noflm commited on
Commit
6cb3cc3
1 Parent(s): e6c60f5

End of training

Browse files
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "epoch": 29.01,
3
- "eval_loss": 0.1459457278251648,
4
- "eval_runtime": 6.2733,
5
- "eval_samples_per_second": 2.869,
6
- "eval_steps_per_second": 0.797,
7
- "eval_wer": 11.585365853658537,
8
- "train_loss": 0.07516751879453659,
9
- "train_runtime": 1282.4235,
10
- "train_samples_per_second": 6.238,
11
- "train_steps_per_second": 0.78
12
  }
 
1
  {
2
+ "epoch": 1111.0,
3
+ "eval_loss": 0.43846404552459717,
4
+ "eval_runtime": 8.4067,
5
+ "eval_samples_per_second": 2.141,
6
+ "eval_steps_per_second": 0.119,
7
+ "eval_wer": 17.073170731707318,
8
+ "train_loss": 0.007888052637434157,
9
+ "train_runtime": 66285.4349,
10
+ "train_samples_per_second": 4.828,
11
+ "train_steps_per_second": 0.151
12
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 29.01,
3
- "eval_loss": 0.1459457278251648,
4
- "eval_runtime": 6.2733,
5
- "eval_samples_per_second": 2.869,
6
- "eval_steps_per_second": 0.797,
7
- "eval_wer": 11.585365853658537
8
  }
 
1
  {
2
+ "epoch": 1111.0,
3
+ "eval_loss": 0.43846404552459717,
4
+ "eval_runtime": 8.4067,
5
+ "eval_samples_per_second": 2.141,
6
+ "eval_steps_per_second": 0.119,
7
+ "eval_wer": 17.073170731707318
8
  }
runs/Dec29_11-05-20_srv/events.out.tfevents.1672378331.srv.13534.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e0bebd6b3506b4e9f48f75ea86f032659c858c249e2f53bb02e1a1c1d0cfdc
3
+ size 358
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 29.01,
3
- "train_loss": 0.07516751879453659,
4
- "train_runtime": 1282.4235,
5
- "train_samples_per_second": 6.238,
6
- "train_steps_per_second": 0.78
7
  }
 
1
  {
2
+ "epoch": 1111.0,
3
+ "train_loss": 0.007888052637434157,
4
+ "train_runtime": 66285.4349,
5
+ "train_samples_per_second": 4.828,
6
+ "train_steps_per_second": 0.151
7
  }
trainer_state.json CHANGED
@@ -1,94 +1,715 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 29.014,
5
- "global_step": 1000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 2.03,
12
- "learning_rate": 1e-05,
13
- "loss": 0.6378,
14
  "step": 100
15
  },
16
  {
17
- "epoch": 5.03,
18
- "learning_rate": 1e-05,
19
- "loss": 0.0803,
20
  "step": 200
21
  },
22
  {
23
- "epoch": 8.03,
24
  "learning_rate": 1e-05,
25
- "loss": 0.0166,
26
  "step": 300
27
  },
28
  {
29
- "epoch": 11.03,
30
  "learning_rate": 1e-05,
31
- "loss": 0.0048,
32
  "step": 400
33
  },
34
  {
35
- "epoch": 14.02,
36
  "learning_rate": 1e-05,
37
- "loss": 0.0037,
38
  "step": 500
39
  },
40
  {
41
- "epoch": 17.02,
42
  "learning_rate": 1e-05,
43
- "loss": 0.0032,
44
  "step": 600
45
  },
46
  {
47
- "epoch": 20.02,
48
  "learning_rate": 1e-05,
49
- "loss": 0.0007,
50
  "step": 700
51
  },
52
  {
53
- "epoch": 23.02,
54
  "learning_rate": 1e-05,
55
- "loss": 0.0011,
56
  "step": 800
57
  },
58
  {
59
- "epoch": 26.02,
60
  "learning_rate": 1e-05,
61
- "loss": 0.0025,
62
  "step": 900
63
  },
64
  {
65
- "epoch": 29.01,
66
  "learning_rate": 1e-05,
67
- "loss": 0.0009,
68
  "step": 1000
69
  },
70
  {
71
- "epoch": 29.01,
72
- "eval_loss": 0.1459457278251648,
73
- "eval_runtime": 5.4122,
74
- "eval_samples_per_second": 3.326,
75
- "eval_steps_per_second": 0.924,
76
- "eval_wer": 11.585365853658537,
77
  "step": 1000
78
  },
79
  {
80
- "epoch": 29.01,
81
- "step": 1000,
82
- "total_flos": 5.1887996928e+17,
83
- "train_loss": 0.07516751879453659,
84
- "train_runtime": 1282.4235,
85
- "train_samples_per_second": 6.238,
86
- "train_steps_per_second": 0.78
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  }
88
  ],
89
- "max_steps": 1000,
90
  "num_train_epochs": 9223372036854775807,
91
- "total_flos": 5.1887996928e+17,
92
  "trial_name": null,
93
  "trial_params": null
94
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1111.0001,
5
+ "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 11.0,
12
+ "learning_rate": 4.85e-06,
13
+ "loss": 0.716,
14
  "step": 100
15
  },
16
  {
17
+ "epoch": 22.0,
18
+ "learning_rate": 9.85e-06,
19
+ "loss": 0.0615,
20
  "step": 200
21
  },
22
  {
23
+ "epoch": 33.0,
24
  "learning_rate": 1e-05,
25
+ "loss": 0.0043,
26
  "step": 300
27
  },
28
  {
29
+ "epoch": 44.0,
30
  "learning_rate": 1e-05,
31
+ "loss": 0.002,
32
  "step": 400
33
  },
34
  {
35
+ "epoch": 55.0,
36
  "learning_rate": 1e-05,
37
+ "loss": 0.0008,
38
  "step": 500
39
  },
40
  {
41
+ "epoch": 66.0,
42
  "learning_rate": 1e-05,
43
+ "loss": 0.0006,
44
  "step": 600
45
  },
46
  {
47
+ "epoch": 77.0,
48
  "learning_rate": 1e-05,
49
+ "loss": 0.0004,
50
  "step": 700
51
  },
52
  {
53
+ "epoch": 88.0,
54
  "learning_rate": 1e-05,
55
+ "loss": 0.0003,
56
  "step": 800
57
  },
58
  {
59
+ "epoch": 99.0,
60
  "learning_rate": 1e-05,
61
+ "loss": 0.0003,
62
  "step": 900
63
  },
64
  {
65
+ "epoch": 111.0,
66
  "learning_rate": 1e-05,
67
+ "loss": 0.0002,
68
  "step": 1000
69
  },
70
  {
71
+ "epoch": 111.0,
72
+ "eval_loss": 0.21552081406116486,
73
+ "eval_runtime": 10.773,
74
+ "eval_samples_per_second": 1.671,
75
+ "eval_steps_per_second": 0.093,
76
+ "eval_wer": 9.75609756097561,
77
  "step": 1000
78
  },
79
  {
80
+ "epoch": 122.0,
81
+ "learning_rate": 1e-05,
82
+ "loss": 0.0002,
83
+ "step": 1100
84
+ },
85
+ {
86
+ "epoch": 133.0,
87
+ "learning_rate": 1e-05,
88
+ "loss": 0.0002,
89
+ "step": 1200
90
+ },
91
+ {
92
+ "epoch": 144.0,
93
+ "learning_rate": 1e-05,
94
+ "loss": 0.0001,
95
+ "step": 1300
96
+ },
97
+ {
98
+ "epoch": 155.0,
99
+ "learning_rate": 1e-05,
100
+ "loss": 0.0001,
101
+ "step": 1400
102
+ },
103
+ {
104
+ "epoch": 166.0,
105
+ "learning_rate": 1e-05,
106
+ "loss": 0.0001,
107
+ "step": 1500
108
+ },
109
+ {
110
+ "epoch": 177.0,
111
+ "learning_rate": 1e-05,
112
+ "loss": 0.0001,
113
+ "step": 1600
114
+ },
115
+ {
116
+ "epoch": 188.0,
117
+ "learning_rate": 1e-05,
118
+ "loss": 0.0001,
119
+ "step": 1700
120
+ },
121
+ {
122
+ "epoch": 199.0,
123
+ "learning_rate": 1e-05,
124
+ "loss": 0.0001,
125
+ "step": 1800
126
+ },
127
+ {
128
+ "epoch": 211.0,
129
+ "learning_rate": 1e-05,
130
+ "loss": 0.0001,
131
+ "step": 1900
132
+ },
133
+ {
134
+ "epoch": 222.0,
135
+ "learning_rate": 1e-05,
136
+ "loss": 0.0001,
137
+ "step": 2000
138
+ },
139
+ {
140
+ "epoch": 222.0,
141
+ "eval_loss": 0.2447899729013443,
142
+ "eval_runtime": 14.1456,
143
+ "eval_samples_per_second": 1.272,
144
+ "eval_steps_per_second": 0.071,
145
+ "eval_wer": 12.195121951219512,
146
+ "step": 2000
147
+ },
148
+ {
149
+ "epoch": 233.0,
150
+ "learning_rate": 1e-05,
151
+ "loss": 0.0001,
152
+ "step": 2100
153
+ },
154
+ {
155
+ "epoch": 244.0,
156
+ "learning_rate": 1e-05,
157
+ "loss": 0.0001,
158
+ "step": 2200
159
+ },
160
+ {
161
+ "epoch": 255.0,
162
+ "learning_rate": 1e-05,
163
+ "loss": 0.0001,
164
+ "step": 2300
165
+ },
166
+ {
167
+ "epoch": 266.0,
168
+ "learning_rate": 1e-05,
169
+ "loss": 0.0001,
170
+ "step": 2400
171
+ },
172
+ {
173
+ "epoch": 277.0,
174
+ "learning_rate": 1e-05,
175
+ "loss": 0.0,
176
+ "step": 2500
177
+ },
178
+ {
179
+ "epoch": 288.0,
180
+ "learning_rate": 1e-05,
181
+ "loss": 0.0,
182
+ "step": 2600
183
+ },
184
+ {
185
+ "epoch": 299.0,
186
+ "learning_rate": 1e-05,
187
+ "loss": 0.0,
188
+ "step": 2700
189
+ },
190
+ {
191
+ "epoch": 311.0,
192
+ "learning_rate": 1e-05,
193
+ "loss": 0.0,
194
+ "step": 2800
195
+ },
196
+ {
197
+ "epoch": 322.0,
198
+ "learning_rate": 1e-05,
199
+ "loss": 0.0,
200
+ "step": 2900
201
+ },
202
+ {
203
+ "epoch": 333.0,
204
+ "learning_rate": 1e-05,
205
+ "loss": 0.0,
206
+ "step": 3000
207
+ },
208
+ {
209
+ "epoch": 333.0,
210
+ "eval_loss": 0.2674005329608917,
211
+ "eval_runtime": 8.0249,
212
+ "eval_samples_per_second": 2.243,
213
+ "eval_steps_per_second": 0.125,
214
+ "eval_wer": 13.414634146341465,
215
+ "step": 3000
216
+ },
217
+ {
218
+ "epoch": 344.0,
219
+ "learning_rate": 1e-05,
220
+ "loss": 0.0,
221
+ "step": 3100
222
+ },
223
+ {
224
+ "epoch": 355.0,
225
+ "learning_rate": 1e-05,
226
+ "loss": 0.0,
227
+ "step": 3200
228
+ },
229
+ {
230
+ "epoch": 366.0,
231
+ "learning_rate": 1e-05,
232
+ "loss": 0.0,
233
+ "step": 3300
234
+ },
235
+ {
236
+ "epoch": 377.0,
237
+ "learning_rate": 1e-05,
238
+ "loss": 0.0,
239
+ "step": 3400
240
+ },
241
+ {
242
+ "epoch": 388.0,
243
+ "learning_rate": 1e-05,
244
+ "loss": 0.0,
245
+ "step": 3500
246
+ },
247
+ {
248
+ "epoch": 399.0,
249
+ "learning_rate": 1e-05,
250
+ "loss": 0.0,
251
+ "step": 3600
252
+ },
253
+ {
254
+ "epoch": 411.0,
255
+ "learning_rate": 1e-05,
256
+ "loss": 0.0,
257
+ "step": 3700
258
+ },
259
+ {
260
+ "epoch": 422.0,
261
+ "learning_rate": 1e-05,
262
+ "loss": 0.0,
263
+ "step": 3800
264
+ },
265
+ {
266
+ "epoch": 433.0,
267
+ "learning_rate": 1e-05,
268
+ "loss": 0.0,
269
+ "step": 3900
270
+ },
271
+ {
272
+ "epoch": 444.0,
273
+ "learning_rate": 1e-05,
274
+ "loss": 0.0,
275
+ "step": 4000
276
+ },
277
+ {
278
+ "epoch": 444.0,
279
+ "eval_loss": 0.29429247975349426,
280
+ "eval_runtime": 7.7984,
281
+ "eval_samples_per_second": 2.308,
282
+ "eval_steps_per_second": 0.128,
283
+ "eval_wer": 15.853658536585366,
284
+ "step": 4000
285
+ },
286
+ {
287
+ "epoch": 455.0,
288
+ "learning_rate": 1e-05,
289
+ "loss": 0.0,
290
+ "step": 4100
291
+ },
292
+ {
293
+ "epoch": 466.0,
294
+ "learning_rate": 1e-05,
295
+ "loss": 0.0,
296
+ "step": 4200
297
+ },
298
+ {
299
+ "epoch": 477.0,
300
+ "learning_rate": 1e-05,
301
+ "loss": 0.0,
302
+ "step": 4300
303
+ },
304
+ {
305
+ "epoch": 488.0,
306
+ "learning_rate": 1e-05,
307
+ "loss": 0.0,
308
+ "step": 4400
309
+ },
310
+ {
311
+ "epoch": 499.0,
312
+ "learning_rate": 1e-05,
313
+ "loss": 0.0,
314
+ "step": 4500
315
+ },
316
+ {
317
+ "epoch": 511.0,
318
+ "learning_rate": 1e-05,
319
+ "loss": 0.0,
320
+ "step": 4600
321
+ },
322
+ {
323
+ "epoch": 522.0,
324
+ "learning_rate": 1e-05,
325
+ "loss": 0.0,
326
+ "step": 4700
327
+ },
328
+ {
329
+ "epoch": 533.0,
330
+ "learning_rate": 1e-05,
331
+ "loss": 0.0,
332
+ "step": 4800
333
+ },
334
+ {
335
+ "epoch": 544.0,
336
+ "learning_rate": 1e-05,
337
+ "loss": 0.0,
338
+ "step": 4900
339
+ },
340
+ {
341
+ "epoch": 555.0,
342
+ "learning_rate": 1e-05,
343
+ "loss": 0.0,
344
+ "step": 5000
345
+ },
346
+ {
347
+ "epoch": 555.0,
348
+ "eval_loss": 0.31815305352211,
349
+ "eval_runtime": 7.3177,
350
+ "eval_samples_per_second": 2.46,
351
+ "eval_steps_per_second": 0.137,
352
+ "eval_wer": 17.073170731707318,
353
+ "step": 5000
354
+ },
355
+ {
356
+ "epoch": 566.0,
357
+ "learning_rate": 1e-05,
358
+ "loss": 0.0,
359
+ "step": 5100
360
+ },
361
+ {
362
+ "epoch": 577.0,
363
+ "learning_rate": 1e-05,
364
+ "loss": 0.0,
365
+ "step": 5200
366
+ },
367
+ {
368
+ "epoch": 588.0,
369
+ "learning_rate": 1e-05,
370
+ "loss": 0.0,
371
+ "step": 5300
372
+ },
373
+ {
374
+ "epoch": 599.0,
375
+ "learning_rate": 1e-05,
376
+ "loss": 0.0,
377
+ "step": 5400
378
+ },
379
+ {
380
+ "epoch": 611.0,
381
+ "learning_rate": 1e-05,
382
+ "loss": 0.0,
383
+ "step": 5500
384
+ },
385
+ {
386
+ "epoch": 622.0,
387
+ "learning_rate": 1e-05,
388
+ "loss": 0.0,
389
+ "step": 5600
390
+ },
391
+ {
392
+ "epoch": 633.0,
393
+ "learning_rate": 1e-05,
394
+ "loss": 0.0,
395
+ "step": 5700
396
+ },
397
+ {
398
+ "epoch": 644.0,
399
+ "learning_rate": 1e-05,
400
+ "loss": 0.0,
401
+ "step": 5800
402
+ },
403
+ {
404
+ "epoch": 655.0,
405
+ "learning_rate": 1e-05,
406
+ "loss": 0.0,
407
+ "step": 5900
408
+ },
409
+ {
410
+ "epoch": 666.0,
411
+ "learning_rate": 1e-05,
412
+ "loss": 0.0,
413
+ "step": 6000
414
+ },
415
+ {
416
+ "epoch": 666.0,
417
+ "eval_loss": 0.35010817646980286,
418
+ "eval_runtime": 7.7729,
419
+ "eval_samples_per_second": 2.316,
420
+ "eval_steps_per_second": 0.129,
421
+ "eval_wer": 18.902439024390244,
422
+ "step": 6000
423
+ },
424
+ {
425
+ "epoch": 677.0,
426
+ "learning_rate": 1e-05,
427
+ "loss": 0.0,
428
+ "step": 6100
429
+ },
430
+ {
431
+ "epoch": 688.0,
432
+ "learning_rate": 1e-05,
433
+ "loss": 0.0,
434
+ "step": 6200
435
+ },
436
+ {
437
+ "epoch": 699.0,
438
+ "learning_rate": 1e-05,
439
+ "loss": 0.0,
440
+ "step": 6300
441
+ },
442
+ {
443
+ "epoch": 711.0,
444
+ "learning_rate": 1e-05,
445
+ "loss": 0.0,
446
+ "step": 6400
447
+ },
448
+ {
449
+ "epoch": 722.0,
450
+ "learning_rate": 1e-05,
451
+ "loss": 0.0,
452
+ "step": 6500
453
+ },
454
+ {
455
+ "epoch": 733.0,
456
+ "learning_rate": 1e-05,
457
+ "loss": 0.0,
458
+ "step": 6600
459
+ },
460
+ {
461
+ "epoch": 744.0,
462
+ "learning_rate": 1e-05,
463
+ "loss": 0.0,
464
+ "step": 6700
465
+ },
466
+ {
467
+ "epoch": 755.0,
468
+ "learning_rate": 1e-05,
469
+ "loss": 0.0,
470
+ "step": 6800
471
+ },
472
+ {
473
+ "epoch": 766.0,
474
+ "learning_rate": 1e-05,
475
+ "loss": 0.0,
476
+ "step": 6900
477
+ },
478
+ {
479
+ "epoch": 777.0,
480
+ "learning_rate": 1e-05,
481
+ "loss": 0.0,
482
+ "step": 7000
483
+ },
484
+ {
485
+ "epoch": 777.0,
486
+ "eval_loss": 0.37315306067466736,
487
+ "eval_runtime": 8.5166,
488
+ "eval_samples_per_second": 2.114,
489
+ "eval_steps_per_second": 0.117,
490
+ "eval_wer": 16.463414634146343,
491
+ "step": 7000
492
+ },
493
+ {
494
+ "epoch": 788.0,
495
+ "learning_rate": 1e-05,
496
+ "loss": 0.0,
497
+ "step": 7100
498
+ },
499
+ {
500
+ "epoch": 799.0,
501
+ "learning_rate": 1e-05,
502
+ "loss": 0.0,
503
+ "step": 7200
504
+ },
505
+ {
506
+ "epoch": 811.0,
507
+ "learning_rate": 1e-05,
508
+ "loss": 0.0,
509
+ "step": 7300
510
+ },
511
+ {
512
+ "epoch": 822.0,
513
+ "learning_rate": 1e-05,
514
+ "loss": 0.0,
515
+ "step": 7400
516
+ },
517
+ {
518
+ "epoch": 833.0,
519
+ "learning_rate": 1e-05,
520
+ "loss": 0.0,
521
+ "step": 7500
522
+ },
523
+ {
524
+ "epoch": 844.0,
525
+ "learning_rate": 1e-05,
526
+ "loss": 0.0,
527
+ "step": 7600
528
+ },
529
+ {
530
+ "epoch": 855.0,
531
+ "learning_rate": 1e-05,
532
+ "loss": 0.0,
533
+ "step": 7700
534
+ },
535
+ {
536
+ "epoch": 866.0,
537
+ "learning_rate": 1e-05,
538
+ "loss": 0.0,
539
+ "step": 7800
540
+ },
541
+ {
542
+ "epoch": 877.0,
543
+ "learning_rate": 1e-05,
544
+ "loss": 0.0,
545
+ "step": 7900
546
+ },
547
+ {
548
+ "epoch": 888.0,
549
+ "learning_rate": 1e-05,
550
+ "loss": 0.0,
551
+ "step": 8000
552
+ },
553
+ {
554
+ "epoch": 888.0,
555
+ "eval_loss": 0.4024837911128998,
556
+ "eval_runtime": 8.2162,
557
+ "eval_samples_per_second": 2.191,
558
+ "eval_steps_per_second": 0.122,
559
+ "eval_wer": 17.073170731707318,
560
+ "step": 8000
561
+ },
562
+ {
563
+ "epoch": 899.0,
564
+ "learning_rate": 1e-05,
565
+ "loss": 0.0,
566
+ "step": 8100
567
+ },
568
+ {
569
+ "epoch": 911.0,
570
+ "learning_rate": 1e-05,
571
+ "loss": 0.0,
572
+ "step": 8200
573
+ },
574
+ {
575
+ "epoch": 922.0,
576
+ "learning_rate": 1e-05,
577
+ "loss": 0.0,
578
+ "step": 8300
579
+ },
580
+ {
581
+ "epoch": 933.0,
582
+ "learning_rate": 1e-05,
583
+ "loss": 0.0,
584
+ "step": 8400
585
+ },
586
+ {
587
+ "epoch": 944.0,
588
+ "learning_rate": 1e-05,
589
+ "loss": 0.0,
590
+ "step": 8500
591
+ },
592
+ {
593
+ "epoch": 955.0,
594
+ "learning_rate": 1e-05,
595
+ "loss": 0.0,
596
+ "step": 8600
597
+ },
598
+ {
599
+ "epoch": 966.0,
600
+ "learning_rate": 1e-05,
601
+ "loss": 0.0,
602
+ "step": 8700
603
+ },
604
+ {
605
+ "epoch": 977.0,
606
+ "learning_rate": 1e-05,
607
+ "loss": 0.0,
608
+ "step": 8800
609
+ },
610
+ {
611
+ "epoch": 988.0,
612
+ "learning_rate": 1e-05,
613
+ "loss": 0.0,
614
+ "step": 8900
615
+ },
616
+ {
617
+ "epoch": 999.0,
618
+ "learning_rate": 1e-05,
619
+ "loss": 0.0,
620
+ "step": 9000
621
+ },
622
+ {
623
+ "epoch": 999.0,
624
+ "eval_loss": 0.4178398847579956,
625
+ "eval_runtime": 8.2617,
626
+ "eval_samples_per_second": 2.179,
627
+ "eval_steps_per_second": 0.121,
628
+ "eval_wer": 20.121951219512198,
629
+ "step": 9000
630
+ },
631
+ {
632
+ "epoch": 1011.0,
633
+ "learning_rate": 1e-05,
634
+ "loss": 0.0,
635
+ "step": 9100
636
+ },
637
+ {
638
+ "epoch": 1022.0,
639
+ "learning_rate": 1e-05,
640
+ "loss": 0.0,
641
+ "step": 9200
642
+ },
643
+ {
644
+ "epoch": 1033.0,
645
+ "learning_rate": 1e-05,
646
+ "loss": 0.0,
647
+ "step": 9300
648
+ },
649
+ {
650
+ "epoch": 1044.0,
651
+ "learning_rate": 1e-05,
652
+ "loss": 0.0,
653
+ "step": 9400
654
+ },
655
+ {
656
+ "epoch": 1055.0,
657
+ "learning_rate": 1e-05,
658
+ "loss": 0.0,
659
+ "step": 9500
660
+ },
661
+ {
662
+ "epoch": 1066.0,
663
+ "learning_rate": 1e-05,
664
+ "loss": 0.0,
665
+ "step": 9600
666
+ },
667
+ {
668
+ "epoch": 1077.0,
669
+ "learning_rate": 1e-05,
670
+ "loss": 0.0,
671
+ "step": 9700
672
+ },
673
+ {
674
+ "epoch": 1088.0,
675
+ "learning_rate": 1e-05,
676
+ "loss": 0.0,
677
+ "step": 9800
678
+ },
679
+ {
680
+ "epoch": 1099.0,
681
+ "learning_rate": 1e-05,
682
+ "loss": 0.0,
683
+ "step": 9900
684
+ },
685
+ {
686
+ "epoch": 1111.0,
687
+ "learning_rate": 1e-05,
688
+ "loss": 0.0,
689
+ "step": 10000
690
+ },
691
+ {
692
+ "epoch": 1111.0,
693
+ "eval_loss": 0.43846404552459717,
694
+ "eval_runtime": 7.9746,
695
+ "eval_samples_per_second": 2.257,
696
+ "eval_steps_per_second": 0.125,
697
+ "eval_wer": 17.073170731707318,
698
+ "step": 10000
699
+ },
700
+ {
701
+ "epoch": 1111.0,
702
+ "step": 10000,
703
+ "total_flos": 1.960224747945984e+19,
704
+ "train_loss": 0.007888052637434157,
705
+ "train_runtime": 66285.4349,
706
+ "train_samples_per_second": 4.828,
707
+ "train_steps_per_second": 0.151
708
  }
709
  ],
710
+ "max_steps": 10000,
711
  "num_train_epochs": 9223372036854775807,
712
+ "total_flos": 1.960224747945984e+19,
713
  "trial_name": null,
714
  "trial_params": null
715
  }