cloudwalkerw commited on
Commit
650dab3
1 Parent(s): 1bad8e0

End of training

Browse files
Files changed (5) hide show
  1. README.md +1 -0
  2. all_results.json +12 -0
  3. eval_results.json +8 -0
  4. train_results.json +7 -0
  5. trainer_state.json +667 -0
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  base_model: microsoft/wavlm-base
3
  tags:
 
4
  - generated_from_trainer
5
  datasets:
6
  - superb
 
1
  ---
2
  base_model: microsoft/wavlm-base
3
  tags:
4
+ - audio-classification
5
  - generated_from_trainer
6
  datasets:
7
  - superb
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.98,
3
+ "eval_accuracy": 0.9694027655192704,
4
+ "eval_loss": 0.22695787250995636,
5
+ "eval_runtime": 7.8971,
6
+ "eval_samples_per_second": 860.819,
7
+ "eval_steps_per_second": 13.549,
8
+ "train_loss": 0.878907411182346,
9
+ "train_runtime": 597.8339,
10
+ "train_samples_per_second": 427.326,
11
+ "train_steps_per_second": 1.664
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.98,
3
+ "eval_accuracy": 0.9694027655192704,
4
+ "eval_loss": 0.22695787250995636,
5
+ "eval_runtime": 7.8971,
6
+ "eval_samples_per_second": 860.819,
7
+ "eval_steps_per_second": 13.549
8
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.98,
3
+ "train_loss": 0.878907411182346,
4
+ "train_runtime": 597.8339,
5
+ "train_samples_per_second": 427.326,
6
+ "train_steps_per_second": 1.664
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,667 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9694027655192704,
3
+ "best_model_checkpoint": "wav2vec2-base-ft-keyword-spotting/checkpoint-995",
4
+ "epoch": 4.981226533166458,
5
+ "eval_steps": 500,
6
+ "global_step": 995,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "learning_rate": 3e-06,
14
+ "loss": 2.4885,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.1,
19
+ "learning_rate": 6e-06,
20
+ "loss": 2.461,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.15,
25
+ "learning_rate": 9e-06,
26
+ "loss": 2.404,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.2,
31
+ "learning_rate": 1.2e-05,
32
+ "loss": 2.2766,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.25,
37
+ "learning_rate": 1.5e-05,
38
+ "loss": 2.0127,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.3,
43
+ "learning_rate": 1.8e-05,
44
+ "loss": 1.8231,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.35,
49
+ "learning_rate": 2.1e-05,
50
+ "loss": 1.7101,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.4,
55
+ "learning_rate": 2.4e-05,
56
+ "loss": 1.6402,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.45,
61
+ "learning_rate": 2.7000000000000002e-05,
62
+ "loss": 1.5429,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.5,
67
+ "learning_rate": 3e-05,
68
+ "loss": 1.4995,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.55,
73
+ "learning_rate": 2.9664804469273744e-05,
74
+ "loss": 1.522,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.6,
79
+ "learning_rate": 2.9329608938547488e-05,
80
+ "loss": 1.5216,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.65,
85
+ "learning_rate": 2.899441340782123e-05,
86
+ "loss": 1.496,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.7,
91
+ "learning_rate": 2.8659217877094975e-05,
92
+ "loss": 1.4857,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.75,
97
+ "learning_rate": 2.8324022346368715e-05,
98
+ "loss": 1.4528,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.8,
103
+ "learning_rate": 2.798882681564246e-05,
104
+ "loss": 1.4026,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.85,
109
+ "learning_rate": 2.7653631284916202e-05,
110
+ "loss": 1.4524,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.9,
115
+ "learning_rate": 2.7318435754189945e-05,
116
+ "loss": 1.3755,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.95,
121
+ "learning_rate": 2.698324022346369e-05,
122
+ "loss": 1.3203,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 1.0,
127
+ "eval_accuracy": 0.6328331862312445,
128
+ "eval_loss": 1.2906286716461182,
129
+ "eval_runtime": 7.8945,
130
+ "eval_samples_per_second": 861.104,
131
+ "eval_steps_per_second": 13.554,
132
+ "step": 199
133
+ },
134
+ {
135
+ "epoch": 1.0,
136
+ "learning_rate": 2.6648044692737432e-05,
137
+ "loss": 1.3231,
138
+ "step": 200
139
+ },
140
+ {
141
+ "epoch": 1.05,
142
+ "learning_rate": 2.6312849162011176e-05,
143
+ "loss": 1.2471,
144
+ "step": 210
145
+ },
146
+ {
147
+ "epoch": 1.1,
148
+ "learning_rate": 2.597765363128492e-05,
149
+ "loss": 1.2807,
150
+ "step": 220
151
+ },
152
+ {
153
+ "epoch": 1.15,
154
+ "learning_rate": 2.564245810055866e-05,
155
+ "loss": 1.2235,
156
+ "step": 230
157
+ },
158
+ {
159
+ "epoch": 1.2,
160
+ "learning_rate": 2.5307262569832403e-05,
161
+ "loss": 1.2313,
162
+ "step": 240
163
+ },
164
+ {
165
+ "epoch": 1.25,
166
+ "learning_rate": 2.4972067039106143e-05,
167
+ "loss": 1.1449,
168
+ "step": 250
169
+ },
170
+ {
171
+ "epoch": 1.3,
172
+ "learning_rate": 2.4636871508379887e-05,
173
+ "loss": 1.1987,
174
+ "step": 260
175
+ },
176
+ {
177
+ "epoch": 1.35,
178
+ "learning_rate": 2.430167597765363e-05,
179
+ "loss": 1.1639,
180
+ "step": 270
181
+ },
182
+ {
183
+ "epoch": 1.4,
184
+ "learning_rate": 2.3966480446927374e-05,
185
+ "loss": 1.0966,
186
+ "step": 280
187
+ },
188
+ {
189
+ "epoch": 1.45,
190
+ "learning_rate": 2.3631284916201117e-05,
191
+ "loss": 1.1318,
192
+ "step": 290
193
+ },
194
+ {
195
+ "epoch": 1.5,
196
+ "learning_rate": 2.329608938547486e-05,
197
+ "loss": 1.0765,
198
+ "step": 300
199
+ },
200
+ {
201
+ "epoch": 1.55,
202
+ "learning_rate": 2.2960893854748604e-05,
203
+ "loss": 1.0647,
204
+ "step": 310
205
+ },
206
+ {
207
+ "epoch": 1.6,
208
+ "learning_rate": 2.2625698324022348e-05,
209
+ "loss": 0.9996,
210
+ "step": 320
211
+ },
212
+ {
213
+ "epoch": 1.65,
214
+ "learning_rate": 2.229050279329609e-05,
215
+ "loss": 1.0009,
216
+ "step": 330
217
+ },
218
+ {
219
+ "epoch": 1.7,
220
+ "learning_rate": 2.195530726256983e-05,
221
+ "loss": 1.0277,
222
+ "step": 340
223
+ },
224
+ {
225
+ "epoch": 1.75,
226
+ "learning_rate": 2.1620111731843575e-05,
227
+ "loss": 1.0153,
228
+ "step": 350
229
+ },
230
+ {
231
+ "epoch": 1.8,
232
+ "learning_rate": 2.1284916201117318e-05,
233
+ "loss": 1.0128,
234
+ "step": 360
235
+ },
236
+ {
237
+ "epoch": 1.85,
238
+ "learning_rate": 2.0949720670391062e-05,
239
+ "loss": 0.9423,
240
+ "step": 370
241
+ },
242
+ {
243
+ "epoch": 1.9,
244
+ "learning_rate": 2.0614525139664805e-05,
245
+ "loss": 0.9471,
246
+ "step": 380
247
+ },
248
+ {
249
+ "epoch": 1.95,
250
+ "learning_rate": 2.027932960893855e-05,
251
+ "loss": 0.9587,
252
+ "step": 390
253
+ },
254
+ {
255
+ "epoch": 2.0,
256
+ "eval_accuracy": 0.7355104442483084,
257
+ "eval_loss": 0.7793017029762268,
258
+ "eval_runtime": 7.9323,
259
+ "eval_samples_per_second": 857.006,
260
+ "eval_steps_per_second": 13.489,
261
+ "step": 399
262
+ },
263
+ {
264
+ "epoch": 2.0,
265
+ "learning_rate": 1.9944134078212292e-05,
266
+ "loss": 0.9263,
267
+ "step": 400
268
+ },
269
+ {
270
+ "epoch": 2.05,
271
+ "learning_rate": 1.9608938547486036e-05,
272
+ "loss": 0.8469,
273
+ "step": 410
274
+ },
275
+ {
276
+ "epoch": 2.1,
277
+ "learning_rate": 1.927374301675978e-05,
278
+ "loss": 0.8733,
279
+ "step": 420
280
+ },
281
+ {
282
+ "epoch": 2.15,
283
+ "learning_rate": 1.893854748603352e-05,
284
+ "loss": 0.85,
285
+ "step": 430
286
+ },
287
+ {
288
+ "epoch": 2.2,
289
+ "learning_rate": 1.8603351955307263e-05,
290
+ "loss": 0.84,
291
+ "step": 440
292
+ },
293
+ {
294
+ "epoch": 2.25,
295
+ "learning_rate": 1.8268156424581006e-05,
296
+ "loss": 0.8049,
297
+ "step": 450
298
+ },
299
+ {
300
+ "epoch": 2.3,
301
+ "learning_rate": 1.793296089385475e-05,
302
+ "loss": 0.7884,
303
+ "step": 460
304
+ },
305
+ {
306
+ "epoch": 2.35,
307
+ "learning_rate": 1.7597765363128493e-05,
308
+ "loss": 0.8033,
309
+ "step": 470
310
+ },
311
+ {
312
+ "epoch": 2.4,
313
+ "learning_rate": 1.7262569832402237e-05,
314
+ "loss": 0.7183,
315
+ "step": 480
316
+ },
317
+ {
318
+ "epoch": 2.45,
319
+ "learning_rate": 1.6927374301675977e-05,
320
+ "loss": 0.7245,
321
+ "step": 490
322
+ },
323
+ {
324
+ "epoch": 2.5,
325
+ "learning_rate": 1.659217877094972e-05,
326
+ "loss": 0.6581,
327
+ "step": 500
328
+ },
329
+ {
330
+ "epoch": 2.55,
331
+ "learning_rate": 1.6256983240223464e-05,
332
+ "loss": 0.6653,
333
+ "step": 510
334
+ },
335
+ {
336
+ "epoch": 2.6,
337
+ "learning_rate": 1.5921787709497207e-05,
338
+ "loss": 0.6699,
339
+ "step": 520
340
+ },
341
+ {
342
+ "epoch": 2.65,
343
+ "learning_rate": 1.5586592178770948e-05,
344
+ "loss": 0.6635,
345
+ "step": 530
346
+ },
347
+ {
348
+ "epoch": 2.7,
349
+ "learning_rate": 1.5251396648044693e-05,
350
+ "loss": 0.6372,
351
+ "step": 540
352
+ },
353
+ {
354
+ "epoch": 2.75,
355
+ "learning_rate": 1.4916201117318435e-05,
356
+ "loss": 0.6368,
357
+ "step": 550
358
+ },
359
+ {
360
+ "epoch": 2.8,
361
+ "learning_rate": 1.4581005586592178e-05,
362
+ "loss": 0.5918,
363
+ "step": 560
364
+ },
365
+ {
366
+ "epoch": 2.85,
367
+ "learning_rate": 1.4245810055865922e-05,
368
+ "loss": 0.6305,
369
+ "step": 570
370
+ },
371
+ {
372
+ "epoch": 2.9,
373
+ "learning_rate": 1.3910614525139665e-05,
374
+ "loss": 0.5916,
375
+ "step": 580
376
+ },
377
+ {
378
+ "epoch": 2.95,
379
+ "learning_rate": 1.3575418994413409e-05,
380
+ "loss": 0.6218,
381
+ "step": 590
382
+ },
383
+ {
384
+ "epoch": 3.0,
385
+ "eval_accuracy": 0.9289496910856134,
386
+ "eval_loss": 0.38581380248069763,
387
+ "eval_runtime": 7.9106,
388
+ "eval_samples_per_second": 859.357,
389
+ "eval_steps_per_second": 13.526,
390
+ "step": 599
391
+ },
392
+ {
393
+ "epoch": 3.0,
394
+ "learning_rate": 1.324022346368715e-05,
395
+ "loss": 0.5873,
396
+ "step": 600
397
+ },
398
+ {
399
+ "epoch": 3.05,
400
+ "learning_rate": 1.2905027932960894e-05,
401
+ "loss": 0.5561,
402
+ "step": 610
403
+ },
404
+ {
405
+ "epoch": 3.1,
406
+ "learning_rate": 1.2569832402234637e-05,
407
+ "loss": 0.5657,
408
+ "step": 620
409
+ },
410
+ {
411
+ "epoch": 3.15,
412
+ "learning_rate": 1.2234636871508381e-05,
413
+ "loss": 0.5355,
414
+ "step": 630
415
+ },
416
+ {
417
+ "epoch": 3.2,
418
+ "learning_rate": 1.1899441340782124e-05,
419
+ "loss": 0.5338,
420
+ "step": 640
421
+ },
422
+ {
423
+ "epoch": 3.25,
424
+ "learning_rate": 1.1564245810055866e-05,
425
+ "loss": 0.5436,
426
+ "step": 650
427
+ },
428
+ {
429
+ "epoch": 3.3,
430
+ "learning_rate": 1.122905027932961e-05,
431
+ "loss": 0.5289,
432
+ "step": 660
433
+ },
434
+ {
435
+ "epoch": 3.35,
436
+ "learning_rate": 1.0893854748603353e-05,
437
+ "loss": 0.4941,
438
+ "step": 670
439
+ },
440
+ {
441
+ "epoch": 3.4,
442
+ "learning_rate": 1.0558659217877095e-05,
443
+ "loss": 0.46,
444
+ "step": 680
445
+ },
446
+ {
447
+ "epoch": 3.45,
448
+ "learning_rate": 1.0223463687150837e-05,
449
+ "loss": 0.4775,
450
+ "step": 690
451
+ },
452
+ {
453
+ "epoch": 3.5,
454
+ "learning_rate": 9.88826815642458e-06,
455
+ "loss": 0.4725,
456
+ "step": 700
457
+ },
458
+ {
459
+ "epoch": 3.55,
460
+ "learning_rate": 9.553072625698324e-06,
461
+ "loss": 0.5098,
462
+ "step": 710
463
+ },
464
+ {
465
+ "epoch": 3.6,
466
+ "learning_rate": 9.217877094972067e-06,
467
+ "loss": 0.4217,
468
+ "step": 720
469
+ },
470
+ {
471
+ "epoch": 3.65,
472
+ "learning_rate": 8.88268156424581e-06,
473
+ "loss": 0.4628,
474
+ "step": 730
475
+ },
476
+ {
477
+ "epoch": 3.7,
478
+ "learning_rate": 8.547486033519553e-06,
479
+ "loss": 0.4573,
480
+ "step": 740
481
+ },
482
+ {
483
+ "epoch": 3.75,
484
+ "learning_rate": 8.212290502793296e-06,
485
+ "loss": 0.4078,
486
+ "step": 750
487
+ },
488
+ {
489
+ "epoch": 3.8,
490
+ "learning_rate": 7.87709497206704e-06,
491
+ "loss": 0.4339,
492
+ "step": 760
493
+ },
494
+ {
495
+ "epoch": 3.85,
496
+ "learning_rate": 7.541899441340783e-06,
497
+ "loss": 0.4426,
498
+ "step": 770
499
+ },
500
+ {
501
+ "epoch": 3.9,
502
+ "learning_rate": 7.206703910614525e-06,
503
+ "loss": 0.4318,
504
+ "step": 780
505
+ },
506
+ {
507
+ "epoch": 3.95,
508
+ "learning_rate": 6.871508379888268e-06,
509
+ "loss": 0.4379,
510
+ "step": 790
511
+ },
512
+ {
513
+ "epoch": 4.0,
514
+ "eval_accuracy": 0.9688143571638718,
515
+ "eval_loss": 0.2581191658973694,
516
+ "eval_runtime": 7.8989,
517
+ "eval_samples_per_second": 860.625,
518
+ "eval_steps_per_second": 13.546,
519
+ "step": 799
520
+ },
521
+ {
522
+ "epoch": 4.01,
523
+ "learning_rate": 6.536312849162011e-06,
524
+ "loss": 0.4175,
525
+ "step": 800
526
+ },
527
+ {
528
+ "epoch": 4.06,
529
+ "learning_rate": 6.2011173184357546e-06,
530
+ "loss": 0.4289,
531
+ "step": 810
532
+ },
533
+ {
534
+ "epoch": 4.11,
535
+ "learning_rate": 5.865921787709497e-06,
536
+ "loss": 0.4106,
537
+ "step": 820
538
+ },
539
+ {
540
+ "epoch": 4.16,
541
+ "learning_rate": 5.530726256983241e-06,
542
+ "loss": 0.4042,
543
+ "step": 830
544
+ },
545
+ {
546
+ "epoch": 4.21,
547
+ "learning_rate": 5.195530726256983e-06,
548
+ "loss": 0.3968,
549
+ "step": 840
550
+ },
551
+ {
552
+ "epoch": 4.26,
553
+ "learning_rate": 4.860335195530726e-06,
554
+ "loss": 0.4241,
555
+ "step": 850
556
+ },
557
+ {
558
+ "epoch": 4.31,
559
+ "learning_rate": 4.5251396648044695e-06,
560
+ "loss": 0.4201,
561
+ "step": 860
562
+ },
563
+ {
564
+ "epoch": 4.36,
565
+ "learning_rate": 4.189944134078212e-06,
566
+ "loss": 0.4136,
567
+ "step": 870
568
+ },
569
+ {
570
+ "epoch": 4.41,
571
+ "learning_rate": 3.854748603351956e-06,
572
+ "loss": 0.4093,
573
+ "step": 880
574
+ },
575
+ {
576
+ "epoch": 4.46,
577
+ "learning_rate": 3.5195530726256983e-06,
578
+ "loss": 0.4178,
579
+ "step": 890
580
+ },
581
+ {
582
+ "epoch": 4.51,
583
+ "learning_rate": 3.1843575418994414e-06,
584
+ "loss": 0.3721,
585
+ "step": 900
586
+ },
587
+ {
588
+ "epoch": 4.56,
589
+ "learning_rate": 2.8491620111731845e-06,
590
+ "loss": 0.3936,
591
+ "step": 910
592
+ },
593
+ {
594
+ "epoch": 4.61,
595
+ "learning_rate": 2.513966480446927e-06,
596
+ "loss": 0.3675,
597
+ "step": 920
598
+ },
599
+ {
600
+ "epoch": 4.66,
601
+ "learning_rate": 2.1787709497206706e-06,
602
+ "loss": 0.4145,
603
+ "step": 930
604
+ },
605
+ {
606
+ "epoch": 4.71,
607
+ "learning_rate": 1.8435754189944133e-06,
608
+ "loss": 0.4089,
609
+ "step": 940
610
+ },
611
+ {
612
+ "epoch": 4.76,
613
+ "learning_rate": 1.5083798882681566e-06,
614
+ "loss": 0.3767,
615
+ "step": 950
616
+ },
617
+ {
618
+ "epoch": 4.81,
619
+ "learning_rate": 1.1731843575418994e-06,
620
+ "loss": 0.3827,
621
+ "step": 960
622
+ },
623
+ {
624
+ "epoch": 4.86,
625
+ "learning_rate": 8.379888268156424e-07,
626
+ "loss": 0.3819,
627
+ "step": 970
628
+ },
629
+ {
630
+ "epoch": 4.91,
631
+ "learning_rate": 5.027932960893855e-07,
632
+ "loss": 0.3897,
633
+ "step": 980
634
+ },
635
+ {
636
+ "epoch": 4.96,
637
+ "learning_rate": 1.675977653631285e-07,
638
+ "loss": 0.3779,
639
+ "step": 990
640
+ },
641
+ {
642
+ "epoch": 4.98,
643
+ "eval_accuracy": 0.9694027655192704,
644
+ "eval_loss": 0.22695787250995636,
645
+ "eval_runtime": 7.9078,
646
+ "eval_samples_per_second": 859.662,
647
+ "eval_steps_per_second": 13.531,
648
+ "step": 995
649
+ },
650
+ {
651
+ "epoch": 4.98,
652
+ "step": 995,
653
+ "total_flos": 2.311202904603648e+18,
654
+ "train_loss": 0.878907411182346,
655
+ "train_runtime": 597.8339,
656
+ "train_samples_per_second": 427.326,
657
+ "train_steps_per_second": 1.664
658
+ }
659
+ ],
660
+ "logging_steps": 10,
661
+ "max_steps": 995,
662
+ "num_train_epochs": 5,
663
+ "save_steps": 500,
664
+ "total_flos": 2.311202904603648e+18,
665
+ "trial_name": null,
666
+ "trial_params": null
667
+ }