Hugging Face's logo

Xenova
/
sponsorblock-classifier-v2

Text Classification
PyTorch
generic
bert
Model card Files Community
Joshua Lochner commited on
Commit
3b31bcb
•
1 Parent(s): 8e622c8

Add model files

Browse files
Files changed (11) hide show
  1. model/added_tokens.json +1 -0
  2. model/config.json +39 -0
  3. model/pytorch_model.bin +3 -0
  4. model/rng_state.pth +3 -0
  5. model/scheduler.pt +3 -0
  6. model/special_tokens_map.json +1 -0
  7. model/tokenizer.json +0 -0
  8. model/tokenizer_config.json +1 -0
  9. model/trainer_state.json +535 -0
  10. model/training_args.bin +3 -0
  11. model/vocab.txt +0 -0
model/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"NO_SEGMENT_TOKEN": 30533, "[Music]": 30529, "END_SELFPROMO_TOKEN": 30537, "START_SPONSOR_TOKEN": 30534, "[Laughter]": 30531, "URL_TOKEN": 30523, "END_SPONSOR_TOKEN": 30535, "LONG_WORD_TOKEN": 30528, "START_INTERACTION_TOKEN": 30538, "END_INTERACTION_TOKEN": 30539, "BETWEEN_SEGMENTS_TOKEN": 30540, "NUMBER_TOKEN": 30526, "HYPHENATED_URL_TOKEN": 30524, "NUMBER_PERCENTAGE_TOKEN": 30525, "EXTRACT_SEGMENTS: ": 30522, "START_SELFPROMO_TOKEN": 30536, "SHORT_HYPHENATED_TOKEN": 30527, "[Applause]": 30530, "PROFANITY_TOKEN": 30532}
model/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/classifier-85000",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": 0,
14
+ "1": 1,
15
+ "2": 2,
16
+ "3": 3
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1,
23
+ "2": 2,
24
+ "3": 3
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "bert",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.17.0",
36
+ "type_vocab_size": 2,
37
+ "use_cache": true,
38
+ "vocab_size": 30541
39
+ }
model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee62e423bcc4da4de843761a54a68290678e57615597df5dfdd86526eb8b12b6
3
+ size 438084653
model/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619e7f66007f3dff9f20798f52a33d5c42492dcff7460d0a460df6fcf4d37aa0
3
+ size 14439
model/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f92dab5bb679e1d43f8424db85d9b6db789bef47de73066c674b510bc751050
3
+ size 623
model/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
model/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "models/classifier-85000", "tokenizer_class": "BertTokenizer"}
model/trainer_state.json ADDED
@@ -0,0 +1,535 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.6386263390044107,
5
+ "global_step": 335000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 1.921235034656585e-05,
13
+ "loss": 0.3334,
14
+ "step": 5000
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 1.8424700693131696e-05,
19
+ "loss": 0.3387,
20
+ "step": 10000
21
+ },
22
+ {
23
+ "epoch": 0.12,
24
+ "learning_rate": 1.7637051039697544e-05,
25
+ "loss": 0.3327,
26
+ "step": 15000
27
+ },
28
+ {
29
+ "epoch": 0.16,
30
+ "learning_rate": 1.684940138626339e-05,
31
+ "loss": 0.3492,
32
+ "step": 20000
33
+ },
34
+ {
35
+ "epoch": 0.2,
36
+ "learning_rate": 1.606175173282924e-05,
37
+ "loss": 0.3349,
38
+ "step": 25000
39
+ },
40
+ {
41
+ "epoch": 0.2,
42
+ "eval_accuracy": 0.9155995845794678,
43
+ "eval_loss": 0.389266699552536,
44
+ "eval_runtime": 551.1932,
45
+ "eval_samples_per_second": 51.289,
46
+ "eval_steps_per_second": 12.823,
47
+ "step": 25000
48
+ },
49
+ {
50
+ "epoch": 0.24,
51
+ "learning_rate": 1.5274102079395087e-05,
52
+ "loss": 0.3279,
53
+ "step": 30000
54
+ },
55
+ {
56
+ "epoch": 0.28,
57
+ "learning_rate": 1.4486452425960932e-05,
58
+ "loss": 0.3301,
59
+ "step": 35000
60
+ },
61
+ {
62
+ "epoch": 0.32,
63
+ "learning_rate": 1.369880277252678e-05,
64
+ "loss": 0.3243,
65
+ "step": 40000
66
+ },
67
+ {
68
+ "epoch": 0.35,
69
+ "learning_rate": 1.2911153119092628e-05,
70
+ "loss": 0.293,
71
+ "step": 45000
72
+ },
73
+ {
74
+ "epoch": 0.39,
75
+ "learning_rate": 1.2123503465658477e-05,
76
+ "loss": 0.3053,
77
+ "step": 50000
78
+ },
79
+ {
80
+ "epoch": 0.39,
81
+ "eval_accuracy": 0.9235231876373291,
82
+ "eval_loss": 0.3810465931892395,
83
+ "eval_runtime": 542.4272,
84
+ "eval_samples_per_second": 52.118,
85
+ "eval_steps_per_second": 13.03,
86
+ "step": 50000
87
+ },
88
+ {
89
+ "epoch": 0.43,
90
+ "learning_rate": 1.1335853812224324e-05,
91
+ "loss": 0.3126,
92
+ "step": 55000
93
+ },
94
+ {
95
+ "epoch": 0.47,
96
+ "learning_rate": 1.0548204158790173e-05,
97
+ "loss": 0.3072,
98
+ "step": 60000
99
+ },
100
+ {
101
+ "epoch": 0.51,
102
+ "learning_rate": 9.760554505356018e-06,
103
+ "loss": 0.2957,
104
+ "step": 65000
105
+ },
106
+ {
107
+ "epoch": 0.55,
108
+ "learning_rate": 8.972904851921865e-06,
109
+ "loss": 0.2968,
110
+ "step": 70000
111
+ },
112
+ {
113
+ "epoch": 0.59,
114
+ "learning_rate": 8.185255198487714e-06,
115
+ "loss": 0.2882,
116
+ "step": 75000
117
+ },
118
+ {
119
+ "epoch": 0.59,
120
+ "eval_accuracy": 0.9224973320960999,
121
+ "eval_loss": 0.37537074089050293,
122
+ "eval_runtime": 521.9317,
123
+ "eval_samples_per_second": 54.164,
124
+ "eval_steps_per_second": 13.542,
125
+ "step": 75000
126
+ },
127
+ {
128
+ "epoch": 0.63,
129
+ "learning_rate": 7.3976055450535615e-06,
130
+ "loss": 0.2754,
131
+ "step": 80000
132
+ },
133
+ {
134
+ "epoch": 0.67,
135
+ "learning_rate": 6.6099558916194085e-06,
136
+ "loss": 0.2607,
137
+ "step": 85000
138
+ },
139
+ {
140
+ "epoch": 0.71,
141
+ "learning_rate": 5.8223062381852555e-06,
142
+ "loss": 0.2818,
143
+ "step": 90000
144
+ },
145
+ {
146
+ "epoch": 0.75,
147
+ "learning_rate": 5.034656584751103e-06,
148
+ "loss": 0.2736,
149
+ "step": 95000
150
+ },
151
+ {
152
+ "epoch": 0.79,
153
+ "learning_rate": 4.24700693131695e-06,
154
+ "loss": 0.2644,
155
+ "step": 100000
156
+ },
157
+ {
158
+ "epoch": 0.79,
159
+ "eval_accuracy": 0.9297842383384705,
160
+ "eval_loss": 0.3645715117454529,
161
+ "eval_runtime": 521.9055,
162
+ "eval_samples_per_second": 54.167,
163
+ "eval_steps_per_second": 13.543,
164
+ "step": 100000
165
+ },
166
+ {
167
+ "epoch": 0.83,
168
+ "learning_rate": 3.459357277882798e-06,
169
+ "loss": 0.2552,
170
+ "step": 105000
171
+ },
172
+ {
173
+ "epoch": 0.87,
174
+ "learning_rate": 2.6717076244486457e-06,
175
+ "loss": 0.266,
176
+ "step": 110000
177
+ },
178
+ {
179
+ "epoch": 0.91,
180
+ "learning_rate": 1.884057971014493e-06,
181
+ "loss": 0.2684,
182
+ "step": 115000
183
+ },
184
+ {
185
+ "epoch": 0.95,
186
+ "learning_rate": 1.0964083175803404e-06,
187
+ "loss": 0.2501,
188
+ "step": 120000
189
+ },
190
+ {
191
+ "epoch": 0.98,
192
+ "learning_rate": 3.087586641461878e-07,
193
+ "loss": 0.273,
194
+ "step": 125000
195
+ },
196
+ {
197
+ "epoch": 0.98,
198
+ "eval_accuracy": 0.9299964904785156,
199
+ "eval_loss": 0.3369257152080536,
200
+ "eval_runtime": 522.7551,
201
+ "eval_samples_per_second": 54.079,
202
+ "eval_steps_per_second": 13.521,
203
+ "step": 125000
204
+ },
205
+ {
206
+ "epoch": 1.02,
207
+ "learning_rate": 1.7952110901071204e-05,
208
+ "loss": 0.2834,
209
+ "step": 130000
210
+ },
211
+ {
212
+ "epoch": 1.06,
213
+ "learning_rate": 1.787334593572779e-05,
214
+ "loss": 0.3047,
215
+ "step": 135000
216
+ },
217
+ {
218
+ "epoch": 1.1,
219
+ "learning_rate": 1.7794580970384373e-05,
220
+ "loss": 0.2963,
221
+ "step": 140000
222
+ },
223
+ {
224
+ "epoch": 1.14,
225
+ "learning_rate": 1.771581600504096e-05,
226
+ "loss": 0.3031,
227
+ "step": 145000
228
+ },
229
+ {
230
+ "epoch": 1.18,
231
+ "learning_rate": 1.7637051039697544e-05,
232
+ "loss": 0.3033,
233
+ "step": 150000
234
+ },
235
+ {
236
+ "epoch": 1.18,
237
+ "eval_accuracy": 0.9257162809371948,
238
+ "eval_loss": 0.4006378650665283,
239
+ "eval_runtime": 519.4649,
240
+ "eval_samples_per_second": 54.421,
241
+ "eval_steps_per_second": 13.606,
242
+ "step": 150000
243
+ },
244
+ {
245
+ "epoch": 1.22,
246
+ "learning_rate": 1.755828607435413e-05,
247
+ "loss": 0.3024,
248
+ "step": 155000
249
+ },
250
+ {
251
+ "epoch": 1.26,
252
+ "learning_rate": 1.7479521109010713e-05,
253
+ "loss": 0.3135,
254
+ "step": 160000
255
+ },
256
+ {
257
+ "epoch": 1.3,
258
+ "learning_rate": 1.74007561436673e-05,
259
+ "loss": 0.3137,
260
+ "step": 165000
261
+ },
262
+ {
263
+ "epoch": 1.34,
264
+ "learning_rate": 1.732199117832388e-05,
265
+ "loss": 0.3227,
266
+ "step": 170000
267
+ },
268
+ {
269
+ "epoch": 1.38,
270
+ "learning_rate": 1.7243226212980467e-05,
271
+ "loss": 0.3246,
272
+ "step": 175000
273
+ },
274
+ {
275
+ "epoch": 1.38,
276
+ "eval_accuracy": 0.924018383026123,
277
+ "eval_loss": 0.3924681842327118,
278
+ "eval_runtime": 518.8244,
279
+ "eval_samples_per_second": 54.489,
280
+ "eval_steps_per_second": 13.623,
281
+ "step": 175000
282
+ },
283
+ {
284
+ "epoch": 1.42,
285
+ "learning_rate": 1.7164461247637053e-05,
286
+ "loss": 0.3281,
287
+ "step": 180000
288
+ },
289
+ {
290
+ "epoch": 1.46,
291
+ "learning_rate": 1.708569628229364e-05,
292
+ "loss": 0.3256,
293
+ "step": 185000
294
+ },
295
+ {
296
+ "epoch": 1.5,
297
+ "learning_rate": 1.700693131695022e-05,
298
+ "loss": 0.313,
299
+ "step": 190000
300
+ },
301
+ {
302
+ "epoch": 1.54,
303
+ "learning_rate": 1.6928166351606807e-05,
304
+ "loss": 0.3313,
305
+ "step": 195000
306
+ },
307
+ {
308
+ "epoch": 1.58,
309
+ "learning_rate": 1.684940138626339e-05,
310
+ "loss": 0.2953,
311
+ "step": 200000
312
+ },
313
+ {
314
+ "epoch": 1.58,
315
+ "eval_accuracy": 0.9212592840194702,
316
+ "eval_loss": 0.3895967900753021,
317
+ "eval_runtime": 526.2623,
318
+ "eval_samples_per_second": 53.718,
319
+ "eval_steps_per_second": 13.431,
320
+ "step": 200000
321
+ },
322
+ {
323
+ "epoch": 1.61,
324
+ "learning_rate": 1.6770636420919976e-05,
325
+ "loss": 0.3103,
326
+ "step": 205000
327
+ },
328
+ {
329
+ "epoch": 1.65,
330
+ "learning_rate": 1.669187145557656e-05,
331
+ "loss": 0.3089,
332
+ "step": 210000
333
+ },
334
+ {
335
+ "epoch": 1.69,
336
+ "learning_rate": 1.6613106490233147e-05,
337
+ "loss": 0.3095,
338
+ "step": 215000
339
+ },
340
+ {
341
+ "epoch": 1.73,
342
+ "learning_rate": 1.653434152488973e-05,
343
+ "loss": 0.3288,
344
+ "step": 220000
345
+ },
346
+ {
347
+ "epoch": 1.77,
348
+ "learning_rate": 1.6455576559546316e-05,
349
+ "loss": 0.3199,
350
+ "step": 225000
351
+ },
352
+ {
353
+ "epoch": 1.77,
354
+ "eval_accuracy": 0.9203749299049377,
355
+ "eval_loss": 0.3942428529262543,
356
+ "eval_runtime": 520.6801,
357
+ "eval_samples_per_second": 54.294,
358
+ "eval_steps_per_second": 13.575,
359
+ "step": 225000
360
+ },
361
+ {
362
+ "epoch": 1.81,
363
+ "learning_rate": 1.6376811594202898e-05,
364
+ "loss": 0.306,
365
+ "step": 230000
366
+ },
367
+ {
368
+ "epoch": 1.85,
369
+ "learning_rate": 1.6298046628859484e-05,
370
+ "loss": 0.3104,
371
+ "step": 235000
372
+ },
373
+ {
374
+ "epoch": 1.89,
375
+ "learning_rate": 1.621928166351607e-05,
376
+ "loss": 0.3139,
377
+ "step": 240000
378
+ },
379
+ {
380
+ "epoch": 1.93,
381
+ "learning_rate": 1.6140516698172656e-05,
382
+ "loss": 0.3179,
383
+ "step": 245000
384
+ },
385
+ {
386
+ "epoch": 1.97,
387
+ "learning_rate": 1.606175173282924e-05,
388
+ "loss": 0.3226,
389
+ "step": 250000
390
+ },
391
+ {
392
+ "epoch": 1.97,
393
+ "eval_accuracy": 0.9243367314338684,
394
+ "eval_loss": 0.4058537185192108,
395
+ "eval_runtime": 552.8946,
396
+ "eval_samples_per_second": 51.131,
397
+ "eval_steps_per_second": 12.784,
398
+ "step": 250000
399
+ },
400
+ {
401
+ "epoch": 2.01,
402
+ "learning_rate": 1.5982986767485824e-05,
403
+ "loss": 0.3167,
404
+ "step": 255000
405
+ },
406
+ {
407
+ "epoch": 2.05,
408
+ "learning_rate": 1.5904221802142407e-05,
409
+ "loss": 0.3034,
410
+ "step": 260000
411
+ },
412
+ {
413
+ "epoch": 2.09,
414
+ "learning_rate": 1.5825456836798993e-05,
415
+ "loss": 0.2976,
416
+ "step": 265000
417
+ },
418
+ {
419
+ "epoch": 2.13,
420
+ "learning_rate": 1.574669187145558e-05,
421
+ "loss": 0.3039,
422
+ "step": 270000
423
+ },
424
+ {
425
+ "epoch": 2.17,
426
+ "learning_rate": 1.5667926906112164e-05,
427
+ "loss": 0.2889,
428
+ "step": 275000
429
+ },
430
+ {
431
+ "epoch": 2.17,
432
+ "eval_accuracy": 0.9221436381340027,
433
+ "eval_loss": 0.39818692207336426,
434
+ "eval_runtime": 508.9512,
435
+ "eval_samples_per_second": 55.546,
436
+ "eval_steps_per_second": 13.887,
437
+ "step": 275000
438
+ },
439
+ {
440
+ "epoch": 2.21,
441
+ "learning_rate": 1.5589161940768747e-05,
442
+ "loss": 0.3079,
443
+ "step": 280000
444
+ },
445
+ {
446
+ "epoch": 2.24,
447
+ "learning_rate": 1.5510396975425333e-05,
448
+ "loss": 0.3148,
449
+ "step": 285000
450
+ },
451
+ {
452
+ "epoch": 2.28,
453
+ "learning_rate": 1.5431632010081915e-05,
454
+ "loss": 0.2829,
455
+ "step": 290000
456
+ },
457
+ {
458
+ "epoch": 2.32,
459
+ "learning_rate": 1.53528670447385e-05,
460
+ "loss": 0.2978,
461
+ "step": 295000
462
+ },
463
+ {
464
+ "epoch": 2.36,
465
+ "learning_rate": 1.5274102079395087e-05,
466
+ "loss": 0.2963,
467
+ "step": 300000
468
+ },
469
+ {
470
+ "epoch": 2.36,
471
+ "eval_accuracy": 0.922957181930542,
472
+ "eval_loss": 0.43214836716651917,
473
+ "eval_runtime": 528.9348,
474
+ "eval_samples_per_second": 53.447,
475
+ "eval_steps_per_second": 13.363,
476
+ "step": 300000
477
+ },
478
+ {
479
+ "epoch": 2.4,
480
+ "learning_rate": 1.5195337114051671e-05,
481
+ "loss": 0.3007,
482
+ "step": 305000
483
+ },
484
+ {
485
+ "epoch": 2.44,
486
+ "learning_rate": 1.5116572148708256e-05,
487
+ "loss": 0.2901,
488
+ "step": 310000
489
+ },
490
+ {
491
+ "epoch": 2.48,
492
+ "learning_rate": 1.5037807183364841e-05,
493
+ "loss": 0.2905,
494
+ "step": 315000
495
+ },
496
+ {
497
+ "epoch": 2.52,
498
+ "learning_rate": 1.4959042218021424e-05,
499
+ "loss": 0.3082,
500
+ "step": 320000
501
+ },
502
+ {
503
+ "epoch": 2.56,
504
+ "learning_rate": 1.488027725267801e-05,
505
+ "loss": 0.2899,
506
+ "step": 325000
507
+ },
508
+ {
509
+ "epoch": 2.56,
510
+ "eval_accuracy": 0.924124538898468,
511
+ "eval_loss": 0.40452826023101807,
512
+ "eval_runtime": 520.2943,
513
+ "eval_samples_per_second": 54.335,
514
+ "eval_steps_per_second": 13.585,
515
+ "step": 325000
516
+ },
517
+ {
518
+ "epoch": 2.6,
519
+ "learning_rate": 1.4801512287334594e-05,
520
+ "loss": 0.301,
521
+ "step": 330000
522
+ },
523
+ {
524
+ "epoch": 2.64,
525
+ "learning_rate": 1.472274732199118e-05,
526
+ "loss": 0.3014,
527
+ "step": 335000
528
+ }
529
+ ],
530
+ "max_steps": 1269600,
531
+ "num_train_epochs": 10,
532
+ "total_flos": 3.525740928655196e+17,
533
+ "trial_name": null,
534
+ "trial_params": null
535
+ }
model/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b494f397d6e04f9394bb348324c79c001055ee1edf517530763a4ad8c2a65e
3
+ size 2991
model/vocab.txt ADDED
The diff for this file is too large to render. See raw diff