Ubuntu commited on
Commit
4ddac69
1 Parent(s): f01532f

Upload finetuned model weight

Browse files
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8858828315703824,
4
+ "eval_loss": 0.4064849317073822,
5
+ "eval_runtime": 32.1089,
6
+ "eval_samples": 9832,
7
+ "eval_samples_per_second": 306.208,
8
+ "train_runtime": 17429.7891,
9
+ "train_samples": 392702,
10
+ "train_samples_per_second": 2.112
11
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/electra-base-discriminator",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "embedding_size": 768,
8
+ "finetuning_task": "mnli",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "electra",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "summary_activation": "gelu",
32
+ "summary_last_dropout": 0.1,
33
+ "summary_type": "first",
34
+ "summary_use_proj": true,
35
+ "transformers_version": "4.6.0.dev0",
36
+ "type_vocab_size": 2,
37
+ "vocab_size": 30522
38
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8858828315703824,
4
+ "eval_loss": 0.4064849317073822,
5
+ "eval_runtime": 32.1089,
6
+ "eval_samples": 9832,
7
+ "eval_samples_per_second": 306.208
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf9b4efdd68d267965785f10c40b1d2b3f2ea845adf2fd37b9a868eaae67b31
3
+ size 438026775
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
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": "google/electra-base-discriminator"}
train_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_runtime": 17429.7891,
4
+ "train_samples": 392702,
5
+ "train_samples_per_second": 2.112
6
+ }
trainer_state.json ADDED
@@ -0,0 +1,461 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 36816,
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": 1.9728378965667103e-05,
13
+ "loss": 0.6455,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 1.9456757931334205e-05,
19
+ "loss": 0.4837,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.12,
24
+ "learning_rate": 1.9185136897001307e-05,
25
+ "loss": 0.4492,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.16,
30
+ "learning_rate": 1.8913515862668405e-05,
31
+ "loss": 0.439,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.2,
36
+ "learning_rate": 1.8641894828335507e-05,
37
+ "loss": 0.4239,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.24,
42
+ "learning_rate": 1.837027379400261e-05,
43
+ "loss": 0.416,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.29,
48
+ "learning_rate": 1.809865275966971e-05,
49
+ "loss": 0.3981,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.33,
54
+ "learning_rate": 1.7827031725336812e-05,
55
+ "loss": 0.4026,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.37,
60
+ "learning_rate": 1.7555410691003914e-05,
61
+ "loss": 0.3964,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.41,
66
+ "learning_rate": 1.7283789656671015e-05,
67
+ "loss": 0.3838,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.45,
72
+ "learning_rate": 1.7012168622338114e-05,
73
+ "loss": 0.3825,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.49,
78
+ "learning_rate": 1.6740547588005215e-05,
79
+ "loss": 0.3679,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.53,
84
+ "learning_rate": 1.6468926553672317e-05,
85
+ "loss": 0.3763,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.57,
90
+ "learning_rate": 1.619730551933942e-05,
91
+ "loss": 0.3633,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.61,
96
+ "learning_rate": 1.592568448500652e-05,
97
+ "loss": 0.371,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.65,
102
+ "learning_rate": 1.5654063450673622e-05,
103
+ "loss": 0.3543,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.69,
108
+ "learning_rate": 1.5382442416340724e-05,
109
+ "loss": 0.3674,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.73,
114
+ "learning_rate": 1.5110821382007822e-05,
115
+ "loss": 0.3498,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.77,
120
+ "learning_rate": 1.4839200347674924e-05,
121
+ "loss": 0.3671,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.81,
126
+ "learning_rate": 1.4567579313342026e-05,
127
+ "loss": 0.3512,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.86,
132
+ "learning_rate": 1.4295958279009128e-05,
133
+ "loss": 0.3608,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.9,
138
+ "learning_rate": 1.402433724467623e-05,
139
+ "loss": 0.3437,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.94,
144
+ "learning_rate": 1.3752716210343331e-05,
145
+ "loss": 0.3508,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.98,
150
+ "learning_rate": 1.3481095176010431e-05,
151
+ "loss": 0.3545,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 1.02,
156
+ "learning_rate": 1.3209474141677531e-05,
157
+ "loss": 0.3019,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 1.06,
162
+ "learning_rate": 1.2937853107344633e-05,
163
+ "loss": 0.2473,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 1.1,
168
+ "learning_rate": 1.2666232073011735e-05,
169
+ "loss": 0.2456,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 1.14,
174
+ "learning_rate": 1.2394611038678836e-05,
175
+ "loss": 0.2516,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.18,
180
+ "learning_rate": 1.2122990004345938e-05,
181
+ "loss": 0.264,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.22,
186
+ "learning_rate": 1.185136897001304e-05,
187
+ "loss": 0.2409,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 1.26,
192
+ "learning_rate": 1.157974793568014e-05,
193
+ "loss": 0.2531,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 1.3,
198
+ "learning_rate": 1.130812690134724e-05,
199
+ "loss": 0.2621,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.34,
204
+ "learning_rate": 1.1036505867014341e-05,
205
+ "loss": 0.2491,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.39,
210
+ "learning_rate": 1.0764884832681443e-05,
211
+ "loss": 0.246,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.43,
216
+ "learning_rate": 1.0493263798348545e-05,
217
+ "loss": 0.2505,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.47,
222
+ "learning_rate": 1.0221642764015647e-05,
223
+ "loss": 0.2432,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.51,
228
+ "learning_rate": 9.950021729682747e-06,
229
+ "loss": 0.2526,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.55,
234
+ "learning_rate": 9.678400695349848e-06,
235
+ "loss": 0.2537,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.59,
240
+ "learning_rate": 9.40677966101695e-06,
241
+ "loss": 0.257,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.63,
246
+ "learning_rate": 9.13515862668405e-06,
247
+ "loss": 0.2569,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.67,
252
+ "learning_rate": 8.863537592351152e-06,
253
+ "loss": 0.2455,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 1.71,
258
+ "learning_rate": 8.591916558018254e-06,
259
+ "loss": 0.2456,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 1.75,
264
+ "learning_rate": 8.320295523685355e-06,
265
+ "loss": 0.2512,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 1.79,
270
+ "learning_rate": 8.048674489352455e-06,
271
+ "loss": 0.2518,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 1.83,
276
+ "learning_rate": 7.777053455019557e-06,
277
+ "loss": 0.2552,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.87,
282
+ "learning_rate": 7.505432420686659e-06,
283
+ "loss": 0.2543,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.91,
288
+ "learning_rate": 7.23381138635376e-06,
289
+ "loss": 0.2554,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 1.96,
294
+ "learning_rate": 6.962190352020861e-06,
295
+ "loss": 0.2454,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 2.0,
300
+ "learning_rate": 6.690569317687963e-06,
301
+ "loss": 0.2346,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 2.04,
306
+ "learning_rate": 6.418948283355063e-06,
307
+ "loss": 0.1721,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 2.08,
312
+ "learning_rate": 6.147327249022165e-06,
313
+ "loss": 0.1701,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 2.12,
318
+ "learning_rate": 5.8757062146892665e-06,
319
+ "loss": 0.1659,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 2.16,
324
+ "learning_rate": 5.6040851803563665e-06,
325
+ "loss": 0.1688,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 2.2,
330
+ "learning_rate": 5.332464146023468e-06,
331
+ "loss": 0.1646,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 2.24,
336
+ "learning_rate": 5.06084311169057e-06,
337
+ "loss": 0.1745,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 2.28,
342
+ "learning_rate": 4.789222077357671e-06,
343
+ "loss": 0.1629,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 2.32,
348
+ "learning_rate": 4.5176010430247726e-06,
349
+ "loss": 0.1725,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 2.36,
354
+ "learning_rate": 4.2459800086918734e-06,
355
+ "loss": 0.1685,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 2.4,
360
+ "learning_rate": 3.974358974358974e-06,
361
+ "loss": 0.1749,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 2.44,
366
+ "learning_rate": 3.702737940026076e-06,
367
+ "loss": 0.1682,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 2.49,
372
+ "learning_rate": 3.431116905693177e-06,
373
+ "loss": 0.166,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 2.53,
378
+ "learning_rate": 3.1594958713602786e-06,
379
+ "loss": 0.173,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 2.57,
384
+ "learning_rate": 2.8878748370273795e-06,
385
+ "loss": 0.1622,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 2.61,
390
+ "learning_rate": 2.6162538026944812e-06,
391
+ "loss": 0.166,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 2.65,
396
+ "learning_rate": 2.344632768361582e-06,
397
+ "loss": 0.1737,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 2.69,
402
+ "learning_rate": 2.0730117340286834e-06,
403
+ "loss": 0.1651,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 2.73,
408
+ "learning_rate": 1.8013906996957845e-06,
409
+ "loss": 0.1691,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 2.77,
414
+ "learning_rate": 1.5297696653628858e-06,
415
+ "loss": 0.1666,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 2.81,
420
+ "learning_rate": 1.258148631029987e-06,
421
+ "loss": 0.1718,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 2.85,
426
+ "learning_rate": 9.865275966970884e-07,
427
+ "loss": 0.1645,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 2.89,
432
+ "learning_rate": 7.149065623641896e-07,
433
+ "loss": 0.1693,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 2.93,
438
+ "learning_rate": 4.432855280312908e-07,
439
+ "loss": 0.1753,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 2.97,
444
+ "learning_rate": 1.7166449369839202e-07,
445
+ "loss": 0.1637,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 3.0,
450
+ "step": 36816,
451
+ "total_flos": 9.906002052709018e+16,
452
+ "train_runtime": 17429.7891,
453
+ "train_samples_per_second": 2.112
454
+ }
455
+ ],
456
+ "max_steps": 36816,
457
+ "num_train_epochs": 3,
458
+ "total_flos": 9.906002052709018e+16,
459
+ "trial_name": null,
460
+ "trial_params": null
461
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fbc33f02f60c8717a558a5d81c5842035f1736d327944beccb6b3bc919fd41a
3
+ size 2415
vocab.txt ADDED
The diff for this file is too large to render. See raw diff