<unused97>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "105": {
844
+ "content": "<unused98>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "106": {
852
+ "content": "<unused99>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "107": {
860
+ "content": ":-)",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "108": {
868
+ "content": ":)",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "109": {
876
+ "content": ",-)",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "110": {
884
+ "content": "(-:",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "111": {
892
+ "content": "(:-)",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "112": {
900
+ "content": "(:-(",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "113": {
908
+ "content": ",-}",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "114": {
916
+ "content": "8-O",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "115": {
924
+ "content": "'-)",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "116": {
932
+ "content": ":-#",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "117": {
940
+ "content": ":-*",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "118": {
948
+ "content": ":-/",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "119": {
956
+ "content": ":->",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "120": {
964
+ "content": ":-@",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "121": {
972
+ "content": ":-d",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "122": {
980
+ "content": ":-V",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "123": {
988
+ "content": ":-X",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "124": {
996
+ "content": ":-\\",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "125": {
1004
+ "content": ":-]",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "126": {
1012
+ "content": ";-(",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "127": {
1020
+ "content": ">;->",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128": {
1028
+ "content": ";^)",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "129": {
1036
+ "content": "%-)",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "130": {
1044
+ "content": "):-(",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "131": {
1052
+ "content": "3:]",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "132": {
1060
+ "content": ":-&",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "133": {
1068
+ "content": "8:-)",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "134": {
1076
+ "content": ":-)8<",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "135": {
1084
+ "content": ":-O",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "136": {
1092
+ "content": ":-6",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "137": {
1100
+ "content": "+:-)",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "138": {
1108
+ "content": "O:-)",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "139": {
1116
+ "content": ":-<",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "140": {
1124
+ "content": ":-?",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "141": {
1132
+ "content": ":-E",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "142": {
1140
+ "content": ":-Q",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "143": {
1148
+ "content": ":-}X",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "144": {
1156
+ "content": ":-[",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "145": {
1164
+ "content": ":-a",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "146": {
1172
+ "content": ":-{",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "147": {
1180
+ "content": ":-{}",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "148": {
1188
+ "content": ":^)",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "149": {
1196
+ "content": "<:-l",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "150": {
1204
+ "content": ":=)",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "151": {
1212
+ "content": ">:->",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "152": {
1220
+ "content": ">:-l",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "153": {
1228
+ "content": "@:-)",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "154": {
1236
+ "content": "@:-}",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "155": {
1244
+ "content": "C=:-)",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "156": {
1252
+ "content": "X:-)",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "157": {
1260
+ "content": "[:-)",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "158": {
1268
+ "content": "[:]",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "159": {
1276
+ "content": "{:-)",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "160": {
1284
+ "content": "l^o",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "161": {
1292
+ "content": "}:^#)",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "162": {
1300
+ "content": ":-(=)",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "163": {
1308
+ "content": "O-)",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "164": {
1316
+ "content": ":-3",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "165": {
1324
+ "content": ": =",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "166": {
1332
+ "content": ":-\"",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "167": {
1340
+ "content": "P-(",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "168": {
1348
+ "content": "?-(",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "169": {
1356
+ "content": "d:-)",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "170": {
1364
+ "content": ":8)",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "171": {
1372
+ "content": ":-7",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "172": {
1380
+ "content": "):-)",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "173": {
1388
+ "content": ":/\\)",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "174": {
1396
+ "content": "8(:-)",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "175": {
1404
+ "content": "([(",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "176": {
1412
+ "content": ":-(*)",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "177": {
1420
+ "content": "&-l",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "178": {
1428
+ "content": ":-e",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "179": {
1436
+ "content": ":(",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "180": {
1444
+ "content": ":,(",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "181": {
1452
+ "content": ":-(",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "182": {
1460
+ "content": ":-P",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "183": {
1468
+ "content": ":-S",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "184": {
1476
+ "content": ":-C",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "185": {
1484
+ "content": ":-r",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "186": {
1492
+ "content": ":-t",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "187": {
1500
+ "content": ":-W",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "188": {
1508
+ "content": "X-(",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "189": {
1516
+ "content": "l-O",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "190": {
1524
+ "content": "l:-O",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "191": {
1532
+ "content": "$-)",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "192": {
1540
+ "content": ":-!",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "193": {
1548
+ "content": ":----}",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "194": {
1556
+ "content": "=:-)",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "195": {
1564
+ "content": "=:-(",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "196": {
1572
+ "content": "3:[",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "197": {
1580
+ "content": "8<:-)",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "198": {
1588
+ "content": ":#)",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "199": {
1596
+ "content": "8-#",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "200": {
1604
+ "content": "B-)",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "201": {
1612
+ "content": "8-)",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "202": {
1620
+ "content": "|-(",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "203": {
1628
+ "content": "H-)",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "204": {
1636
+ "content": "]-I",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "205": {
1644
+ "content": "V^J",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "206": {
1652
+ "content": "+-(",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "207": {
1660
+ "content": "~:-P",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "208": {
1668
+ "content": "`'",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "209": {
1676
+ "content": "L-P",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "210": {
1684
+ "content": "BI",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "211": {
1692
+ "content": "O |",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "212": {
1700
+ "content": "^^",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "213": {
1708
+ "content": "ㅜㅜ",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "214": {
1716
+ "content": "ㅠㅠ",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "215": {
1724
+ "content": "ㅡㅡ",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "216": {
1732
+ "content": "😀",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "217": {
1740
+ "content": "😃",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "218": {
1748
+ "content": "😄",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "219": {
1756
+ "content": "😁",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "220": {
1764
+ "content": "😆",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "221": {
1772
+ "content": "😅",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "222": {
1780
+ "content": "🤣",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "223": {
1788
+ "content": "😂",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "224": {
1796
+ "content": "🙂",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "225": {
1804
+ "content": "🙃",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "226": {
1812
+ "content": "😉",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "227": {
1820
+ "content": "😊",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "228": {
1828
+ "content": "😇",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ }
1835
+ },
1836
+ "bos_token": "</s>",
1837
+ "clean_up_tokenization_spaces": true,
1838
+ "eos_token": "</s>",
1839
+ "mask_token": "<mask>",
1840
+ "max_length": 64,
1841
+ "model_max_length": 1000000000000000019884624838656,
1842
+ "pad_to_multiple_of": null,
1843
+ "pad_token": "<pad>",
1844
+ "pad_token_type_id": 0,
1845
+ "padding_side": "right",
1846
+ "stride": 0,
1847
+ "tokenizer_class": "PreTrainedTokenizerFast",
1848
+ "truncation_side": "right",
1849
+ "truncation_strategy": "longest_first",
1850
+ "unk_token": "<unk>"
1851
+ }
trainer_state.json ADDED
@@ -0,0 +1,1701 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.996825396825397,
5
+ "eval_steps": 500,
6
+ "global_step": 118000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.012698412698412698,
13
+ "grad_norm": 0.4761015474796295,
14
+ "learning_rate": 1.9915343915343918e-05,
15
+ "loss": 0.0794,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.025396825396825397,
20
+ "grad_norm": 0.43550318479537964,
21
+ "learning_rate": 1.983068783068783e-05,
22
+ "loss": 0.0811,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.0380952380952381,
27
+ "grad_norm": 0.4672704339027405,
28
+ "learning_rate": 1.9746031746031748e-05,
29
+ "loss": 0.0819,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.050793650793650794,
34
+ "grad_norm": 0.5426394939422607,
35
+ "learning_rate": 1.9661375661375664e-05,
36
+ "loss": 0.0829,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.06349206349206349,
41
+ "grad_norm": 0.3974975645542145,
42
+ "learning_rate": 1.9576719576719577e-05,
43
+ "loss": 0.0816,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.0761904761904762,
48
+ "grad_norm": 0.6599302887916565,
49
+ "learning_rate": 1.9492063492063494e-05,
50
+ "loss": 0.0815,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.08888888888888889,
55
+ "grad_norm": 0.35329556465148926,
56
+ "learning_rate": 1.9407407407407407e-05,
57
+ "loss": 0.0841,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.10158730158730159,
62
+ "grad_norm": 0.42421749234199524,
63
+ "learning_rate": 1.9322751322751327e-05,
64
+ "loss": 0.0833,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.11428571428571428,
69
+ "grad_norm": 0.4479866325855255,
70
+ "learning_rate": 1.923809523809524e-05,
71
+ "loss": 0.0839,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.12698412698412698,
76
+ "grad_norm": 0.372086763381958,
77
+ "learning_rate": 1.9153439153439156e-05,
78
+ "loss": 0.0835,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.13968253968253969,
83
+ "grad_norm": 0.38730981945991516,
84
+ "learning_rate": 1.906878306878307e-05,
85
+ "loss": 0.0841,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.1523809523809524,
90
+ "grad_norm": 0.5003937482833862,
91
+ "learning_rate": 1.8984126984126986e-05,
92
+ "loss": 0.0829,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.16507936507936508,
97
+ "grad_norm": 0.42826735973358154,
98
+ "learning_rate": 1.8899470899470903e-05,
99
+ "loss": 0.0835,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.17777777777777778,
104
+ "grad_norm": 0.49070820212364197,
105
+ "learning_rate": 1.8814814814814816e-05,
106
+ "loss": 0.0827,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.19047619047619047,
111
+ "grad_norm": 0.4903796911239624,
112
+ "learning_rate": 1.8730158730158732e-05,
113
+ "loss": 0.0823,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.20317460317460317,
118
+ "grad_norm": 0.4144362211227417,
119
+ "learning_rate": 1.8645502645502645e-05,
120
+ "loss": 0.0842,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.21587301587301588,
125
+ "grad_norm": 0.6519999504089355,
126
+ "learning_rate": 1.8560846560846562e-05,
127
+ "loss": 0.0827,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.22857142857142856,
132
+ "grad_norm": 0.37082576751708984,
133
+ "learning_rate": 1.8476190476190478e-05,
134
+ "loss": 0.0835,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.24126984126984127,
139
+ "grad_norm": 0.319024920463562,
140
+ "learning_rate": 1.8391534391534395e-05,
141
+ "loss": 0.0829,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.25396825396825395,
146
+ "grad_norm": 0.4173873960971832,
147
+ "learning_rate": 1.8306878306878308e-05,
148
+ "loss": 0.0814,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.26666666666666666,
153
+ "grad_norm": 0.4521333873271942,
154
+ "learning_rate": 1.8222222222222224e-05,
155
+ "loss": 0.0825,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.27936507936507937,
160
+ "grad_norm": 0.4372086822986603,
161
+ "learning_rate": 1.8137566137566137e-05,
162
+ "loss": 0.0844,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.2920634920634921,
167
+ "grad_norm": 0.40673378109931946,
168
+ "learning_rate": 1.8052910052910054e-05,
169
+ "loss": 0.0846,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.3047619047619048,
174
+ "grad_norm": 0.524502694606781,
175
+ "learning_rate": 1.796825396825397e-05,
176
+ "loss": 0.0843,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.31746031746031744,
181
+ "grad_norm": 0.36854442954063416,
182
+ "learning_rate": 1.7883597883597884e-05,
183
+ "loss": 0.0838,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.33015873015873015,
188
+ "grad_norm": 0.4694221019744873,
189
+ "learning_rate": 1.77989417989418e-05,
190
+ "loss": 0.0834,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.34285714285714286,
195
+ "grad_norm": 0.384512335062027,
196
+ "learning_rate": 1.7714285714285717e-05,
197
+ "loss": 0.0825,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 0.35555555555555557,
202
+ "grad_norm": 0.3776947855949402,
203
+ "learning_rate": 1.7629629629629633e-05,
204
+ "loss": 0.081,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 0.3682539682539683,
209
+ "grad_norm": 0.44691145420074463,
210
+ "learning_rate": 1.7544973544973546e-05,
211
+ "loss": 0.0844,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 0.38095238095238093,
216
+ "grad_norm": 0.38754552602767944,
217
+ "learning_rate": 1.7460317460317463e-05,
218
+ "loss": 0.0834,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.39365079365079364,
223
+ "grad_norm": 0.3924926221370697,
224
+ "learning_rate": 1.7375661375661376e-05,
225
+ "loss": 0.0836,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 0.40634920634920635,
230
+ "grad_norm": 0.41219380497932434,
231
+ "learning_rate": 1.7291005291005292e-05,
232
+ "loss": 0.0827,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 0.41904761904761906,
237
+ "grad_norm": 0.36697277426719666,
238
+ "learning_rate": 1.720634920634921e-05,
239
+ "loss": 0.0833,
240
+ "step": 16500
241
+ },
242
+ {
243
+ "epoch": 0.43174603174603177,
244
+ "grad_norm": 0.37833482027053833,
245
+ "learning_rate": 1.7121693121693125e-05,
246
+ "loss": 0.0831,
247
+ "step": 17000
248
+ },
249
+ {
250
+ "epoch": 0.4444444444444444,
251
+ "grad_norm": 0.33408552408218384,
252
+ "learning_rate": 1.7037037037037038e-05,
253
+ "loss": 0.0818,
254
+ "step": 17500
255
+ },
256
+ {
257
+ "epoch": 0.45714285714285713,
258
+ "grad_norm": 0.4245634377002716,
259
+ "learning_rate": 1.6952380952380955e-05,
260
+ "loss": 0.0838,
261
+ "step": 18000
262
+ },
263
+ {
264
+ "epoch": 0.46984126984126984,
265
+ "grad_norm": 0.4424809217453003,
266
+ "learning_rate": 1.6867724867724868e-05,
267
+ "loss": 0.0828,
268
+ "step": 18500
269
+ },
270
+ {
271
+ "epoch": 0.48253968253968255,
272
+ "grad_norm": 0.47369641065597534,
273
+ "learning_rate": 1.6783068783068784e-05,
274
+ "loss": 0.0828,
275
+ "step": 19000
276
+ },
277
+ {
278
+ "epoch": 0.49523809523809526,
279
+ "grad_norm": 0.417057603597641,
280
+ "learning_rate": 1.66984126984127e-05,
281
+ "loss": 0.0839,
282
+ "step": 19500
283
+ },
284
+ {
285
+ "epoch": 0.5079365079365079,
286
+ "grad_norm": 0.450612336397171,
287
+ "learning_rate": 1.6613756613756614e-05,
288
+ "loss": 0.0832,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 0.5206349206349207,
293
+ "grad_norm": 0.35937097668647766,
294
+ "learning_rate": 1.652910052910053e-05,
295
+ "loss": 0.0816,
296
+ "step": 20500
297
+ },
298
+ {
299
+ "epoch": 0.5333333333333333,
300
+ "grad_norm": 0.4366040527820587,
301
+ "learning_rate": 1.6444444444444444e-05,
302
+ "loss": 0.0817,
303
+ "step": 21000
304
+ },
305
+ {
306
+ "epoch": 0.546031746031746,
307
+ "grad_norm": 0.3630824387073517,
308
+ "learning_rate": 1.6359788359788363e-05,
309
+ "loss": 0.0823,
310
+ "step": 21500
311
+ },
312
+ {
313
+ "epoch": 0.5587301587301587,
314
+ "grad_norm": 0.45653077960014343,
315
+ "learning_rate": 1.6275132275132277e-05,
316
+ "loss": 0.0814,
317
+ "step": 22000
318
+ },
319
+ {
320
+ "epoch": 0.5714285714285714,
321
+ "grad_norm": 0.4124685525894165,
322
+ "learning_rate": 1.6190476190476193e-05,
323
+ "loss": 0.0828,
324
+ "step": 22500
325
+ },
326
+ {
327
+ "epoch": 0.5841269841269842,
328
+ "grad_norm": 0.4182330071926117,
329
+ "learning_rate": 1.6105820105820106e-05,
330
+ "loss": 0.0825,
331
+ "step": 23000
332
+ },
333
+ {
334
+ "epoch": 0.5968253968253968,
335
+ "grad_norm": 0.7457558512687683,
336
+ "learning_rate": 1.6021164021164023e-05,
337
+ "loss": 0.0828,
338
+ "step": 23500
339
+ },
340
+ {
341
+ "epoch": 0.6095238095238096,
342
+ "grad_norm": 0.41049671173095703,
343
+ "learning_rate": 1.5936507936507936e-05,
344
+ "loss": 0.0831,
345
+ "step": 24000
346
+ },
347
+ {
348
+ "epoch": 0.6222222222222222,
349
+ "grad_norm": 0.4230283498764038,
350
+ "learning_rate": 1.5851851851851852e-05,
351
+ "loss": 0.0823,
352
+ "step": 24500
353
+ },
354
+ {
355
+ "epoch": 0.6349206349206349,
356
+ "grad_norm": 0.38568949699401855,
357
+ "learning_rate": 1.576719576719577e-05,
358
+ "loss": 0.0811,
359
+ "step": 25000
360
+ },
361
+ {
362
+ "epoch": 0.6476190476190476,
363
+ "grad_norm": 0.42709481716156006,
364
+ "learning_rate": 1.5682539682539685e-05,
365
+ "loss": 0.0818,
366
+ "step": 25500
367
+ },
368
+ {
369
+ "epoch": 0.6603174603174603,
370
+ "grad_norm": 0.37508589029312134,
371
+ "learning_rate": 1.55978835978836e-05,
372
+ "loss": 0.0828,
373
+ "step": 26000
374
+ },
375
+ {
376
+ "epoch": 0.6730158730158731,
377
+ "grad_norm": 0.43134260177612305,
378
+ "learning_rate": 1.5513227513227515e-05,
379
+ "loss": 0.0824,
380
+ "step": 26500
381
+ },
382
+ {
383
+ "epoch": 0.6857142857142857,
384
+ "grad_norm": 0.37693992257118225,
385
+ "learning_rate": 1.542857142857143e-05,
386
+ "loss": 0.0811,
387
+ "step": 27000
388
+ },
389
+ {
390
+ "epoch": 0.6984126984126984,
391
+ "grad_norm": 0.34098678827285767,
392
+ "learning_rate": 1.5343915343915344e-05,
393
+ "loss": 0.0819,
394
+ "step": 27500
395
+ },
396
+ {
397
+ "epoch": 0.7111111111111111,
398
+ "grad_norm": 0.47179728746414185,
399
+ "learning_rate": 1.525925925925926e-05,
400
+ "loss": 0.082,
401
+ "step": 28000
402
+ },
403
+ {
404
+ "epoch": 0.7238095238095238,
405
+ "grad_norm": 0.4184609651565552,
406
+ "learning_rate": 1.5174603174603176e-05,
407
+ "loss": 0.0825,
408
+ "step": 28500
409
+ },
410
+ {
411
+ "epoch": 0.7365079365079366,
412
+ "grad_norm": 0.3582792282104492,
413
+ "learning_rate": 1.508994708994709e-05,
414
+ "loss": 0.0821,
415
+ "step": 29000
416
+ },
417
+ {
418
+ "epoch": 0.7492063492063492,
419
+ "grad_norm": 0.5200299620628357,
420
+ "learning_rate": 1.5005291005291007e-05,
421
+ "loss": 0.0817,
422
+ "step": 29500
423
+ },
424
+ {
425
+ "epoch": 0.7619047619047619,
426
+ "grad_norm": 0.4461567997932434,
427
+ "learning_rate": 1.4920634920634922e-05,
428
+ "loss": 0.0814,
429
+ "step": 30000
430
+ },
431
+ {
432
+ "epoch": 0.7746031746031746,
433
+ "grad_norm": 0.3920634388923645,
434
+ "learning_rate": 1.4835978835978837e-05,
435
+ "loss": 0.0819,
436
+ "step": 30500
437
+ },
438
+ {
439
+ "epoch": 0.7873015873015873,
440
+ "grad_norm": 0.41001540422439575,
441
+ "learning_rate": 1.4751322751322751e-05,
442
+ "loss": 0.0802,
443
+ "step": 31000
444
+ },
445
+ {
446
+ "epoch": 0.8,
447
+ "grad_norm": 0.4187995493412018,
448
+ "learning_rate": 1.4666666666666666e-05,
449
+ "loss": 0.0816,
450
+ "step": 31500
451
+ },
452
+ {
453
+ "epoch": 0.8126984126984127,
454
+ "grad_norm": 0.39321765303611755,
455
+ "learning_rate": 1.4582010582010584e-05,
456
+ "loss": 0.0824,
457
+ "step": 32000
458
+ },
459
+ {
460
+ "epoch": 0.8253968253968254,
461
+ "grad_norm": 0.3958302140235901,
462
+ "learning_rate": 1.44973544973545e-05,
463
+ "loss": 0.0801,
464
+ "step": 32500
465
+ },
466
+ {
467
+ "epoch": 0.8380952380952381,
468
+ "grad_norm": 0.3932056725025177,
469
+ "learning_rate": 1.4412698412698414e-05,
470
+ "loss": 0.0808,
471
+ "step": 33000
472
+ },
473
+ {
474
+ "epoch": 0.8507936507936508,
475
+ "grad_norm": 0.3314465284347534,
476
+ "learning_rate": 1.4328042328042329e-05,
477
+ "loss": 0.0827,
478
+ "step": 33500
479
+ },
480
+ {
481
+ "epoch": 0.8634920634920635,
482
+ "grad_norm": 0.43675485253334045,
483
+ "learning_rate": 1.4243386243386244e-05,
484
+ "loss": 0.0811,
485
+ "step": 34000
486
+ },
487
+ {
488
+ "epoch": 0.8761904761904762,
489
+ "grad_norm": 0.6284595131874084,
490
+ "learning_rate": 1.415873015873016e-05,
491
+ "loss": 0.0805,
492
+ "step": 34500
493
+ },
494
+ {
495
+ "epoch": 0.8888888888888888,
496
+ "grad_norm": 0.39293691515922546,
497
+ "learning_rate": 1.4074074074074075e-05,
498
+ "loss": 0.0803,
499
+ "step": 35000
500
+ },
501
+ {
502
+ "epoch": 0.9015873015873016,
503
+ "grad_norm": 0.4092639088630676,
504
+ "learning_rate": 1.398941798941799e-05,
505
+ "loss": 0.0813,
506
+ "step": 35500
507
+ },
508
+ {
509
+ "epoch": 0.9142857142857143,
510
+ "grad_norm": 0.41005492210388184,
511
+ "learning_rate": 1.3904761904761905e-05,
512
+ "loss": 0.0811,
513
+ "step": 36000
514
+ },
515
+ {
516
+ "epoch": 0.926984126984127,
517
+ "grad_norm": 0.5190646052360535,
518
+ "learning_rate": 1.3820105820105821e-05,
519
+ "loss": 0.0811,
520
+ "step": 36500
521
+ },
522
+ {
523
+ "epoch": 0.9396825396825397,
524
+ "grad_norm": 0.32034316658973694,
525
+ "learning_rate": 1.3735449735449738e-05,
526
+ "loss": 0.0812,
527
+ "step": 37000
528
+ },
529
+ {
530
+ "epoch": 0.9523809523809523,
531
+ "grad_norm": 0.4857613742351532,
532
+ "learning_rate": 1.3650793650793652e-05,
533
+ "loss": 0.0813,
534
+ "step": 37500
535
+ },
536
+ {
537
+ "epoch": 0.9650793650793651,
538
+ "grad_norm": 0.4523787796497345,
539
+ "learning_rate": 1.3566137566137567e-05,
540
+ "loss": 0.0816,
541
+ "step": 38000
542
+ },
543
+ {
544
+ "epoch": 0.9777777777777777,
545
+ "grad_norm": 0.4204433262348175,
546
+ "learning_rate": 1.3481481481481482e-05,
547
+ "loss": 0.0806,
548
+ "step": 38500
549
+ },
550
+ {
551
+ "epoch": 0.9904761904761905,
552
+ "grad_norm": 0.4313475787639618,
553
+ "learning_rate": 1.3396825396825397e-05,
554
+ "loss": 0.0806,
555
+ "step": 39000
556
+ },
557
+ {
558
+ "epoch": 1.0,
559
+ "eval_loss": 0.07647726684808731,
560
+ "eval_runtime": 270.8786,
561
+ "eval_samples_per_second": 516.837,
562
+ "eval_steps_per_second": 64.605,
563
+ "step": 39375
564
+ },
565
+ {
566
+ "epoch": 1.0031746031746032,
567
+ "grad_norm": 0.44939786195755005,
568
+ "learning_rate": 1.3312169312169313e-05,
569
+ "loss": 0.0795,
570
+ "step": 39500
571
+ },
572
+ {
573
+ "epoch": 1.0158730158730158,
574
+ "grad_norm": 0.48013949394226074,
575
+ "learning_rate": 1.322751322751323e-05,
576
+ "loss": 0.0751,
577
+ "step": 40000
578
+ },
579
+ {
580
+ "epoch": 1.0285714285714285,
581
+ "grad_norm": 0.4185923635959625,
582
+ "learning_rate": 1.3142857142857145e-05,
583
+ "loss": 0.0736,
584
+ "step": 40500
585
+ },
586
+ {
587
+ "epoch": 1.0412698412698413,
588
+ "grad_norm": 0.397386759519577,
589
+ "learning_rate": 1.305820105820106e-05,
590
+ "loss": 0.0748,
591
+ "step": 41000
592
+ },
593
+ {
594
+ "epoch": 1.053968253968254,
595
+ "grad_norm": 0.39524805545806885,
596
+ "learning_rate": 1.2973544973544974e-05,
597
+ "loss": 0.0735,
598
+ "step": 41500
599
+ },
600
+ {
601
+ "epoch": 1.0666666666666667,
602
+ "grad_norm": 0.34505075216293335,
603
+ "learning_rate": 1.288888888888889e-05,
604
+ "loss": 0.0746,
605
+ "step": 42000
606
+ },
607
+ {
608
+ "epoch": 1.0793650793650793,
609
+ "grad_norm": 0.37381839752197266,
610
+ "learning_rate": 1.2804232804232805e-05,
611
+ "loss": 0.0728,
612
+ "step": 42500
613
+ },
614
+ {
615
+ "epoch": 1.0920634920634922,
616
+ "grad_norm": 0.6797782182693481,
617
+ "learning_rate": 1.271957671957672e-05,
618
+ "loss": 0.0741,
619
+ "step": 43000
620
+ },
621
+ {
622
+ "epoch": 1.1047619047619048,
623
+ "grad_norm": 0.41272956132888794,
624
+ "learning_rate": 1.2634920634920635e-05,
625
+ "loss": 0.0738,
626
+ "step": 43500
627
+ },
628
+ {
629
+ "epoch": 1.1174603174603175,
630
+ "grad_norm": 0.382468044757843,
631
+ "learning_rate": 1.255026455026455e-05,
632
+ "loss": 0.0738,
633
+ "step": 44000
634
+ },
635
+ {
636
+ "epoch": 1.1301587301587301,
637
+ "grad_norm": 0.3978229761123657,
638
+ "learning_rate": 1.2465608465608468e-05,
639
+ "loss": 0.074,
640
+ "step": 44500
641
+ },
642
+ {
643
+ "epoch": 1.1428571428571428,
644
+ "grad_norm": 0.3431326746940613,
645
+ "learning_rate": 1.2380952380952383e-05,
646
+ "loss": 0.0745,
647
+ "step": 45000
648
+ },
649
+ {
650
+ "epoch": 1.1555555555555554,
651
+ "grad_norm": 0.3610997200012207,
652
+ "learning_rate": 1.2296296296296298e-05,
653
+ "loss": 0.0729,
654
+ "step": 45500
655
+ },
656
+ {
657
+ "epoch": 1.1682539682539683,
658
+ "grad_norm": 0.49680083990097046,
659
+ "learning_rate": 1.2211640211640212e-05,
660
+ "loss": 0.0732,
661
+ "step": 46000
662
+ },
663
+ {
664
+ "epoch": 1.180952380952381,
665
+ "grad_norm": 0.3833047151565552,
666
+ "learning_rate": 1.2126984126984127e-05,
667
+ "loss": 0.0732,
668
+ "step": 46500
669
+ },
670
+ {
671
+ "epoch": 1.1936507936507936,
672
+ "grad_norm": 0.2808152139186859,
673
+ "learning_rate": 1.2042328042328044e-05,
674
+ "loss": 0.0733,
675
+ "step": 47000
676
+ },
677
+ {
678
+ "epoch": 1.2063492063492063,
679
+ "grad_norm": 0.5429581999778748,
680
+ "learning_rate": 1.1957671957671959e-05,
681
+ "loss": 0.0729,
682
+ "step": 47500
683
+ },
684
+ {
685
+ "epoch": 1.2190476190476192,
686
+ "grad_norm": 0.34248363971710205,
687
+ "learning_rate": 1.1873015873015873e-05,
688
+ "loss": 0.0746,
689
+ "step": 48000
690
+ },
691
+ {
692
+ "epoch": 1.2317460317460318,
693
+ "grad_norm": 0.5099675059318542,
694
+ "learning_rate": 1.1788359788359788e-05,
695
+ "loss": 0.0739,
696
+ "step": 48500
697
+ },
698
+ {
699
+ "epoch": 1.2444444444444445,
700
+ "grad_norm": 0.3858914375305176,
701
+ "learning_rate": 1.1703703703703703e-05,
702
+ "loss": 0.0721,
703
+ "step": 49000
704
+ },
705
+ {
706
+ "epoch": 1.2571428571428571,
707
+ "grad_norm": 0.3453405201435089,
708
+ "learning_rate": 1.1619047619047621e-05,
709
+ "loss": 0.0737,
710
+ "step": 49500
711
+ },
712
+ {
713
+ "epoch": 1.2698412698412698,
714
+ "grad_norm": 0.4647195637226105,
715
+ "learning_rate": 1.1534391534391536e-05,
716
+ "loss": 0.0736,
717
+ "step": 50000
718
+ },
719
+ {
720
+ "epoch": 1.2825396825396824,
721
+ "grad_norm": 0.4548490345478058,
722
+ "learning_rate": 1.144973544973545e-05,
723
+ "loss": 0.0742,
724
+ "step": 50500
725
+ },
726
+ {
727
+ "epoch": 1.2952380952380953,
728
+ "grad_norm": 0.4145970046520233,
729
+ "learning_rate": 1.1365079365079366e-05,
730
+ "loss": 0.0748,
731
+ "step": 51000
732
+ },
733
+ {
734
+ "epoch": 1.307936507936508,
735
+ "grad_norm": 0.4032251536846161,
736
+ "learning_rate": 1.128042328042328e-05,
737
+ "loss": 0.073,
738
+ "step": 51500
739
+ },
740
+ {
741
+ "epoch": 1.3206349206349206,
742
+ "grad_norm": 0.5053452849388123,
743
+ "learning_rate": 1.1195767195767197e-05,
744
+ "loss": 0.0742,
745
+ "step": 52000
746
+ },
747
+ {
748
+ "epoch": 1.3333333333333333,
749
+ "grad_norm": 0.42281991243362427,
750
+ "learning_rate": 1.1111111111111113e-05,
751
+ "loss": 0.0728,
752
+ "step": 52500
753
+ },
754
+ {
755
+ "epoch": 1.3460317460317461,
756
+ "grad_norm": 0.4088720679283142,
757
+ "learning_rate": 1.1026455026455028e-05,
758
+ "loss": 0.0737,
759
+ "step": 53000
760
+ },
761
+ {
762
+ "epoch": 1.3587301587301588,
763
+ "grad_norm": 0.4682016968727112,
764
+ "learning_rate": 1.0941798941798943e-05,
765
+ "loss": 0.0754,
766
+ "step": 53500
767
+ },
768
+ {
769
+ "epoch": 1.3714285714285714,
770
+ "grad_norm": 0.35886242985725403,
771
+ "learning_rate": 1.0857142857142858e-05,
772
+ "loss": 0.0739,
773
+ "step": 54000
774
+ },
775
+ {
776
+ "epoch": 1.384126984126984,
777
+ "grad_norm": 0.5034026503562927,
778
+ "learning_rate": 1.0772486772486774e-05,
779
+ "loss": 0.0744,
780
+ "step": 54500
781
+ },
782
+ {
783
+ "epoch": 1.3968253968253967,
784
+ "grad_norm": 0.6038418412208557,
785
+ "learning_rate": 1.0687830687830689e-05,
786
+ "loss": 0.073,
787
+ "step": 55000
788
+ },
789
+ {
790
+ "epoch": 1.4095238095238094,
791
+ "grad_norm": 0.4263134002685547,
792
+ "learning_rate": 1.0603174603174604e-05,
793
+ "loss": 0.0743,
794
+ "step": 55500
795
+ },
796
+ {
797
+ "epoch": 1.4222222222222223,
798
+ "grad_norm": 0.3092331886291504,
799
+ "learning_rate": 1.0518518518518519e-05,
800
+ "loss": 0.0747,
801
+ "step": 56000
802
+ },
803
+ {
804
+ "epoch": 1.434920634920635,
805
+ "grad_norm": 0.41775885224342346,
806
+ "learning_rate": 1.0433862433862433e-05,
807
+ "loss": 0.0736,
808
+ "step": 56500
809
+ },
810
+ {
811
+ "epoch": 1.4476190476190476,
812
+ "grad_norm": 0.3818839192390442,
813
+ "learning_rate": 1.0349206349206352e-05,
814
+ "loss": 0.0736,
815
+ "step": 57000
816
+ },
817
+ {
818
+ "epoch": 1.4603174603174602,
819
+ "grad_norm": 0.42527565360069275,
820
+ "learning_rate": 1.0264550264550266e-05,
821
+ "loss": 0.0741,
822
+ "step": 57500
823
+ },
824
+ {
825
+ "epoch": 1.4730158730158731,
826
+ "grad_norm": 0.37903305888175964,
827
+ "learning_rate": 1.0179894179894181e-05,
828
+ "loss": 0.0727,
829
+ "step": 58000
830
+ },
831
+ {
832
+ "epoch": 1.4857142857142858,
833
+ "grad_norm": 0.41770797967910767,
834
+ "learning_rate": 1.0095238095238096e-05,
835
+ "loss": 0.0733,
836
+ "step": 58500
837
+ },
838
+ {
839
+ "epoch": 1.4984126984126984,
840
+ "grad_norm": 0.6334396600723267,
841
+ "learning_rate": 1.001058201058201e-05,
842
+ "loss": 0.073,
843
+ "step": 59000
844
+ },
845
+ {
846
+ "epoch": 1.511111111111111,
847
+ "grad_norm": 0.3735711872577667,
848
+ "learning_rate": 9.925925925925927e-06,
849
+ "loss": 0.0739,
850
+ "step": 59500
851
+ },
852
+ {
853
+ "epoch": 1.5238095238095237,
854
+ "grad_norm": 0.40507185459136963,
855
+ "learning_rate": 9.841269841269842e-06,
856
+ "loss": 0.0731,
857
+ "step": 60000
858
+ },
859
+ {
860
+ "epoch": 1.5365079365079364,
861
+ "grad_norm": 0.4952349066734314,
862
+ "learning_rate": 9.756613756613757e-06,
863
+ "loss": 0.0741,
864
+ "step": 60500
865
+ },
866
+ {
867
+ "epoch": 1.5492063492063493,
868
+ "grad_norm": 0.4670361280441284,
869
+ "learning_rate": 9.671957671957672e-06,
870
+ "loss": 0.0736,
871
+ "step": 61000
872
+ },
873
+ {
874
+ "epoch": 1.561904761904762,
875
+ "grad_norm": 0.2984641492366791,
876
+ "learning_rate": 9.587301587301588e-06,
877
+ "loss": 0.0732,
878
+ "step": 61500
879
+ },
880
+ {
881
+ "epoch": 1.5746031746031746,
882
+ "grad_norm": 0.5101374983787537,
883
+ "learning_rate": 9.502645502645503e-06,
884
+ "loss": 0.0759,
885
+ "step": 62000
886
+ },
887
+ {
888
+ "epoch": 1.5873015873015874,
889
+ "grad_norm": 0.38656944036483765,
890
+ "learning_rate": 9.417989417989418e-06,
891
+ "loss": 0.0741,
892
+ "step": 62500
893
+ },
894
+ {
895
+ "epoch": 1.6,
896
+ "grad_norm": 0.508953869342804,
897
+ "learning_rate": 9.333333333333334e-06,
898
+ "loss": 0.0737,
899
+ "step": 63000
900
+ },
901
+ {
902
+ "epoch": 1.6126984126984127,
903
+ "grad_norm": 0.49415382742881775,
904
+ "learning_rate": 9.248677248677249e-06,
905
+ "loss": 0.0736,
906
+ "step": 63500
907
+ },
908
+ {
909
+ "epoch": 1.6253968253968254,
910
+ "grad_norm": 0.48334264755249023,
911
+ "learning_rate": 9.164021164021166e-06,
912
+ "loss": 0.0739,
913
+ "step": 64000
914
+ },
915
+ {
916
+ "epoch": 1.638095238095238,
917
+ "grad_norm": 0.3960755467414856,
918
+ "learning_rate": 9.07936507936508e-06,
919
+ "loss": 0.0723,
920
+ "step": 64500
921
+ },
922
+ {
923
+ "epoch": 1.6507936507936507,
924
+ "grad_norm": 0.4537145495414734,
925
+ "learning_rate": 8.994708994708995e-06,
926
+ "loss": 0.0723,
927
+ "step": 65000
928
+ },
929
+ {
930
+ "epoch": 1.6634920634920634,
931
+ "grad_norm": 0.4759564697742462,
932
+ "learning_rate": 8.910052910052912e-06,
933
+ "loss": 0.0737,
934
+ "step": 65500
935
+ },
936
+ {
937
+ "epoch": 1.6761904761904762,
938
+ "grad_norm": 0.564620316028595,
939
+ "learning_rate": 8.825396825396827e-06,
940
+ "loss": 0.0726,
941
+ "step": 66000
942
+ },
943
+ {
944
+ "epoch": 1.6888888888888889,
945
+ "grad_norm": 0.3793913424015045,
946
+ "learning_rate": 8.740740740740741e-06,
947
+ "loss": 0.0725,
948
+ "step": 66500
949
+ },
950
+ {
951
+ "epoch": 1.7015873015873015,
952
+ "grad_norm": 0.3748345673084259,
953
+ "learning_rate": 8.656084656084656e-06,
954
+ "loss": 0.0734,
955
+ "step": 67000
956
+ },
957
+ {
958
+ "epoch": 1.7142857142857144,
959
+ "grad_norm": 0.31550857424736023,
960
+ "learning_rate": 8.571428571428571e-06,
961
+ "loss": 0.0728,
962
+ "step": 67500
963
+ },
964
+ {
965
+ "epoch": 1.726984126984127,
966
+ "grad_norm": 0.39485469460487366,
967
+ "learning_rate": 8.486772486772487e-06,
968
+ "loss": 0.074,
969
+ "step": 68000
970
+ },
971
+ {
972
+ "epoch": 1.7396825396825397,
973
+ "grad_norm": 0.3833816647529602,
974
+ "learning_rate": 8.402116402116402e-06,
975
+ "loss": 0.0727,
976
+ "step": 68500
977
+ },
978
+ {
979
+ "epoch": 1.7523809523809524,
980
+ "grad_norm": 0.45526403188705444,
981
+ "learning_rate": 8.317460317460319e-06,
982
+ "loss": 0.0721,
983
+ "step": 69000
984
+ },
985
+ {
986
+ "epoch": 1.765079365079365,
987
+ "grad_norm": 0.4437309801578522,
988
+ "learning_rate": 8.232804232804234e-06,
989
+ "loss": 0.0714,
990
+ "step": 69500
991
+ },
992
+ {
993
+ "epoch": 1.7777777777777777,
994
+ "grad_norm": 0.3827795386314392,
995
+ "learning_rate": 8.148148148148148e-06,
996
+ "loss": 0.0736,
997
+ "step": 70000
998
+ },
999
+ {
1000
+ "epoch": 1.7904761904761903,
1001
+ "grad_norm": 0.3821280896663666,
1002
+ "learning_rate": 8.063492063492065e-06,
1003
+ "loss": 0.0742,
1004
+ "step": 70500
1005
+ },
1006
+ {
1007
+ "epoch": 1.8031746031746032,
1008
+ "grad_norm": 0.3558200001716614,
1009
+ "learning_rate": 7.97883597883598e-06,
1010
+ "loss": 0.0733,
1011
+ "step": 71000
1012
+ },
1013
+ {
1014
+ "epoch": 1.8158730158730159,
1015
+ "grad_norm": 0.35507771372795105,
1016
+ "learning_rate": 7.894179894179896e-06,
1017
+ "loss": 0.073,
1018
+ "step": 71500
1019
+ },
1020
+ {
1021
+ "epoch": 1.8285714285714287,
1022
+ "grad_norm": 0.4878668785095215,
1023
+ "learning_rate": 7.809523809523811e-06,
1024
+ "loss": 0.0726,
1025
+ "step": 72000
1026
+ },
1027
+ {
1028
+ "epoch": 1.8412698412698414,
1029
+ "grad_norm": 0.46924230456352234,
1030
+ "learning_rate": 7.724867724867726e-06,
1031
+ "loss": 0.0729,
1032
+ "step": 72500
1033
+ },
1034
+ {
1035
+ "epoch": 1.853968253968254,
1036
+ "grad_norm": 0.5545886158943176,
1037
+ "learning_rate": 7.64021164021164e-06,
1038
+ "loss": 0.0728,
1039
+ "step": 73000
1040
+ },
1041
+ {
1042
+ "epoch": 1.8666666666666667,
1043
+ "grad_norm": 0.33820512890815735,
1044
+ "learning_rate": 7.555555555555556e-06,
1045
+ "loss": 0.0727,
1046
+ "step": 73500
1047
+ },
1048
+ {
1049
+ "epoch": 1.8793650793650793,
1050
+ "grad_norm": 0.4180295169353485,
1051
+ "learning_rate": 7.470899470899472e-06,
1052
+ "loss": 0.0722,
1053
+ "step": 74000
1054
+ },
1055
+ {
1056
+ "epoch": 1.892063492063492,
1057
+ "grad_norm": 0.41895756125450134,
1058
+ "learning_rate": 7.386243386243387e-06,
1059
+ "loss": 0.0721,
1060
+ "step": 74500
1061
+ },
1062
+ {
1063
+ "epoch": 1.9047619047619047,
1064
+ "grad_norm": 0.37801581621170044,
1065
+ "learning_rate": 7.301587301587301e-06,
1066
+ "loss": 0.0754,
1067
+ "step": 75000
1068
+ },
1069
+ {
1070
+ "epoch": 1.9174603174603173,
1071
+ "grad_norm": 0.42890599370002747,
1072
+ "learning_rate": 7.216931216931218e-06,
1073
+ "loss": 0.0727,
1074
+ "step": 75500
1075
+ },
1076
+ {
1077
+ "epoch": 1.9301587301587302,
1078
+ "grad_norm": 0.36311328411102295,
1079
+ "learning_rate": 7.132275132275133e-06,
1080
+ "loss": 0.0732,
1081
+ "step": 76000
1082
+ },
1083
+ {
1084
+ "epoch": 1.9428571428571428,
1085
+ "grad_norm": 0.4069361090660095,
1086
+ "learning_rate": 7.047619047619048e-06,
1087
+ "loss": 0.0731,
1088
+ "step": 76500
1089
+ },
1090
+ {
1091
+ "epoch": 1.9555555555555557,
1092
+ "grad_norm": 0.38275209069252014,
1093
+ "learning_rate": 6.962962962962964e-06,
1094
+ "loss": 0.0729,
1095
+ "step": 77000
1096
+ },
1097
+ {
1098
+ "epoch": 1.9682539682539684,
1099
+ "grad_norm": 0.3496081829071045,
1100
+ "learning_rate": 6.878306878306879e-06,
1101
+ "loss": 0.0725,
1102
+ "step": 77500
1103
+ },
1104
+ {
1105
+ "epoch": 1.980952380952381,
1106
+ "grad_norm": 0.37429070472717285,
1107
+ "learning_rate": 6.7936507936507944e-06,
1108
+ "loss": 0.0726,
1109
+ "step": 78000
1110
+ },
1111
+ {
1112
+ "epoch": 1.9936507936507937,
1113
+ "grad_norm": 0.4195725619792938,
1114
+ "learning_rate": 6.708994708994709e-06,
1115
+ "loss": 0.0724,
1116
+ "step": 78500
1117
+ },
1118
+ {
1119
+ "epoch": 2.0,
1120
+ "eval_loss": 0.0749795213341713,
1121
+ "eval_runtime": 269.1515,
1122
+ "eval_samples_per_second": 520.153,
1123
+ "eval_steps_per_second": 65.019,
1124
+ "step": 78750
1125
+ },
1126
+ {
1127
+ "epoch": 2.0063492063492063,
1128
+ "grad_norm": 0.4257189631462097,
1129
+ "learning_rate": 6.624338624338626e-06,
1130
+ "loss": 0.07,
1131
+ "step": 79000
1132
+ },
1133
+ {
1134
+ "epoch": 2.019047619047619,
1135
+ "grad_norm": 0.37472862005233765,
1136
+ "learning_rate": 6.5396825396825405e-06,
1137
+ "loss": 0.0664,
1138
+ "step": 79500
1139
+ },
1140
+ {
1141
+ "epoch": 2.0317460317460316,
1142
+ "grad_norm": 0.4728703796863556,
1143
+ "learning_rate": 6.455026455026455e-06,
1144
+ "loss": 0.0664,
1145
+ "step": 80000
1146
+ },
1147
+ {
1148
+ "epoch": 2.0444444444444443,
1149
+ "grad_norm": 0.42774897813796997,
1150
+ "learning_rate": 6.370370370370371e-06,
1151
+ "loss": 0.0661,
1152
+ "step": 80500
1153
+ },
1154
+ {
1155
+ "epoch": 2.057142857142857,
1156
+ "grad_norm": 0.4025447368621826,
1157
+ "learning_rate": 6.285714285714286e-06,
1158
+ "loss": 0.0679,
1159
+ "step": 81000
1160
+ },
1161
+ {
1162
+ "epoch": 2.06984126984127,
1163
+ "grad_norm": 0.41302409768104553,
1164
+ "learning_rate": 6.201058201058202e-06,
1165
+ "loss": 0.0662,
1166
+ "step": 81500
1167
+ },
1168
+ {
1169
+ "epoch": 2.0825396825396827,
1170
+ "grad_norm": 0.4339478611946106,
1171
+ "learning_rate": 6.116402116402117e-06,
1172
+ "loss": 0.0662,
1173
+ "step": 82000
1174
+ },
1175
+ {
1176
+ "epoch": 2.0952380952380953,
1177
+ "grad_norm": 0.38711288571357727,
1178
+ "learning_rate": 6.031746031746032e-06,
1179
+ "loss": 0.0677,
1180
+ "step": 82500
1181
+ },
1182
+ {
1183
+ "epoch": 2.107936507936508,
1184
+ "grad_norm": 0.44815394282341003,
1185
+ "learning_rate": 5.9470899470899475e-06,
1186
+ "loss": 0.0674,
1187
+ "step": 83000
1188
+ },
1189
+ {
1190
+ "epoch": 2.1206349206349207,
1191
+ "grad_norm": 0.4252176582813263,
1192
+ "learning_rate": 5.862433862433863e-06,
1193
+ "loss": 0.067,
1194
+ "step": 83500
1195
+ },
1196
+ {
1197
+ "epoch": 2.1333333333333333,
1198
+ "grad_norm": 0.4019823670387268,
1199
+ "learning_rate": 5.777777777777778e-06,
1200
+ "loss": 0.0676,
1201
+ "step": 84000
1202
+ },
1203
+ {
1204
+ "epoch": 2.146031746031746,
1205
+ "grad_norm": 0.37775805592536926,
1206
+ "learning_rate": 5.693121693121694e-06,
1207
+ "loss": 0.0671,
1208
+ "step": 84500
1209
+ },
1210
+ {
1211
+ "epoch": 2.1587301587301586,
1212
+ "grad_norm": 0.5179104208946228,
1213
+ "learning_rate": 5.6084656084656084e-06,
1214
+ "loss": 0.0671,
1215
+ "step": 85000
1216
+ },
1217
+ {
1218
+ "epoch": 2.1714285714285713,
1219
+ "grad_norm": 0.37160980701446533,
1220
+ "learning_rate": 5.523809523809525e-06,
1221
+ "loss": 0.0677,
1222
+ "step": 85500
1223
+ },
1224
+ {
1225
+ "epoch": 2.1841269841269844,
1226
+ "grad_norm": 0.4610843360424042,
1227
+ "learning_rate": 5.43915343915344e-06,
1228
+ "loss": 0.0671,
1229
+ "step": 86000
1230
+ },
1231
+ {
1232
+ "epoch": 2.196825396825397,
1233
+ "grad_norm": 0.4135109484195709,
1234
+ "learning_rate": 5.3544973544973545e-06,
1235
+ "loss": 0.0678,
1236
+ "step": 86500
1237
+ },
1238
+ {
1239
+ "epoch": 2.2095238095238097,
1240
+ "grad_norm": 0.38079920411109924,
1241
+ "learning_rate": 5.26984126984127e-06,
1242
+ "loss": 0.0678,
1243
+ "step": 87000
1244
+ },
1245
+ {
1246
+ "epoch": 2.2222222222222223,
1247
+ "grad_norm": 0.39888954162597656,
1248
+ "learning_rate": 5.185185185185185e-06,
1249
+ "loss": 0.0669,
1250
+ "step": 87500
1251
+ },
1252
+ {
1253
+ "epoch": 2.234920634920635,
1254
+ "grad_norm": 0.37562116980552673,
1255
+ "learning_rate": 5.1005291005291015e-06,
1256
+ "loss": 0.0661,
1257
+ "step": 88000
1258
+ },
1259
+ {
1260
+ "epoch": 2.2476190476190476,
1261
+ "grad_norm": 0.4394863247871399,
1262
+ "learning_rate": 5.015873015873016e-06,
1263
+ "loss": 0.0671,
1264
+ "step": 88500
1265
+ },
1266
+ {
1267
+ "epoch": 2.2603174603174603,
1268
+ "grad_norm": 0.4748270511627197,
1269
+ "learning_rate": 4.931216931216932e-06,
1270
+ "loss": 0.067,
1271
+ "step": 89000
1272
+ },
1273
+ {
1274
+ "epoch": 2.273015873015873,
1275
+ "grad_norm": 0.4593636095523834,
1276
+ "learning_rate": 4.846560846560847e-06,
1277
+ "loss": 0.067,
1278
+ "step": 89500
1279
+ },
1280
+ {
1281
+ "epoch": 2.2857142857142856,
1282
+ "grad_norm": 0.3517415225505829,
1283
+ "learning_rate": 4.761904761904762e-06,
1284
+ "loss": 0.0669,
1285
+ "step": 90000
1286
+ },
1287
+ {
1288
+ "epoch": 2.2984126984126982,
1289
+ "grad_norm": 0.40983742475509644,
1290
+ "learning_rate": 4.677248677248677e-06,
1291
+ "loss": 0.0681,
1292
+ "step": 90500
1293
+ },
1294
+ {
1295
+ "epoch": 2.311111111111111,
1296
+ "grad_norm": 0.46570950746536255,
1297
+ "learning_rate": 4.592592592592593e-06,
1298
+ "loss": 0.0672,
1299
+ "step": 91000
1300
+ },
1301
+ {
1302
+ "epoch": 2.323809523809524,
1303
+ "grad_norm": 0.4733307957649231,
1304
+ "learning_rate": 4.5079365079365085e-06,
1305
+ "loss": 0.0671,
1306
+ "step": 91500
1307
+ },
1308
+ {
1309
+ "epoch": 2.3365079365079366,
1310
+ "grad_norm": 0.38432806730270386,
1311
+ "learning_rate": 4.423280423280424e-06,
1312
+ "loss": 0.0672,
1313
+ "step": 92000
1314
+ },
1315
+ {
1316
+ "epoch": 2.3492063492063493,
1317
+ "grad_norm": 0.31346267461776733,
1318
+ "learning_rate": 4.338624338624339e-06,
1319
+ "loss": 0.066,
1320
+ "step": 92500
1321
+ },
1322
+ {
1323
+ "epoch": 2.361904761904762,
1324
+ "grad_norm": 0.5612916350364685,
1325
+ "learning_rate": 4.2539682539682546e-06,
1326
+ "loss": 0.0666,
1327
+ "step": 93000
1328
+ },
1329
+ {
1330
+ "epoch": 2.3746031746031746,
1331
+ "grad_norm": 0.3445761501789093,
1332
+ "learning_rate": 4.169312169312169e-06,
1333
+ "loss": 0.0675,
1334
+ "step": 93500
1335
+ },
1336
+ {
1337
+ "epoch": 2.3873015873015873,
1338
+ "grad_norm": 0.41335174441337585,
1339
+ "learning_rate": 4.084656084656085e-06,
1340
+ "loss": 0.0676,
1341
+ "step": 94000
1342
+ },
1343
+ {
1344
+ "epoch": 2.4,
1345
+ "grad_norm": 0.42691895365715027,
1346
+ "learning_rate": 4.000000000000001e-06,
1347
+ "loss": 0.0669,
1348
+ "step": 94500
1349
+ },
1350
+ {
1351
+ "epoch": 2.4126984126984126,
1352
+ "grad_norm": 0.44459807872772217,
1353
+ "learning_rate": 3.9153439153439155e-06,
1354
+ "loss": 0.0661,
1355
+ "step": 95000
1356
+ },
1357
+ {
1358
+ "epoch": 2.425396825396825,
1359
+ "grad_norm": 0.39611610770225525,
1360
+ "learning_rate": 3.830687830687831e-06,
1361
+ "loss": 0.0665,
1362
+ "step": 95500
1363
+ },
1364
+ {
1365
+ "epoch": 2.4380952380952383,
1366
+ "grad_norm": 0.41603508591651917,
1367
+ "learning_rate": 3.7460317460317463e-06,
1368
+ "loss": 0.067,
1369
+ "step": 96000
1370
+ },
1371
+ {
1372
+ "epoch": 2.450793650793651,
1373
+ "grad_norm": 0.45685020089149475,
1374
+ "learning_rate": 3.661375661375662e-06,
1375
+ "loss": 0.0664,
1376
+ "step": 96500
1377
+ },
1378
+ {
1379
+ "epoch": 2.4634920634920636,
1380
+ "grad_norm": 0.41426390409469604,
1381
+ "learning_rate": 3.5767195767195772e-06,
1382
+ "loss": 0.0665,
1383
+ "step": 97000
1384
+ },
1385
+ {
1386
+ "epoch": 2.4761904761904763,
1387
+ "grad_norm": 0.4311801791191101,
1388
+ "learning_rate": 3.492063492063492e-06,
1389
+ "loss": 0.0673,
1390
+ "step": 97500
1391
+ },
1392
+ {
1393
+ "epoch": 2.488888888888889,
1394
+ "grad_norm": 0.39366066455841064,
1395
+ "learning_rate": 3.4074074074074077e-06,
1396
+ "loss": 0.0676,
1397
+ "step": 98000
1398
+ },
1399
+ {
1400
+ "epoch": 2.5015873015873016,
1401
+ "grad_norm": 0.46240171790122986,
1402
+ "learning_rate": 3.322751322751323e-06,
1403
+ "loss": 0.0674,
1404
+ "step": 98500
1405
+ },
1406
+ {
1407
+ "epoch": 2.5142857142857142,
1408
+ "grad_norm": 0.45865318179130554,
1409
+ "learning_rate": 3.2380952380952385e-06,
1410
+ "loss": 0.0671,
1411
+ "step": 99000
1412
+ },
1413
+ {
1414
+ "epoch": 2.526984126984127,
1415
+ "grad_norm": 0.38405075669288635,
1416
+ "learning_rate": 3.1534391534391538e-06,
1417
+ "loss": 0.0678,
1418
+ "step": 99500
1419
+ },
1420
+ {
1421
+ "epoch": 2.5396825396825395,
1422
+ "grad_norm": 0.48667874932289124,
1423
+ "learning_rate": 3.068783068783069e-06,
1424
+ "loss": 0.0661,
1425
+ "step": 100000
1426
+ },
1427
+ {
1428
+ "epoch": 2.552380952380952,
1429
+ "grad_norm": 0.3919212818145752,
1430
+ "learning_rate": 2.984126984126984e-06,
1431
+ "loss": 0.0654,
1432
+ "step": 100500
1433
+ },
1434
+ {
1435
+ "epoch": 2.565079365079365,
1436
+ "grad_norm": 0.4081352651119232,
1437
+ "learning_rate": 2.8994708994709e-06,
1438
+ "loss": 0.0669,
1439
+ "step": 101000
1440
+ },
1441
+ {
1442
+ "epoch": 2.5777777777777775,
1443
+ "grad_norm": 0.33449599146842957,
1444
+ "learning_rate": 2.814814814814815e-06,
1445
+ "loss": 0.0655,
1446
+ "step": 101500
1447
+ },
1448
+ {
1449
+ "epoch": 2.5904761904761906,
1450
+ "grad_norm": 0.37508487701416016,
1451
+ "learning_rate": 2.7301587301587303e-06,
1452
+ "loss": 0.0659,
1453
+ "step": 102000
1454
+ },
1455
+ {
1456
+ "epoch": 2.6031746031746033,
1457
+ "grad_norm": 0.43301156163215637,
1458
+ "learning_rate": 2.6455026455026455e-06,
1459
+ "loss": 0.0684,
1460
+ "step": 102500
1461
+ },
1462
+ {
1463
+ "epoch": 2.615873015873016,
1464
+ "grad_norm": 0.31652727723121643,
1465
+ "learning_rate": 2.560846560846561e-06,
1466
+ "loss": 0.0674,
1467
+ "step": 103000
1468
+ },
1469
+ {
1470
+ "epoch": 2.6285714285714286,
1471
+ "grad_norm": 0.38132810592651367,
1472
+ "learning_rate": 2.4761904761904764e-06,
1473
+ "loss": 0.0665,
1474
+ "step": 103500
1475
+ },
1476
+ {
1477
+ "epoch": 2.641269841269841,
1478
+ "grad_norm": 0.4249517023563385,
1479
+ "learning_rate": 2.3915343915343916e-06,
1480
+ "loss": 0.0678,
1481
+ "step": 104000
1482
+ },
1483
+ {
1484
+ "epoch": 2.653968253968254,
1485
+ "grad_norm": 0.42605915665626526,
1486
+ "learning_rate": 2.3068783068783073e-06,
1487
+ "loss": 0.0659,
1488
+ "step": 104500
1489
+ },
1490
+ {
1491
+ "epoch": 2.6666666666666665,
1492
+ "grad_norm": 0.4002751111984253,
1493
+ "learning_rate": 2.222222222222222e-06,
1494
+ "loss": 0.0665,
1495
+ "step": 105000
1496
+ },
1497
+ {
1498
+ "epoch": 2.6793650793650796,
1499
+ "grad_norm": 0.5232521891593933,
1500
+ "learning_rate": 2.1375661375661377e-06,
1501
+ "loss": 0.0676,
1502
+ "step": 105500
1503
+ },
1504
+ {
1505
+ "epoch": 2.6920634920634923,
1506
+ "grad_norm": 0.409422367811203,
1507
+ "learning_rate": 2.0529100529100534e-06,
1508
+ "loss": 0.0658,
1509
+ "step": 106000
1510
+ },
1511
+ {
1512
+ "epoch": 2.704761904761905,
1513
+ "grad_norm": 0.3971617519855499,
1514
+ "learning_rate": 1.968253968253968e-06,
1515
+ "loss": 0.0655,
1516
+ "step": 106500
1517
+ },
1518
+ {
1519
+ "epoch": 2.7174603174603176,
1520
+ "grad_norm": 0.35877570509910583,
1521
+ "learning_rate": 1.8835978835978838e-06,
1522
+ "loss": 0.0673,
1523
+ "step": 107000
1524
+ },
1525
+ {
1526
+ "epoch": 2.7301587301587302,
1527
+ "grad_norm": 0.36749425530433655,
1528
+ "learning_rate": 1.798941798941799e-06,
1529
+ "loss": 0.0681,
1530
+ "step": 107500
1531
+ },
1532
+ {
1533
+ "epoch": 2.742857142857143,
1534
+ "grad_norm": 0.3727457821369171,
1535
+ "learning_rate": 1.7142857142857145e-06,
1536
+ "loss": 0.0665,
1537
+ "step": 108000
1538
+ },
1539
+ {
1540
+ "epoch": 2.7555555555555555,
1541
+ "grad_norm": 0.40977808833122253,
1542
+ "learning_rate": 1.62962962962963e-06,
1543
+ "loss": 0.0672,
1544
+ "step": 108500
1545
+ },
1546
+ {
1547
+ "epoch": 2.768253968253968,
1548
+ "grad_norm": 0.4265407621860504,
1549
+ "learning_rate": 1.5449735449735451e-06,
1550
+ "loss": 0.0666,
1551
+ "step": 109000
1552
+ },
1553
+ {
1554
+ "epoch": 2.780952380952381,
1555
+ "grad_norm": 0.3894596993923187,
1556
+ "learning_rate": 1.4603174603174606e-06,
1557
+ "loss": 0.0673,
1558
+ "step": 109500
1559
+ },
1560
+ {
1561
+ "epoch": 2.7936507936507935,
1562
+ "grad_norm": 0.526606023311615,
1563
+ "learning_rate": 1.3756613756613758e-06,
1564
+ "loss": 0.0676,
1565
+ "step": 110000
1566
+ },
1567
+ {
1568
+ "epoch": 2.806349206349206,
1569
+ "grad_norm": 0.2910812497138977,
1570
+ "learning_rate": 1.2910052910052912e-06,
1571
+ "loss": 0.0671,
1572
+ "step": 110500
1573
+ },
1574
+ {
1575
+ "epoch": 2.819047619047619,
1576
+ "grad_norm": 0.3701234757900238,
1577
+ "learning_rate": 1.2063492063492065e-06,
1578
+ "loss": 0.0666,
1579
+ "step": 111000
1580
+ },
1581
+ {
1582
+ "epoch": 2.831746031746032,
1583
+ "grad_norm": 0.3969452679157257,
1584
+ "learning_rate": 1.1216931216931217e-06,
1585
+ "loss": 0.0668,
1586
+ "step": 111500
1587
+ },
1588
+ {
1589
+ "epoch": 2.8444444444444446,
1590
+ "grad_norm": 0.4415270686149597,
1591
+ "learning_rate": 1.0370370370370371e-06,
1592
+ "loss": 0.0661,
1593
+ "step": 112000
1594
+ },
1595
+ {
1596
+ "epoch": 2.857142857142857,
1597
+ "grad_norm": 0.3490103483200073,
1598
+ "learning_rate": 9.523809523809525e-07,
1599
+ "loss": 0.0658,
1600
+ "step": 112500
1601
+ },
1602
+ {
1603
+ "epoch": 2.86984126984127,
1604
+ "grad_norm": 0.35733526945114136,
1605
+ "learning_rate": 8.677248677248679e-07,
1606
+ "loss": 0.0661,
1607
+ "step": 113000
1608
+ },
1609
+ {
1610
+ "epoch": 2.8825396825396825,
1611
+ "grad_norm": 0.4992692172527313,
1612
+ "learning_rate": 7.830687830687832e-07,
1613
+ "loss": 0.068,
1614
+ "step": 113500
1615
+ },
1616
+ {
1617
+ "epoch": 2.895238095238095,
1618
+ "grad_norm": 0.4047030508518219,
1619
+ "learning_rate": 6.984126984126984e-07,
1620
+ "loss": 0.0683,
1621
+ "step": 114000
1622
+ },
1623
+ {
1624
+ "epoch": 2.907936507936508,
1625
+ "grad_norm": 0.4468993544578552,
1626
+ "learning_rate": 6.137566137566138e-07,
1627
+ "loss": 0.0664,
1628
+ "step": 114500
1629
+ },
1630
+ {
1631
+ "epoch": 2.9206349206349205,
1632
+ "grad_norm": 0.41356751322746277,
1633
+ "learning_rate": 5.291005291005291e-07,
1634
+ "loss": 0.067,
1635
+ "step": 115000
1636
+ },
1637
+ {
1638
+ "epoch": 2.9333333333333336,
1639
+ "grad_norm": 0.4459340572357178,
1640
+ "learning_rate": 4.444444444444445e-07,
1641
+ "loss": 0.0671,
1642
+ "step": 115500
1643
+ },
1644
+ {
1645
+ "epoch": 2.9460317460317462,
1646
+ "grad_norm": 0.42610964179039,
1647
+ "learning_rate": 3.597883597883598e-07,
1648
+ "loss": 0.0664,
1649
+ "step": 116000
1650
+ },
1651
+ {
1652
+ "epoch": 2.958730158730159,
1653
+ "grad_norm": 0.5059521794319153,
1654
+ "learning_rate": 2.7513227513227515e-07,
1655
+ "loss": 0.0658,
1656
+ "step": 116500
1657
+ },
1658
+ {
1659
+ "epoch": 2.9714285714285715,
1660
+ "grad_norm": 0.3404170572757721,
1661
+ "learning_rate": 1.904761904761905e-07,
1662
+ "loss": 0.0667,
1663
+ "step": 117000
1664
+ },
1665
+ {
1666
+ "epoch": 2.984126984126984,
1667
+ "grad_norm": 0.4388870894908905,
1668
+ "learning_rate": 1.0582010582010582e-07,
1669
+ "loss": 0.0658,
1670
+ "step": 117500
1671
+ },
1672
+ {
1673
+ "epoch": 2.996825396825397,
1674
+ "grad_norm": 0.39170539379119873,
1675
+ "learning_rate": 2.1164021164021167e-08,
1676
+ "loss": 0.0665,
1677
+ "step": 118000
1678
+ }
1679
+ ],
1680
+ "logging_steps": 500,
1681
+ "max_steps": 118125,
1682
+ "num_input_tokens_seen": 0,
1683
+ "num_train_epochs": 3,
1684
+ "save_steps": 500,
1685
+ "stateful_callbacks": {
1686
+ "TrainerControl": {
1687
+ "args": {
1688
+ "should_epoch_stop": false,
1689
+ "should_evaluate": false,
1690
+ "should_log": false,
1691
+ "should_save": true,
1692
+ "should_training_stop": false
1693
+ },
1694
+ "attributes": {}
1695
+ }
1696
+ },
1697
+ "total_flos": 1.4389780414464e+17,
1698
+ "train_batch_size": 32,
1699
+ "trial_name": null,
1700
+ "trial_params": null
1701
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81545b8cc983615fb0af2c31741d2dfd4278b622a909b3d3f368ef0bd4f905d0
3
+ size 5240