DunnBC22 commited on
Commit
3107e20
1 Parent(s): 9e4aca3

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +7 -0
  2. train_results.json +7 -0
  3. trainer_state.json +547 -0
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.94,
3
+ "train_loss": 0.35526800215724974,
4
+ "train_runtime": 45263.0947,
5
+ "train_samples_per_second": 1.414,
6
+ "train_steps_per_second": 0.011
7
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.94,
3
+ "train_loss": 0.35526800215724974,
4
+ "train_runtime": 45263.0947,
5
+ "train_samples_per_second": 1.414,
6
+ "train_steps_per_second": 0.011
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,547 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.936,
5
+ "global_step": 496,
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": 1.0000000000000002e-06,
13
+ "loss": 2.1204,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.13,
18
+ "learning_rate": 8.000000000000001e-06,
19
+ "loss": 2.1463,
20
+ "step": 8
21
+ },
22
+ {
23
+ "epoch": 0.26,
24
+ "learning_rate": 1.6000000000000003e-05,
25
+ "loss": 1.8788,
26
+ "step": 16
27
+ },
28
+ {
29
+ "epoch": 0.38,
30
+ "learning_rate": 2.4e-05,
31
+ "loss": 1.6339,
32
+ "step": 24
33
+ },
34
+ {
35
+ "epoch": 0.51,
36
+ "learning_rate": 3.2000000000000005e-05,
37
+ "loss": 1.4717,
38
+ "step": 32
39
+ },
40
+ {
41
+ "epoch": 0.64,
42
+ "learning_rate": 4e-05,
43
+ "loss": 1.2297,
44
+ "step": 40
45
+ },
46
+ {
47
+ "epoch": 0.77,
48
+ "learning_rate": 4.8e-05,
49
+ "loss": 1.008,
50
+ "step": 48
51
+ },
52
+ {
53
+ "epoch": 0.9,
54
+ "learning_rate": 4.9327354260089685e-05,
55
+ "loss": 0.8316,
56
+ "step": 56
57
+ },
58
+ {
59
+ "epoch": 0.99,
60
+ "eval_Macro F1": 0.7014511124514329,
61
+ "eval_Macro Precision": 0.6819163828588641,
62
+ "eval_Macro Recall": 0.7429670943209584,
63
+ "eval_Micro F1": 0.743,
64
+ "eval_Micro Precision": 0.743,
65
+ "eval_Micro Recall": 0.743,
66
+ "eval_Weighted F1": 0.702015038120142,
67
+ "eval_Weighted Precision": 0.6827499598363416,
68
+ "eval_Weighted Recall": 0.743,
69
+ "eval_accuracy": 0.743,
70
+ "eval_loss": 0.7518972158432007,
71
+ "eval_runtime": 447.9624,
72
+ "eval_samples_per_second": 4.465,
73
+ "eval_steps_per_second": 0.141,
74
+ "step": 62
75
+ },
76
+ {
77
+ "epoch": 1.02,
78
+ "learning_rate": 4.8430493273542606e-05,
79
+ "loss": 0.751,
80
+ "step": 64
81
+ },
82
+ {
83
+ "epoch": 1.15,
84
+ "learning_rate": 4.7533632286995514e-05,
85
+ "loss": 0.6157,
86
+ "step": 72
87
+ },
88
+ {
89
+ "epoch": 1.28,
90
+ "learning_rate": 4.6636771300448435e-05,
91
+ "loss": 0.534,
92
+ "step": 80
93
+ },
94
+ {
95
+ "epoch": 1.41,
96
+ "learning_rate": 4.573991031390134e-05,
97
+ "loss": 0.4818,
98
+ "step": 88
99
+ },
100
+ {
101
+ "epoch": 1.54,
102
+ "learning_rate": 4.4843049327354265e-05,
103
+ "loss": 0.4119,
104
+ "step": 96
105
+ },
106
+ {
107
+ "epoch": 1.66,
108
+ "learning_rate": 4.394618834080718e-05,
109
+ "loss": 0.3738,
110
+ "step": 104
111
+ },
112
+ {
113
+ "epoch": 1.79,
114
+ "learning_rate": 4.3049327354260094e-05,
115
+ "loss": 0.3613,
116
+ "step": 112
117
+ },
118
+ {
119
+ "epoch": 1.92,
120
+ "learning_rate": 4.215246636771301e-05,
121
+ "loss": 0.3561,
122
+ "step": 120
123
+ },
124
+ {
125
+ "epoch": 2.0,
126
+ "eval_Macro F1": 0.9399641065415552,
127
+ "eval_Macro Precision": 0.9480023804705043,
128
+ "eval_Macro Recall": 0.9394177169921687,
129
+ "eval_Micro F1": 0.9395,
130
+ "eval_Micro Precision": 0.9395,
131
+ "eval_Micro Recall": 0.9395,
132
+ "eval_Weighted F1": 0.9400723727432211,
133
+ "eval_Weighted Precision": 0.9482020576131688,
134
+ "eval_Weighted Recall": 0.9395,
135
+ "eval_accuracy": 0.9395,
136
+ "eval_loss": 0.23021972179412842,
137
+ "eval_runtime": 447.7687,
138
+ "eval_samples_per_second": 4.467,
139
+ "eval_steps_per_second": 0.141,
140
+ "step": 125
141
+ },
142
+ {
143
+ "epoch": 2.05,
144
+ "learning_rate": 4.125560538116592e-05,
145
+ "loss": 0.343,
146
+ "step": 128
147
+ },
148
+ {
149
+ "epoch": 2.18,
150
+ "learning_rate": 4.035874439461884e-05,
151
+ "loss": 0.2871,
152
+ "step": 136
153
+ },
154
+ {
155
+ "epoch": 2.3,
156
+ "learning_rate": 3.9461883408071745e-05,
157
+ "loss": 0.2976,
158
+ "step": 144
159
+ },
160
+ {
161
+ "epoch": 2.43,
162
+ "learning_rate": 3.8565022421524667e-05,
163
+ "loss": 0.2644,
164
+ "step": 152
165
+ },
166
+ {
167
+ "epoch": 2.56,
168
+ "learning_rate": 3.766816143497758e-05,
169
+ "loss": 0.2489,
170
+ "step": 160
171
+ },
172
+ {
173
+ "epoch": 2.69,
174
+ "learning_rate": 3.6771300448430496e-05,
175
+ "loss": 0.2646,
176
+ "step": 168
177
+ },
178
+ {
179
+ "epoch": 2.82,
180
+ "learning_rate": 3.587443946188341e-05,
181
+ "loss": 0.2206,
182
+ "step": 176
183
+ },
184
+ {
185
+ "epoch": 2.94,
186
+ "learning_rate": 3.4977578475336325e-05,
187
+ "loss": 0.2222,
188
+ "step": 184
189
+ },
190
+ {
191
+ "epoch": 2.99,
192
+ "eval_Macro F1": 0.9560784374426261,
193
+ "eval_Macro Precision": 0.960026790280936,
194
+ "eval_Macro Recall": 0.9551284727306868,
195
+ "eval_Micro F1": 0.956,
196
+ "eval_Micro Precision": 0.956,
197
+ "eval_Micro Recall": 0.956,
198
+ "eval_Weighted F1": 0.9564097977894885,
199
+ "eval_Weighted Precision": 0.9597888158665016,
200
+ "eval_Weighted Recall": 0.956,
201
+ "eval_accuracy": 0.956,
202
+ "eval_loss": 0.1349564790725708,
203
+ "eval_runtime": 446.9116,
204
+ "eval_samples_per_second": 4.475,
205
+ "eval_steps_per_second": 0.141,
206
+ "step": 187
207
+ },
208
+ {
209
+ "epoch": 3.07,
210
+ "learning_rate": 3.408071748878924e-05,
211
+ "loss": 0.2258,
212
+ "step": 192
213
+ },
214
+ {
215
+ "epoch": 3.2,
216
+ "learning_rate": 3.3183856502242154e-05,
217
+ "loss": 0.207,
218
+ "step": 200
219
+ },
220
+ {
221
+ "epoch": 3.33,
222
+ "learning_rate": 3.228699551569507e-05,
223
+ "loss": 0.1826,
224
+ "step": 208
225
+ },
226
+ {
227
+ "epoch": 3.46,
228
+ "learning_rate": 3.139013452914798e-05,
229
+ "loss": 0.1929,
230
+ "step": 216
231
+ },
232
+ {
233
+ "epoch": 3.58,
234
+ "learning_rate": 3.0493273542600898e-05,
235
+ "loss": 0.2159,
236
+ "step": 224
237
+ },
238
+ {
239
+ "epoch": 3.71,
240
+ "learning_rate": 2.9596412556053816e-05,
241
+ "loss": 0.1813,
242
+ "step": 232
243
+ },
244
+ {
245
+ "epoch": 3.84,
246
+ "learning_rate": 2.8699551569506727e-05,
247
+ "loss": 0.1723,
248
+ "step": 240
249
+ },
250
+ {
251
+ "epoch": 3.97,
252
+ "learning_rate": 2.7802690582959645e-05,
253
+ "loss": 0.1705,
254
+ "step": 248
255
+ },
256
+ {
257
+ "epoch": 4.0,
258
+ "eval_Macro F1": 0.9725373484087296,
259
+ "eval_Macro Precision": 0.9740041726370726,
260
+ "eval_Macro Recall": 0.9721459242124089,
261
+ "eval_Micro F1": 0.9725,
262
+ "eval_Micro Precision": 0.9725,
263
+ "eval_Micro Recall": 0.9725,
264
+ "eval_Weighted F1": 0.9727108492700939,
265
+ "eval_Weighted Precision": 0.9739894365164001,
266
+ "eval_Weighted Recall": 0.9725,
267
+ "eval_accuracy": 0.9725,
268
+ "eval_loss": 0.0872766375541687,
269
+ "eval_runtime": 435.148,
270
+ "eval_samples_per_second": 4.596,
271
+ "eval_steps_per_second": 0.145,
272
+ "step": 250
273
+ },
274
+ {
275
+ "epoch": 4.1,
276
+ "learning_rate": 2.6905829596412556e-05,
277
+ "loss": 0.1824,
278
+ "step": 256
279
+ },
280
+ {
281
+ "epoch": 4.22,
282
+ "learning_rate": 2.600896860986547e-05,
283
+ "loss": 0.1877,
284
+ "step": 264
285
+ },
286
+ {
287
+ "epoch": 4.35,
288
+ "learning_rate": 2.511210762331839e-05,
289
+ "loss": 0.2047,
290
+ "step": 272
291
+ },
292
+ {
293
+ "epoch": 4.48,
294
+ "learning_rate": 2.4215246636771303e-05,
295
+ "loss": 0.1814,
296
+ "step": 280
297
+ },
298
+ {
299
+ "epoch": 4.61,
300
+ "learning_rate": 2.3318385650224218e-05,
301
+ "loss": 0.1396,
302
+ "step": 288
303
+ },
304
+ {
305
+ "epoch": 4.74,
306
+ "learning_rate": 2.2421524663677132e-05,
307
+ "loss": 0.1233,
308
+ "step": 296
309
+ },
310
+ {
311
+ "epoch": 4.86,
312
+ "learning_rate": 2.1524663677130047e-05,
313
+ "loss": 0.1612,
314
+ "step": 304
315
+ },
316
+ {
317
+ "epoch": 4.99,
318
+ "learning_rate": 2.062780269058296e-05,
319
+ "loss": 0.1541,
320
+ "step": 312
321
+ },
322
+ {
323
+ "epoch": 4.99,
324
+ "eval_Macro F1": 0.9823741759080236,
325
+ "eval_Macro Precision": 0.9829774434613384,
326
+ "eval_Macro Recall": 0.9821795541998369,
327
+ "eval_Micro F1": 0.9825,
328
+ "eval_Micro Precision": 0.9825,
329
+ "eval_Micro Recall": 0.9825,
330
+ "eval_Weighted F1": 0.982525654398398,
331
+ "eval_Weighted Precision": 0.9829534667560904,
332
+ "eval_Weighted Recall": 0.9825,
333
+ "eval_accuracy": 0.9825,
334
+ "eval_loss": 0.06422679126262665,
335
+ "eval_runtime": 424.7541,
336
+ "eval_samples_per_second": 4.709,
337
+ "eval_steps_per_second": 0.148,
338
+ "step": 312
339
+ },
340
+ {
341
+ "epoch": 5.12,
342
+ "learning_rate": 1.9730941704035873e-05,
343
+ "loss": 0.137,
344
+ "step": 320
345
+ },
346
+ {
347
+ "epoch": 5.25,
348
+ "learning_rate": 1.883408071748879e-05,
349
+ "loss": 0.1577,
350
+ "step": 328
351
+ },
352
+ {
353
+ "epoch": 5.38,
354
+ "learning_rate": 1.7937219730941705e-05,
355
+ "loss": 0.1378,
356
+ "step": 336
357
+ },
358
+ {
359
+ "epoch": 5.5,
360
+ "learning_rate": 1.704035874439462e-05,
361
+ "loss": 0.1795,
362
+ "step": 344
363
+ },
364
+ {
365
+ "epoch": 5.63,
366
+ "learning_rate": 1.6143497757847534e-05,
367
+ "loss": 0.1447,
368
+ "step": 352
369
+ },
370
+ {
371
+ "epoch": 5.76,
372
+ "learning_rate": 1.5246636771300449e-05,
373
+ "loss": 0.1235,
374
+ "step": 360
375
+ },
376
+ {
377
+ "epoch": 5.89,
378
+ "learning_rate": 1.4349775784753363e-05,
379
+ "loss": 0.1253,
380
+ "step": 368
381
+ },
382
+ {
383
+ "epoch": 6.0,
384
+ "eval_Macro F1": 0.991431216491566,
385
+ "eval_Macro Precision": 0.9916198483282233,
386
+ "eval_Macro Recall": 0.9913450460193864,
387
+ "eval_Micro F1": 0.9915,
388
+ "eval_Micro Precision": 0.9915,
389
+ "eval_Micro Recall": 0.9915,
390
+ "eval_Weighted F1": 0.9915159731866887,
391
+ "eval_Weighted Precision": 0.9916339514381117,
392
+ "eval_Weighted Recall": 0.9915,
393
+ "eval_accuracy": 0.9915,
394
+ "eval_loss": 0.033043112605810165,
395
+ "eval_runtime": 424.2354,
396
+ "eval_samples_per_second": 4.714,
397
+ "eval_steps_per_second": 0.149,
398
+ "step": 375
399
+ },
400
+ {
401
+ "epoch": 6.02,
402
+ "learning_rate": 1.3452914798206278e-05,
403
+ "loss": 0.1134,
404
+ "step": 376
405
+ },
406
+ {
407
+ "epoch": 6.14,
408
+ "learning_rate": 1.2556053811659194e-05,
409
+ "loss": 0.1393,
410
+ "step": 384
411
+ },
412
+ {
413
+ "epoch": 6.27,
414
+ "learning_rate": 1.1659192825112109e-05,
415
+ "loss": 0.0912,
416
+ "step": 392
417
+ },
418
+ {
419
+ "epoch": 6.4,
420
+ "learning_rate": 1.0762331838565023e-05,
421
+ "loss": 0.1131,
422
+ "step": 400
423
+ },
424
+ {
425
+ "epoch": 6.53,
426
+ "learning_rate": 9.865470852017936e-06,
427
+ "loss": 0.1255,
428
+ "step": 408
429
+ },
430
+ {
431
+ "epoch": 6.66,
432
+ "learning_rate": 8.968609865470853e-06,
433
+ "loss": 0.1418,
434
+ "step": 416
435
+ },
436
+ {
437
+ "epoch": 6.78,
438
+ "learning_rate": 8.071748878923767e-06,
439
+ "loss": 0.1399,
440
+ "step": 424
441
+ },
442
+ {
443
+ "epoch": 6.91,
444
+ "learning_rate": 7.174887892376682e-06,
445
+ "loss": 0.1196,
446
+ "step": 432
447
+ },
448
+ {
449
+ "epoch": 6.99,
450
+ "eval_Macro F1": 0.9820075650260679,
451
+ "eval_Macro Precision": 0.983170950573056,
452
+ "eval_Macro Recall": 0.9817144393341324,
453
+ "eval_Micro F1": 0.982,
454
+ "eval_Micro Precision": 0.982,
455
+ "eval_Micro Recall": 0.982,
456
+ "eval_Weighted F1": 0.9821570480740702,
457
+ "eval_Weighted Precision": 0.9831749197494307,
458
+ "eval_Weighted Recall": 0.982,
459
+ "eval_accuracy": 0.982,
460
+ "eval_loss": 0.05244705080986023,
461
+ "eval_runtime": 424.1947,
462
+ "eval_samples_per_second": 4.715,
463
+ "eval_steps_per_second": 0.149,
464
+ "step": 437
465
+ },
466
+ {
467
+ "epoch": 7.04,
468
+ "learning_rate": 6.278026905829597e-06,
469
+ "loss": 0.1201,
470
+ "step": 440
471
+ },
472
+ {
473
+ "epoch": 7.17,
474
+ "learning_rate": 5.381165919282512e-06,
475
+ "loss": 0.1111,
476
+ "step": 448
477
+ },
478
+ {
479
+ "epoch": 7.3,
480
+ "learning_rate": 4.484304932735426e-06,
481
+ "loss": 0.1021,
482
+ "step": 456
483
+ },
484
+ {
485
+ "epoch": 7.42,
486
+ "learning_rate": 3.587443946188341e-06,
487
+ "loss": 0.1158,
488
+ "step": 464
489
+ },
490
+ {
491
+ "epoch": 7.55,
492
+ "learning_rate": 2.690582959641256e-06,
493
+ "loss": 0.1321,
494
+ "step": 472
495
+ },
496
+ {
497
+ "epoch": 7.68,
498
+ "learning_rate": 1.7937219730941704e-06,
499
+ "loss": 0.1429,
500
+ "step": 480
501
+ },
502
+ {
503
+ "epoch": 7.81,
504
+ "learning_rate": 8.968609865470852e-07,
505
+ "loss": 0.1103,
506
+ "step": 488
507
+ },
508
+ {
509
+ "epoch": 7.94,
510
+ "learning_rate": 0.0,
511
+ "loss": 0.0896,
512
+ "step": 496
513
+ },
514
+ {
515
+ "epoch": 7.94,
516
+ "eval_Macro F1": 0.9863352307981634,
517
+ "eval_Macro Precision": 0.9869554360352077,
518
+ "eval_Macro Recall": 0.986134153009335,
519
+ "eval_Micro F1": 0.9865,
520
+ "eval_Micro Precision": 0.9865,
521
+ "eval_Micro Recall": 0.9865,
522
+ "eval_Weighted F1": 0.9865091518400995,
523
+ "eval_Weighted Precision": 0.9869273604184196,
524
+ "eval_Weighted Recall": 0.9865,
525
+ "eval_accuracy": 0.9865,
526
+ "eval_loss": 0.04359065368771553,
527
+ "eval_runtime": 424.3089,
528
+ "eval_samples_per_second": 4.714,
529
+ "eval_steps_per_second": 0.148,
530
+ "step": 496
531
+ },
532
+ {
533
+ "epoch": 7.94,
534
+ "step": 496,
535
+ "total_flos": 4.920648490788323e+18,
536
+ "train_loss": 0.35526800215724974,
537
+ "train_runtime": 45263.0947,
538
+ "train_samples_per_second": 1.414,
539
+ "train_steps_per_second": 0.011
540
+ }
541
+ ],
542
+ "max_steps": 496,
543
+ "num_train_epochs": 8,
544
+ "total_flos": 4.920648490788323e+18,
545
+ "trial_name": null,
546
+ "trial_params": null
547
+ }