portega commited on
Commit
7155e5b
1 Parent(s): 9d37fec

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.31.0",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 31002
27
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a5a5d627ddd0d0f0d5ad8c0c734ad01346384aa3c1dbe74bc0567d402f5e3a
3
+ size 878931077
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b7bd63cb92594faac70cbaa563537f502da11831806336c63a02090bc41d5e
3
+ size 439474993
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fef167f4fcb072d5407d72e5d7478b0e7174b67f2ec87c6420827d2b5e179e0
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b0610b44697b59bf91bf3bc0a8875296851ff3533b86161e98903a04261cf6
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": false,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
trainer_state.json ADDED
@@ -0,0 +1,703 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9928047404063205,
5
+ "global_step": 56500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.955911399548533e-05,
13
+ "loss": 1.0947,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.911822799097065e-05,
19
+ "loss": 0.9881,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 4.867734198645598e-05,
25
+ "loss": 0.9375,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.07,
30
+ "learning_rate": 4.8236455981941316e-05,
31
+ "loss": 0.9275,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 4.779556997742664e-05,
37
+ "loss": 0.9047,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.11,
42
+ "learning_rate": 4.7354683972911966e-05,
43
+ "loss": 0.8813,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "learning_rate": 4.6913797968397295e-05,
49
+ "loss": 0.8806,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.14,
54
+ "learning_rate": 4.647291196388262e-05,
55
+ "loss": 0.8718,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.16,
60
+ "learning_rate": 4.6032025959367945e-05,
61
+ "loss": 0.8828,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.18,
66
+ "learning_rate": 4.559113995485327e-05,
67
+ "loss": 0.8524,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.19,
72
+ "learning_rate": 4.51502539503386e-05,
73
+ "loss": 0.8464,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.21,
78
+ "learning_rate": 4.470936794582393e-05,
79
+ "loss": 0.8411,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.23,
84
+ "learning_rate": 4.426848194130926e-05,
85
+ "loss": 0.839,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.25,
90
+ "learning_rate": 4.382759593679459e-05,
91
+ "loss": 0.838,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.26,
96
+ "learning_rate": 4.338670993227991e-05,
97
+ "loss": 0.8531,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.28,
102
+ "learning_rate": 4.294582392776524e-05,
103
+ "loss": 0.8109,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.3,
108
+ "learning_rate": 4.2504937923250566e-05,
109
+ "loss": 0.8364,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.32,
114
+ "learning_rate": 4.2064051918735894e-05,
115
+ "loss": 0.8249,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.34,
120
+ "learning_rate": 4.1623165914221216e-05,
121
+ "loss": 0.8349,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.35,
126
+ "learning_rate": 4.118227990970655e-05,
127
+ "loss": 0.8136,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.37,
132
+ "learning_rate": 4.074139390519188e-05,
133
+ "loss": 0.8099,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.39,
138
+ "learning_rate": 4.03005079006772e-05,
139
+ "loss": 0.8054,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.41,
144
+ "learning_rate": 3.985962189616253e-05,
145
+ "loss": 0.8195,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.42,
150
+ "learning_rate": 3.941873589164786e-05,
151
+ "loss": 0.8646,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.44,
156
+ "learning_rate": 3.897784988713318e-05,
157
+ "loss": 0.8038,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.46,
162
+ "learning_rate": 3.853696388261851e-05,
163
+ "loss": 0.7897,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.48,
168
+ "learning_rate": 3.8096077878103843e-05,
169
+ "loss": 0.7991,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.49,
174
+ "learning_rate": 3.7655191873589165e-05,
175
+ "loss": 0.7834,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.51,
180
+ "learning_rate": 3.7214305869074494e-05,
181
+ "loss": 0.8035,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.53,
186
+ "learning_rate": 3.677341986455982e-05,
187
+ "loss": 0.7965,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.55,
192
+ "learning_rate": 3.633253386004515e-05,
193
+ "loss": 0.8022,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.56,
198
+ "learning_rate": 3.589164785553047e-05,
199
+ "loss": 0.7959,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.58,
204
+ "learning_rate": 3.54507618510158e-05,
205
+ "loss": 0.8167,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.6,
210
+ "learning_rate": 3.500987584650113e-05,
211
+ "loss": 0.8003,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.62,
216
+ "learning_rate": 3.456898984198646e-05,
217
+ "loss": 0.8143,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.63,
222
+ "learning_rate": 3.4128103837471786e-05,
223
+ "loss": 0.797,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.65,
228
+ "learning_rate": 3.3687217832957114e-05,
229
+ "loss": 0.7655,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.67,
234
+ "learning_rate": 3.324633182844244e-05,
235
+ "loss": 0.7821,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.69,
240
+ "learning_rate": 3.2805445823927765e-05,
241
+ "loss": 0.7721,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.71,
246
+ "learning_rate": 3.236455981941309e-05,
247
+ "loss": 0.835,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.72,
252
+ "learning_rate": 3.192367381489842e-05,
253
+ "loss": 0.7945,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.74,
258
+ "learning_rate": 3.148278781038374e-05,
259
+ "loss": 0.8042,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.76,
264
+ "learning_rate": 3.104190180586908e-05,
265
+ "loss": 0.7661,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.78,
270
+ "learning_rate": 3.060101580135441e-05,
271
+ "loss": 0.7981,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.79,
276
+ "learning_rate": 3.0160129796839732e-05,
277
+ "loss": 0.7588,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.81,
282
+ "learning_rate": 2.9719243792325057e-05,
283
+ "loss": 0.837,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.83,
288
+ "learning_rate": 2.9278357787810385e-05,
289
+ "loss": 0.7686,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.85,
294
+ "learning_rate": 2.883747178329571e-05,
295
+ "loss": 0.7711,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.86,
300
+ "learning_rate": 2.839658577878104e-05,
301
+ "loss": 0.7785,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.88,
306
+ "learning_rate": 2.795569977426637e-05,
307
+ "loss": 0.7949,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.9,
312
+ "learning_rate": 2.7514813769751696e-05,
313
+ "loss": 0.7737,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.92,
318
+ "learning_rate": 2.7073927765237024e-05,
319
+ "loss": 0.7719,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.93,
324
+ "learning_rate": 2.663304176072235e-05,
325
+ "loss": 0.7666,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.95,
330
+ "learning_rate": 2.6192155756207674e-05,
331
+ "loss": 0.7678,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.97,
336
+ "learning_rate": 2.5751269751693003e-05,
337
+ "loss": 0.8034,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.99,
342
+ "learning_rate": 2.5310383747178328e-05,
343
+ "loss": 0.748,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 1.0,
348
+ "eval_accuracy": 0.6928090453147888,
349
+ "eval_loss": 0.7356609106063843,
350
+ "eval_runtime": 352.934,
351
+ "eval_samples_per_second": 66.945,
352
+ "eval_steps_per_second": 11.158,
353
+ "step": 28352
354
+ },
355
+ {
356
+ "epoch": 1.01,
357
+ "learning_rate": 2.486949774266366e-05,
358
+ "loss": 0.7526,
359
+ "step": 28500
360
+ },
361
+ {
362
+ "epoch": 1.02,
363
+ "learning_rate": 2.4428611738148985e-05,
364
+ "loss": 0.6793,
365
+ "step": 29000
366
+ },
367
+ {
368
+ "epoch": 1.04,
369
+ "learning_rate": 2.398772573363431e-05,
370
+ "loss": 0.7199,
371
+ "step": 29500
372
+ },
373
+ {
374
+ "epoch": 1.06,
375
+ "learning_rate": 2.3546839729119642e-05,
376
+ "loss": 0.6832,
377
+ "step": 30000
378
+ },
379
+ {
380
+ "epoch": 1.08,
381
+ "learning_rate": 2.3105953724604967e-05,
382
+ "loss": 0.6787,
383
+ "step": 30500
384
+ },
385
+ {
386
+ "epoch": 1.09,
387
+ "learning_rate": 2.2665067720090295e-05,
388
+ "loss": 0.6795,
389
+ "step": 31000
390
+ },
391
+ {
392
+ "epoch": 1.11,
393
+ "learning_rate": 2.222418171557562e-05,
394
+ "loss": 0.6592,
395
+ "step": 31500
396
+ },
397
+ {
398
+ "epoch": 1.13,
399
+ "learning_rate": 2.178329571106095e-05,
400
+ "loss": 0.6692,
401
+ "step": 32000
402
+ },
403
+ {
404
+ "epoch": 1.15,
405
+ "learning_rate": 2.1342409706546277e-05,
406
+ "loss": 0.6884,
407
+ "step": 32500
408
+ },
409
+ {
410
+ "epoch": 1.16,
411
+ "learning_rate": 2.0901523702031602e-05,
412
+ "loss": 0.6915,
413
+ "step": 33000
414
+ },
415
+ {
416
+ "epoch": 1.18,
417
+ "learning_rate": 2.046063769751693e-05,
418
+ "loss": 0.659,
419
+ "step": 33500
420
+ },
421
+ {
422
+ "epoch": 1.2,
423
+ "learning_rate": 2.001975169300226e-05,
424
+ "loss": 0.6741,
425
+ "step": 34000
426
+ },
427
+ {
428
+ "epoch": 1.22,
429
+ "learning_rate": 1.9578865688487584e-05,
430
+ "loss": 0.6489,
431
+ "step": 34500
432
+ },
433
+ {
434
+ "epoch": 1.23,
435
+ "learning_rate": 1.9137979683972913e-05,
436
+ "loss": 0.6568,
437
+ "step": 35000
438
+ },
439
+ {
440
+ "epoch": 1.25,
441
+ "learning_rate": 1.869709367945824e-05,
442
+ "loss": 0.6982,
443
+ "step": 35500
444
+ },
445
+ {
446
+ "epoch": 1.27,
447
+ "learning_rate": 1.8256207674943566e-05,
448
+ "loss": 0.6673,
449
+ "step": 36000
450
+ },
451
+ {
452
+ "epoch": 1.29,
453
+ "learning_rate": 1.7815321670428895e-05,
454
+ "loss": 0.675,
455
+ "step": 36500
456
+ },
457
+ {
458
+ "epoch": 1.31,
459
+ "learning_rate": 1.737443566591422e-05,
460
+ "loss": 0.6711,
461
+ "step": 37000
462
+ },
463
+ {
464
+ "epoch": 1.32,
465
+ "learning_rate": 1.693354966139955e-05,
466
+ "loss": 0.6643,
467
+ "step": 37500
468
+ },
469
+ {
470
+ "epoch": 1.34,
471
+ "learning_rate": 1.6492663656884877e-05,
472
+ "loss": 0.6788,
473
+ "step": 38000
474
+ },
475
+ {
476
+ "epoch": 1.36,
477
+ "learning_rate": 1.6051777652370205e-05,
478
+ "loss": 0.6976,
479
+ "step": 38500
480
+ },
481
+ {
482
+ "epoch": 1.38,
483
+ "learning_rate": 1.561089164785553e-05,
484
+ "loss": 0.6543,
485
+ "step": 39000
486
+ },
487
+ {
488
+ "epoch": 1.39,
489
+ "learning_rate": 1.5170005643340859e-05,
490
+ "loss": 0.6651,
491
+ "step": 39500
492
+ },
493
+ {
494
+ "epoch": 1.41,
495
+ "learning_rate": 1.4729119638826185e-05,
496
+ "loss": 0.6512,
497
+ "step": 40000
498
+ },
499
+ {
500
+ "epoch": 1.43,
501
+ "learning_rate": 1.4288233634311512e-05,
502
+ "loss": 0.6417,
503
+ "step": 40500
504
+ },
505
+ {
506
+ "epoch": 1.45,
507
+ "learning_rate": 1.3847347629796839e-05,
508
+ "loss": 0.662,
509
+ "step": 41000
510
+ },
511
+ {
512
+ "epoch": 1.46,
513
+ "learning_rate": 1.3406461625282169e-05,
514
+ "loss": 0.6715,
515
+ "step": 41500
516
+ },
517
+ {
518
+ "epoch": 1.48,
519
+ "learning_rate": 1.2965575620767496e-05,
520
+ "loss": 0.6519,
521
+ "step": 42000
522
+ },
523
+ {
524
+ "epoch": 1.5,
525
+ "learning_rate": 1.2524689616252821e-05,
526
+ "loss": 0.627,
527
+ "step": 42500
528
+ },
529
+ {
530
+ "epoch": 1.52,
531
+ "learning_rate": 1.208380361173815e-05,
532
+ "loss": 0.6357,
533
+ "step": 43000
534
+ },
535
+ {
536
+ "epoch": 1.53,
537
+ "learning_rate": 1.1642917607223478e-05,
538
+ "loss": 0.6612,
539
+ "step": 43500
540
+ },
541
+ {
542
+ "epoch": 1.55,
543
+ "learning_rate": 1.1202031602708805e-05,
544
+ "loss": 0.688,
545
+ "step": 44000
546
+ },
547
+ {
548
+ "epoch": 1.57,
549
+ "learning_rate": 1.0761145598194131e-05,
550
+ "loss": 0.6556,
551
+ "step": 44500
552
+ },
553
+ {
554
+ "epoch": 1.59,
555
+ "learning_rate": 1.0320259593679458e-05,
556
+ "loss": 0.6514,
557
+ "step": 45000
558
+ },
559
+ {
560
+ "epoch": 1.6,
561
+ "learning_rate": 9.879373589164786e-06,
562
+ "loss": 0.6476,
563
+ "step": 45500
564
+ },
565
+ {
566
+ "epoch": 1.62,
567
+ "learning_rate": 9.438487584650113e-06,
568
+ "loss": 0.6519,
569
+ "step": 46000
570
+ },
571
+ {
572
+ "epoch": 1.64,
573
+ "learning_rate": 8.997601580135442e-06,
574
+ "loss": 0.612,
575
+ "step": 46500
576
+ },
577
+ {
578
+ "epoch": 1.66,
579
+ "learning_rate": 8.556715575620767e-06,
580
+ "loss": 0.6314,
581
+ "step": 47000
582
+ },
583
+ {
584
+ "epoch": 1.68,
585
+ "learning_rate": 8.115829571106095e-06,
586
+ "loss": 0.6279,
587
+ "step": 47500
588
+ },
589
+ {
590
+ "epoch": 1.69,
591
+ "learning_rate": 7.674943566591422e-06,
592
+ "loss": 0.6498,
593
+ "step": 48000
594
+ },
595
+ {
596
+ "epoch": 1.71,
597
+ "learning_rate": 7.23405756207675e-06,
598
+ "loss": 0.6608,
599
+ "step": 48500
600
+ },
601
+ {
602
+ "epoch": 1.73,
603
+ "learning_rate": 6.793171557562076e-06,
604
+ "loss": 0.645,
605
+ "step": 49000
606
+ },
607
+ {
608
+ "epoch": 1.75,
609
+ "learning_rate": 6.352285553047405e-06,
610
+ "loss": 0.6612,
611
+ "step": 49500
612
+ },
613
+ {
614
+ "epoch": 1.76,
615
+ "learning_rate": 5.9113995485327315e-06,
616
+ "loss": 0.6263,
617
+ "step": 50000
618
+ },
619
+ {
620
+ "epoch": 1.78,
621
+ "learning_rate": 5.470513544018059e-06,
622
+ "loss": 0.6374,
623
+ "step": 50500
624
+ },
625
+ {
626
+ "epoch": 1.8,
627
+ "learning_rate": 5.029627539503387e-06,
628
+ "loss": 0.6385,
629
+ "step": 51000
630
+ },
631
+ {
632
+ "epoch": 1.82,
633
+ "learning_rate": 4.5887415349887135e-06,
634
+ "loss": 0.6362,
635
+ "step": 51500
636
+ },
637
+ {
638
+ "epoch": 1.83,
639
+ "learning_rate": 4.147855530474041e-06,
640
+ "loss": 0.6342,
641
+ "step": 52000
642
+ },
643
+ {
644
+ "epoch": 1.85,
645
+ "learning_rate": 3.7069695259593683e-06,
646
+ "loss": 0.6714,
647
+ "step": 52500
648
+ },
649
+ {
650
+ "epoch": 1.87,
651
+ "learning_rate": 3.2660835214446955e-06,
652
+ "loss": 0.6355,
653
+ "step": 53000
654
+ },
655
+ {
656
+ "epoch": 1.89,
657
+ "learning_rate": 2.8251975169300226e-06,
658
+ "loss": 0.6151,
659
+ "step": 53500
660
+ },
661
+ {
662
+ "epoch": 1.9,
663
+ "learning_rate": 2.38431151241535e-06,
664
+ "loss": 0.6461,
665
+ "step": 54000
666
+ },
667
+ {
668
+ "epoch": 1.92,
669
+ "learning_rate": 1.943425507900677e-06,
670
+ "loss": 0.6533,
671
+ "step": 54500
672
+ },
673
+ {
674
+ "epoch": 1.94,
675
+ "learning_rate": 1.5025395033860046e-06,
676
+ "loss": 0.6376,
677
+ "step": 55000
678
+ },
679
+ {
680
+ "epoch": 1.96,
681
+ "learning_rate": 1.0616534988713318e-06,
682
+ "loss": 0.5976,
683
+ "step": 55500
684
+ },
685
+ {
686
+ "epoch": 1.98,
687
+ "learning_rate": 6.207674943566591e-07,
688
+ "loss": 0.6318,
689
+ "step": 56000
690
+ },
691
+ {
692
+ "epoch": 1.99,
693
+ "learning_rate": 1.7988148984198645e-07,
694
+ "loss": 0.6471,
695
+ "step": 56500
696
+ }
697
+ ],
698
+ "max_steps": 56704,
699
+ "num_train_epochs": 2,
700
+ "total_flos": 7.589219989624102e+16,
701
+ "trial_name": null,
702
+ "trial_params": null
703
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9beef423c1581085ae665e4850f49fe37218015107c4e08a199d5abee2074475
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff