Daniil Larionov commited on
Commit
f5ec177
1 Parent(s): db4a092

End of training

Browse files
all_results.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "epoch": 10.0,
3
  "eval_accuracy": 0.9306930899620056,
4
- "eval_f1": 0.93671679197995,
5
- "eval_loss": 0.41272762417793274,
6
- "eval_runtime": 0.4653,
7
  "eval_samples": 101,
8
- "eval_samples_per_second": 217.085,
9
- "eval_steps_per_second": 27.942,
10
- "train_loss": 0.13977860778839768,
11
- "train_runtime": 198.4818,
12
  "train_samples": 908,
13
- "train_samples_per_second": 45.747,
14
- "train_steps_per_second": 2.872
15
  }
 
1
  {
2
  "epoch": 10.0,
3
  "eval_accuracy": 0.9306930899620056,
4
+ "eval_f1": 0.9582299421009098,
5
+ "eval_loss": 0.34674331545829773,
6
+ "eval_runtime": 0.4903,
7
  "eval_samples": 101,
8
+ "eval_samples_per_second": 206.006,
9
+ "eval_steps_per_second": 26.516,
10
+ "train_loss": 0.1306122770016245,
11
+ "train_runtime": 204.1571,
12
  "train_samples": 908,
13
+ "train_samples_per_second": 44.476,
14
+ "train_steps_per_second": 2.792
15
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 10.0,
3
- "eval_f1": 0.93671679197995,
4
- "eval_loss": 0.41272762417793274,
5
- "eval_runtime": 0.4653,
6
  "eval_samples": 101,
7
- "eval_samples_per_second": 217.085,
8
- "eval_steps_per_second": 27.942
9
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_f1": 0.9582299421009098,
4
+ "eval_loss": 0.34674331545829773,
5
+ "eval_runtime": 0.4903,
6
  "eval_samples": 101,
7
+ "eval_samples_per_second": 206.006,
8
+ "eval_steps_per_second": 26.516
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d808456fa214046393e22744d89134969e94d58b5b9ae0abf3c32760104e492e
3
  size 713322669
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9747285b4996ff3a0603abb92da386b2136d2fee245abddf02c308b134c30c9
3
  size 713322669
runs/1636579739.6190994/events.out.tfevents.1636579739.5690110ef819.17607.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137be04d26a574dede66e3c696c1a7fe7fdfa05eb154ef6b0eaf4d036cd90745
3
+ size 4480
runs/events.out.tfevents.1636579739.5690110ef819.17607.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4fefcdd90ffba612b3922aaa6ae907c18d5077a4be025fad91a477fb2baa7c5
3
+ size 25189
runs/events.out.tfevents.1636579996.5690110ef819.17607.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dabefde4bf7af35ee4eb3ac3f95270ee46fb2e5cc5b562612ca7c23f5ee26665
3
+ size 357
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 10.0,
3
- "train_loss": 0.13977860778839768,
4
- "train_runtime": 198.4818,
5
  "train_samples": 908,
6
- "train_samples_per_second": 45.747,
7
- "train_steps_per_second": 2.872
8
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "train_loss": 0.1306122770016245,
4
+ "train_runtime": 204.1571,
5
  "train_samples": 908,
6
+ "train_samples_per_second": 44.476,
7
+ "train_steps_per_second": 2.792
8
  }
trainer_state.json CHANGED
@@ -10,685 +10,685 @@
10
  {
11
  "epoch": 0.02,
12
  "learning_rate": 1.4285714285714286e-06,
13
- "loss": 1.0367,
14
  "step": 1
15
  },
16
  {
17
  "epoch": 0.09,
18
  "learning_rate": 7.142857142857143e-06,
19
- "loss": 1.098,
20
  "step": 5
21
  },
22
  {
23
  "epoch": 0.18,
24
  "learning_rate": 1.4285714285714285e-05,
25
- "loss": 0.9615,
26
  "step": 10
27
  },
28
  {
29
  "epoch": 0.26,
30
  "learning_rate": 2.1428571428571428e-05,
31
- "loss": 0.8549,
32
  "step": 15
33
  },
34
  {
35
  "epoch": 0.35,
36
  "learning_rate": 2.857142857142857e-05,
37
- "loss": 0.7821,
38
  "step": 20
39
  },
40
  {
41
  "epoch": 0.44,
42
  "learning_rate": 3.571428571428572e-05,
43
- "loss": 0.7201,
44
  "step": 25
45
  },
46
  {
47
  "epoch": 0.53,
48
  "learning_rate": 4.2857142857142856e-05,
49
- "loss": 0.7456,
50
  "step": 30
51
  },
52
  {
53
  "epoch": 0.61,
54
  "learning_rate": 5e-05,
55
- "loss": 0.7142,
56
  "step": 35
57
  },
58
  {
59
  "epoch": 0.7,
60
  "learning_rate": 4.998922515567496e-05,
61
- "loss": 0.7209,
62
  "step": 40
63
  },
64
  {
65
  "epoch": 0.79,
66
  "learning_rate": 4.995690991048146e-05,
67
- "loss": 0.6287,
68
  "step": 45
69
  },
70
  {
71
  "epoch": 0.88,
72
  "learning_rate": 4.99030821197584e-05,
73
- "loss": 0.5931,
74
  "step": 50
75
  },
76
  {
77
  "epoch": 0.96,
78
  "learning_rate": 4.982778818239101e-05,
79
- "loss": 0.3712,
80
  "step": 55
81
  },
82
  {
83
  "epoch": 1.0,
84
- "eval_f1": 0.8771697070204532,
85
- "eval_loss": 0.31964054703712463,
86
- "eval_runtime": 0.7969,
87
- "eval_samples_per_second": 126.74,
88
- "eval_steps_per_second": 16.313,
89
  "step": 57
90
  },
91
  {
92
  "epoch": 1.05,
93
  "learning_rate": 4.97310930008156e-05,
94
- "loss": 0.2417,
95
  "step": 60
96
  },
97
  {
98
  "epoch": 1.14,
99
  "learning_rate": 4.961307992507443e-05,
100
- "loss": 0.479,
101
  "step": 65
102
  },
103
  {
104
  "epoch": 1.23,
105
  "learning_rate": 4.947385068096907e-05,
106
- "loss": 0.3856,
107
  "step": 70
108
  },
109
  {
110
  "epoch": 1.32,
111
  "learning_rate": 4.9313525282373974e-05,
112
- "loss": 0.4473,
113
  "step": 75
114
  },
115
  {
116
  "epoch": 1.4,
117
  "learning_rate": 4.9132241927786035e-05,
118
- "loss": 0.3996,
119
  "step": 80
120
  },
121
  {
122
  "epoch": 1.49,
123
  "learning_rate": 4.893015688119921e-05,
124
- "loss": 0.3493,
125
  "step": 85
126
  },
127
  {
128
  "epoch": 1.58,
129
  "learning_rate": 4.870744433740688e-05,
130
- "loss": 0.2517,
131
  "step": 90
132
  },
133
  {
134
  "epoch": 1.67,
135
  "learning_rate": 4.8464296271848155e-05,
136
- "loss": 0.2712,
137
  "step": 95
138
  },
139
  {
140
  "epoch": 1.75,
141
  "learning_rate": 4.8200922275127355e-05,
142
- "loss": 0.1581,
143
  "step": 100
144
  },
145
  {
146
  "epoch": 1.84,
147
  "learning_rate": 4.7917549372349616e-05,
148
- "loss": 0.4589,
149
  "step": 105
150
  },
151
  {
152
  "epoch": 1.93,
153
  "learning_rate": 4.761442182742799e-05,
154
- "loss": 0.1617,
155
  "step": 110
156
  },
157
  {
158
  "epoch": 2.0,
159
- "eval_f1": 0.892094017094017,
160
- "eval_loss": 0.29778197407722473,
161
- "eval_runtime": 0.4586,
162
- "eval_samples_per_second": 220.238,
163
- "eval_steps_per_second": 28.347,
164
  "step": 114
165
  },
166
  {
167
  "epoch": 2.02,
168
  "learning_rate": 4.7291800932531064e-05,
169
- "loss": 0.327,
170
  "step": 115
171
  },
172
  {
173
  "epoch": 2.11,
174
  "learning_rate": 4.694996478285231e-05,
175
- "loss": 0.1373,
176
  "step": 120
177
  },
178
  {
179
  "epoch": 2.19,
180
  "learning_rate": 4.6589208036895535e-05,
181
- "loss": 0.1583,
182
  "step": 125
183
  },
184
  {
185
  "epoch": 2.28,
186
  "learning_rate": 4.620984166248288e-05,
187
- "loss": 0.1642,
188
  "step": 130
189
  },
190
  {
191
  "epoch": 2.37,
192
  "learning_rate": 4.581219266870446e-05,
193
- "loss": 0.126,
194
  "step": 135
195
  },
196
  {
197
  "epoch": 2.46,
198
  "learning_rate": 4.53966038240406e-05,
199
- "loss": 0.1036,
200
  "step": 140
201
  },
202
  {
203
  "epoch": 2.54,
204
  "learning_rate": 4.496343336089965e-05,
205
- "loss": 0.0361,
206
  "step": 145
207
  },
208
  {
209
  "epoch": 2.63,
210
  "learning_rate": 4.4513054666826146e-05,
211
- "loss": 0.1544,
212
  "step": 150
213
  },
214
  {
215
  "epoch": 2.72,
216
  "learning_rate": 4.4045855962645363e-05,
217
- "loss": 0.0069,
218
  "step": 155
219
  },
220
  {
221
  "epoch": 2.81,
222
  "learning_rate": 4.3562239967821805e-05,
223
- "loss": 0.1332,
224
  "step": 160
225
  },
226
  {
227
  "epoch": 2.89,
228
  "learning_rate": 4.306262355332006e-05,
229
- "loss": 0.4542,
230
  "step": 165
231
  },
232
  {
233
  "epoch": 2.98,
234
  "learning_rate": 4.254743738226721e-05,
235
- "loss": 0.2084,
236
  "step": 170
237
  },
238
  {
239
  "epoch": 3.0,
240
- "eval_f1": 0.95822994210091,
241
- "eval_loss": 0.19439974427223206,
242
- "eval_runtime": 1.7156,
243
- "eval_samples_per_second": 58.872,
244
- "eval_steps_per_second": 7.578,
245
  "step": 171
246
  },
247
  {
248
  "epoch": 3.07,
249
  "learning_rate": 4.201712553872658e-05,
250
- "loss": 0.0252,
251
  "step": 175
252
  },
253
  {
254
  "epoch": 3.16,
255
  "learning_rate": 4.147214514490278e-05,
256
- "loss": 0.0166,
257
  "step": 180
258
  },
259
  {
260
  "epoch": 3.25,
261
  "learning_rate": 4.0912965967108125e-05,
262
- "loss": 0.0085,
263
  "step": 185
264
  },
265
  {
266
  "epoch": 3.33,
267
  "learning_rate": 4.034007001082985e-05,
268
- "loss": 0.0824,
269
  "step": 190
270
  },
271
  {
272
  "epoch": 3.42,
273
  "learning_rate": 3.975395110524742e-05,
274
- "loss": 0.1629,
275
  "step": 195
276
  },
277
  {
278
  "epoch": 3.51,
279
  "learning_rate": 3.9155114477557933e-05,
280
- "loss": 0.0485,
281
  "step": 200
282
  },
283
  {
284
  "epoch": 3.6,
285
  "learning_rate": 3.854407631747654e-05,
286
- "loss": 0.0384,
287
  "step": 205
288
  },
289
  {
290
  "epoch": 3.68,
291
  "learning_rate": 3.792136333228735e-05,
292
- "loss": 0.1495,
293
  "step": 210
294
  },
295
  {
296
  "epoch": 3.77,
297
  "learning_rate": 3.728751229282836e-05,
298
- "loss": 0.0615,
299
  "step": 215
300
  },
301
  {
302
  "epoch": 3.86,
303
  "learning_rate": 3.664306957080159e-05,
304
- "loss": 0.2062,
305
  "step": 220
306
  },
307
  {
308
  "epoch": 3.95,
309
  "learning_rate": 3.598859066780754e-05,
310
- "loss": 0.1497,
311
  "step": 225
312
  },
313
  {
314
  "epoch": 4.0,
315
- "eval_f1": 0.93671679197995,
316
- "eval_loss": 0.2901856303215027,
317
- "eval_runtime": 0.4385,
318
- "eval_samples_per_second": 230.348,
319
- "eval_steps_per_second": 29.649,
320
  "step": 228
321
  },
322
  {
323
  "epoch": 4.04,
324
  "learning_rate": 3.5324639736509714e-05,
325
- "loss": 0.0948,
326
  "step": 230
327
  },
328
  {
329
  "epoch": 4.12,
330
  "learning_rate": 3.4651789094342044e-05,
331
- "loss": 0.0662,
332
  "step": 235
333
  },
334
  {
335
  "epoch": 4.21,
336
  "learning_rate": 3.39706187301784e-05,
337
- "loss": 0.1637,
338
  "step": 240
339
  },
340
  {
341
  "epoch": 4.3,
342
  "learning_rate": 3.3281715804389403e-05,
343
- "loss": 0.0159,
344
  "step": 245
345
  },
346
  {
347
  "epoch": 4.39,
348
  "learning_rate": 3.258567414271748e-05,
349
- "loss": 0.0065,
350
  "step": 250
351
  },
352
  {
353
  "epoch": 4.47,
354
  "learning_rate": 3.18830937244065e-05,
355
- "loss": 0.0039,
356
  "step": 255
357
  },
358
  {
359
  "epoch": 4.56,
360
  "learning_rate": 3.117458016502711e-05,
361
- "loss": 0.0063,
362
  "step": 260
363
  },
364
  {
365
  "epoch": 4.65,
366
  "learning_rate": 3.046074419444366e-05,
367
- "loss": 0.0055,
368
  "step": 265
369
  },
370
  {
371
  "epoch": 4.74,
372
  "learning_rate": 2.9742201130372693e-05,
373
- "loss": 0.002,
374
  "step": 270
375
  },
376
  {
377
  "epoch": 4.82,
378
  "learning_rate": 2.901957034798671e-05,
379
- "loss": 0.003,
380
  "step": 275
381
  },
382
  {
383
  "epoch": 4.91,
384
  "learning_rate": 2.8293474746020472e-05,
385
- "loss": 0.0605,
386
  "step": 280
387
  },
388
  {
389
  "epoch": 5.0,
390
  "learning_rate": 2.756454020984009e-05,
391
- "loss": 0.2006,
392
  "step": 285
393
  },
394
  {
395
  "epoch": 5.0,
396
  "eval_f1": 0.9475324675324674,
397
- "eval_loss": 0.3412802219390869,
398
- "eval_runtime": 0.4664,
399
- "eval_samples_per_second": 216.553,
400
- "eval_steps_per_second": 27.873,
401
  "step": 285
402
  },
403
  {
404
  "epoch": 5.09,
405
  "learning_rate": 2.68333950719376e-05,
406
- "loss": 0.0644,
407
  "step": 290
408
  },
409
  {
410
  "epoch": 5.18,
411
  "learning_rate": 2.6100669570316195e-05,
412
- "loss": 0.0029,
413
  "step": 295
414
  },
415
  {
416
  "epoch": 5.26,
417
  "learning_rate": 2.5366995305232916e-05,
418
- "loss": 0.002,
419
  "step": 300
420
  },
421
  {
422
  "epoch": 5.35,
423
  "learning_rate": 2.463300469476709e-05,
424
- "loss": 0.0027,
425
  "step": 305
426
  },
427
  {
428
  "epoch": 5.44,
429
  "learning_rate": 2.3899330429683807e-05,
430
- "loss": 0.1243,
431
  "step": 310
432
  },
433
  {
434
  "epoch": 5.53,
435
  "learning_rate": 2.3166604928062406e-05,
436
- "loss": 0.0174,
437
  "step": 315
438
  },
439
  {
440
  "epoch": 5.61,
441
  "learning_rate": 2.243545979015992e-05,
442
- "loss": 0.0337,
443
  "step": 320
444
  },
445
  {
446
  "epoch": 5.7,
447
  "learning_rate": 2.1706525253979534e-05,
448
- "loss": 0.0016,
449
  "step": 325
450
  },
451
  {
452
  "epoch": 5.79,
453
  "learning_rate": 2.0980429652013297e-05,
454
- "loss": 0.0015,
455
  "step": 330
456
  },
457
  {
458
  "epoch": 5.88,
459
  "learning_rate": 2.025779886962731e-05,
460
- "loss": 0.0014,
461
  "step": 335
462
  },
463
  {
464
  "epoch": 5.96,
465
  "learning_rate": 1.9539255805556344e-05,
466
- "loss": 0.0147,
467
  "step": 340
468
  },
469
  {
470
  "epoch": 6.0,
471
- "eval_f1": 0.9146959459459459,
472
- "eval_loss": 0.4439590275287628,
473
- "eval_runtime": 0.4644,
474
- "eval_samples_per_second": 217.491,
475
- "eval_steps_per_second": 27.994,
476
  "step": 342
477
  },
478
  {
479
  "epoch": 6.05,
480
  "learning_rate": 1.8825419834972902e-05,
481
- "loss": 0.0012,
482
  "step": 345
483
  },
484
  {
485
  "epoch": 6.14,
486
  "learning_rate": 1.811690627559351e-05,
487
- "loss": 0.0696,
488
  "step": 350
489
  },
490
  {
491
  "epoch": 6.23,
492
  "learning_rate": 1.7414325857282526e-05,
493
- "loss": 0.0012,
494
  "step": 355
495
  },
496
  {
497
  "epoch": 6.32,
498
  "learning_rate": 1.6718284195610606e-05,
499
- "loss": 0.0233,
500
  "step": 360
501
  },
502
  {
503
  "epoch": 6.4,
504
  "learning_rate": 1.6029381269821604e-05,
505
- "loss": 0.0205,
506
  "step": 365
507
  },
508
  {
509
  "epoch": 6.49,
510
  "learning_rate": 1.534821090565796e-05,
511
- "loss": 0.001,
512
  "step": 370
513
  },
514
  {
515
  "epoch": 6.58,
516
  "learning_rate": 1.4675360263490295e-05,
517
- "loss": 0.002,
518
  "step": 375
519
  },
520
  {
521
  "epoch": 6.67,
522
  "learning_rate": 1.4011409332192472e-05,
523
- "loss": 0.1466,
524
  "step": 380
525
  },
526
  {
527
  "epoch": 6.75,
528
  "learning_rate": 1.335693042919841e-05,
529
- "loss": 0.001,
530
  "step": 385
531
  },
532
  {
533
  "epoch": 6.84,
534
  "learning_rate": 1.2712487707171645e-05,
535
- "loss": 0.0012,
536
  "step": 390
537
  },
538
  {
539
  "epoch": 6.93,
540
  "learning_rate": 1.2078636667712649e-05,
541
- "loss": 0.0011,
542
  "step": 395
543
  },
544
  {
545
  "epoch": 7.0,
546
- "eval_f1": 0.9475324675324674,
547
- "eval_loss": 0.3331538140773773,
548
- "eval_runtime": 0.4482,
549
- "eval_samples_per_second": 225.335,
550
- "eval_steps_per_second": 29.003,
551
  "step": 399
552
  },
553
  {
554
  "epoch": 7.02,
555
  "learning_rate": 1.1455923682523475e-05,
556
- "loss": 0.0009,
557
  "step": 400
558
  },
559
  {
560
  "epoch": 7.11,
561
  "learning_rate": 1.0844885522442074e-05,
562
- "loss": 0.0013,
563
  "step": 405
564
  },
565
  {
566
  "epoch": 7.19,
567
  "learning_rate": 1.0246048894752589e-05,
568
- "loss": 0.0009,
569
  "step": 410
570
  },
571
  {
572
  "epoch": 7.28,
573
  "learning_rate": 9.659929989170154e-06,
574
- "loss": 0.001,
575
  "step": 415
576
  },
577
  {
578
  "epoch": 7.37,
579
  "learning_rate": 9.087034032891883e-06,
580
- "loss": 0.001,
581
  "step": 420
582
  },
583
  {
584
  "epoch": 7.46,
585
  "learning_rate": 8.527854855097225e-06,
586
- "loss": 0.0008,
587
  "step": 425
588
  },
589
  {
590
  "epoch": 7.54,
591
  "learning_rate": 7.982874461273438e-06,
592
- "loss": 0.0008,
593
  "step": 430
594
  },
595
  {
596
  "epoch": 7.63,
597
  "learning_rate": 7.452562617732794e-06,
598
- "loss": 0.0009,
599
  "step": 435
600
  },
601
  {
602
  "epoch": 7.72,
603
  "learning_rate": 6.93737644667995e-06,
604
- "loss": 0.0006,
605
  "step": 440
606
  },
607
  {
608
  "epoch": 7.81,
609
  "learning_rate": 6.4377600321782e-06,
610
- "loss": 0.0007,
611
  "step": 445
612
  },
613
  {
614
  "epoch": 7.89,
615
  "learning_rate": 5.954144037354645e-06,
616
- "loss": 0.0007,
617
  "step": 450
618
  },
619
  {
620
  "epoch": 7.98,
621
  "learning_rate": 5.486945333173851e-06,
622
- "loss": 0.0008,
623
  "step": 455
624
  },
625
  {
626
  "epoch": 8.0,
627
- "eval_f1": 0.9257742782152232,
628
- "eval_loss": 0.4345126152038574,
629
- "eval_runtime": 0.4442,
630
- "eval_samples_per_second": 227.385,
631
- "eval_steps_per_second": 29.267,
632
  "step": 456
633
  },
634
  {
635
  "epoch": 8.07,
636
  "learning_rate": 5.036566639100351e-06,
637
- "loss": 0.0006,
638
  "step": 460
639
  },
640
  {
641
  "epoch": 8.16,
642
  "learning_rate": 4.603396175959404e-06,
643
- "loss": 0.0006,
644
  "step": 465
645
  },
646
  {
647
  "epoch": 8.25,
648
  "learning_rate": 4.187807331295549e-06,
649
- "loss": 0.0006,
650
  "step": 470
651
  },
652
  {
653
  "epoch": 8.33,
654
  "learning_rate": 3.7901583375171273e-06,
655
- "loss": 0.0069,
656
  "step": 475
657
  },
658
  {
659
  "epoch": 8.42,
660
  "learning_rate": 3.4107919631044732e-06,
661
- "loss": 0.0006,
662
  "step": 480
663
  },
664
  {
665
  "epoch": 8.51,
666
  "learning_rate": 3.0500352171476897e-06,
667
- "loss": 0.0006,
668
  "step": 485
669
  },
670
  {
671
  "epoch": 8.6,
672
  "learning_rate": 2.708199067468939e-06,
673
- "loss": 0.0007,
674
  "step": 490
675
  },
676
  {
677
  "epoch": 8.68,
678
  "learning_rate": 2.385578172572009e-06,
679
- "loss": 0.0006,
680
  "step": 495
681
  },
682
  {
683
  "epoch": 8.77,
684
  "learning_rate": 2.0824506276503897e-06,
685
- "loss": 0.0006,
686
  "step": 500
687
  },
688
  {
689
  "epoch": 8.86,
690
  "learning_rate": 1.7990777248726442e-06,
691
- "loss": 0.0005,
692
  "step": 505
693
  },
694
  {
@@ -699,107 +699,107 @@
699
  },
700
  {
701
  "epoch": 9.0,
702
- "eval_f1": 0.93671679197995,
703
- "eval_loss": 0.4083709418773651,
704
- "eval_runtime": 0.4634,
705
- "eval_samples_per_second": 217.946,
706
- "eval_steps_per_second": 28.053,
707
  "step": 513
708
  },
709
  {
710
  "epoch": 9.04,
711
  "learning_rate": 1.2925556625931173e-06,
712
- "loss": 0.0006,
713
  "step": 515
714
  },
715
  {
716
  "epoch": 9.12,
717
  "learning_rate": 1.0698431188007952e-06,
718
- "loss": 0.0006,
719
  "step": 520
720
  },
721
  {
722
  "epoch": 9.21,
723
  "learning_rate": 8.677580722139672e-07,
724
- "loss": 0.0005,
725
  "step": 525
726
  },
727
  {
728
  "epoch": 9.3,
729
  "learning_rate": 6.864747176260289e-07,
730
- "loss": 0.0006,
731
  "step": 530
732
  },
733
  {
734
  "epoch": 9.39,
735
  "learning_rate": 5.261493190309303e-07,
736
- "loss": 0.0006,
737
  "step": 535
738
  },
739
  {
740
  "epoch": 9.47,
741
  "learning_rate": 3.8692007492557024e-07,
742
- "loss": 0.0005,
743
  "step": 540
744
  },
745
  {
746
  "epoch": 9.56,
747
  "learning_rate": 2.6890699918440676e-07,
748
- "loss": 0.0005,
749
  "step": 545
750
  },
751
  {
752
  "epoch": 9.65,
753
  "learning_rate": 1.7221181760899152e-07,
754
- "loss": 0.0005,
755
  "step": 550
756
  },
757
  {
758
  "epoch": 9.74,
759
  "learning_rate": 9.691788024160376e-08,
760
- "loss": 0.0005,
761
  "step": 555
762
  },
763
  {
764
  "epoch": 9.82,
765
  "learning_rate": 4.3090089518540987e-08,
766
- "loss": 0.0006,
767
  "step": 560
768
  },
769
  {
770
  "epoch": 9.91,
771
  "learning_rate": 1.0774844325039946e-08,
772
- "loss": 0.0005,
773
  "step": 565
774
  },
775
  {
776
  "epoch": 10.0,
777
  "learning_rate": 0.0,
778
- "loss": 0.0005,
779
  "step": 570
780
  },
781
  {
782
  "epoch": 10.0,
783
- "eval_f1": 0.93671679197995,
784
- "eval_loss": 0.41272762417793274,
785
- "eval_runtime": 1.6882,
786
- "eval_samples_per_second": 59.826,
787
- "eval_steps_per_second": 7.7,
788
  "step": 570
789
  },
790
  {
791
  "epoch": 10.0,
792
  "step": 570,
793
- "total_flos": 197328896575272.0,
794
- "train_loss": 0.13977860778839768,
795
- "train_runtime": 198.4818,
796
- "train_samples_per_second": 45.747,
797
- "train_steps_per_second": 2.872
798
  }
799
  ],
800
  "max_steps": 570,
801
  "num_train_epochs": 10,
802
- "total_flos": 197328896575272.0,
803
  "trial_name": null,
804
  "trial_params": null
805
  }
 
10
  {
11
  "epoch": 0.02,
12
  "learning_rate": 1.4285714285714286e-06,
13
+ "loss": 1.0505,
14
  "step": 1
15
  },
16
  {
17
  "epoch": 0.09,
18
  "learning_rate": 7.142857142857143e-06,
19
+ "loss": 1.0492,
20
  "step": 5
21
  },
22
  {
23
  "epoch": 0.18,
24
  "learning_rate": 1.4285714285714285e-05,
25
+ "loss": 0.9748,
26
  "step": 10
27
  },
28
  {
29
  "epoch": 0.26,
30
  "learning_rate": 2.1428571428571428e-05,
31
+ "loss": 0.8762,
32
  "step": 15
33
  },
34
  {
35
  "epoch": 0.35,
36
  "learning_rate": 2.857142857142857e-05,
37
+ "loss": 0.8256,
38
  "step": 20
39
  },
40
  {
41
  "epoch": 0.44,
42
  "learning_rate": 3.571428571428572e-05,
43
+ "loss": 0.7251,
44
  "step": 25
45
  },
46
  {
47
  "epoch": 0.53,
48
  "learning_rate": 4.2857142857142856e-05,
49
+ "loss": 0.7001,
50
  "step": 30
51
  },
52
  {
53
  "epoch": 0.61,
54
  "learning_rate": 5e-05,
55
+ "loss": 0.7778,
56
  "step": 35
57
  },
58
  {
59
  "epoch": 0.7,
60
  "learning_rate": 4.998922515567496e-05,
61
+ "loss": 0.717,
62
  "step": 40
63
  },
64
  {
65
  "epoch": 0.79,
66
  "learning_rate": 4.995690991048146e-05,
67
+ "loss": 0.6061,
68
  "step": 45
69
  },
70
  {
71
  "epoch": 0.88,
72
  "learning_rate": 4.99030821197584e-05,
73
+ "loss": 0.6697,
74
  "step": 50
75
  },
76
  {
77
  "epoch": 0.96,
78
  "learning_rate": 4.982778818239101e-05,
79
+ "loss": 0.5166,
80
  "step": 55
81
  },
82
  {
83
  "epoch": 1.0,
84
+ "eval_f1": 0.8101503759398496,
85
+ "eval_loss": 0.3769623637199402,
86
+ "eval_runtime": 0.4531,
87
+ "eval_samples_per_second": 222.919,
88
+ "eval_steps_per_second": 28.692,
89
  "step": 57
90
  },
91
  {
92
  "epoch": 1.05,
93
  "learning_rate": 4.97310930008156e-05,
94
+ "loss": 0.3785,
95
  "step": 60
96
  },
97
  {
98
  "epoch": 1.14,
99
  "learning_rate": 4.961307992507443e-05,
100
+ "loss": 0.3636,
101
  "step": 65
102
  },
103
  {
104
  "epoch": 1.23,
105
  "learning_rate": 4.947385068096907e-05,
106
+ "loss": 0.2444,
107
  "step": 70
108
  },
109
  {
110
  "epoch": 1.32,
111
  "learning_rate": 4.9313525282373974e-05,
112
+ "loss": 0.3221,
113
  "step": 75
114
  },
115
  {
116
  "epoch": 1.4,
117
  "learning_rate": 4.9132241927786035e-05,
118
+ "loss": 0.2809,
119
  "step": 80
120
  },
121
  {
122
  "epoch": 1.49,
123
  "learning_rate": 4.893015688119921e-05,
124
+ "loss": 0.2881,
125
  "step": 85
126
  },
127
  {
128
  "epoch": 1.58,
129
  "learning_rate": 4.870744433740688e-05,
130
+ "loss": 0.551,
131
  "step": 90
132
  },
133
  {
134
  "epoch": 1.67,
135
  "learning_rate": 4.8464296271848155e-05,
136
+ "loss": 0.3958,
137
  "step": 95
138
  },
139
  {
140
  "epoch": 1.75,
141
  "learning_rate": 4.8200922275127355e-05,
142
+ "loss": 0.2684,
143
  "step": 100
144
  },
145
  {
146
  "epoch": 1.84,
147
  "learning_rate": 4.7917549372349616e-05,
148
+ "loss": 0.2475,
149
  "step": 105
150
  },
151
  {
152
  "epoch": 1.93,
153
  "learning_rate": 4.761442182742799e-05,
154
+ "loss": 0.3798,
155
  "step": 110
156
  },
157
  {
158
  "epoch": 2.0,
159
+ "eval_f1": 0.9373449131513648,
160
+ "eval_loss": 0.1983204036951065,
161
+ "eval_runtime": 0.4749,
162
+ "eval_samples_per_second": 212.673,
163
+ "eval_steps_per_second": 27.374,
164
  "step": 114
165
  },
166
  {
167
  "epoch": 2.02,
168
  "learning_rate": 4.7291800932531064e-05,
169
+ "loss": 0.2115,
170
  "step": 115
171
  },
172
  {
173
  "epoch": 2.11,
174
  "learning_rate": 4.694996478285231e-05,
175
+ "loss": 0.1353,
176
  "step": 120
177
  },
178
  {
179
  "epoch": 2.19,
180
  "learning_rate": 4.6589208036895535e-05,
181
+ "loss": 0.1655,
182
  "step": 125
183
  },
184
  {
185
  "epoch": 2.28,
186
  "learning_rate": 4.620984166248288e-05,
187
+ "loss": 0.0176,
188
  "step": 130
189
  },
190
  {
191
  "epoch": 2.37,
192
  "learning_rate": 4.581219266870446e-05,
193
+ "loss": 0.1215,
194
  "step": 135
195
  },
196
  {
197
  "epoch": 2.46,
198
  "learning_rate": 4.53966038240406e-05,
199
+ "loss": 0.2696,
200
  "step": 140
201
  },
202
  {
203
  "epoch": 2.54,
204
  "learning_rate": 4.496343336089965e-05,
205
+ "loss": 0.133,
206
  "step": 145
207
  },
208
  {
209
  "epoch": 2.63,
210
  "learning_rate": 4.4513054666826146e-05,
211
+ "loss": 0.1062,
212
  "step": 150
213
  },
214
  {
215
  "epoch": 2.72,
216
  "learning_rate": 4.4045855962645363e-05,
217
+ "loss": 0.0457,
218
  "step": 155
219
  },
220
  {
221
  "epoch": 2.81,
222
  "learning_rate": 4.3562239967821805e-05,
223
+ "loss": 0.0962,
224
  "step": 160
225
  },
226
  {
227
  "epoch": 2.89,
228
  "learning_rate": 4.306262355332006e-05,
229
+ "loss": 0.1332,
230
  "step": 165
231
  },
232
  {
233
  "epoch": 2.98,
234
  "learning_rate": 4.254743738226721e-05,
235
+ "loss": 0.141,
236
  "step": 170
237
  },
238
  {
239
  "epoch": 3.0,
240
+ "eval_f1": 0.93671679197995,
241
+ "eval_loss": 0.20440134406089783,
242
+ "eval_runtime": 1.8358,
243
+ "eval_samples_per_second": 55.017,
244
+ "eval_steps_per_second": 7.081,
245
  "step": 171
246
  },
247
  {
248
  "epoch": 3.07,
249
  "learning_rate": 4.201712553872658e-05,
250
+ "loss": 0.0891,
251
  "step": 175
252
  },
253
  {
254
  "epoch": 3.16,
255
  "learning_rate": 4.147214514490278e-05,
256
+ "loss": 0.0163,
257
  "step": 180
258
  },
259
  {
260
  "epoch": 3.25,
261
  "learning_rate": 4.0912965967108125e-05,
262
+ "loss": 0.0076,
263
  "step": 185
264
  },
265
  {
266
  "epoch": 3.33,
267
  "learning_rate": 4.034007001082985e-05,
268
+ "loss": 0.0571,
269
  "step": 190
270
  },
271
  {
272
  "epoch": 3.42,
273
  "learning_rate": 3.975395110524742e-05,
274
+ "loss": 0.0092,
275
  "step": 195
276
  },
277
  {
278
  "epoch": 3.51,
279
  "learning_rate": 3.9155114477557933e-05,
280
+ "loss": 0.0838,
281
  "step": 200
282
  },
283
  {
284
  "epoch": 3.6,
285
  "learning_rate": 3.854407631747654e-05,
286
+ "loss": 0.0844,
287
  "step": 205
288
  },
289
  {
290
  "epoch": 3.68,
291
  "learning_rate": 3.792136333228735e-05,
292
+ "loss": 0.0055,
293
  "step": 210
294
  },
295
  {
296
  "epoch": 3.77,
297
  "learning_rate": 3.728751229282836e-05,
298
+ "loss": 0.0681,
299
  "step": 215
300
  },
301
  {
302
  "epoch": 3.86,
303
  "learning_rate": 3.664306957080159e-05,
304
+ "loss": 0.1278,
305
  "step": 220
306
  },
307
  {
308
  "epoch": 3.95,
309
  "learning_rate": 3.598859066780754e-05,
310
+ "loss": 0.1156,
311
  "step": 225
312
  },
313
  {
314
  "epoch": 4.0,
315
+ "eval_f1": 0.9480292271277143,
316
+ "eval_loss": 0.23232503235340118,
317
+ "eval_runtime": 0.4615,
318
+ "eval_samples_per_second": 218.85,
319
+ "eval_steps_per_second": 28.169,
320
  "step": 228
321
  },
322
  {
323
  "epoch": 4.04,
324
  "learning_rate": 3.5324639736509714e-05,
325
+ "loss": 0.0024,
326
  "step": 230
327
  },
328
  {
329
  "epoch": 4.12,
330
  "learning_rate": 3.4651789094342044e-05,
331
+ "loss": 0.0089,
332
  "step": 235
333
  },
334
  {
335
  "epoch": 4.21,
336
  "learning_rate": 3.39706187301784e-05,
337
+ "loss": 0.0021,
338
  "step": 240
339
  },
340
  {
341
  "epoch": 4.3,
342
  "learning_rate": 3.3281715804389403e-05,
343
+ "loss": 0.0144,
344
  "step": 245
345
  },
346
  {
347
  "epoch": 4.39,
348
  "learning_rate": 3.258567414271748e-05,
349
+ "loss": 0.0048,
350
  "step": 250
351
  },
352
  {
353
  "epoch": 4.47,
354
  "learning_rate": 3.18830937244065e-05,
355
+ "loss": 0.0602,
356
  "step": 255
357
  },
358
  {
359
  "epoch": 4.56,
360
  "learning_rate": 3.117458016502711e-05,
361
+ "loss": 0.0018,
362
  "step": 260
363
  },
364
  {
365
  "epoch": 4.65,
366
  "learning_rate": 3.046074419444366e-05,
367
+ "loss": 0.1578,
368
  "step": 265
369
  },
370
  {
371
  "epoch": 4.74,
372
  "learning_rate": 2.9742201130372693e-05,
373
+ "loss": 0.0016,
374
  "step": 270
375
  },
376
  {
377
  "epoch": 4.82,
378
  "learning_rate": 2.901957034798671e-05,
379
+ "loss": 0.0904,
380
  "step": 275
381
  },
382
  {
383
  "epoch": 4.91,
384
  "learning_rate": 2.8293474746020472e-05,
385
+ "loss": 0.002,
386
  "step": 280
387
  },
388
  {
389
  "epoch": 5.0,
390
  "learning_rate": 2.756454020984009e-05,
391
+ "loss": 0.001,
392
  "step": 285
393
  },
394
  {
395
  "epoch": 5.0,
396
  "eval_f1": 0.9475324675324674,
397
+ "eval_loss": 0.32515278458595276,
398
+ "eval_runtime": 0.4776,
399
+ "eval_samples_per_second": 211.452,
400
+ "eval_steps_per_second": 27.217,
401
  "step": 285
402
  },
403
  {
404
  "epoch": 5.09,
405
  "learning_rate": 2.68333950719376e-05,
406
+ "loss": 0.0594,
407
  "step": 290
408
  },
409
  {
410
  "epoch": 5.18,
411
  "learning_rate": 2.6100669570316195e-05,
412
+ "loss": 0.0015,
413
  "step": 295
414
  },
415
  {
416
  "epoch": 5.26,
417
  "learning_rate": 2.5366995305232916e-05,
418
+ "loss": 0.0016,
419
  "step": 300
420
  },
421
  {
422
  "epoch": 5.35,
423
  "learning_rate": 2.463300469476709e-05,
424
+ "loss": 0.0019,
425
  "step": 305
426
  },
427
  {
428
  "epoch": 5.44,
429
  "learning_rate": 2.3899330429683807e-05,
430
+ "loss": 0.0009,
431
  "step": 310
432
  },
433
  {
434
  "epoch": 5.53,
435
  "learning_rate": 2.3166604928062406e-05,
436
+ "loss": 0.0009,
437
  "step": 315
438
  },
439
  {
440
  "epoch": 5.61,
441
  "learning_rate": 2.243545979015992e-05,
442
+ "loss": 0.0011,
443
  "step": 320
444
  },
445
  {
446
  "epoch": 5.7,
447
  "learning_rate": 2.1706525253979534e-05,
448
+ "loss": 0.0187,
449
  "step": 325
450
  },
451
  {
452
  "epoch": 5.79,
453
  "learning_rate": 2.0980429652013297e-05,
454
+ "loss": 0.0084,
455
  "step": 330
456
  },
457
  {
458
  "epoch": 5.88,
459
  "learning_rate": 2.025779886962731e-05,
460
+ "loss": 0.0052,
461
  "step": 335
462
  },
463
  {
464
  "epoch": 5.96,
465
  "learning_rate": 1.9539255805556344e-05,
466
+ "loss": 0.0022,
467
  "step": 340
468
  },
469
  {
470
  "epoch": 6.0,
471
+ "eval_f1": 0.9582299421009098,
472
+ "eval_loss": 0.297787070274353,
473
+ "eval_runtime": 0.4642,
474
+ "eval_samples_per_second": 217.568,
475
+ "eval_steps_per_second": 28.004,
476
  "step": 342
477
  },
478
  {
479
  "epoch": 6.05,
480
  "learning_rate": 1.8825419834972902e-05,
481
+ "loss": 0.0005,
482
  "step": 345
483
  },
484
  {
485
  "epoch": 6.14,
486
  "learning_rate": 1.811690627559351e-05,
487
+ "loss": 0.0005,
488
  "step": 350
489
  },
490
  {
491
  "epoch": 6.23,
492
  "learning_rate": 1.7414325857282526e-05,
493
+ "loss": 0.0006,
494
  "step": 355
495
  },
496
  {
497
  "epoch": 6.32,
498
  "learning_rate": 1.6718284195610606e-05,
499
+ "loss": 0.0006,
500
  "step": 360
501
  },
502
  {
503
  "epoch": 6.4,
504
  "learning_rate": 1.6029381269821604e-05,
505
+ "loss": 0.0005,
506
  "step": 365
507
  },
508
  {
509
  "epoch": 6.49,
510
  "learning_rate": 1.534821090565796e-05,
511
+ "loss": 0.0005,
512
  "step": 370
513
  },
514
  {
515
  "epoch": 6.58,
516
  "learning_rate": 1.4675360263490295e-05,
517
+ "loss": 0.0004,
518
  "step": 375
519
  },
520
  {
521
  "epoch": 6.67,
522
  "learning_rate": 1.4011409332192472e-05,
523
+ "loss": 0.0005,
524
  "step": 380
525
  },
526
  {
527
  "epoch": 6.75,
528
  "learning_rate": 1.335693042919841e-05,
529
+ "loss": 0.0004,
530
  "step": 385
531
  },
532
  {
533
  "epoch": 6.84,
534
  "learning_rate": 1.2712487707171645e-05,
535
+ "loss": 0.0004,
536
  "step": 390
537
  },
538
  {
539
  "epoch": 6.93,
540
  "learning_rate": 1.2078636667712649e-05,
541
+ "loss": 0.0258,
542
  "step": 395
543
  },
544
  {
545
  "epoch": 7.0,
546
+ "eval_f1": 0.9582299421009098,
547
+ "eval_loss": 0.3218303322792053,
548
+ "eval_runtime": 0.465,
549
+ "eval_samples_per_second": 217.191,
550
+ "eval_steps_per_second": 27.955,
551
  "step": 399
552
  },
553
  {
554
  "epoch": 7.02,
555
  "learning_rate": 1.1455923682523475e-05,
556
+ "loss": 0.0004,
557
  "step": 400
558
  },
559
  {
560
  "epoch": 7.11,
561
  "learning_rate": 1.0844885522442074e-05,
562
+ "loss": 0.0004,
563
  "step": 405
564
  },
565
  {
566
  "epoch": 7.19,
567
  "learning_rate": 1.0246048894752589e-05,
568
+ "loss": 0.0004,
569
  "step": 410
570
  },
571
  {
572
  "epoch": 7.28,
573
  "learning_rate": 9.659929989170154e-06,
574
+ "loss": 0.0004,
575
  "step": 415
576
  },
577
  {
578
  "epoch": 7.37,
579
  "learning_rate": 9.087034032891883e-06,
580
+ "loss": 0.0003,
581
  "step": 420
582
  },
583
  {
584
  "epoch": 7.46,
585
  "learning_rate": 8.527854855097225e-06,
586
+ "loss": 0.0003,
587
  "step": 425
588
  },
589
  {
590
  "epoch": 7.54,
591
  "learning_rate": 7.982874461273438e-06,
592
+ "loss": 0.0003,
593
  "step": 430
594
  },
595
  {
596
  "epoch": 7.63,
597
  "learning_rate": 7.452562617732794e-06,
598
+ "loss": 0.0003,
599
  "step": 435
600
  },
601
  {
602
  "epoch": 7.72,
603
  "learning_rate": 6.93737644667995e-06,
604
+ "loss": 0.0005,
605
  "step": 440
606
  },
607
  {
608
  "epoch": 7.81,
609
  "learning_rate": 6.4377600321782e-06,
610
+ "loss": 0.0003,
611
  "step": 445
612
  },
613
  {
614
  "epoch": 7.89,
615
  "learning_rate": 5.954144037354645e-06,
616
+ "loss": 0.0003,
617
  "step": 450
618
  },
619
  {
620
  "epoch": 7.98,
621
  "learning_rate": 5.486945333173851e-06,
622
+ "loss": 0.0004,
623
  "step": 455
624
  },
625
  {
626
  "epoch": 8.0,
627
+ "eval_f1": 0.9582299421009098,
628
+ "eval_loss": 0.34266912937164307,
629
+ "eval_runtime": 0.4692,
630
+ "eval_samples_per_second": 215.269,
631
+ "eval_steps_per_second": 27.708,
632
  "step": 456
633
  },
634
  {
635
  "epoch": 8.07,
636
  "learning_rate": 5.036566639100351e-06,
637
+ "loss": 0.0003,
638
  "step": 460
639
  },
640
  {
641
  "epoch": 8.16,
642
  "learning_rate": 4.603396175959404e-06,
643
+ "loss": 0.0003,
644
  "step": 465
645
  },
646
  {
647
  "epoch": 8.25,
648
  "learning_rate": 4.187807331295549e-06,
649
+ "loss": 0.0003,
650
  "step": 470
651
  },
652
  {
653
  "epoch": 8.33,
654
  "learning_rate": 3.7901583375171273e-06,
655
+ "loss": 0.0003,
656
  "step": 475
657
  },
658
  {
659
  "epoch": 8.42,
660
  "learning_rate": 3.4107919631044732e-06,
661
+ "loss": 0.0002,
662
  "step": 480
663
  },
664
  {
665
  "epoch": 8.51,
666
  "learning_rate": 3.0500352171476897e-06,
667
+ "loss": 0.0003,
668
  "step": 485
669
  },
670
  {
671
  "epoch": 8.6,
672
  "learning_rate": 2.708199067468939e-06,
673
+ "loss": 0.0003,
674
  "step": 490
675
  },
676
  {
677
  "epoch": 8.68,
678
  "learning_rate": 2.385578172572009e-06,
679
+ "loss": 0.0003,
680
  "step": 495
681
  },
682
  {
683
  "epoch": 8.77,
684
  "learning_rate": 2.0824506276503897e-06,
685
+ "loss": 0.0003,
686
  "step": 500
687
  },
688
  {
689
  "epoch": 8.86,
690
  "learning_rate": 1.7990777248726442e-06,
691
+ "loss": 0.0003,
692
  "step": 505
693
  },
694
  {
 
699
  },
700
  {
701
  "epoch": 9.0,
702
+ "eval_f1": 0.9582299421009098,
703
+ "eval_loss": 0.345493346452713,
704
+ "eval_runtime": 0.4796,
705
+ "eval_samples_per_second": 210.593,
706
+ "eval_steps_per_second": 27.106,
707
  "step": 513
708
  },
709
  {
710
  "epoch": 9.04,
711
  "learning_rate": 1.2925556625931173e-06,
712
+ "loss": 0.0003,
713
  "step": 515
714
  },
715
  {
716
  "epoch": 9.12,
717
  "learning_rate": 1.0698431188007952e-06,
718
+ "loss": 0.0003,
719
  "step": 520
720
  },
721
  {
722
  "epoch": 9.21,
723
  "learning_rate": 8.677580722139672e-07,
724
+ "loss": 0.0002,
725
  "step": 525
726
  },
727
  {
728
  "epoch": 9.3,
729
  "learning_rate": 6.864747176260289e-07,
730
+ "loss": 0.0002,
731
  "step": 530
732
  },
733
  {
734
  "epoch": 9.39,
735
  "learning_rate": 5.261493190309303e-07,
736
+ "loss": 0.0003,
737
  "step": 535
738
  },
739
  {
740
  "epoch": 9.47,
741
  "learning_rate": 3.8692007492557024e-07,
742
+ "loss": 0.0003,
743
  "step": 540
744
  },
745
  {
746
  "epoch": 9.56,
747
  "learning_rate": 2.6890699918440676e-07,
748
+ "loss": 0.0003,
749
  "step": 545
750
  },
751
  {
752
  "epoch": 9.65,
753
  "learning_rate": 1.7221181760899152e-07,
754
+ "loss": 0.0002,
755
  "step": 550
756
  },
757
  {
758
  "epoch": 9.74,
759
  "learning_rate": 9.691788024160376e-08,
760
+ "loss": 0.0003,
761
  "step": 555
762
  },
763
  {
764
  "epoch": 9.82,
765
  "learning_rate": 4.3090089518540987e-08,
766
+ "loss": 0.0003,
767
  "step": 560
768
  },
769
  {
770
  "epoch": 9.91,
771
  "learning_rate": 1.0774844325039946e-08,
772
+ "loss": 0.0002,
773
  "step": 565
774
  },
775
  {
776
  "epoch": 10.0,
777
  "learning_rate": 0.0,
778
+ "loss": 0.0002,
779
  "step": 570
780
  },
781
  {
782
  "epoch": 10.0,
783
+ "eval_f1": 0.9582299421009098,
784
+ "eval_loss": 0.34674331545829773,
785
+ "eval_runtime": 1.7746,
786
+ "eval_samples_per_second": 56.914,
787
+ "eval_steps_per_second": 7.326,
788
  "step": 570
789
  },
790
  {
791
  "epoch": 10.0,
792
  "step": 570,
793
+ "total_flos": 199916863707456.0,
794
+ "train_loss": 0.1306122770016245,
795
+ "train_runtime": 204.1571,
796
+ "train_samples_per_second": 44.476,
797
+ "train_steps_per_second": 2.792
798
  }
799
  ],
800
  "max_steps": 570,
801
  "num_train_epochs": 10,
802
+ "total_flos": 199916863707456.0,
803
  "trial_name": null,
804
  "trial_params": null
805
  }