Dai Dai commited on
Commit
be3f3a4
1 Parent(s): 828f5bf

upload files

Browse files
Files changed (7) hide show
  1. README.md +1 -3
  2. config.json +23 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. trainer_state.json +446 -0
  6. training_args.bin +3 -0
  7. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1 @@
1
- ---
2
- license: cc-by-4.0
3
- ---
 
1
+ cp /home/gdpr/Desktop/Experiments/2021-06/19-01-roberta-lm-mimic/mimic128-4gpu/checkpoint-36000/* ./
 
 
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
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-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "type_vocab_size": 1,
22
+ "vocab_size": 50265
23
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a019a009316fbacb661a83355e54e730202129f54e88fd2f01e962c3e36f12f
3
+ size 498880850
trainer_state.json ADDED
@@ -0,0 +1,446 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_metric_at_epoch": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 14.598540145985401,
6
+ "global_step": 36000,
7
+ "latest_metric": null,
8
+ "log_history": [
9
+ {
10
+ "epoch": 0.2,
11
+ "learning_rate": 4.9324141659908085e-05,
12
+ "loss": 1.7428,
13
+ "step": 500
14
+ },
15
+ {
16
+ "epoch": 0.41,
17
+ "learning_rate": 4.864828331981617e-05,
18
+ "loss": 1.2225,
19
+ "step": 1000
20
+ },
21
+ {
22
+ "epoch": 0.61,
23
+ "learning_rate": 4.797242497972425e-05,
24
+ "loss": 1.0975,
25
+ "step": 1500
26
+ },
27
+ {
28
+ "epoch": 0.81,
29
+ "learning_rate": 4.729656663963233e-05,
30
+ "loss": 1.0237,
31
+ "step": 2000
32
+ },
33
+ {
34
+ "epoch": 1.01,
35
+ "learning_rate": 4.6620708299540416e-05,
36
+ "loss": 0.9755,
37
+ "step": 2500
38
+ },
39
+ {
40
+ "epoch": 1.22,
41
+ "learning_rate": 4.59448499594485e-05,
42
+ "loss": 0.9379,
43
+ "step": 3000
44
+ },
45
+ {
46
+ "epoch": 1.42,
47
+ "learning_rate": 4.526899161935659e-05,
48
+ "loss": 0.9069,
49
+ "step": 3500
50
+ },
51
+ {
52
+ "epoch": 1.62,
53
+ "learning_rate": 4.459313327926467e-05,
54
+ "loss": 0.882,
55
+ "step": 4000
56
+ },
57
+ {
58
+ "epoch": 1.82,
59
+ "learning_rate": 4.3917274939172754e-05,
60
+ "loss": 0.8649,
61
+ "step": 4500
62
+ },
63
+ {
64
+ "epoch": 2.03,
65
+ "learning_rate": 4.3241416599080836e-05,
66
+ "loss": 0.8487,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.23,
71
+ "learning_rate": 4.256555825898892e-05,
72
+ "loss": 0.8321,
73
+ "step": 5500
74
+ },
75
+ {
76
+ "epoch": 2.43,
77
+ "learning_rate": 4.1889699918897e-05,
78
+ "loss": 0.818,
79
+ "step": 6000
80
+ },
81
+ {
82
+ "epoch": 2.64,
83
+ "learning_rate": 4.1213841578805084e-05,
84
+ "loss": 0.8052,
85
+ "step": 6500
86
+ },
87
+ {
88
+ "epoch": 2.84,
89
+ "learning_rate": 4.053798323871317e-05,
90
+ "loss": 0.7936,
91
+ "step": 7000
92
+ },
93
+ {
94
+ "epoch": 3.04,
95
+ "learning_rate": 3.986212489862125e-05,
96
+ "loss": 0.7868,
97
+ "step": 7500
98
+ },
99
+ {
100
+ "epoch": 3.24,
101
+ "learning_rate": 3.918626655852933e-05,
102
+ "loss": 0.7777,
103
+ "step": 8000
104
+ },
105
+ {
106
+ "epoch": 3.45,
107
+ "learning_rate": 3.8510408218437415e-05,
108
+ "loss": 0.7685,
109
+ "step": 8500
110
+ },
111
+ {
112
+ "epoch": 3.65,
113
+ "learning_rate": 3.78345498783455e-05,
114
+ "loss": 0.7632,
115
+ "step": 9000
116
+ },
117
+ {
118
+ "epoch": 3.85,
119
+ "learning_rate": 3.715869153825358e-05,
120
+ "loss": 0.754,
121
+ "step": 9500
122
+ },
123
+ {
124
+ "epoch": 4.06,
125
+ "learning_rate": 3.648283319816166e-05,
126
+ "loss": 0.7486,
127
+ "step": 10000
128
+ },
129
+ {
130
+ "epoch": 4.26,
131
+ "learning_rate": 3.580697485806975e-05,
132
+ "loss": 0.742,
133
+ "step": 10500
134
+ },
135
+ {
136
+ "epoch": 4.46,
137
+ "learning_rate": 3.5131116517977835e-05,
138
+ "loss": 0.7353,
139
+ "step": 11000
140
+ },
141
+ {
142
+ "epoch": 4.66,
143
+ "learning_rate": 3.445525817788592e-05,
144
+ "loss": 0.7304,
145
+ "step": 11500
146
+ },
147
+ {
148
+ "epoch": 4.87,
149
+ "learning_rate": 3.3779399837794e-05,
150
+ "loss": 0.7271,
151
+ "step": 12000
152
+ },
153
+ {
154
+ "epoch": 5.07,
155
+ "learning_rate": 3.3103541497702084e-05,
156
+ "loss": 0.7213,
157
+ "step": 12500
158
+ },
159
+ {
160
+ "epoch": 5.27,
161
+ "learning_rate": 3.2427683157610166e-05,
162
+ "loss": 0.7156,
163
+ "step": 13000
164
+ },
165
+ {
166
+ "epoch": 5.47,
167
+ "learning_rate": 3.175182481751825e-05,
168
+ "loss": 0.7111,
169
+ "step": 13500
170
+ },
171
+ {
172
+ "epoch": 5.68,
173
+ "learning_rate": 3.107596647742633e-05,
174
+ "loss": 0.7087,
175
+ "step": 14000
176
+ },
177
+ {
178
+ "epoch": 5.88,
179
+ "learning_rate": 3.0400108137334414e-05,
180
+ "loss": 0.7067,
181
+ "step": 14500
182
+ },
183
+ {
184
+ "epoch": 6.08,
185
+ "learning_rate": 2.9724249797242497e-05,
186
+ "loss": 0.7015,
187
+ "step": 15000
188
+ },
189
+ {
190
+ "epoch": 6.29,
191
+ "learning_rate": 2.904839145715058e-05,
192
+ "loss": 0.6951,
193
+ "step": 15500
194
+ },
195
+ {
196
+ "epoch": 6.49,
197
+ "learning_rate": 2.8372533117058663e-05,
198
+ "loss": 0.6922,
199
+ "step": 16000
200
+ },
201
+ {
202
+ "epoch": 6.69,
203
+ "learning_rate": 2.7696674776966745e-05,
204
+ "loss": 0.6917,
205
+ "step": 16500
206
+ },
207
+ {
208
+ "epoch": 6.89,
209
+ "learning_rate": 2.7020816436874835e-05,
210
+ "loss": 0.6869,
211
+ "step": 17000
212
+ },
213
+ {
214
+ "epoch": 7.1,
215
+ "learning_rate": 2.6344958096782917e-05,
216
+ "loss": 0.6834,
217
+ "step": 17500
218
+ },
219
+ {
220
+ "epoch": 7.3,
221
+ "learning_rate": 2.5669099756691e-05,
222
+ "loss": 0.6819,
223
+ "step": 18000
224
+ },
225
+ {
226
+ "epoch": 7.5,
227
+ "learning_rate": 2.499324141659908e-05,
228
+ "loss": 0.6801,
229
+ "step": 18500
230
+ },
231
+ {
232
+ "epoch": 7.7,
233
+ "learning_rate": 2.4317383076507166e-05,
234
+ "loss": 0.6755,
235
+ "step": 19000
236
+ },
237
+ {
238
+ "epoch": 7.91,
239
+ "learning_rate": 2.3641524736415248e-05,
240
+ "loss": 0.6734,
241
+ "step": 19500
242
+ },
243
+ {
244
+ "epoch": 8.11,
245
+ "learning_rate": 2.296566639632333e-05,
246
+ "loss": 0.6706,
247
+ "step": 20000
248
+ },
249
+ {
250
+ "epoch": 8.31,
251
+ "learning_rate": 2.2289808056231414e-05,
252
+ "loss": 0.6688,
253
+ "step": 20500
254
+ },
255
+ {
256
+ "epoch": 8.52,
257
+ "learning_rate": 2.1613949716139496e-05,
258
+ "loss": 0.6662,
259
+ "step": 21000
260
+ },
261
+ {
262
+ "epoch": 8.72,
263
+ "learning_rate": 2.093809137604758e-05,
264
+ "loss": 0.6636,
265
+ "step": 21500
266
+ },
267
+ {
268
+ "epoch": 8.92,
269
+ "learning_rate": 2.0262233035955662e-05,
270
+ "loss": 0.6622,
271
+ "step": 22000
272
+ },
273
+ {
274
+ "epoch": 9.12,
275
+ "learning_rate": 1.9586374695863748e-05,
276
+ "loss": 0.6593,
277
+ "step": 22500
278
+ },
279
+ {
280
+ "epoch": 9.33,
281
+ "learning_rate": 1.891051635577183e-05,
282
+ "loss": 0.6568,
283
+ "step": 23000
284
+ },
285
+ {
286
+ "epoch": 9.53,
287
+ "learning_rate": 1.8234658015679913e-05,
288
+ "loss": 0.6563,
289
+ "step": 23500
290
+ },
291
+ {
292
+ "epoch": 9.73,
293
+ "learning_rate": 1.7558799675587996e-05,
294
+ "loss": 0.6542,
295
+ "step": 24000
296
+ },
297
+ {
298
+ "epoch": 9.94,
299
+ "learning_rate": 1.688294133549608e-05,
300
+ "loss": 0.6535,
301
+ "step": 24500
302
+ },
303
+ {
304
+ "epoch": 10.14,
305
+ "learning_rate": 1.620708299540416e-05,
306
+ "loss": 0.6486,
307
+ "step": 25000
308
+ },
309
+ {
310
+ "epoch": 10.34,
311
+ "learning_rate": 1.5531224655312247e-05,
312
+ "loss": 0.6485,
313
+ "step": 25500
314
+ },
315
+ {
316
+ "epoch": 10.54,
317
+ "learning_rate": 1.4855366315220332e-05,
318
+ "loss": 0.6474,
319
+ "step": 26000
320
+ },
321
+ {
322
+ "epoch": 10.75,
323
+ "learning_rate": 1.4179507975128415e-05,
324
+ "loss": 0.647,
325
+ "step": 26500
326
+ },
327
+ {
328
+ "epoch": 10.95,
329
+ "learning_rate": 1.3503649635036497e-05,
330
+ "loss": 0.6451,
331
+ "step": 27000
332
+ },
333
+ {
334
+ "epoch": 11.15,
335
+ "learning_rate": 1.282779129494458e-05,
336
+ "loss": 0.6426,
337
+ "step": 27500
338
+ },
339
+ {
340
+ "epoch": 11.35,
341
+ "learning_rate": 1.2151932954852663e-05,
342
+ "loss": 0.6431,
343
+ "step": 28000
344
+ },
345
+ {
346
+ "epoch": 11.56,
347
+ "learning_rate": 1.1476074614760747e-05,
348
+ "loss": 0.641,
349
+ "step": 28500
350
+ },
351
+ {
352
+ "epoch": 11.76,
353
+ "learning_rate": 1.080021627466883e-05,
354
+ "loss": 0.6414,
355
+ "step": 29000
356
+ },
357
+ {
358
+ "epoch": 11.96,
359
+ "learning_rate": 1.0124357934576913e-05,
360
+ "loss": 0.6382,
361
+ "step": 29500
362
+ },
363
+ {
364
+ "epoch": 12.17,
365
+ "learning_rate": 9.448499594484997e-06,
366
+ "loss": 0.635,
367
+ "step": 30000
368
+ },
369
+ {
370
+ "epoch": 12.37,
371
+ "learning_rate": 8.77264125439308e-06,
372
+ "loss": 0.6357,
373
+ "step": 30500
374
+ },
375
+ {
376
+ "epoch": 12.57,
377
+ "learning_rate": 8.096782914301162e-06,
378
+ "loss": 0.634,
379
+ "step": 31000
380
+ },
381
+ {
382
+ "epoch": 12.77,
383
+ "learning_rate": 7.420924574209247e-06,
384
+ "loss": 0.6338,
385
+ "step": 31500
386
+ },
387
+ {
388
+ "epoch": 12.98,
389
+ "learning_rate": 6.7450662341173294e-06,
390
+ "loss": 0.633,
391
+ "step": 32000
392
+ },
393
+ {
394
+ "epoch": 13.18,
395
+ "learning_rate": 6.069207894025412e-06,
396
+ "loss": 0.6301,
397
+ "step": 32500
398
+ },
399
+ {
400
+ "epoch": 13.38,
401
+ "learning_rate": 5.393349553933496e-06,
402
+ "loss": 0.6313,
403
+ "step": 33000
404
+ },
405
+ {
406
+ "epoch": 13.58,
407
+ "learning_rate": 4.717491213841578e-06,
408
+ "loss": 0.6294,
409
+ "step": 33500
410
+ },
411
+ {
412
+ "epoch": 13.79,
413
+ "learning_rate": 4.041632873749662e-06,
414
+ "loss": 0.6311,
415
+ "step": 34000
416
+ },
417
+ {
418
+ "epoch": 13.99,
419
+ "learning_rate": 3.365774533657746e-06,
420
+ "loss": 0.631,
421
+ "step": 34500
422
+ },
423
+ {
424
+ "epoch": 14.19,
425
+ "learning_rate": 2.6899161935658286e-06,
426
+ "loss": 0.6274,
427
+ "step": 35000
428
+ },
429
+ {
430
+ "epoch": 14.4,
431
+ "learning_rate": 2.014057853473912e-06,
432
+ "loss": 0.6274,
433
+ "step": 35500
434
+ },
435
+ {
436
+ "epoch": 14.6,
437
+ "learning_rate": 1.3381995133819951e-06,
438
+ "loss": 0.6273,
439
+ "step": 36000
440
+ }
441
+ ],
442
+ "max_steps": 36990,
443
+ "num_train_epochs": 15,
444
+ "start_time": 1624121724.3048394,
445
+ "total_flos": 0
446
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7bb9abd5b424962b89c0b7b12d6796f4ae4470ad68977139c0bc46c00398af
3
+ size 1391
vocab.json ADDED
The diff for this file is too large to render. See raw diff