dima806 commited on
Commit
1d53a4b
1 Parent(s): ac79bb8

Delete checkpoint-756

Browse files
checkpoint-756/config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "_name_or_path": "distilbert-base-cased",
3
- "activation": "gelu",
4
- "architectures": [
5
- "DistilBertForSequenceClassification"
6
- ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
11
- "id2label": {
12
- "0": "NO DISASTER",
13
- "1": "DISASTER"
14
- },
15
- "initializer_range": 0.02,
16
- "max_position_embeddings": 512,
17
- "model_type": "distilbert",
18
- "n_heads": 12,
19
- "n_layers": 6,
20
- "output_past": true,
21
- "pad_token_id": 0,
22
- "problem_type": "single_label_classification",
23
- "qa_dropout": 0.1,
24
- "seq_classif_dropout": 0.2,
25
- "sinusoidal_pos_embds": false,
26
- "tie_weights_": true,
27
- "torch_dtype": "float32",
28
- "transformers_version": "4.30.2",
29
- "vocab_size": 28996
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-756/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:efb10dfe5299689219604d3ceb372df330c6967d53616523135abf5362e11545
3
- size 526325317
 
 
 
 
checkpoint-756/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cc9d288e32bb2c554a28d860a0e1375a9fdcb015fa51cd40a734d4e85f60243
3
- size 263167661
 
 
 
 
checkpoint-756/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d8bd453b05b9ce290bca55689a8177f0cd66b36710d7c98b9d0a0aadab0fba3
3
- size 14575
 
 
 
 
checkpoint-756/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e47d8e09f616bdcb80a8dbdbfea8a723fbdfff60b864ffebf36d87a5b43372b0
3
- size 627
 
 
 
 
checkpoint-756/trainer_state.json DELETED
@@ -1,4570 +0,0 @@
1
- {
2
- "best_metric": 0.40209120512008667,
3
- "best_model_checkpoint": "./disaster-tweet-distilbert-classification/checkpoint-378",
4
- "epoch": 2.0,
5
- "global_step": 756,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.0,
12
- "learning_rate": 1.0000000000000002e-06,
13
- "loss": 0.7503,
14
- "step": 1
15
- },
16
- {
17
- "epoch": 0.01,
18
- "learning_rate": 2.0000000000000003e-06,
19
- "loss": 0.7789,
20
- "step": 2
21
- },
22
- {
23
- "epoch": 0.01,
24
- "learning_rate": 3e-06,
25
- "loss": 0.7344,
26
- "step": 3
27
- },
28
- {
29
- "epoch": 0.01,
30
- "learning_rate": 4.000000000000001e-06,
31
- "loss": 0.7709,
32
- "step": 4
33
- },
34
- {
35
- "epoch": 0.01,
36
- "learning_rate": 5e-06,
37
- "loss": 0.6884,
38
- "step": 5
39
- },
40
- {
41
- "epoch": 0.02,
42
- "learning_rate": 6e-06,
43
- "loss": 0.7087,
44
- "step": 6
45
- },
46
- {
47
- "epoch": 0.02,
48
- "learning_rate": 7.000000000000001e-06,
49
- "loss": 0.6655,
50
- "step": 7
51
- },
52
- {
53
- "epoch": 0.02,
54
- "learning_rate": 8.000000000000001e-06,
55
- "loss": 0.6978,
56
- "step": 8
57
- },
58
- {
59
- "epoch": 0.02,
60
- "learning_rate": 9e-06,
61
- "loss": 0.7435,
62
- "step": 9
63
- },
64
- {
65
- "epoch": 0.03,
66
- "learning_rate": 1e-05,
67
- "loss": 0.719,
68
- "step": 10
69
- },
70
- {
71
- "epoch": 0.03,
72
- "learning_rate": 1.1000000000000001e-05,
73
- "loss": 0.7129,
74
- "step": 11
75
- },
76
- {
77
- "epoch": 0.03,
78
- "learning_rate": 1.2e-05,
79
- "loss": 0.7249,
80
- "step": 12
81
- },
82
- {
83
- "epoch": 0.03,
84
- "learning_rate": 1.3000000000000001e-05,
85
- "loss": 0.7436,
86
- "step": 13
87
- },
88
- {
89
- "epoch": 0.04,
90
- "learning_rate": 1.4000000000000001e-05,
91
- "loss": 0.6886,
92
- "step": 14
93
- },
94
- {
95
- "epoch": 0.04,
96
- "learning_rate": 1.5e-05,
97
- "loss": 0.702,
98
- "step": 15
99
- },
100
- {
101
- "epoch": 0.04,
102
- "learning_rate": 1.6000000000000003e-05,
103
- "loss": 0.7105,
104
- "step": 16
105
- },
106
- {
107
- "epoch": 0.04,
108
- "learning_rate": 1.7000000000000003e-05,
109
- "loss": 0.6709,
110
- "step": 17
111
- },
112
- {
113
- "epoch": 0.05,
114
- "learning_rate": 1.8e-05,
115
- "loss": 0.6767,
116
- "step": 18
117
- },
118
- {
119
- "epoch": 0.05,
120
- "learning_rate": 1.9e-05,
121
- "loss": 0.6784,
122
- "step": 19
123
- },
124
- {
125
- "epoch": 0.05,
126
- "learning_rate": 2e-05,
127
- "loss": 0.7016,
128
- "step": 20
129
- },
130
- {
131
- "epoch": 0.06,
132
- "learning_rate": 2.1e-05,
133
- "loss": 0.6308,
134
- "step": 21
135
- },
136
- {
137
- "epoch": 0.06,
138
- "learning_rate": 2.2000000000000003e-05,
139
- "loss": 0.645,
140
- "step": 22
141
- },
142
- {
143
- "epoch": 0.06,
144
- "learning_rate": 2.3000000000000003e-05,
145
- "loss": 0.6845,
146
- "step": 23
147
- },
148
- {
149
- "epoch": 0.06,
150
- "learning_rate": 2.4e-05,
151
- "loss": 0.6891,
152
- "step": 24
153
- },
154
- {
155
- "epoch": 0.07,
156
- "learning_rate": 2.5e-05,
157
- "loss": 0.5914,
158
- "step": 25
159
- },
160
- {
161
- "epoch": 0.07,
162
- "learning_rate": 2.6000000000000002e-05,
163
- "loss": 0.6916,
164
- "step": 26
165
- },
166
- {
167
- "epoch": 0.07,
168
- "learning_rate": 2.7000000000000002e-05,
169
- "loss": 0.5884,
170
- "step": 27
171
- },
172
- {
173
- "epoch": 0.07,
174
- "learning_rate": 2.8000000000000003e-05,
175
- "loss": 0.6587,
176
- "step": 28
177
- },
178
- {
179
- "epoch": 0.08,
180
- "learning_rate": 2.9e-05,
181
- "loss": 0.6008,
182
- "step": 29
183
- },
184
- {
185
- "epoch": 0.08,
186
- "learning_rate": 3e-05,
187
- "loss": 0.6717,
188
- "step": 30
189
- },
190
- {
191
- "epoch": 0.08,
192
- "learning_rate": 3.1e-05,
193
- "loss": 0.5795,
194
- "step": 31
195
- },
196
- {
197
- "epoch": 0.08,
198
- "learning_rate": 3.2000000000000005e-05,
199
- "loss": 0.6358,
200
- "step": 32
201
- },
202
- {
203
- "epoch": 0.09,
204
- "learning_rate": 3.3e-05,
205
- "loss": 0.7508,
206
- "step": 33
207
- },
208
- {
209
- "epoch": 0.09,
210
- "learning_rate": 3.4000000000000007e-05,
211
- "loss": 0.6601,
212
- "step": 34
213
- },
214
- {
215
- "epoch": 0.09,
216
- "learning_rate": 3.5e-05,
217
- "loss": 0.6573,
218
- "step": 35
219
- },
220
- {
221
- "epoch": 0.1,
222
- "learning_rate": 3.6e-05,
223
- "loss": 0.5695,
224
- "step": 36
225
- },
226
- {
227
- "epoch": 0.1,
228
- "learning_rate": 3.7e-05,
229
- "loss": 0.5535,
230
- "step": 37
231
- },
232
- {
233
- "epoch": 0.1,
234
- "learning_rate": 3.8e-05,
235
- "loss": 0.5813,
236
- "step": 38
237
- },
238
- {
239
- "epoch": 0.1,
240
- "learning_rate": 3.9000000000000006e-05,
241
- "loss": 0.5224,
242
- "step": 39
243
- },
244
- {
245
- "epoch": 0.11,
246
- "learning_rate": 4e-05,
247
- "loss": 0.4757,
248
- "step": 40
249
- },
250
- {
251
- "epoch": 0.11,
252
- "learning_rate": 4.1e-05,
253
- "loss": 0.5529,
254
- "step": 41
255
- },
256
- {
257
- "epoch": 0.11,
258
- "learning_rate": 4.2e-05,
259
- "loss": 0.4964,
260
- "step": 42
261
- },
262
- {
263
- "epoch": 0.11,
264
- "learning_rate": 4.3e-05,
265
- "loss": 0.4565,
266
- "step": 43
267
- },
268
- {
269
- "epoch": 0.12,
270
- "learning_rate": 4.4000000000000006e-05,
271
- "loss": 0.5848,
272
- "step": 44
273
- },
274
- {
275
- "epoch": 0.12,
276
- "learning_rate": 4.5e-05,
277
- "loss": 0.7333,
278
- "step": 45
279
- },
280
- {
281
- "epoch": 0.12,
282
- "learning_rate": 4.600000000000001e-05,
283
- "loss": 0.5224,
284
- "step": 46
285
- },
286
- {
287
- "epoch": 0.12,
288
- "learning_rate": 4.7e-05,
289
- "loss": 0.4826,
290
- "step": 47
291
- },
292
- {
293
- "epoch": 0.13,
294
- "learning_rate": 4.8e-05,
295
- "loss": 0.4328,
296
- "step": 48
297
- },
298
- {
299
- "epoch": 0.13,
300
- "learning_rate": 4.9e-05,
301
- "loss": 0.2546,
302
- "step": 49
303
- },
304
- {
305
- "epoch": 0.13,
306
- "learning_rate": 5e-05,
307
- "loss": 0.2636,
308
- "step": 50
309
- },
310
- {
311
- "epoch": 0.13,
312
- "learning_rate": 4.998659517426274e-05,
313
- "loss": 0.4116,
314
- "step": 51
315
- },
316
- {
317
- "epoch": 0.14,
318
- "learning_rate": 4.997319034852547e-05,
319
- "loss": 0.3191,
320
- "step": 52
321
- },
322
- {
323
- "epoch": 0.14,
324
- "learning_rate": 4.995978552278821e-05,
325
- "loss": 0.2822,
326
- "step": 53
327
- },
328
- {
329
- "epoch": 0.14,
330
- "learning_rate": 4.994638069705094e-05,
331
- "loss": 0.8821,
332
- "step": 54
333
- },
334
- {
335
- "epoch": 0.15,
336
- "learning_rate": 4.993297587131368e-05,
337
- "loss": 0.483,
338
- "step": 55
339
- },
340
- {
341
- "epoch": 0.15,
342
- "learning_rate": 4.9919571045576406e-05,
343
- "loss": 0.7164,
344
- "step": 56
345
- },
346
- {
347
- "epoch": 0.15,
348
- "learning_rate": 4.990616621983915e-05,
349
- "loss": 0.4161,
350
- "step": 57
351
- },
352
- {
353
- "epoch": 0.15,
354
- "learning_rate": 4.989276139410188e-05,
355
- "loss": 0.2668,
356
- "step": 58
357
- },
358
- {
359
- "epoch": 0.16,
360
- "learning_rate": 4.987935656836462e-05,
361
- "loss": 0.5255,
362
- "step": 59
363
- },
364
- {
365
- "epoch": 0.16,
366
- "learning_rate": 4.986595174262735e-05,
367
- "loss": 0.3784,
368
- "step": 60
369
- },
370
- {
371
- "epoch": 0.16,
372
- "learning_rate": 4.985254691689008e-05,
373
- "loss": 0.5065,
374
- "step": 61
375
- },
376
- {
377
- "epoch": 0.16,
378
- "learning_rate": 4.983914209115282e-05,
379
- "loss": 0.1988,
380
- "step": 62
381
- },
382
- {
383
- "epoch": 0.17,
384
- "learning_rate": 4.982573726541555e-05,
385
- "loss": 0.4362,
386
- "step": 63
387
- },
388
- {
389
- "epoch": 0.17,
390
- "learning_rate": 4.981233243967829e-05,
391
- "loss": 0.6619,
392
- "step": 64
393
- },
394
- {
395
- "epoch": 0.17,
396
- "learning_rate": 4.979892761394102e-05,
397
- "loss": 0.3217,
398
- "step": 65
399
- },
400
- {
401
- "epoch": 0.17,
402
- "learning_rate": 4.978552278820375e-05,
403
- "loss": 0.2967,
404
- "step": 66
405
- },
406
- {
407
- "epoch": 0.18,
408
- "learning_rate": 4.977211796246649e-05,
409
- "loss": 0.2429,
410
- "step": 67
411
- },
412
- {
413
- "epoch": 0.18,
414
- "learning_rate": 4.975871313672922e-05,
415
- "loss": 0.6642,
416
- "step": 68
417
- },
418
- {
419
- "epoch": 0.18,
420
- "learning_rate": 4.974530831099196e-05,
421
- "loss": 0.56,
422
- "step": 69
423
- },
424
- {
425
- "epoch": 0.19,
426
- "learning_rate": 4.973190348525469e-05,
427
- "loss": 1.2979,
428
- "step": 70
429
- },
430
- {
431
- "epoch": 0.19,
432
- "learning_rate": 4.9718498659517427e-05,
433
- "loss": 0.5287,
434
- "step": 71
435
- },
436
- {
437
- "epoch": 0.19,
438
- "learning_rate": 4.970509383378016e-05,
439
- "loss": 0.4684,
440
- "step": 72
441
- },
442
- {
443
- "epoch": 0.19,
444
- "learning_rate": 4.96916890080429e-05,
445
- "loss": 0.283,
446
- "step": 73
447
- },
448
- {
449
- "epoch": 0.2,
450
- "learning_rate": 4.967828418230563e-05,
451
- "loss": 0.6818,
452
- "step": 74
453
- },
454
- {
455
- "epoch": 0.2,
456
- "learning_rate": 4.966487935656837e-05,
457
- "loss": 0.6141,
458
- "step": 75
459
- },
460
- {
461
- "epoch": 0.2,
462
- "learning_rate": 4.96514745308311e-05,
463
- "loss": 0.5046,
464
- "step": 76
465
- },
466
- {
467
- "epoch": 0.2,
468
- "learning_rate": 4.963806970509384e-05,
469
- "loss": 0.5266,
470
- "step": 77
471
- },
472
- {
473
- "epoch": 0.21,
474
- "learning_rate": 4.962466487935657e-05,
475
- "loss": 0.5944,
476
- "step": 78
477
- },
478
- {
479
- "epoch": 0.21,
480
- "learning_rate": 4.961126005361931e-05,
481
- "loss": 0.5631,
482
- "step": 79
483
- },
484
- {
485
- "epoch": 0.21,
486
- "learning_rate": 4.959785522788204e-05,
487
- "loss": 0.4791,
488
- "step": 80
489
- },
490
- {
491
- "epoch": 0.21,
492
- "learning_rate": 4.958445040214477e-05,
493
- "loss": 0.5645,
494
- "step": 81
495
- },
496
- {
497
- "epoch": 0.22,
498
- "learning_rate": 4.957104557640751e-05,
499
- "loss": 0.4349,
500
- "step": 82
501
- },
502
- {
503
- "epoch": 0.22,
504
- "learning_rate": 4.955764075067024e-05,
505
- "loss": 0.3865,
506
- "step": 83
507
- },
508
- {
509
- "epoch": 0.22,
510
- "learning_rate": 4.954423592493298e-05,
511
- "loss": 0.486,
512
- "step": 84
513
- },
514
- {
515
- "epoch": 0.22,
516
- "learning_rate": 4.953083109919571e-05,
517
- "loss": 0.2179,
518
- "step": 85
519
- },
520
- {
521
- "epoch": 0.23,
522
- "learning_rate": 4.951742627345845e-05,
523
- "loss": 0.3896,
524
- "step": 86
525
- },
526
- {
527
- "epoch": 0.23,
528
- "learning_rate": 4.950402144772118e-05,
529
- "loss": 0.4247,
530
- "step": 87
531
- },
532
- {
533
- "epoch": 0.23,
534
- "learning_rate": 4.949061662198392e-05,
535
- "loss": 0.4906,
536
- "step": 88
537
- },
538
- {
539
- "epoch": 0.24,
540
- "learning_rate": 4.947721179624665e-05,
541
- "loss": 0.4483,
542
- "step": 89
543
- },
544
- {
545
- "epoch": 0.24,
546
- "learning_rate": 4.946380697050939e-05,
547
- "loss": 0.557,
548
- "step": 90
549
- },
550
- {
551
- "epoch": 0.24,
552
- "learning_rate": 4.9450402144772116e-05,
553
- "loss": 0.7521,
554
- "step": 91
555
- },
556
- {
557
- "epoch": 0.24,
558
- "learning_rate": 4.943699731903486e-05,
559
- "loss": 0.3103,
560
- "step": 92
561
- },
562
- {
563
- "epoch": 0.25,
564
- "learning_rate": 4.9423592493297586e-05,
565
- "loss": 0.757,
566
- "step": 93
567
- },
568
- {
569
- "epoch": 0.25,
570
- "learning_rate": 4.941018766756033e-05,
571
- "loss": 0.8248,
572
- "step": 94
573
- },
574
- {
575
- "epoch": 0.25,
576
- "learning_rate": 4.9396782841823056e-05,
577
- "loss": 0.4591,
578
- "step": 95
579
- },
580
- {
581
- "epoch": 0.25,
582
- "learning_rate": 4.938337801608579e-05,
583
- "loss": 0.3912,
584
- "step": 96
585
- },
586
- {
587
- "epoch": 0.26,
588
- "learning_rate": 4.9369973190348526e-05,
589
- "loss": 0.5289,
590
- "step": 97
591
- },
592
- {
593
- "epoch": 0.26,
594
- "learning_rate": 4.935656836461126e-05,
595
- "loss": 0.3264,
596
- "step": 98
597
- },
598
- {
599
- "epoch": 0.26,
600
- "learning_rate": 4.9343163538874e-05,
601
- "loss": 0.2947,
602
- "step": 99
603
- },
604
- {
605
- "epoch": 0.26,
606
- "learning_rate": 4.932975871313673e-05,
607
- "loss": 0.2647,
608
- "step": 100
609
- },
610
- {
611
- "epoch": 0.27,
612
- "learning_rate": 4.931635388739946e-05,
613
- "loss": 0.3691,
614
- "step": 101
615
- },
616
- {
617
- "epoch": 0.27,
618
- "learning_rate": 4.93029490616622e-05,
619
- "loss": 0.4796,
620
- "step": 102
621
- },
622
- {
623
- "epoch": 0.27,
624
- "learning_rate": 4.928954423592493e-05,
625
- "loss": 0.4827,
626
- "step": 103
627
- },
628
- {
629
- "epoch": 0.28,
630
- "learning_rate": 4.927613941018767e-05,
631
- "loss": 0.2672,
632
- "step": 104
633
- },
634
- {
635
- "epoch": 0.28,
636
- "learning_rate": 4.92627345844504e-05,
637
- "loss": 0.7456,
638
- "step": 105
639
- },
640
- {
641
- "epoch": 0.28,
642
- "learning_rate": 4.9249329758713136e-05,
643
- "loss": 0.5206,
644
- "step": 106
645
- },
646
- {
647
- "epoch": 0.28,
648
- "learning_rate": 4.923592493297587e-05,
649
- "loss": 0.3576,
650
- "step": 107
651
- },
652
- {
653
- "epoch": 0.29,
654
- "learning_rate": 4.9222520107238606e-05,
655
- "loss": 0.2596,
656
- "step": 108
657
- },
658
- {
659
- "epoch": 0.29,
660
- "learning_rate": 4.920911528150134e-05,
661
- "loss": 0.4115,
662
- "step": 109
663
- },
664
- {
665
- "epoch": 0.29,
666
- "learning_rate": 4.9195710455764076e-05,
667
- "loss": 0.3481,
668
- "step": 110
669
- },
670
- {
671
- "epoch": 0.29,
672
- "learning_rate": 4.918230563002681e-05,
673
- "loss": 0.4387,
674
- "step": 111
675
- },
676
- {
677
- "epoch": 0.3,
678
- "learning_rate": 4.916890080428955e-05,
679
- "loss": 0.5023,
680
- "step": 112
681
- },
682
- {
683
- "epoch": 0.3,
684
- "learning_rate": 4.915549597855228e-05,
685
- "loss": 0.5916,
686
- "step": 113
687
- },
688
- {
689
- "epoch": 0.3,
690
- "learning_rate": 4.914209115281502e-05,
691
- "loss": 0.5467,
692
- "step": 114
693
- },
694
- {
695
- "epoch": 0.3,
696
- "learning_rate": 4.912868632707775e-05,
697
- "loss": 0.5631,
698
- "step": 115
699
- },
700
- {
701
- "epoch": 0.31,
702
- "learning_rate": 4.911528150134049e-05,
703
- "loss": 0.5512,
704
- "step": 116
705
- },
706
- {
707
- "epoch": 0.31,
708
- "learning_rate": 4.910187667560322e-05,
709
- "loss": 0.5546,
710
- "step": 117
711
- },
712
- {
713
- "epoch": 0.31,
714
- "learning_rate": 4.908847184986595e-05,
715
- "loss": 0.4209,
716
- "step": 118
717
- },
718
- {
719
- "epoch": 0.31,
720
- "learning_rate": 4.907506702412869e-05,
721
- "loss": 0.6064,
722
- "step": 119
723
- },
724
- {
725
- "epoch": 0.32,
726
- "learning_rate": 4.906166219839142e-05,
727
- "loss": 0.5301,
728
- "step": 120
729
- },
730
- {
731
- "epoch": 0.32,
732
- "learning_rate": 4.904825737265416e-05,
733
- "loss": 0.436,
734
- "step": 121
735
- },
736
- {
737
- "epoch": 0.32,
738
- "learning_rate": 4.903485254691689e-05,
739
- "loss": 0.726,
740
- "step": 122
741
- },
742
- {
743
- "epoch": 0.33,
744
- "learning_rate": 4.9021447721179626e-05,
745
- "loss": 0.5288,
746
- "step": 123
747
- },
748
- {
749
- "epoch": 0.33,
750
- "learning_rate": 4.900804289544236e-05,
751
- "loss": 0.4887,
752
- "step": 124
753
- },
754
- {
755
- "epoch": 0.33,
756
- "learning_rate": 4.8994638069705097e-05,
757
- "loss": 0.3752,
758
- "step": 125
759
- },
760
- {
761
- "epoch": 0.33,
762
- "learning_rate": 4.898123324396783e-05,
763
- "loss": 0.4895,
764
- "step": 126
765
- },
766
- {
767
- "epoch": 0.34,
768
- "learning_rate": 4.896782841823057e-05,
769
- "loss": 0.5046,
770
- "step": 127
771
- },
772
- {
773
- "epoch": 0.34,
774
- "learning_rate": 4.8954423592493295e-05,
775
- "loss": 0.3953,
776
- "step": 128
777
- },
778
- {
779
- "epoch": 0.34,
780
- "learning_rate": 4.894101876675604e-05,
781
- "loss": 0.2015,
782
- "step": 129
783
- },
784
- {
785
- "epoch": 0.34,
786
- "learning_rate": 4.8927613941018765e-05,
787
- "loss": 0.5165,
788
- "step": 130
789
- },
790
- {
791
- "epoch": 0.35,
792
- "learning_rate": 4.891420911528151e-05,
793
- "loss": 0.4237,
794
- "step": 131
795
- },
796
- {
797
- "epoch": 0.35,
798
- "learning_rate": 4.8900804289544236e-05,
799
- "loss": 0.239,
800
- "step": 132
801
- },
802
- {
803
- "epoch": 0.35,
804
- "learning_rate": 4.888739946380697e-05,
805
- "loss": 0.5515,
806
- "step": 133
807
- },
808
- {
809
- "epoch": 0.35,
810
- "learning_rate": 4.8873994638069706e-05,
811
- "loss": 0.303,
812
- "step": 134
813
- },
814
- {
815
- "epoch": 0.36,
816
- "learning_rate": 4.886058981233244e-05,
817
- "loss": 0.2867,
818
- "step": 135
819
- },
820
- {
821
- "epoch": 0.36,
822
- "learning_rate": 4.8847184986595176e-05,
823
- "loss": 0.6756,
824
- "step": 136
825
- },
826
- {
827
- "epoch": 0.36,
828
- "learning_rate": 4.883378016085791e-05,
829
- "loss": 0.4996,
830
- "step": 137
831
- },
832
- {
833
- "epoch": 0.37,
834
- "learning_rate": 4.8820375335120646e-05,
835
- "loss": 0.2798,
836
- "step": 138
837
- },
838
- {
839
- "epoch": 0.37,
840
- "learning_rate": 4.880697050938338e-05,
841
- "loss": 0.8877,
842
- "step": 139
843
- },
844
- {
845
- "epoch": 0.37,
846
- "learning_rate": 4.879356568364612e-05,
847
- "loss": 0.5022,
848
- "step": 140
849
- },
850
- {
851
- "epoch": 0.37,
852
- "learning_rate": 4.878016085790885e-05,
853
- "loss": 0.2177,
854
- "step": 141
855
- },
856
- {
857
- "epoch": 0.38,
858
- "learning_rate": 4.876675603217159e-05,
859
- "loss": 0.8708,
860
- "step": 142
861
- },
862
- {
863
- "epoch": 0.38,
864
- "learning_rate": 4.8753351206434315e-05,
865
- "loss": 0.719,
866
- "step": 143
867
- },
868
- {
869
- "epoch": 0.38,
870
- "learning_rate": 4.873994638069706e-05,
871
- "loss": 0.562,
872
- "step": 144
873
- },
874
- {
875
- "epoch": 0.38,
876
- "learning_rate": 4.8726541554959786e-05,
877
- "loss": 0.492,
878
- "step": 145
879
- },
880
- {
881
- "epoch": 0.39,
882
- "learning_rate": 4.871313672922253e-05,
883
- "loss": 0.4637,
884
- "step": 146
885
- },
886
- {
887
- "epoch": 0.39,
888
- "learning_rate": 4.8699731903485256e-05,
889
- "loss": 0.4132,
890
- "step": 147
891
- },
892
- {
893
- "epoch": 0.39,
894
- "learning_rate": 4.868632707774799e-05,
895
- "loss": 0.2889,
896
- "step": 148
897
- },
898
- {
899
- "epoch": 0.39,
900
- "learning_rate": 4.8672922252010726e-05,
901
- "loss": 0.2213,
902
- "step": 149
903
- },
904
- {
905
- "epoch": 0.4,
906
- "learning_rate": 4.865951742627346e-05,
907
- "loss": 0.9268,
908
- "step": 150
909
- },
910
- {
911
- "epoch": 0.4,
912
- "learning_rate": 4.8646112600536196e-05,
913
- "loss": 0.2852,
914
- "step": 151
915
- },
916
- {
917
- "epoch": 0.4,
918
- "learning_rate": 4.863270777479893e-05,
919
- "loss": 0.4599,
920
- "step": 152
921
- },
922
- {
923
- "epoch": 0.4,
924
- "learning_rate": 4.861930294906166e-05,
925
- "loss": 0.1913,
926
- "step": 153
927
- },
928
- {
929
- "epoch": 0.41,
930
- "learning_rate": 4.86058981233244e-05,
931
- "loss": 0.4488,
932
- "step": 154
933
- },
934
- {
935
- "epoch": 0.41,
936
- "learning_rate": 4.859249329758713e-05,
937
- "loss": 0.9022,
938
- "step": 155
939
- },
940
- {
941
- "epoch": 0.41,
942
- "learning_rate": 4.857908847184987e-05,
943
- "loss": 0.5221,
944
- "step": 156
945
- },
946
- {
947
- "epoch": 0.42,
948
- "learning_rate": 4.85656836461126e-05,
949
- "loss": 0.2394,
950
- "step": 157
951
- },
952
- {
953
- "epoch": 0.42,
954
- "learning_rate": 4.8552278820375336e-05,
955
- "loss": 0.3332,
956
- "step": 158
957
- },
958
- {
959
- "epoch": 0.42,
960
- "learning_rate": 4.853887399463807e-05,
961
- "loss": 0.4015,
962
- "step": 159
963
- },
964
- {
965
- "epoch": 0.42,
966
- "learning_rate": 4.8525469168900806e-05,
967
- "loss": 0.4461,
968
- "step": 160
969
- },
970
- {
971
- "epoch": 0.43,
972
- "learning_rate": 4.851206434316354e-05,
973
- "loss": 0.337,
974
- "step": 161
975
- },
976
- {
977
- "epoch": 0.43,
978
- "learning_rate": 4.8498659517426276e-05,
979
- "loss": 0.4908,
980
- "step": 162
981
- },
982
- {
983
- "epoch": 0.43,
984
- "learning_rate": 4.848525469168901e-05,
985
- "loss": 0.526,
986
- "step": 163
987
- },
988
- {
989
- "epoch": 0.43,
990
- "learning_rate": 4.8471849865951746e-05,
991
- "loss": 0.5262,
992
- "step": 164
993
- },
994
- {
995
- "epoch": 0.44,
996
- "learning_rate": 4.845844504021448e-05,
997
- "loss": 0.6818,
998
- "step": 165
999
- },
1000
- {
1001
- "epoch": 0.44,
1002
- "learning_rate": 4.8445040214477217e-05,
1003
- "loss": 0.3154,
1004
- "step": 166
1005
- },
1006
- {
1007
- "epoch": 0.44,
1008
- "learning_rate": 4.843163538873995e-05,
1009
- "loss": 0.5963,
1010
- "step": 167
1011
- },
1012
- {
1013
- "epoch": 0.44,
1014
- "learning_rate": 4.841823056300268e-05,
1015
- "loss": 0.4451,
1016
- "step": 168
1017
- },
1018
- {
1019
- "epoch": 0.45,
1020
- "learning_rate": 4.840482573726542e-05,
1021
- "loss": 0.5969,
1022
- "step": 169
1023
- },
1024
- {
1025
- "epoch": 0.45,
1026
- "learning_rate": 4.839142091152815e-05,
1027
- "loss": 0.438,
1028
- "step": 170
1029
- },
1030
- {
1031
- "epoch": 0.45,
1032
- "learning_rate": 4.837801608579089e-05,
1033
- "loss": 0.4827,
1034
- "step": 171
1035
- },
1036
- {
1037
- "epoch": 0.46,
1038
- "learning_rate": 4.836461126005362e-05,
1039
- "loss": 0.2029,
1040
- "step": 172
1041
- },
1042
- {
1043
- "epoch": 0.46,
1044
- "learning_rate": 4.8351206434316356e-05,
1045
- "loss": 0.5195,
1046
- "step": 173
1047
- },
1048
- {
1049
- "epoch": 0.46,
1050
- "learning_rate": 4.833780160857909e-05,
1051
- "loss": 0.517,
1052
- "step": 174
1053
- },
1054
- {
1055
- "epoch": 0.46,
1056
- "learning_rate": 4.8324396782841826e-05,
1057
- "loss": 0.5532,
1058
- "step": 175
1059
- },
1060
- {
1061
- "epoch": 0.47,
1062
- "learning_rate": 4.831099195710456e-05,
1063
- "loss": 0.4198,
1064
- "step": 176
1065
- },
1066
- {
1067
- "epoch": 0.47,
1068
- "learning_rate": 4.8297587131367296e-05,
1069
- "loss": 0.8386,
1070
- "step": 177
1071
- },
1072
- {
1073
- "epoch": 0.47,
1074
- "learning_rate": 4.8284182305630025e-05,
1075
- "loss": 0.575,
1076
- "step": 178
1077
- },
1078
- {
1079
- "epoch": 0.47,
1080
- "learning_rate": 4.8270777479892766e-05,
1081
- "loss": 0.6156,
1082
- "step": 179
1083
- },
1084
- {
1085
- "epoch": 0.48,
1086
- "learning_rate": 4.8257372654155495e-05,
1087
- "loss": 0.7044,
1088
- "step": 180
1089
- },
1090
- {
1091
- "epoch": 0.48,
1092
- "learning_rate": 4.824396782841824e-05,
1093
- "loss": 0.5712,
1094
- "step": 181
1095
- },
1096
- {
1097
- "epoch": 0.48,
1098
- "learning_rate": 4.8230563002680965e-05,
1099
- "loss": 0.34,
1100
- "step": 182
1101
- },
1102
- {
1103
- "epoch": 0.48,
1104
- "learning_rate": 4.82171581769437e-05,
1105
- "loss": 0.5773,
1106
- "step": 183
1107
- },
1108
- {
1109
- "epoch": 0.49,
1110
- "learning_rate": 4.8203753351206435e-05,
1111
- "loss": 0.546,
1112
- "step": 184
1113
- },
1114
- {
1115
- "epoch": 0.49,
1116
- "learning_rate": 4.819034852546917e-05,
1117
- "loss": 0.3955,
1118
- "step": 185
1119
- },
1120
- {
1121
- "epoch": 0.49,
1122
- "learning_rate": 4.8176943699731906e-05,
1123
- "loss": 0.5921,
1124
- "step": 186
1125
- },
1126
- {
1127
- "epoch": 0.49,
1128
- "learning_rate": 4.816353887399464e-05,
1129
- "loss": 0.3108,
1130
- "step": 187
1131
- },
1132
- {
1133
- "epoch": 0.5,
1134
- "learning_rate": 4.8150134048257376e-05,
1135
- "loss": 0.5469,
1136
- "step": 188
1137
- },
1138
- {
1139
- "epoch": 0.5,
1140
- "learning_rate": 4.813672922252011e-05,
1141
- "loss": 0.64,
1142
- "step": 189
1143
- },
1144
- {
1145
- "epoch": 0.5,
1146
- "learning_rate": 4.8123324396782846e-05,
1147
- "loss": 0.5153,
1148
- "step": 190
1149
- },
1150
- {
1151
- "epoch": 0.51,
1152
- "learning_rate": 4.810991957104558e-05,
1153
- "loss": 0.4719,
1154
- "step": 191
1155
- },
1156
- {
1157
- "epoch": 0.51,
1158
- "learning_rate": 4.8096514745308316e-05,
1159
- "loss": 0.52,
1160
- "step": 192
1161
- },
1162
- {
1163
- "epoch": 0.51,
1164
- "learning_rate": 4.8083109919571045e-05,
1165
- "loss": 0.5114,
1166
- "step": 193
1167
- },
1168
- {
1169
- "epoch": 0.51,
1170
- "learning_rate": 4.806970509383379e-05,
1171
- "loss": 0.5469,
1172
- "step": 194
1173
- },
1174
- {
1175
- "epoch": 0.52,
1176
- "learning_rate": 4.8056300268096515e-05,
1177
- "loss": 0.3435,
1178
- "step": 195
1179
- },
1180
- {
1181
- "epoch": 0.52,
1182
- "learning_rate": 4.804289544235926e-05,
1183
- "loss": 0.6469,
1184
- "step": 196
1185
- },
1186
- {
1187
- "epoch": 0.52,
1188
- "learning_rate": 4.8029490616621985e-05,
1189
- "loss": 0.6595,
1190
- "step": 197
1191
- },
1192
- {
1193
- "epoch": 0.52,
1194
- "learning_rate": 4.801608579088472e-05,
1195
- "loss": 0.5503,
1196
- "step": 198
1197
- },
1198
- {
1199
- "epoch": 0.53,
1200
- "learning_rate": 4.8002680965147456e-05,
1201
- "loss": 0.3799,
1202
- "step": 199
1203
- },
1204
- {
1205
- "epoch": 0.53,
1206
- "learning_rate": 4.798927613941019e-05,
1207
- "loss": 0.417,
1208
- "step": 200
1209
- },
1210
- {
1211
- "epoch": 0.53,
1212
- "learning_rate": 4.7975871313672926e-05,
1213
- "loss": 0.5281,
1214
- "step": 201
1215
- },
1216
- {
1217
- "epoch": 0.53,
1218
- "learning_rate": 4.796246648793566e-05,
1219
- "loss": 0.3439,
1220
- "step": 202
1221
- },
1222
- {
1223
- "epoch": 0.54,
1224
- "learning_rate": 4.794906166219839e-05,
1225
- "loss": 0.5777,
1226
- "step": 203
1227
- },
1228
- {
1229
- "epoch": 0.54,
1230
- "learning_rate": 4.793565683646113e-05,
1231
- "loss": 0.5286,
1232
- "step": 204
1233
- },
1234
- {
1235
- "epoch": 0.54,
1236
- "learning_rate": 4.792225201072386e-05,
1237
- "loss": 0.4302,
1238
- "step": 205
1239
- },
1240
- {
1241
- "epoch": 0.54,
1242
- "learning_rate": 4.79088471849866e-05,
1243
- "loss": 0.5413,
1244
- "step": 206
1245
- },
1246
- {
1247
- "epoch": 0.55,
1248
- "learning_rate": 4.789544235924933e-05,
1249
- "loss": 0.3087,
1250
- "step": 207
1251
- },
1252
- {
1253
- "epoch": 0.55,
1254
- "learning_rate": 4.7882037533512065e-05,
1255
- "loss": 0.4385,
1256
- "step": 208
1257
- },
1258
- {
1259
- "epoch": 0.55,
1260
- "learning_rate": 4.78686327077748e-05,
1261
- "loss": 0.7137,
1262
- "step": 209
1263
- },
1264
- {
1265
- "epoch": 0.56,
1266
- "learning_rate": 4.7855227882037535e-05,
1267
- "loss": 0.6278,
1268
- "step": 210
1269
- },
1270
- {
1271
- "epoch": 0.56,
1272
- "learning_rate": 4.784182305630027e-05,
1273
- "loss": 0.2832,
1274
- "step": 211
1275
- },
1276
- {
1277
- "epoch": 0.56,
1278
- "learning_rate": 4.7828418230563005e-05,
1279
- "loss": 0.5899,
1280
- "step": 212
1281
- },
1282
- {
1283
- "epoch": 0.56,
1284
- "learning_rate": 4.7815013404825734e-05,
1285
- "loss": 0.4421,
1286
- "step": 213
1287
- },
1288
- {
1289
- "epoch": 0.57,
1290
- "learning_rate": 4.7801608579088476e-05,
1291
- "loss": 0.3411,
1292
- "step": 214
1293
- },
1294
- {
1295
- "epoch": 0.57,
1296
- "learning_rate": 4.7788203753351204e-05,
1297
- "loss": 0.4236,
1298
- "step": 215
1299
- },
1300
- {
1301
- "epoch": 0.57,
1302
- "learning_rate": 4.7774798927613946e-05,
1303
- "loss": 0.4444,
1304
- "step": 216
1305
- },
1306
- {
1307
- "epoch": 0.57,
1308
- "learning_rate": 4.7761394101876674e-05,
1309
- "loss": 0.4765,
1310
- "step": 217
1311
- },
1312
- {
1313
- "epoch": 0.58,
1314
- "learning_rate": 4.774798927613941e-05,
1315
- "loss": 0.2453,
1316
- "step": 218
1317
- },
1318
- {
1319
- "epoch": 0.58,
1320
- "learning_rate": 4.7734584450402145e-05,
1321
- "loss": 0.2765,
1322
- "step": 219
1323
- },
1324
- {
1325
- "epoch": 0.58,
1326
- "learning_rate": 4.772117962466488e-05,
1327
- "loss": 0.2075,
1328
- "step": 220
1329
- },
1330
- {
1331
- "epoch": 0.58,
1332
- "learning_rate": 4.7707774798927615e-05,
1333
- "loss": 0.5905,
1334
- "step": 221
1335
- },
1336
- {
1337
- "epoch": 0.59,
1338
- "learning_rate": 4.769436997319035e-05,
1339
- "loss": 0.3457,
1340
- "step": 222
1341
- },
1342
- {
1343
- "epoch": 0.59,
1344
- "learning_rate": 4.7680965147453085e-05,
1345
- "loss": 0.5986,
1346
- "step": 223
1347
- },
1348
- {
1349
- "epoch": 0.59,
1350
- "learning_rate": 4.766756032171582e-05,
1351
- "loss": 0.3881,
1352
- "step": 224
1353
- },
1354
- {
1355
- "epoch": 0.6,
1356
- "learning_rate": 4.7654155495978555e-05,
1357
- "loss": 0.5655,
1358
- "step": 225
1359
- },
1360
- {
1361
- "epoch": 0.6,
1362
- "learning_rate": 4.764075067024129e-05,
1363
- "loss": 0.6156,
1364
- "step": 226
1365
- },
1366
- {
1367
- "epoch": 0.6,
1368
- "learning_rate": 4.7627345844504026e-05,
1369
- "loss": 0.4784,
1370
- "step": 227
1371
- },
1372
- {
1373
- "epoch": 0.6,
1374
- "learning_rate": 4.7613941018766754e-05,
1375
- "loss": 0.5195,
1376
- "step": 228
1377
- },
1378
- {
1379
- "epoch": 0.61,
1380
- "learning_rate": 4.7600536193029496e-05,
1381
- "loss": 0.66,
1382
- "step": 229
1383
- },
1384
- {
1385
- "epoch": 0.61,
1386
- "learning_rate": 4.7587131367292224e-05,
1387
- "loss": 0.4104,
1388
- "step": 230
1389
- },
1390
- {
1391
- "epoch": 0.61,
1392
- "learning_rate": 4.7573726541554966e-05,
1393
- "loss": 0.3478,
1394
- "step": 231
1395
- },
1396
- {
1397
- "epoch": 0.61,
1398
- "learning_rate": 4.7560321715817695e-05,
1399
- "loss": 0.2037,
1400
- "step": 232
1401
- },
1402
- {
1403
- "epoch": 0.62,
1404
- "learning_rate": 4.754691689008043e-05,
1405
- "loss": 0.75,
1406
- "step": 233
1407
- },
1408
- {
1409
- "epoch": 0.62,
1410
- "learning_rate": 4.7533512064343165e-05,
1411
- "loss": 0.4237,
1412
- "step": 234
1413
- },
1414
- {
1415
- "epoch": 0.62,
1416
- "learning_rate": 4.75201072386059e-05,
1417
- "loss": 0.2372,
1418
- "step": 235
1419
- },
1420
- {
1421
- "epoch": 0.62,
1422
- "learning_rate": 4.7506702412868635e-05,
1423
- "loss": 0.7874,
1424
- "step": 236
1425
- },
1426
- {
1427
- "epoch": 0.63,
1428
- "learning_rate": 4.749329758713137e-05,
1429
- "loss": 0.5751,
1430
- "step": 237
1431
- },
1432
- {
1433
- "epoch": 0.63,
1434
- "learning_rate": 4.7479892761394105e-05,
1435
- "loss": 0.5801,
1436
- "step": 238
1437
- },
1438
- {
1439
- "epoch": 0.63,
1440
- "learning_rate": 4.746648793565684e-05,
1441
- "loss": 0.4983,
1442
- "step": 239
1443
- },
1444
- {
1445
- "epoch": 0.63,
1446
- "learning_rate": 4.745308310991957e-05,
1447
- "loss": 0.4215,
1448
- "step": 240
1449
- },
1450
- {
1451
- "epoch": 0.64,
1452
- "learning_rate": 4.743967828418231e-05,
1453
- "loss": 0.3655,
1454
- "step": 241
1455
- },
1456
- {
1457
- "epoch": 0.64,
1458
- "learning_rate": 4.742627345844504e-05,
1459
- "loss": 0.523,
1460
- "step": 242
1461
- },
1462
- {
1463
- "epoch": 0.64,
1464
- "learning_rate": 4.741286863270778e-05,
1465
- "loss": 0.5952,
1466
- "step": 243
1467
- },
1468
- {
1469
- "epoch": 0.65,
1470
- "learning_rate": 4.739946380697051e-05,
1471
- "loss": 0.4226,
1472
- "step": 244
1473
- },
1474
- {
1475
- "epoch": 0.65,
1476
- "learning_rate": 4.7386058981233244e-05,
1477
- "loss": 0.316,
1478
- "step": 245
1479
- },
1480
- {
1481
- "epoch": 0.65,
1482
- "learning_rate": 4.737265415549598e-05,
1483
- "loss": 0.5096,
1484
- "step": 246
1485
- },
1486
- {
1487
- "epoch": 0.65,
1488
- "learning_rate": 4.7359249329758715e-05,
1489
- "loss": 0.435,
1490
- "step": 247
1491
- },
1492
- {
1493
- "epoch": 0.66,
1494
- "learning_rate": 4.734584450402145e-05,
1495
- "loss": 0.7516,
1496
- "step": 248
1497
- },
1498
- {
1499
- "epoch": 0.66,
1500
- "learning_rate": 4.7332439678284185e-05,
1501
- "loss": 0.531,
1502
- "step": 249
1503
- },
1504
- {
1505
- "epoch": 0.66,
1506
- "learning_rate": 4.731903485254692e-05,
1507
- "loss": 0.4096,
1508
- "step": 250
1509
- },
1510
- {
1511
- "epoch": 0.66,
1512
- "learning_rate": 4.7305630026809655e-05,
1513
- "loss": 0.387,
1514
- "step": 251
1515
- },
1516
- {
1517
- "epoch": 0.67,
1518
- "learning_rate": 4.729222520107239e-05,
1519
- "loss": 0.5468,
1520
- "step": 252
1521
- },
1522
- {
1523
- "epoch": 0.67,
1524
- "learning_rate": 4.7278820375335125e-05,
1525
- "loss": 0.4613,
1526
- "step": 253
1527
- },
1528
- {
1529
- "epoch": 0.67,
1530
- "learning_rate": 4.726541554959786e-05,
1531
- "loss": 0.8437,
1532
- "step": 254
1533
- },
1534
- {
1535
- "epoch": 0.67,
1536
- "learning_rate": 4.725201072386059e-05,
1537
- "loss": 0.522,
1538
- "step": 255
1539
- },
1540
- {
1541
- "epoch": 0.68,
1542
- "learning_rate": 4.723860589812333e-05,
1543
- "loss": 0.3922,
1544
- "step": 256
1545
- },
1546
- {
1547
- "epoch": 0.68,
1548
- "learning_rate": 4.722520107238606e-05,
1549
- "loss": 0.5114,
1550
- "step": 257
1551
- },
1552
- {
1553
- "epoch": 0.68,
1554
- "learning_rate": 4.72117962466488e-05,
1555
- "loss": 0.6148,
1556
- "step": 258
1557
- },
1558
- {
1559
- "epoch": 0.69,
1560
- "learning_rate": 4.719839142091153e-05,
1561
- "loss": 0.4578,
1562
- "step": 259
1563
- },
1564
- {
1565
- "epoch": 0.69,
1566
- "learning_rate": 4.7184986595174265e-05,
1567
- "loss": 0.6286,
1568
- "step": 260
1569
- },
1570
- {
1571
- "epoch": 0.69,
1572
- "learning_rate": 4.7171581769437e-05,
1573
- "loss": 0.5883,
1574
- "step": 261
1575
- },
1576
- {
1577
- "epoch": 0.69,
1578
- "learning_rate": 4.7158176943699735e-05,
1579
- "loss": 0.5634,
1580
- "step": 262
1581
- },
1582
- {
1583
- "epoch": 0.7,
1584
- "learning_rate": 4.714477211796247e-05,
1585
- "loss": 0.4085,
1586
- "step": 263
1587
- },
1588
- {
1589
- "epoch": 0.7,
1590
- "learning_rate": 4.7131367292225205e-05,
1591
- "loss": 0.2988,
1592
- "step": 264
1593
- },
1594
- {
1595
- "epoch": 0.7,
1596
- "learning_rate": 4.7117962466487934e-05,
1597
- "loss": 0.6353,
1598
- "step": 265
1599
- },
1600
- {
1601
- "epoch": 0.7,
1602
- "learning_rate": 4.7104557640750675e-05,
1603
- "loss": 0.4598,
1604
- "step": 266
1605
- },
1606
- {
1607
- "epoch": 0.71,
1608
- "learning_rate": 4.7091152815013404e-05,
1609
- "loss": 0.5072,
1610
- "step": 267
1611
- },
1612
- {
1613
- "epoch": 0.71,
1614
- "learning_rate": 4.7077747989276146e-05,
1615
- "loss": 0.49,
1616
- "step": 268
1617
- },
1618
- {
1619
- "epoch": 0.71,
1620
- "learning_rate": 4.7064343163538874e-05,
1621
- "loss": 0.7225,
1622
- "step": 269
1623
- },
1624
- {
1625
- "epoch": 0.71,
1626
- "learning_rate": 4.705093833780161e-05,
1627
- "loss": 0.5332,
1628
- "step": 270
1629
- },
1630
- {
1631
- "epoch": 0.72,
1632
- "learning_rate": 4.7037533512064344e-05,
1633
- "loss": 0.6064,
1634
- "step": 271
1635
- },
1636
- {
1637
- "epoch": 0.72,
1638
- "learning_rate": 4.702412868632708e-05,
1639
- "loss": 0.3518,
1640
- "step": 272
1641
- },
1642
- {
1643
- "epoch": 0.72,
1644
- "learning_rate": 4.7010723860589815e-05,
1645
- "loss": 0.3673,
1646
- "step": 273
1647
- },
1648
- {
1649
- "epoch": 0.72,
1650
- "learning_rate": 4.699731903485255e-05,
1651
- "loss": 0.4688,
1652
- "step": 274
1653
- },
1654
- {
1655
- "epoch": 0.73,
1656
- "learning_rate": 4.6983914209115285e-05,
1657
- "loss": 0.5389,
1658
- "step": 275
1659
- },
1660
- {
1661
- "epoch": 0.73,
1662
- "learning_rate": 4.697050938337802e-05,
1663
- "loss": 0.374,
1664
- "step": 276
1665
- },
1666
- {
1667
- "epoch": 0.73,
1668
- "learning_rate": 4.6957104557640755e-05,
1669
- "loss": 0.475,
1670
- "step": 277
1671
- },
1672
- {
1673
- "epoch": 0.74,
1674
- "learning_rate": 4.694369973190349e-05,
1675
- "loss": 0.5397,
1676
- "step": 278
1677
- },
1678
- {
1679
- "epoch": 0.74,
1680
- "learning_rate": 4.6930294906166225e-05,
1681
- "loss": 0.3821,
1682
- "step": 279
1683
- },
1684
- {
1685
- "epoch": 0.74,
1686
- "learning_rate": 4.6916890080428954e-05,
1687
- "loss": 0.3372,
1688
- "step": 280
1689
- },
1690
- {
1691
- "epoch": 0.74,
1692
- "learning_rate": 4.6903485254691696e-05,
1693
- "loss": 0.6652,
1694
- "step": 281
1695
- },
1696
- {
1697
- "epoch": 0.75,
1698
- "learning_rate": 4.6890080428954424e-05,
1699
- "loss": 0.2894,
1700
- "step": 282
1701
- },
1702
- {
1703
- "epoch": 0.75,
1704
- "learning_rate": 4.6876675603217166e-05,
1705
- "loss": 0.5639,
1706
- "step": 283
1707
- },
1708
- {
1709
- "epoch": 0.75,
1710
- "learning_rate": 4.6863270777479894e-05,
1711
- "loss": 0.353,
1712
- "step": 284
1713
- },
1714
- {
1715
- "epoch": 0.75,
1716
- "learning_rate": 4.684986595174263e-05,
1717
- "loss": 0.2932,
1718
- "step": 285
1719
- },
1720
- {
1721
- "epoch": 0.76,
1722
- "learning_rate": 4.6836461126005364e-05,
1723
- "loss": 0.467,
1724
- "step": 286
1725
- },
1726
- {
1727
- "epoch": 0.76,
1728
- "learning_rate": 4.68230563002681e-05,
1729
- "loss": 0.4732,
1730
- "step": 287
1731
- },
1732
- {
1733
- "epoch": 0.76,
1734
- "learning_rate": 4.6809651474530835e-05,
1735
- "loss": 0.1808,
1736
- "step": 288
1737
- },
1738
- {
1739
- "epoch": 0.76,
1740
- "learning_rate": 4.679624664879357e-05,
1741
- "loss": 0.6031,
1742
- "step": 289
1743
- },
1744
- {
1745
- "epoch": 0.77,
1746
- "learning_rate": 4.67828418230563e-05,
1747
- "loss": 0.2555,
1748
- "step": 290
1749
- },
1750
- {
1751
- "epoch": 0.77,
1752
- "learning_rate": 4.676943699731904e-05,
1753
- "loss": 0.4041,
1754
- "step": 291
1755
- },
1756
- {
1757
- "epoch": 0.77,
1758
- "learning_rate": 4.675603217158177e-05,
1759
- "loss": 0.7822,
1760
- "step": 292
1761
- },
1762
- {
1763
- "epoch": 0.78,
1764
- "learning_rate": 4.674262734584451e-05,
1765
- "loss": 0.138,
1766
- "step": 293
1767
- },
1768
- {
1769
- "epoch": 0.78,
1770
- "learning_rate": 4.672922252010724e-05,
1771
- "loss": 0.2746,
1772
- "step": 294
1773
- },
1774
- {
1775
- "epoch": 0.78,
1776
- "learning_rate": 4.6715817694369974e-05,
1777
- "loss": 0.5835,
1778
- "step": 295
1779
- },
1780
- {
1781
- "epoch": 0.78,
1782
- "learning_rate": 4.670241286863271e-05,
1783
- "loss": 0.2367,
1784
- "step": 296
1785
- },
1786
- {
1787
- "epoch": 0.79,
1788
- "learning_rate": 4.6689008042895444e-05,
1789
- "loss": 0.3247,
1790
- "step": 297
1791
- },
1792
- {
1793
- "epoch": 0.79,
1794
- "learning_rate": 4.667560321715818e-05,
1795
- "loss": 0.306,
1796
- "step": 298
1797
- },
1798
- {
1799
- "epoch": 0.79,
1800
- "learning_rate": 4.6662198391420914e-05,
1801
- "loss": 0.2825,
1802
- "step": 299
1803
- },
1804
- {
1805
- "epoch": 0.79,
1806
- "learning_rate": 4.664879356568364e-05,
1807
- "loss": 0.6102,
1808
- "step": 300
1809
- },
1810
- {
1811
- "epoch": 0.8,
1812
- "learning_rate": 4.6635388739946385e-05,
1813
- "loss": 0.3613,
1814
- "step": 301
1815
- },
1816
- {
1817
- "epoch": 0.8,
1818
- "learning_rate": 4.662198391420911e-05,
1819
- "loss": 0.6327,
1820
- "step": 302
1821
- },
1822
- {
1823
- "epoch": 0.8,
1824
- "learning_rate": 4.6608579088471855e-05,
1825
- "loss": 0.4059,
1826
- "step": 303
1827
- },
1828
- {
1829
- "epoch": 0.8,
1830
- "learning_rate": 4.659517426273458e-05,
1831
- "loss": 0.4027,
1832
- "step": 304
1833
- },
1834
- {
1835
- "epoch": 0.81,
1836
- "learning_rate": 4.658176943699732e-05,
1837
- "loss": 0.9133,
1838
- "step": 305
1839
- },
1840
- {
1841
- "epoch": 0.81,
1842
- "learning_rate": 4.6568364611260054e-05,
1843
- "loss": 0.1869,
1844
- "step": 306
1845
- },
1846
- {
1847
- "epoch": 0.81,
1848
- "learning_rate": 4.655495978552279e-05,
1849
- "loss": 0.3987,
1850
- "step": 307
1851
- },
1852
- {
1853
- "epoch": 0.81,
1854
- "learning_rate": 4.6541554959785524e-05,
1855
- "loss": 0.6114,
1856
- "step": 308
1857
- },
1858
- {
1859
- "epoch": 0.82,
1860
- "learning_rate": 4.652815013404826e-05,
1861
- "loss": 0.4406,
1862
- "step": 309
1863
- },
1864
- {
1865
- "epoch": 0.82,
1866
- "learning_rate": 4.6514745308310994e-05,
1867
- "loss": 0.2954,
1868
- "step": 310
1869
- },
1870
- {
1871
- "epoch": 0.82,
1872
- "learning_rate": 4.650134048257373e-05,
1873
- "loss": 0.5067,
1874
- "step": 311
1875
- },
1876
- {
1877
- "epoch": 0.83,
1878
- "learning_rate": 4.6487935656836464e-05,
1879
- "loss": 0.3985,
1880
- "step": 312
1881
- },
1882
- {
1883
- "epoch": 0.83,
1884
- "learning_rate": 4.64745308310992e-05,
1885
- "loss": 0.3756,
1886
- "step": 313
1887
- },
1888
- {
1889
- "epoch": 0.83,
1890
- "learning_rate": 4.6461126005361935e-05,
1891
- "loss": 0.2618,
1892
- "step": 314
1893
- },
1894
- {
1895
- "epoch": 0.83,
1896
- "learning_rate": 4.644772117962466e-05,
1897
- "loss": 0.4992,
1898
- "step": 315
1899
- },
1900
- {
1901
- "epoch": 0.84,
1902
- "learning_rate": 4.6434316353887405e-05,
1903
- "loss": 0.8224,
1904
- "step": 316
1905
- },
1906
- {
1907
- "epoch": 0.84,
1908
- "learning_rate": 4.642091152815013e-05,
1909
- "loss": 0.3425,
1910
- "step": 317
1911
- },
1912
- {
1913
- "epoch": 0.84,
1914
- "learning_rate": 4.6407506702412875e-05,
1915
- "loss": 0.4062,
1916
- "step": 318
1917
- },
1918
- {
1919
- "epoch": 0.84,
1920
- "learning_rate": 4.6394101876675603e-05,
1921
- "loss": 0.4748,
1922
- "step": 319
1923
- },
1924
- {
1925
- "epoch": 0.85,
1926
- "learning_rate": 4.638069705093834e-05,
1927
- "loss": 0.6857,
1928
- "step": 320
1929
- },
1930
- {
1931
- "epoch": 0.85,
1932
- "learning_rate": 4.6367292225201074e-05,
1933
- "loss": 0.5368,
1934
- "step": 321
1935
- },
1936
- {
1937
- "epoch": 0.85,
1938
- "learning_rate": 4.635388739946381e-05,
1939
- "loss": 0.5571,
1940
- "step": 322
1941
- },
1942
- {
1943
- "epoch": 0.85,
1944
- "learning_rate": 4.6340482573726544e-05,
1945
- "loss": 0.3045,
1946
- "step": 323
1947
- },
1948
- {
1949
- "epoch": 0.86,
1950
- "learning_rate": 4.632707774798928e-05,
1951
- "loss": 0.3189,
1952
- "step": 324
1953
- },
1954
- {
1955
- "epoch": 0.86,
1956
- "learning_rate": 4.631367292225201e-05,
1957
- "loss": 0.3033,
1958
- "step": 325
1959
- },
1960
- {
1961
- "epoch": 0.86,
1962
- "learning_rate": 4.630026809651475e-05,
1963
- "loss": 0.4659,
1964
- "step": 326
1965
- },
1966
- {
1967
- "epoch": 0.87,
1968
- "learning_rate": 4.628686327077748e-05,
1969
- "loss": 0.4058,
1970
- "step": 327
1971
- },
1972
- {
1973
- "epoch": 0.87,
1974
- "learning_rate": 4.627345844504022e-05,
1975
- "loss": 0.6745,
1976
- "step": 328
1977
- },
1978
- {
1979
- "epoch": 0.87,
1980
- "learning_rate": 4.626005361930295e-05,
1981
- "loss": 0.3259,
1982
- "step": 329
1983
- },
1984
- {
1985
- "epoch": 0.87,
1986
- "learning_rate": 4.624664879356568e-05,
1987
- "loss": 0.5126,
1988
- "step": 330
1989
- },
1990
- {
1991
- "epoch": 0.88,
1992
- "learning_rate": 4.623324396782842e-05,
1993
- "loss": 0.2759,
1994
- "step": 331
1995
- },
1996
- {
1997
- "epoch": 0.88,
1998
- "learning_rate": 4.621983914209115e-05,
1999
- "loss": 0.2512,
2000
- "step": 332
2001
- },
2002
- {
2003
- "epoch": 0.88,
2004
- "learning_rate": 4.620643431635389e-05,
2005
- "loss": 0.3046,
2006
- "step": 333
2007
- },
2008
- {
2009
- "epoch": 0.88,
2010
- "learning_rate": 4.6193029490616624e-05,
2011
- "loss": 0.3931,
2012
- "step": 334
2013
- },
2014
- {
2015
- "epoch": 0.89,
2016
- "learning_rate": 4.617962466487936e-05,
2017
- "loss": 0.4838,
2018
- "step": 335
2019
- },
2020
- {
2021
- "epoch": 0.89,
2022
- "learning_rate": 4.6166219839142094e-05,
2023
- "loss": 0.2925,
2024
- "step": 336
2025
- },
2026
- {
2027
- "epoch": 0.89,
2028
- "learning_rate": 4.615281501340483e-05,
2029
- "loss": 0.4481,
2030
- "step": 337
2031
- },
2032
- {
2033
- "epoch": 0.89,
2034
- "learning_rate": 4.6139410187667564e-05,
2035
- "loss": 0.4528,
2036
- "step": 338
2037
- },
2038
- {
2039
- "epoch": 0.9,
2040
- "learning_rate": 4.61260053619303e-05,
2041
- "loss": 0.2934,
2042
- "step": 339
2043
- },
2044
- {
2045
- "epoch": 0.9,
2046
- "learning_rate": 4.611260053619303e-05,
2047
- "loss": 0.609,
2048
- "step": 340
2049
- },
2050
- {
2051
- "epoch": 0.9,
2052
- "learning_rate": 4.609919571045577e-05,
2053
- "loss": 0.8988,
2054
- "step": 341
2055
- },
2056
- {
2057
- "epoch": 0.9,
2058
- "learning_rate": 4.60857908847185e-05,
2059
- "loss": 1.1222,
2060
- "step": 342
2061
- },
2062
- {
2063
- "epoch": 0.91,
2064
- "learning_rate": 4.607238605898124e-05,
2065
- "loss": 0.3265,
2066
- "step": 343
2067
- },
2068
- {
2069
- "epoch": 0.91,
2070
- "learning_rate": 4.605898123324397e-05,
2071
- "loss": 0.4722,
2072
- "step": 344
2073
- },
2074
- {
2075
- "epoch": 0.91,
2076
- "learning_rate": 4.60455764075067e-05,
2077
- "loss": 0.2791,
2078
- "step": 345
2079
- },
2080
- {
2081
- "epoch": 0.92,
2082
- "learning_rate": 4.603217158176944e-05,
2083
- "loss": 0.4183,
2084
- "step": 346
2085
- },
2086
- {
2087
- "epoch": 0.92,
2088
- "learning_rate": 4.6018766756032174e-05,
2089
- "loss": 0.5323,
2090
- "step": 347
2091
- },
2092
- {
2093
- "epoch": 0.92,
2094
- "learning_rate": 4.600536193029491e-05,
2095
- "loss": 0.6108,
2096
- "step": 348
2097
- },
2098
- {
2099
- "epoch": 0.92,
2100
- "learning_rate": 4.5991957104557644e-05,
2101
- "loss": 0.2875,
2102
- "step": 349
2103
- },
2104
- {
2105
- "epoch": 0.93,
2106
- "learning_rate": 4.597855227882037e-05,
2107
- "loss": 0.6642,
2108
- "step": 350
2109
- },
2110
- {
2111
- "epoch": 0.93,
2112
- "learning_rate": 4.5965147453083114e-05,
2113
- "loss": 0.5244,
2114
- "step": 351
2115
- },
2116
- {
2117
- "epoch": 0.93,
2118
- "learning_rate": 4.595174262734584e-05,
2119
- "loss": 0.5562,
2120
- "step": 352
2121
- },
2122
- {
2123
- "epoch": 0.93,
2124
- "learning_rate": 4.5938337801608584e-05,
2125
- "loss": 0.3972,
2126
- "step": 353
2127
- },
2128
- {
2129
- "epoch": 0.94,
2130
- "learning_rate": 4.592493297587131e-05,
2131
- "loss": 0.4532,
2132
- "step": 354
2133
- },
2134
- {
2135
- "epoch": 0.94,
2136
- "learning_rate": 4.591152815013405e-05,
2137
- "loss": 0.3368,
2138
- "step": 355
2139
- },
2140
- {
2141
- "epoch": 0.94,
2142
- "learning_rate": 4.589812332439678e-05,
2143
- "loss": 0.171,
2144
- "step": 356
2145
- },
2146
- {
2147
- "epoch": 0.94,
2148
- "learning_rate": 4.588471849865952e-05,
2149
- "loss": 0.4036,
2150
- "step": 357
2151
- },
2152
- {
2153
- "epoch": 0.95,
2154
- "learning_rate": 4.587131367292225e-05,
2155
- "loss": 0.4305,
2156
- "step": 358
2157
- },
2158
- {
2159
- "epoch": 0.95,
2160
- "learning_rate": 4.585790884718499e-05,
2161
- "loss": 0.2643,
2162
- "step": 359
2163
- },
2164
- {
2165
- "epoch": 0.95,
2166
- "learning_rate": 4.5844504021447723e-05,
2167
- "loss": 0.3782,
2168
- "step": 360
2169
- },
2170
- {
2171
- "epoch": 0.96,
2172
- "learning_rate": 4.583109919571046e-05,
2173
- "loss": 0.1673,
2174
- "step": 361
2175
- },
2176
- {
2177
- "epoch": 0.96,
2178
- "learning_rate": 4.5817694369973194e-05,
2179
- "loss": 0.3969,
2180
- "step": 362
2181
- },
2182
- {
2183
- "epoch": 0.96,
2184
- "learning_rate": 4.580428954423593e-05,
2185
- "loss": 0.3249,
2186
- "step": 363
2187
- },
2188
- {
2189
- "epoch": 0.96,
2190
- "learning_rate": 4.5790884718498664e-05,
2191
- "loss": 0.1656,
2192
- "step": 364
2193
- },
2194
- {
2195
- "epoch": 0.97,
2196
- "learning_rate": 4.57774798927614e-05,
2197
- "loss": 0.4551,
2198
- "step": 365
2199
- },
2200
- {
2201
- "epoch": 0.97,
2202
- "learning_rate": 4.5764075067024134e-05,
2203
- "loss": 0.6075,
2204
- "step": 366
2205
- },
2206
- {
2207
- "epoch": 0.97,
2208
- "learning_rate": 4.575067024128686e-05,
2209
- "loss": 0.4699,
2210
- "step": 367
2211
- },
2212
- {
2213
- "epoch": 0.97,
2214
- "learning_rate": 4.5737265415549605e-05,
2215
- "loss": 0.5752,
2216
- "step": 368
2217
- },
2218
- {
2219
- "epoch": 0.98,
2220
- "learning_rate": 4.572386058981233e-05,
2221
- "loss": 0.3114,
2222
- "step": 369
2223
- },
2224
- {
2225
- "epoch": 0.98,
2226
- "learning_rate": 4.5710455764075075e-05,
2227
- "loss": 0.7407,
2228
- "step": 370
2229
- },
2230
- {
2231
- "epoch": 0.98,
2232
- "learning_rate": 4.56970509383378e-05,
2233
- "loss": 0.6427,
2234
- "step": 371
2235
- },
2236
- {
2237
- "epoch": 0.98,
2238
- "learning_rate": 4.568364611260054e-05,
2239
- "loss": 0.5021,
2240
- "step": 372
2241
- },
2242
- {
2243
- "epoch": 0.99,
2244
- "learning_rate": 4.5670241286863273e-05,
2245
- "loss": 0.4209,
2246
- "step": 373
2247
- },
2248
- {
2249
- "epoch": 0.99,
2250
- "learning_rate": 4.565683646112601e-05,
2251
- "loss": 0.5957,
2252
- "step": 374
2253
- },
2254
- {
2255
- "epoch": 0.99,
2256
- "learning_rate": 4.5643431635388744e-05,
2257
- "loss": 0.495,
2258
- "step": 375
2259
- },
2260
- {
2261
- "epoch": 0.99,
2262
- "learning_rate": 4.563002680965148e-05,
2263
- "loss": 0.3101,
2264
- "step": 376
2265
- },
2266
- {
2267
- "epoch": 1.0,
2268
- "learning_rate": 4.561662198391421e-05,
2269
- "loss": 0.472,
2270
- "step": 377
2271
- },
2272
- {
2273
- "epoch": 1.0,
2274
- "learning_rate": 4.560321715817695e-05,
2275
- "loss": 0.4607,
2276
- "step": 378
2277
- },
2278
- {
2279
- "epoch": 1.0,
2280
- "eval_f1": 0.7914963205233032,
2281
- "eval_loss": 0.40209120512008667,
2282
- "eval_runtime": 2.1585,
2283
- "eval_samples_per_second": 700.949,
2284
- "eval_steps_per_second": 44.012,
2285
- "step": 378
2286
- },
2287
- {
2288
- "epoch": 1.0,
2289
- "learning_rate": 4.558981233243968e-05,
2290
- "loss": 0.2422,
2291
- "step": 379
2292
- },
2293
- {
2294
- "epoch": 1.01,
2295
- "learning_rate": 4.557640750670242e-05,
2296
- "loss": 0.2074,
2297
- "step": 380
2298
- },
2299
- {
2300
- "epoch": 1.01,
2301
- "learning_rate": 4.556300268096515e-05,
2302
- "loss": 0.4469,
2303
- "step": 381
2304
- },
2305
- {
2306
- "epoch": 1.01,
2307
- "learning_rate": 4.554959785522788e-05,
2308
- "loss": 0.3121,
2309
- "step": 382
2310
- },
2311
- {
2312
- "epoch": 1.01,
2313
- "learning_rate": 4.553619302949062e-05,
2314
- "loss": 0.3634,
2315
- "step": 383
2316
- },
2317
- {
2318
- "epoch": 1.02,
2319
- "learning_rate": 4.552278820375335e-05,
2320
- "loss": 0.2139,
2321
- "step": 384
2322
- },
2323
- {
2324
- "epoch": 1.02,
2325
- "learning_rate": 4.550938337801609e-05,
2326
- "loss": 0.5273,
2327
- "step": 385
2328
- },
2329
- {
2330
- "epoch": 1.02,
2331
- "learning_rate": 4.549597855227882e-05,
2332
- "loss": 0.1228,
2333
- "step": 386
2334
- },
2335
- {
2336
- "epoch": 1.02,
2337
- "learning_rate": 4.548257372654156e-05,
2338
- "loss": 0.2459,
2339
- "step": 387
2340
- },
2341
- {
2342
- "epoch": 1.03,
2343
- "learning_rate": 4.5469168900804294e-05,
2344
- "loss": 0.443,
2345
- "step": 388
2346
- },
2347
- {
2348
- "epoch": 1.03,
2349
- "learning_rate": 4.545576407506703e-05,
2350
- "loss": 0.364,
2351
- "step": 389
2352
- },
2353
- {
2354
- "epoch": 1.03,
2355
- "learning_rate": 4.5442359249329764e-05,
2356
- "loss": 0.4071,
2357
- "step": 390
2358
- },
2359
- {
2360
- "epoch": 1.03,
2361
- "learning_rate": 4.54289544235925e-05,
2362
- "loss": 0.3876,
2363
- "step": 391
2364
- },
2365
- {
2366
- "epoch": 1.04,
2367
- "learning_rate": 4.541554959785523e-05,
2368
- "loss": 0.5239,
2369
- "step": 392
2370
- },
2371
- {
2372
- "epoch": 1.04,
2373
- "learning_rate": 4.540214477211797e-05,
2374
- "loss": 0.4548,
2375
- "step": 393
2376
- },
2377
- {
2378
- "epoch": 1.04,
2379
- "learning_rate": 4.53887399463807e-05,
2380
- "loss": 0.3588,
2381
- "step": 394
2382
- },
2383
- {
2384
- "epoch": 1.04,
2385
- "learning_rate": 4.537533512064344e-05,
2386
- "loss": 0.2693,
2387
- "step": 395
2388
- },
2389
- {
2390
- "epoch": 1.05,
2391
- "learning_rate": 4.536193029490617e-05,
2392
- "loss": 0.3773,
2393
- "step": 396
2394
- },
2395
- {
2396
- "epoch": 1.05,
2397
- "learning_rate": 4.53485254691689e-05,
2398
- "loss": 0.3982,
2399
- "step": 397
2400
- },
2401
- {
2402
- "epoch": 1.05,
2403
- "learning_rate": 4.533512064343164e-05,
2404
- "loss": 0.2074,
2405
- "step": 398
2406
- },
2407
- {
2408
- "epoch": 1.06,
2409
- "learning_rate": 4.532171581769437e-05,
2410
- "loss": 0.3322,
2411
- "step": 399
2412
- },
2413
- {
2414
- "epoch": 1.06,
2415
- "learning_rate": 4.530831099195711e-05,
2416
- "loss": 0.118,
2417
- "step": 400
2418
- },
2419
- {
2420
- "epoch": 1.06,
2421
- "learning_rate": 4.5294906166219844e-05,
2422
- "loss": 0.6216,
2423
- "step": 401
2424
- },
2425
- {
2426
- "epoch": 1.06,
2427
- "learning_rate": 4.528150134048257e-05,
2428
- "loss": 0.4028,
2429
- "step": 402
2430
- },
2431
- {
2432
- "epoch": 1.07,
2433
- "learning_rate": 4.5268096514745314e-05,
2434
- "loss": 0.3179,
2435
- "step": 403
2436
- },
2437
- {
2438
- "epoch": 1.07,
2439
- "learning_rate": 4.525469168900804e-05,
2440
- "loss": 0.2815,
2441
- "step": 404
2442
- },
2443
- {
2444
- "epoch": 1.07,
2445
- "learning_rate": 4.5241286863270784e-05,
2446
- "loss": 0.2366,
2447
- "step": 405
2448
- },
2449
- {
2450
- "epoch": 1.07,
2451
- "learning_rate": 4.522788203753351e-05,
2452
- "loss": 0.14,
2453
- "step": 406
2454
- },
2455
- {
2456
- "epoch": 1.08,
2457
- "learning_rate": 4.521447721179625e-05,
2458
- "loss": 0.1255,
2459
- "step": 407
2460
- },
2461
- {
2462
- "epoch": 1.08,
2463
- "learning_rate": 4.520107238605898e-05,
2464
- "loss": 0.1482,
2465
- "step": 408
2466
- },
2467
- {
2468
- "epoch": 1.08,
2469
- "learning_rate": 4.518766756032172e-05,
2470
- "loss": 0.665,
2471
- "step": 409
2472
- },
2473
- {
2474
- "epoch": 1.08,
2475
- "learning_rate": 4.517426273458445e-05,
2476
- "loss": 0.2535,
2477
- "step": 410
2478
- },
2479
- {
2480
- "epoch": 1.09,
2481
- "learning_rate": 4.516085790884719e-05,
2482
- "loss": 0.1716,
2483
- "step": 411
2484
- },
2485
- {
2486
- "epoch": 1.09,
2487
- "learning_rate": 4.5147453083109916e-05,
2488
- "loss": 0.0765,
2489
- "step": 412
2490
- },
2491
- {
2492
- "epoch": 1.09,
2493
- "learning_rate": 4.513404825737266e-05,
2494
- "loss": 0.1238,
2495
- "step": 413
2496
- },
2497
- {
2498
- "epoch": 1.1,
2499
- "learning_rate": 4.512064343163539e-05,
2500
- "loss": 0.3877,
2501
- "step": 414
2502
- },
2503
- {
2504
- "epoch": 1.1,
2505
- "learning_rate": 4.510723860589813e-05,
2506
- "loss": 0.206,
2507
- "step": 415
2508
- },
2509
- {
2510
- "epoch": 1.1,
2511
- "learning_rate": 4.509383378016086e-05,
2512
- "loss": 0.1822,
2513
- "step": 416
2514
- },
2515
- {
2516
- "epoch": 1.1,
2517
- "learning_rate": 4.508042895442359e-05,
2518
- "loss": 0.2294,
2519
- "step": 417
2520
- },
2521
- {
2522
- "epoch": 1.11,
2523
- "learning_rate": 4.506702412868633e-05,
2524
- "loss": 0.7083,
2525
- "step": 418
2526
- },
2527
- {
2528
- "epoch": 1.11,
2529
- "learning_rate": 4.505361930294906e-05,
2530
- "loss": 0.325,
2531
- "step": 419
2532
- },
2533
- {
2534
- "epoch": 1.11,
2535
- "learning_rate": 4.50402144772118e-05,
2536
- "loss": 0.2378,
2537
- "step": 420
2538
- },
2539
- {
2540
- "epoch": 1.11,
2541
- "learning_rate": 4.502680965147453e-05,
2542
- "loss": 0.2494,
2543
- "step": 421
2544
- },
2545
- {
2546
- "epoch": 1.12,
2547
- "learning_rate": 4.501340482573727e-05,
2548
- "loss": 0.3812,
2549
- "step": 422
2550
- },
2551
- {
2552
- "epoch": 1.12,
2553
- "learning_rate": 4.5e-05,
2554
- "loss": 0.1491,
2555
- "step": 423
2556
- },
2557
- {
2558
- "epoch": 1.12,
2559
- "learning_rate": 4.498659517426274e-05,
2560
- "loss": 0.0833,
2561
- "step": 424
2562
- },
2563
- {
2564
- "epoch": 1.12,
2565
- "learning_rate": 4.497319034852547e-05,
2566
- "loss": 0.4637,
2567
- "step": 425
2568
- },
2569
- {
2570
- "epoch": 1.13,
2571
- "learning_rate": 4.495978552278821e-05,
2572
- "loss": 0.2594,
2573
- "step": 426
2574
- },
2575
- {
2576
- "epoch": 1.13,
2577
- "learning_rate": 4.4946380697050937e-05,
2578
- "loss": 0.4136,
2579
- "step": 427
2580
- },
2581
- {
2582
- "epoch": 1.13,
2583
- "learning_rate": 4.493297587131368e-05,
2584
- "loss": 0.4962,
2585
- "step": 428
2586
- },
2587
- {
2588
- "epoch": 1.13,
2589
- "learning_rate": 4.491957104557641e-05,
2590
- "loss": 0.0842,
2591
- "step": 429
2592
- },
2593
- {
2594
- "epoch": 1.14,
2595
- "learning_rate": 4.490616621983915e-05,
2596
- "loss": 0.4761,
2597
- "step": 430
2598
- },
2599
- {
2600
- "epoch": 1.14,
2601
- "learning_rate": 4.489276139410188e-05,
2602
- "loss": 0.4351,
2603
- "step": 431
2604
- },
2605
- {
2606
- "epoch": 1.14,
2607
- "learning_rate": 4.487935656836461e-05,
2608
- "loss": 0.4226,
2609
- "step": 432
2610
- },
2611
- {
2612
- "epoch": 1.15,
2613
- "learning_rate": 4.486595174262735e-05,
2614
- "loss": 0.5714,
2615
- "step": 433
2616
- },
2617
- {
2618
- "epoch": 1.15,
2619
- "learning_rate": 4.485254691689008e-05,
2620
- "loss": 0.2034,
2621
- "step": 434
2622
- },
2623
- {
2624
- "epoch": 1.15,
2625
- "learning_rate": 4.483914209115282e-05,
2626
- "loss": 0.3354,
2627
- "step": 435
2628
- },
2629
- {
2630
- "epoch": 1.15,
2631
- "learning_rate": 4.482573726541555e-05,
2632
- "loss": 0.7503,
2633
- "step": 436
2634
- },
2635
- {
2636
- "epoch": 1.16,
2637
- "learning_rate": 4.481233243967828e-05,
2638
- "loss": 0.1542,
2639
- "step": 437
2640
- },
2641
- {
2642
- "epoch": 1.16,
2643
- "learning_rate": 4.479892761394102e-05,
2644
- "loss": 0.3067,
2645
- "step": 438
2646
- },
2647
- {
2648
- "epoch": 1.16,
2649
- "learning_rate": 4.478552278820375e-05,
2650
- "loss": 0.4134,
2651
- "step": 439
2652
- },
2653
- {
2654
- "epoch": 1.16,
2655
- "learning_rate": 4.477211796246649e-05,
2656
- "loss": 0.1458,
2657
- "step": 440
2658
- },
2659
- {
2660
- "epoch": 1.17,
2661
- "learning_rate": 4.475871313672922e-05,
2662
- "loss": 0.2814,
2663
- "step": 441
2664
- },
2665
- {
2666
- "epoch": 1.17,
2667
- "learning_rate": 4.474530831099196e-05,
2668
- "loss": 0.1751,
2669
- "step": 442
2670
- },
2671
- {
2672
- "epoch": 1.17,
2673
- "learning_rate": 4.473190348525469e-05,
2674
- "loss": 0.4144,
2675
- "step": 443
2676
- },
2677
- {
2678
- "epoch": 1.17,
2679
- "learning_rate": 4.471849865951743e-05,
2680
- "loss": 0.3275,
2681
- "step": 444
2682
- },
2683
- {
2684
- "epoch": 1.18,
2685
- "learning_rate": 4.470509383378016e-05,
2686
- "loss": 0.3083,
2687
- "step": 445
2688
- },
2689
- {
2690
- "epoch": 1.18,
2691
- "learning_rate": 4.46916890080429e-05,
2692
- "loss": 0.4185,
2693
- "step": 446
2694
- },
2695
- {
2696
- "epoch": 1.18,
2697
- "learning_rate": 4.467828418230563e-05,
2698
- "loss": 0.3181,
2699
- "step": 447
2700
- },
2701
- {
2702
- "epoch": 1.19,
2703
- "learning_rate": 4.466487935656837e-05,
2704
- "loss": 0.438,
2705
- "step": 448
2706
- },
2707
- {
2708
- "epoch": 1.19,
2709
- "learning_rate": 4.46514745308311e-05,
2710
- "loss": 0.4509,
2711
- "step": 449
2712
- },
2713
- {
2714
- "epoch": 1.19,
2715
- "learning_rate": 4.463806970509384e-05,
2716
- "loss": 0.4597,
2717
- "step": 450
2718
- },
2719
- {
2720
- "epoch": 1.19,
2721
- "learning_rate": 4.462466487935657e-05,
2722
- "loss": 0.3123,
2723
- "step": 451
2724
- },
2725
- {
2726
- "epoch": 1.2,
2727
- "learning_rate": 4.46112600536193e-05,
2728
- "loss": 0.376,
2729
- "step": 452
2730
- },
2731
- {
2732
- "epoch": 1.2,
2733
- "learning_rate": 4.459785522788204e-05,
2734
- "loss": 0.2392,
2735
- "step": 453
2736
- },
2737
- {
2738
- "epoch": 1.2,
2739
- "learning_rate": 4.458445040214477e-05,
2740
- "loss": 0.4451,
2741
- "step": 454
2742
- },
2743
- {
2744
- "epoch": 1.2,
2745
- "learning_rate": 4.4571045576407513e-05,
2746
- "loss": 0.2436,
2747
- "step": 455
2748
- },
2749
- {
2750
- "epoch": 1.21,
2751
- "learning_rate": 4.455764075067024e-05,
2752
- "loss": 0.2944,
2753
- "step": 456
2754
- },
2755
- {
2756
- "epoch": 1.21,
2757
- "learning_rate": 4.454423592493298e-05,
2758
- "loss": 0.323,
2759
- "step": 457
2760
- },
2761
- {
2762
- "epoch": 1.21,
2763
- "learning_rate": 4.453083109919571e-05,
2764
- "loss": 0.1966,
2765
- "step": 458
2766
- },
2767
- {
2768
- "epoch": 1.21,
2769
- "learning_rate": 4.451742627345845e-05,
2770
- "loss": 0.273,
2771
- "step": 459
2772
- },
2773
- {
2774
- "epoch": 1.22,
2775
- "learning_rate": 4.450402144772118e-05,
2776
- "loss": 0.3498,
2777
- "step": 460
2778
- },
2779
- {
2780
- "epoch": 1.22,
2781
- "learning_rate": 4.449061662198392e-05,
2782
- "loss": 0.458,
2783
- "step": 461
2784
- },
2785
- {
2786
- "epoch": 1.22,
2787
- "learning_rate": 4.4477211796246646e-05,
2788
- "loss": 0.1607,
2789
- "step": 462
2790
- },
2791
- {
2792
- "epoch": 1.22,
2793
- "learning_rate": 4.446380697050939e-05,
2794
- "loss": 0.5712,
2795
- "step": 463
2796
- },
2797
- {
2798
- "epoch": 1.23,
2799
- "learning_rate": 4.4450402144772116e-05,
2800
- "loss": 0.0908,
2801
- "step": 464
2802
- },
2803
- {
2804
- "epoch": 1.23,
2805
- "learning_rate": 4.443699731903486e-05,
2806
- "loss": 0.2625,
2807
- "step": 465
2808
- },
2809
- {
2810
- "epoch": 1.23,
2811
- "learning_rate": 4.4423592493297586e-05,
2812
- "loss": 0.368,
2813
- "step": 466
2814
- },
2815
- {
2816
- "epoch": 1.24,
2817
- "learning_rate": 4.441018766756032e-05,
2818
- "loss": 0.5096,
2819
- "step": 467
2820
- },
2821
- {
2822
- "epoch": 1.24,
2823
- "learning_rate": 4.4396782841823057e-05,
2824
- "loss": 0.209,
2825
- "step": 468
2826
- },
2827
- {
2828
- "epoch": 1.24,
2829
- "learning_rate": 4.438337801608579e-05,
2830
- "loss": 0.5235,
2831
- "step": 469
2832
- },
2833
- {
2834
- "epoch": 1.24,
2835
- "learning_rate": 4.436997319034853e-05,
2836
- "loss": 0.5116,
2837
- "step": 470
2838
- },
2839
- {
2840
- "epoch": 1.25,
2841
- "learning_rate": 4.435656836461126e-05,
2842
- "loss": 0.49,
2843
- "step": 471
2844
- },
2845
- {
2846
- "epoch": 1.25,
2847
- "learning_rate": 4.4343163538874e-05,
2848
- "loss": 0.4409,
2849
- "step": 472
2850
- },
2851
- {
2852
- "epoch": 1.25,
2853
- "learning_rate": 4.432975871313673e-05,
2854
- "loss": 0.1324,
2855
- "step": 473
2856
- },
2857
- {
2858
- "epoch": 1.25,
2859
- "learning_rate": 4.431635388739947e-05,
2860
- "loss": 0.1257,
2861
- "step": 474
2862
- },
2863
- {
2864
- "epoch": 1.26,
2865
- "learning_rate": 4.43029490616622e-05,
2866
- "loss": 0.3844,
2867
- "step": 475
2868
- },
2869
- {
2870
- "epoch": 1.26,
2871
- "learning_rate": 4.428954423592494e-05,
2872
- "loss": 0.2942,
2873
- "step": 476
2874
- },
2875
- {
2876
- "epoch": 1.26,
2877
- "learning_rate": 4.4276139410187666e-05,
2878
- "loss": 0.316,
2879
- "step": 477
2880
- },
2881
- {
2882
- "epoch": 1.26,
2883
- "learning_rate": 4.426273458445041e-05,
2884
- "loss": 0.3724,
2885
- "step": 478
2886
- },
2887
- {
2888
- "epoch": 1.27,
2889
- "learning_rate": 4.4249329758713136e-05,
2890
- "loss": 0.4498,
2891
- "step": 479
2892
- },
2893
- {
2894
- "epoch": 1.27,
2895
- "learning_rate": 4.423592493297588e-05,
2896
- "loss": 0.2677,
2897
- "step": 480
2898
- },
2899
- {
2900
- "epoch": 1.27,
2901
- "learning_rate": 4.4222520107238607e-05,
2902
- "loss": 0.3331,
2903
- "step": 481
2904
- },
2905
- {
2906
- "epoch": 1.28,
2907
- "learning_rate": 4.420911528150134e-05,
2908
- "loss": 0.4375,
2909
- "step": 482
2910
- },
2911
- {
2912
- "epoch": 1.28,
2913
- "learning_rate": 4.419571045576408e-05,
2914
- "loss": 0.3097,
2915
- "step": 483
2916
- },
2917
- {
2918
- "epoch": 1.28,
2919
- "learning_rate": 4.418230563002681e-05,
2920
- "loss": 0.4438,
2921
- "step": 484
2922
- },
2923
- {
2924
- "epoch": 1.28,
2925
- "learning_rate": 4.416890080428955e-05,
2926
- "loss": 0.3648,
2927
- "step": 485
2928
- },
2929
- {
2930
- "epoch": 1.29,
2931
- "learning_rate": 4.415549597855228e-05,
2932
- "loss": 0.3023,
2933
- "step": 486
2934
- },
2935
- {
2936
- "epoch": 1.29,
2937
- "learning_rate": 4.414209115281502e-05,
2938
- "loss": 0.2963,
2939
- "step": 487
2940
- },
2941
- {
2942
- "epoch": 1.29,
2943
- "learning_rate": 4.412868632707775e-05,
2944
- "loss": 0.1749,
2945
- "step": 488
2946
- },
2947
- {
2948
- "epoch": 1.29,
2949
- "learning_rate": 4.411528150134048e-05,
2950
- "loss": 0.2006,
2951
- "step": 489
2952
- },
2953
- {
2954
- "epoch": 1.3,
2955
- "learning_rate": 4.410187667560322e-05,
2956
- "loss": 0.0923,
2957
- "step": 490
2958
- },
2959
- {
2960
- "epoch": 1.3,
2961
- "learning_rate": 4.408847184986595e-05,
2962
- "loss": 0.2665,
2963
- "step": 491
2964
- },
2965
- {
2966
- "epoch": 1.3,
2967
- "learning_rate": 4.407506702412869e-05,
2968
- "loss": 0.3378,
2969
- "step": 492
2970
- },
2971
- {
2972
- "epoch": 1.3,
2973
- "learning_rate": 4.406166219839142e-05,
2974
- "loss": 0.2543,
2975
- "step": 493
2976
- },
2977
- {
2978
- "epoch": 1.31,
2979
- "learning_rate": 4.4048257372654156e-05,
2980
- "loss": 0.2521,
2981
- "step": 494
2982
- },
2983
- {
2984
- "epoch": 1.31,
2985
- "learning_rate": 4.403485254691689e-05,
2986
- "loss": 0.1616,
2987
- "step": 495
2988
- },
2989
- {
2990
- "epoch": 1.31,
2991
- "learning_rate": 4.402144772117963e-05,
2992
- "loss": 0.1445,
2993
- "step": 496
2994
- },
2995
- {
2996
- "epoch": 1.31,
2997
- "learning_rate": 4.400804289544236e-05,
2998
- "loss": 0.5352,
2999
- "step": 497
3000
- },
3001
- {
3002
- "epoch": 1.32,
3003
- "learning_rate": 4.39946380697051e-05,
3004
- "loss": 0.0654,
3005
- "step": 498
3006
- },
3007
- {
3008
- "epoch": 1.32,
3009
- "learning_rate": 4.398123324396783e-05,
3010
- "loss": 0.4354,
3011
- "step": 499
3012
- },
3013
- {
3014
- "epoch": 1.32,
3015
- "learning_rate": 4.396782841823057e-05,
3016
- "loss": 0.3893,
3017
- "step": 500
3018
- },
3019
- {
3020
- "epoch": 1.33,
3021
- "learning_rate": 4.39544235924933e-05,
3022
- "loss": 0.2779,
3023
- "step": 501
3024
- },
3025
- {
3026
- "epoch": 1.33,
3027
- "learning_rate": 4.394101876675604e-05,
3028
- "loss": 0.3702,
3029
- "step": 502
3030
- },
3031
- {
3032
- "epoch": 1.33,
3033
- "learning_rate": 4.392761394101877e-05,
3034
- "loss": 0.3899,
3035
- "step": 503
3036
- },
3037
- {
3038
- "epoch": 1.33,
3039
- "learning_rate": 4.39142091152815e-05,
3040
- "loss": 0.3091,
3041
- "step": 504
3042
- },
3043
- {
3044
- "epoch": 1.34,
3045
- "learning_rate": 4.390080428954424e-05,
3046
- "loss": 0.2143,
3047
- "step": 505
3048
- },
3049
- {
3050
- "epoch": 1.34,
3051
- "learning_rate": 4.388739946380697e-05,
3052
- "loss": 0.2551,
3053
- "step": 506
3054
- },
3055
- {
3056
- "epoch": 1.34,
3057
- "learning_rate": 4.387399463806971e-05,
3058
- "loss": 0.2227,
3059
- "step": 507
3060
- },
3061
- {
3062
- "epoch": 1.34,
3063
- "learning_rate": 4.386058981233244e-05,
3064
- "loss": 0.1383,
3065
- "step": 508
3066
- },
3067
- {
3068
- "epoch": 1.35,
3069
- "learning_rate": 4.384718498659518e-05,
3070
- "loss": 0.3463,
3071
- "step": 509
3072
- },
3073
- {
3074
- "epoch": 1.35,
3075
- "learning_rate": 4.383378016085791e-05,
3076
- "loss": 0.1104,
3077
- "step": 510
3078
- },
3079
- {
3080
- "epoch": 1.35,
3081
- "learning_rate": 4.382037533512065e-05,
3082
- "loss": 0.2439,
3083
- "step": 511
3084
- },
3085
- {
3086
- "epoch": 1.35,
3087
- "learning_rate": 4.380697050938338e-05,
3088
- "loss": 0.0725,
3089
- "step": 512
3090
- },
3091
- {
3092
- "epoch": 1.36,
3093
- "learning_rate": 4.379356568364612e-05,
3094
- "loss": 0.4928,
3095
- "step": 513
3096
- },
3097
- {
3098
- "epoch": 1.36,
3099
- "learning_rate": 4.3780160857908846e-05,
3100
- "loss": 0.0903,
3101
- "step": 514
3102
- },
3103
- {
3104
- "epoch": 1.36,
3105
- "learning_rate": 4.376675603217159e-05,
3106
- "loss": 0.1808,
3107
- "step": 515
3108
- },
3109
- {
3110
- "epoch": 1.37,
3111
- "learning_rate": 4.3753351206434316e-05,
3112
- "loss": 0.617,
3113
- "step": 516
3114
- },
3115
- {
3116
- "epoch": 1.37,
3117
- "learning_rate": 4.373994638069706e-05,
3118
- "loss": 0.0333,
3119
- "step": 517
3120
- },
3121
- {
3122
- "epoch": 1.37,
3123
- "learning_rate": 4.3726541554959786e-05,
3124
- "loss": 0.1113,
3125
- "step": 518
3126
- },
3127
- {
3128
- "epoch": 1.37,
3129
- "learning_rate": 4.371313672922252e-05,
3130
- "loss": 0.4604,
3131
- "step": 519
3132
- },
3133
- {
3134
- "epoch": 1.38,
3135
- "learning_rate": 4.3699731903485256e-05,
3136
- "loss": 0.4267,
3137
- "step": 520
3138
- },
3139
- {
3140
- "epoch": 1.38,
3141
- "learning_rate": 4.368632707774799e-05,
3142
- "loss": 0.2621,
3143
- "step": 521
3144
- },
3145
- {
3146
- "epoch": 1.38,
3147
- "learning_rate": 4.3672922252010727e-05,
3148
- "loss": 0.3236,
3149
- "step": 522
3150
- },
3151
- {
3152
- "epoch": 1.38,
3153
- "learning_rate": 4.365951742627346e-05,
3154
- "loss": 0.0559,
3155
- "step": 523
3156
- },
3157
- {
3158
- "epoch": 1.39,
3159
- "learning_rate": 4.364611260053619e-05,
3160
- "loss": 0.0801,
3161
- "step": 524
3162
- },
3163
- {
3164
- "epoch": 1.39,
3165
- "learning_rate": 4.363270777479893e-05,
3166
- "loss": 0.0518,
3167
- "step": 525
3168
- },
3169
- {
3170
- "epoch": 1.39,
3171
- "learning_rate": 4.361930294906166e-05,
3172
- "loss": 0.0618,
3173
- "step": 526
3174
- },
3175
- {
3176
- "epoch": 1.39,
3177
- "learning_rate": 4.36058981233244e-05,
3178
- "loss": 0.3043,
3179
- "step": 527
3180
- },
3181
- {
3182
- "epoch": 1.4,
3183
- "learning_rate": 4.359249329758713e-05,
3184
- "loss": 0.4693,
3185
- "step": 528
3186
- },
3187
- {
3188
- "epoch": 1.4,
3189
- "learning_rate": 4.3579088471849866e-05,
3190
- "loss": 0.2978,
3191
- "step": 529
3192
- },
3193
- {
3194
- "epoch": 1.4,
3195
- "learning_rate": 4.35656836461126e-05,
3196
- "loss": 0.0817,
3197
- "step": 530
3198
- },
3199
- {
3200
- "epoch": 1.4,
3201
- "learning_rate": 4.3552278820375336e-05,
3202
- "loss": 0.0784,
3203
- "step": 531
3204
- },
3205
- {
3206
- "epoch": 1.41,
3207
- "learning_rate": 4.353887399463807e-05,
3208
- "loss": 0.5389,
3209
- "step": 532
3210
- },
3211
- {
3212
- "epoch": 1.41,
3213
- "learning_rate": 4.3525469168900806e-05,
3214
- "loss": 0.2337,
3215
- "step": 533
3216
- },
3217
- {
3218
- "epoch": 1.41,
3219
- "learning_rate": 4.351206434316354e-05,
3220
- "loss": 0.3189,
3221
- "step": 534
3222
- },
3223
- {
3224
- "epoch": 1.42,
3225
- "learning_rate": 4.3498659517426276e-05,
3226
- "loss": 0.2503,
3227
- "step": 535
3228
- },
3229
- {
3230
- "epoch": 1.42,
3231
- "learning_rate": 4.348525469168901e-05,
3232
- "loss": 0.333,
3233
- "step": 536
3234
- },
3235
- {
3236
- "epoch": 1.42,
3237
- "learning_rate": 4.347184986595175e-05,
3238
- "loss": 0.2311,
3239
- "step": 537
3240
- },
3241
- {
3242
- "epoch": 1.42,
3243
- "learning_rate": 4.345844504021448e-05,
3244
- "loss": 0.5196,
3245
- "step": 538
3246
- },
3247
- {
3248
- "epoch": 1.43,
3249
- "learning_rate": 4.344504021447721e-05,
3250
- "loss": 0.5466,
3251
- "step": 539
3252
- },
3253
- {
3254
- "epoch": 1.43,
3255
- "learning_rate": 4.343163538873995e-05,
3256
- "loss": 0.4296,
3257
- "step": 540
3258
- },
3259
- {
3260
- "epoch": 1.43,
3261
- "learning_rate": 4.341823056300268e-05,
3262
- "loss": 0.6559,
3263
- "step": 541
3264
- },
3265
- {
3266
- "epoch": 1.43,
3267
- "learning_rate": 4.340482573726542e-05,
3268
- "loss": 0.6134,
3269
- "step": 542
3270
- },
3271
- {
3272
- "epoch": 1.44,
3273
- "learning_rate": 4.339142091152815e-05,
3274
- "loss": 0.5614,
3275
- "step": 543
3276
- },
3277
- {
3278
- "epoch": 1.44,
3279
- "learning_rate": 4.3378016085790886e-05,
3280
- "loss": 0.3143,
3281
- "step": 544
3282
- },
3283
- {
3284
- "epoch": 1.44,
3285
- "learning_rate": 4.336461126005362e-05,
3286
- "loss": 0.564,
3287
- "step": 545
3288
- },
3289
- {
3290
- "epoch": 1.44,
3291
- "learning_rate": 4.3351206434316356e-05,
3292
- "loss": 0.2141,
3293
- "step": 546
3294
- },
3295
- {
3296
- "epoch": 1.45,
3297
- "learning_rate": 4.333780160857909e-05,
3298
- "loss": 0.5886,
3299
- "step": 547
3300
- },
3301
- {
3302
- "epoch": 1.45,
3303
- "learning_rate": 4.3324396782841826e-05,
3304
- "loss": 0.2129,
3305
- "step": 548
3306
- },
3307
- {
3308
- "epoch": 1.45,
3309
- "learning_rate": 4.3310991957104555e-05,
3310
- "loss": 0.2491,
3311
- "step": 549
3312
- },
3313
- {
3314
- "epoch": 1.46,
3315
- "learning_rate": 4.32975871313673e-05,
3316
- "loss": 0.4023,
3317
- "step": 550
3318
- },
3319
- {
3320
- "epoch": 1.46,
3321
- "learning_rate": 4.3284182305630025e-05,
3322
- "loss": 0.2159,
3323
- "step": 551
3324
- },
3325
- {
3326
- "epoch": 1.46,
3327
- "learning_rate": 4.327077747989277e-05,
3328
- "loss": 0.2975,
3329
- "step": 552
3330
- },
3331
- {
3332
- "epoch": 1.46,
3333
- "learning_rate": 4.3257372654155495e-05,
3334
- "loss": 0.165,
3335
- "step": 553
3336
- },
3337
- {
3338
- "epoch": 1.47,
3339
- "learning_rate": 4.324396782841823e-05,
3340
- "loss": 0.063,
3341
- "step": 554
3342
- },
3343
- {
3344
- "epoch": 1.47,
3345
- "learning_rate": 4.3230563002680966e-05,
3346
- "loss": 0.4209,
3347
- "step": 555
3348
- },
3349
- {
3350
- "epoch": 1.47,
3351
- "learning_rate": 4.32171581769437e-05,
3352
- "loss": 0.2704,
3353
- "step": 556
3354
- },
3355
- {
3356
- "epoch": 1.47,
3357
- "learning_rate": 4.3203753351206436e-05,
3358
- "loss": 0.6455,
3359
- "step": 557
3360
- },
3361
- {
3362
- "epoch": 1.48,
3363
- "learning_rate": 4.319034852546917e-05,
3364
- "loss": 0.3354,
3365
- "step": 558
3366
- },
3367
- {
3368
- "epoch": 1.48,
3369
- "learning_rate": 4.3176943699731906e-05,
3370
- "loss": 0.4069,
3371
- "step": 559
3372
- },
3373
- {
3374
- "epoch": 1.48,
3375
- "learning_rate": 4.316353887399464e-05,
3376
- "loss": 0.2334,
3377
- "step": 560
3378
- },
3379
- {
3380
- "epoch": 1.48,
3381
- "learning_rate": 4.3150134048257376e-05,
3382
- "loss": 0.4192,
3383
- "step": 561
3384
- },
3385
- {
3386
- "epoch": 1.49,
3387
- "learning_rate": 4.313672922252011e-05,
3388
- "loss": 0.2942,
3389
- "step": 562
3390
- },
3391
- {
3392
- "epoch": 1.49,
3393
- "learning_rate": 4.3123324396782847e-05,
3394
- "loss": 0.2503,
3395
- "step": 563
3396
- },
3397
- {
3398
- "epoch": 1.49,
3399
- "learning_rate": 4.3109919571045575e-05,
3400
- "loss": 0.15,
3401
- "step": 564
3402
- },
3403
- {
3404
- "epoch": 1.49,
3405
- "learning_rate": 4.309651474530832e-05,
3406
- "loss": 0.6895,
3407
- "step": 565
3408
- },
3409
- {
3410
- "epoch": 1.5,
3411
- "learning_rate": 4.3083109919571045e-05,
3412
- "loss": 0.2462,
3413
- "step": 566
3414
- },
3415
- {
3416
- "epoch": 1.5,
3417
- "learning_rate": 4.306970509383379e-05,
3418
- "loss": 0.142,
3419
- "step": 567
3420
- },
3421
- {
3422
- "epoch": 1.5,
3423
- "learning_rate": 4.3056300268096515e-05,
3424
- "loss": 0.4838,
3425
- "step": 568
3426
- },
3427
- {
3428
- "epoch": 1.51,
3429
- "learning_rate": 4.304289544235925e-05,
3430
- "loss": 0.4714,
3431
- "step": 569
3432
- },
3433
- {
3434
- "epoch": 1.51,
3435
- "learning_rate": 4.3029490616621986e-05,
3436
- "loss": 0.4916,
3437
- "step": 570
3438
- },
3439
- {
3440
- "epoch": 1.51,
3441
- "learning_rate": 4.301608579088472e-05,
3442
- "loss": 0.2001,
3443
- "step": 571
3444
- },
3445
- {
3446
- "epoch": 1.51,
3447
- "learning_rate": 4.3002680965147456e-05,
3448
- "loss": 0.3897,
3449
- "step": 572
3450
- },
3451
- {
3452
- "epoch": 1.52,
3453
- "learning_rate": 4.298927613941019e-05,
3454
- "loss": 0.1723,
3455
- "step": 573
3456
- },
3457
- {
3458
- "epoch": 1.52,
3459
- "learning_rate": 4.297587131367292e-05,
3460
- "loss": 0.4095,
3461
- "step": 574
3462
- },
3463
- {
3464
- "epoch": 1.52,
3465
- "learning_rate": 4.296246648793566e-05,
3466
- "loss": 0.2615,
3467
- "step": 575
3468
- },
3469
- {
3470
- "epoch": 1.52,
3471
- "learning_rate": 4.294906166219839e-05,
3472
- "loss": 0.221,
3473
- "step": 576
3474
- },
3475
- {
3476
- "epoch": 1.53,
3477
- "learning_rate": 4.293565683646113e-05,
3478
- "loss": 0.1373,
3479
- "step": 577
3480
- },
3481
- {
3482
- "epoch": 1.53,
3483
- "learning_rate": 4.292225201072386e-05,
3484
- "loss": 0.313,
3485
- "step": 578
3486
- },
3487
- {
3488
- "epoch": 1.53,
3489
- "learning_rate": 4.2908847184986595e-05,
3490
- "loss": 0.4608,
3491
- "step": 579
3492
- },
3493
- {
3494
- "epoch": 1.53,
3495
- "learning_rate": 4.289544235924933e-05,
3496
- "loss": 0.2894,
3497
- "step": 580
3498
- },
3499
- {
3500
- "epoch": 1.54,
3501
- "learning_rate": 4.2882037533512065e-05,
3502
- "loss": 0.5123,
3503
- "step": 581
3504
- },
3505
- {
3506
- "epoch": 1.54,
3507
- "learning_rate": 4.28686327077748e-05,
3508
- "loss": 0.3287,
3509
- "step": 582
3510
- },
3511
- {
3512
- "epoch": 1.54,
3513
- "learning_rate": 4.2855227882037536e-05,
3514
- "loss": 0.4634,
3515
- "step": 583
3516
- },
3517
- {
3518
- "epoch": 1.54,
3519
- "learning_rate": 4.284182305630027e-05,
3520
- "loss": 0.0753,
3521
- "step": 584
3522
- },
3523
- {
3524
- "epoch": 1.55,
3525
- "learning_rate": 4.2828418230563006e-05,
3526
- "loss": 0.5287,
3527
- "step": 585
3528
- },
3529
- {
3530
- "epoch": 1.55,
3531
- "learning_rate": 4.281501340482574e-05,
3532
- "loss": 0.5483,
3533
- "step": 586
3534
- },
3535
- {
3536
- "epoch": 1.55,
3537
- "learning_rate": 4.2801608579088476e-05,
3538
- "loss": 0.1076,
3539
- "step": 587
3540
- },
3541
- {
3542
- "epoch": 1.56,
3543
- "learning_rate": 4.278820375335121e-05,
3544
- "loss": 0.232,
3545
- "step": 588
3546
- },
3547
- {
3548
- "epoch": 1.56,
3549
- "learning_rate": 4.277479892761394e-05,
3550
- "loss": 0.4706,
3551
- "step": 589
3552
- },
3553
- {
3554
- "epoch": 1.56,
3555
- "learning_rate": 4.276139410187668e-05,
3556
- "loss": 0.5791,
3557
- "step": 590
3558
- },
3559
- {
3560
- "epoch": 1.56,
3561
- "learning_rate": 4.274798927613941e-05,
3562
- "loss": 0.4995,
3563
- "step": 591
3564
- },
3565
- {
3566
- "epoch": 1.57,
3567
- "learning_rate": 4.273458445040215e-05,
3568
- "loss": 0.3419,
3569
- "step": 592
3570
- },
3571
- {
3572
- "epoch": 1.57,
3573
- "learning_rate": 4.272117962466488e-05,
3574
- "loss": 0.2728,
3575
- "step": 593
3576
- },
3577
- {
3578
- "epoch": 1.57,
3579
- "learning_rate": 4.2707774798927615e-05,
3580
- "loss": 0.3598,
3581
- "step": 594
3582
- },
3583
- {
3584
- "epoch": 1.57,
3585
- "learning_rate": 4.269436997319035e-05,
3586
- "loss": 0.2669,
3587
- "step": 595
3588
- },
3589
- {
3590
- "epoch": 1.58,
3591
- "learning_rate": 4.2680965147453086e-05,
3592
- "loss": 0.4091,
3593
- "step": 596
3594
- },
3595
- {
3596
- "epoch": 1.58,
3597
- "learning_rate": 4.266756032171582e-05,
3598
- "loss": 0.7653,
3599
- "step": 597
3600
- },
3601
- {
3602
- "epoch": 1.58,
3603
- "learning_rate": 4.2654155495978556e-05,
3604
- "loss": 0.4323,
3605
- "step": 598
3606
- },
3607
- {
3608
- "epoch": 1.58,
3609
- "learning_rate": 4.2640750670241284e-05,
3610
- "loss": 0.2147,
3611
- "step": 599
3612
- },
3613
- {
3614
- "epoch": 1.59,
3615
- "learning_rate": 4.2627345844504026e-05,
3616
- "loss": 0.2229,
3617
- "step": 600
3618
- },
3619
- {
3620
- "epoch": 1.59,
3621
- "learning_rate": 4.2613941018766754e-05,
3622
- "loss": 0.1477,
3623
- "step": 601
3624
- },
3625
- {
3626
- "epoch": 1.59,
3627
- "learning_rate": 4.2600536193029496e-05,
3628
- "loss": 0.4813,
3629
- "step": 602
3630
- },
3631
- {
3632
- "epoch": 1.6,
3633
- "learning_rate": 4.2587131367292225e-05,
3634
- "loss": 0.2719,
3635
- "step": 603
3636
- },
3637
- {
3638
- "epoch": 1.6,
3639
- "learning_rate": 4.257372654155496e-05,
3640
- "loss": 0.1577,
3641
- "step": 604
3642
- },
3643
- {
3644
- "epoch": 1.6,
3645
- "learning_rate": 4.2560321715817695e-05,
3646
- "loss": 0.5718,
3647
- "step": 605
3648
- },
3649
- {
3650
- "epoch": 1.6,
3651
- "learning_rate": 4.254691689008043e-05,
3652
- "loss": 0.1481,
3653
- "step": 606
3654
- },
3655
- {
3656
- "epoch": 1.61,
3657
- "learning_rate": 4.2533512064343165e-05,
3658
- "loss": 0.3548,
3659
- "step": 607
3660
- },
3661
- {
3662
- "epoch": 1.61,
3663
- "learning_rate": 4.25201072386059e-05,
3664
- "loss": 0.1907,
3665
- "step": 608
3666
- },
3667
- {
3668
- "epoch": 1.61,
3669
- "learning_rate": 4.250670241286863e-05,
3670
- "loss": 0.4215,
3671
- "step": 609
3672
- },
3673
- {
3674
- "epoch": 1.61,
3675
- "learning_rate": 4.249329758713137e-05,
3676
- "loss": 0.0681,
3677
- "step": 610
3678
- },
3679
- {
3680
- "epoch": 1.62,
3681
- "learning_rate": 4.24798927613941e-05,
3682
- "loss": 0.514,
3683
- "step": 611
3684
- },
3685
- {
3686
- "epoch": 1.62,
3687
- "learning_rate": 4.246648793565684e-05,
3688
- "loss": 0.1242,
3689
- "step": 612
3690
- },
3691
- {
3692
- "epoch": 1.62,
3693
- "learning_rate": 4.245308310991957e-05,
3694
- "loss": 0.217,
3695
- "step": 613
3696
- },
3697
- {
3698
- "epoch": 1.62,
3699
- "learning_rate": 4.243967828418231e-05,
3700
- "loss": 0.1641,
3701
- "step": 614
3702
- },
3703
- {
3704
- "epoch": 1.63,
3705
- "learning_rate": 4.242627345844504e-05,
3706
- "loss": 0.7095,
3707
- "step": 615
3708
- },
3709
- {
3710
- "epoch": 1.63,
3711
- "learning_rate": 4.2412868632707775e-05,
3712
- "loss": 0.359,
3713
- "step": 616
3714
- },
3715
- {
3716
- "epoch": 1.63,
3717
- "learning_rate": 4.239946380697051e-05,
3718
- "loss": 0.94,
3719
- "step": 617
3720
- },
3721
- {
3722
- "epoch": 1.63,
3723
- "learning_rate": 4.2386058981233245e-05,
3724
- "loss": 0.5194,
3725
- "step": 618
3726
- },
3727
- {
3728
- "epoch": 1.64,
3729
- "learning_rate": 4.237265415549598e-05,
3730
- "loss": 0.3398,
3731
- "step": 619
3732
- },
3733
- {
3734
- "epoch": 1.64,
3735
- "learning_rate": 4.2359249329758715e-05,
3736
- "loss": 0.2305,
3737
- "step": 620
3738
- },
3739
- {
3740
- "epoch": 1.64,
3741
- "learning_rate": 4.234584450402145e-05,
3742
- "loss": 0.6045,
3743
- "step": 621
3744
- },
3745
- {
3746
- "epoch": 1.65,
3747
- "learning_rate": 4.2332439678284185e-05,
3748
- "loss": 0.3196,
3749
- "step": 622
3750
- },
3751
- {
3752
- "epoch": 1.65,
3753
- "learning_rate": 4.231903485254692e-05,
3754
- "loss": 0.0753,
3755
- "step": 623
3756
- },
3757
- {
3758
- "epoch": 1.65,
3759
- "learning_rate": 4.2305630026809656e-05,
3760
- "loss": 0.2732,
3761
- "step": 624
3762
- },
3763
- {
3764
- "epoch": 1.65,
3765
- "learning_rate": 4.229222520107239e-05,
3766
- "loss": 0.4372,
3767
- "step": 625
3768
- },
3769
- {
3770
- "epoch": 1.66,
3771
- "learning_rate": 4.227882037533512e-05,
3772
- "loss": 0.1299,
3773
- "step": 626
3774
- },
3775
- {
3776
- "epoch": 1.66,
3777
- "learning_rate": 4.226541554959786e-05,
3778
- "loss": 0.2928,
3779
- "step": 627
3780
- },
3781
- {
3782
- "epoch": 1.66,
3783
- "learning_rate": 4.225201072386059e-05,
3784
- "loss": 0.2028,
3785
- "step": 628
3786
- },
3787
- {
3788
- "epoch": 1.66,
3789
- "learning_rate": 4.223860589812333e-05,
3790
- "loss": 0.2725,
3791
- "step": 629
3792
- },
3793
- {
3794
- "epoch": 1.67,
3795
- "learning_rate": 4.222520107238606e-05,
3796
- "loss": 0.0851,
3797
- "step": 630
3798
- },
3799
- {
3800
- "epoch": 1.67,
3801
- "learning_rate": 4.2211796246648795e-05,
3802
- "loss": 0.1471,
3803
- "step": 631
3804
- },
3805
- {
3806
- "epoch": 1.67,
3807
- "learning_rate": 4.219839142091153e-05,
3808
- "loss": 0.1986,
3809
- "step": 632
3810
- },
3811
- {
3812
- "epoch": 1.67,
3813
- "learning_rate": 4.2184986595174265e-05,
3814
- "loss": 0.5156,
3815
- "step": 633
3816
- },
3817
- {
3818
- "epoch": 1.68,
3819
- "learning_rate": 4.2171581769437e-05,
3820
- "loss": 0.5286,
3821
- "step": 634
3822
- },
3823
- {
3824
- "epoch": 1.68,
3825
- "learning_rate": 4.2158176943699735e-05,
3826
- "loss": 0.3635,
3827
- "step": 635
3828
- },
3829
- {
3830
- "epoch": 1.68,
3831
- "learning_rate": 4.2144772117962464e-05,
3832
- "loss": 0.1407,
3833
- "step": 636
3834
- },
3835
- {
3836
- "epoch": 1.69,
3837
- "learning_rate": 4.2131367292225206e-05,
3838
- "loss": 0.1042,
3839
- "step": 637
3840
- },
3841
- {
3842
- "epoch": 1.69,
3843
- "learning_rate": 4.2117962466487934e-05,
3844
- "loss": 0.1553,
3845
- "step": 638
3846
- },
3847
- {
3848
- "epoch": 1.69,
3849
- "learning_rate": 4.2104557640750676e-05,
3850
- "loss": 0.1665,
3851
- "step": 639
3852
- },
3853
- {
3854
- "epoch": 1.69,
3855
- "learning_rate": 4.2091152815013404e-05,
3856
- "loss": 0.3706,
3857
- "step": 640
3858
- },
3859
- {
3860
- "epoch": 1.7,
3861
- "learning_rate": 4.207774798927614e-05,
3862
- "loss": 0.6195,
3863
- "step": 641
3864
- },
3865
- {
3866
- "epoch": 1.7,
3867
- "learning_rate": 4.2064343163538874e-05,
3868
- "loss": 0.1341,
3869
- "step": 642
3870
- },
3871
- {
3872
- "epoch": 1.7,
3873
- "learning_rate": 4.205093833780161e-05,
3874
- "loss": 0.5384,
3875
- "step": 643
3876
- },
3877
- {
3878
- "epoch": 1.7,
3879
- "learning_rate": 4.2037533512064345e-05,
3880
- "loss": 0.2802,
3881
- "step": 644
3882
- },
3883
- {
3884
- "epoch": 1.71,
3885
- "learning_rate": 4.202412868632708e-05,
3886
- "loss": 0.3812,
3887
- "step": 645
3888
- },
3889
- {
3890
- "epoch": 1.71,
3891
- "learning_rate": 4.2010723860589815e-05,
3892
- "loss": 0.2433,
3893
- "step": 646
3894
- },
3895
- {
3896
- "epoch": 1.71,
3897
- "learning_rate": 4.199731903485255e-05,
3898
- "loss": 0.0642,
3899
- "step": 647
3900
- },
3901
- {
3902
- "epoch": 1.71,
3903
- "learning_rate": 4.1983914209115285e-05,
3904
- "loss": 0.0547,
3905
- "step": 648
3906
- },
3907
- {
3908
- "epoch": 1.72,
3909
- "learning_rate": 4.197050938337802e-05,
3910
- "loss": 0.4388,
3911
- "step": 649
3912
- },
3913
- {
3914
- "epoch": 1.72,
3915
- "learning_rate": 4.1957104557640756e-05,
3916
- "loss": 0.8228,
3917
- "step": 650
3918
- },
3919
- {
3920
- "epoch": 1.72,
3921
- "learning_rate": 4.1943699731903484e-05,
3922
- "loss": 0.6453,
3923
- "step": 651
3924
- },
3925
- {
3926
- "epoch": 1.72,
3927
- "learning_rate": 4.1930294906166226e-05,
3928
- "loss": 0.3367,
3929
- "step": 652
3930
- },
3931
- {
3932
- "epoch": 1.73,
3933
- "learning_rate": 4.1916890080428954e-05,
3934
- "loss": 0.2139,
3935
- "step": 653
3936
- },
3937
- {
3938
- "epoch": 1.73,
3939
- "learning_rate": 4.1903485254691696e-05,
3940
- "loss": 0.2144,
3941
- "step": 654
3942
- },
3943
- {
3944
- "epoch": 1.73,
3945
- "learning_rate": 4.1890080428954424e-05,
3946
- "loss": 0.3894,
3947
- "step": 655
3948
- },
3949
- {
3950
- "epoch": 1.74,
3951
- "learning_rate": 4.187667560321716e-05,
3952
- "loss": 0.0891,
3953
- "step": 656
3954
- },
3955
- {
3956
- "epoch": 1.74,
3957
- "learning_rate": 4.1863270777479895e-05,
3958
- "loss": 0.1287,
3959
- "step": 657
3960
- },
3961
- {
3962
- "epoch": 1.74,
3963
- "learning_rate": 4.184986595174263e-05,
3964
- "loss": 0.2826,
3965
- "step": 658
3966
- },
3967
- {
3968
- "epoch": 1.74,
3969
- "learning_rate": 4.1836461126005365e-05,
3970
- "loss": 0.474,
3971
- "step": 659
3972
- },
3973
- {
3974
- "epoch": 1.75,
3975
- "learning_rate": 4.18230563002681e-05,
3976
- "loss": 0.4228,
3977
- "step": 660
3978
- },
3979
- {
3980
- "epoch": 1.75,
3981
- "learning_rate": 4.180965147453083e-05,
3982
- "loss": 0.4952,
3983
- "step": 661
3984
- },
3985
- {
3986
- "epoch": 1.75,
3987
- "learning_rate": 4.179624664879357e-05,
3988
- "loss": 0.173,
3989
- "step": 662
3990
- },
3991
- {
3992
- "epoch": 1.75,
3993
- "learning_rate": 4.17828418230563e-05,
3994
- "loss": 0.363,
3995
- "step": 663
3996
- },
3997
- {
3998
- "epoch": 1.76,
3999
- "learning_rate": 4.176943699731904e-05,
4000
- "loss": 0.4404,
4001
- "step": 664
4002
- },
4003
- {
4004
- "epoch": 1.76,
4005
- "learning_rate": 4.175603217158177e-05,
4006
- "loss": 0.486,
4007
- "step": 665
4008
- },
4009
- {
4010
- "epoch": 1.76,
4011
- "learning_rate": 4.1742627345844504e-05,
4012
- "loss": 0.4463,
4013
- "step": 666
4014
- },
4015
- {
4016
- "epoch": 1.76,
4017
- "learning_rate": 4.172922252010724e-05,
4018
- "loss": 0.2409,
4019
- "step": 667
4020
- },
4021
- {
4022
- "epoch": 1.77,
4023
- "learning_rate": 4.1715817694369974e-05,
4024
- "loss": 0.5291,
4025
- "step": 668
4026
- },
4027
- {
4028
- "epoch": 1.77,
4029
- "learning_rate": 4.170241286863271e-05,
4030
- "loss": 0.069,
4031
- "step": 669
4032
- },
4033
- {
4034
- "epoch": 1.77,
4035
- "learning_rate": 4.1689008042895445e-05,
4036
- "loss": 0.4162,
4037
- "step": 670
4038
- },
4039
- {
4040
- "epoch": 1.78,
4041
- "learning_rate": 4.167560321715818e-05,
4042
- "loss": 0.6171,
4043
- "step": 671
4044
- },
4045
- {
4046
- "epoch": 1.78,
4047
- "learning_rate": 4.1662198391420915e-05,
4048
- "loss": 0.3097,
4049
- "step": 672
4050
- },
4051
- {
4052
- "epoch": 1.78,
4053
- "learning_rate": 4.164879356568365e-05,
4054
- "loss": 0.5109,
4055
- "step": 673
4056
- },
4057
- {
4058
- "epoch": 1.78,
4059
- "learning_rate": 4.1635388739946385e-05,
4060
- "loss": 0.2169,
4061
- "step": 674
4062
- },
4063
- {
4064
- "epoch": 1.79,
4065
- "learning_rate": 4.162198391420912e-05,
4066
- "loss": 0.2406,
4067
- "step": 675
4068
- },
4069
- {
4070
- "epoch": 1.79,
4071
- "learning_rate": 4.160857908847185e-05,
4072
- "loss": 0.1853,
4073
- "step": 676
4074
- },
4075
- {
4076
- "epoch": 1.79,
4077
- "learning_rate": 4.159517426273459e-05,
4078
- "loss": 0.5743,
4079
- "step": 677
4080
- },
4081
- {
4082
- "epoch": 1.79,
4083
- "learning_rate": 4.158176943699732e-05,
4084
- "loss": 0.5432,
4085
- "step": 678
4086
- },
4087
- {
4088
- "epoch": 1.8,
4089
- "learning_rate": 4.156836461126006e-05,
4090
- "loss": 0.2033,
4091
- "step": 679
4092
- },
4093
- {
4094
- "epoch": 1.8,
4095
- "learning_rate": 4.155495978552279e-05,
4096
- "loss": 0.3848,
4097
- "step": 680
4098
- },
4099
- {
4100
- "epoch": 1.8,
4101
- "learning_rate": 4.1541554959785524e-05,
4102
- "loss": 0.1721,
4103
- "step": 681
4104
- },
4105
- {
4106
- "epoch": 1.8,
4107
- "learning_rate": 4.152815013404826e-05,
4108
- "loss": 0.3793,
4109
- "step": 682
4110
- },
4111
- {
4112
- "epoch": 1.81,
4113
- "learning_rate": 4.1514745308310994e-05,
4114
- "loss": 0.3848,
4115
- "step": 683
4116
- },
4117
- {
4118
- "epoch": 1.81,
4119
- "learning_rate": 4.150134048257373e-05,
4120
- "loss": 0.186,
4121
- "step": 684
4122
- },
4123
- {
4124
- "epoch": 1.81,
4125
- "learning_rate": 4.1487935656836465e-05,
4126
- "loss": 0.2692,
4127
- "step": 685
4128
- },
4129
- {
4130
- "epoch": 1.81,
4131
- "learning_rate": 4.147453083109919e-05,
4132
- "loss": 0.3839,
4133
- "step": 686
4134
- },
4135
- {
4136
- "epoch": 1.82,
4137
- "learning_rate": 4.1461126005361935e-05,
4138
- "loss": 0.3037,
4139
- "step": 687
4140
- },
4141
- {
4142
- "epoch": 1.82,
4143
- "learning_rate": 4.144772117962466e-05,
4144
- "loss": 0.6401,
4145
- "step": 688
4146
- },
4147
- {
4148
- "epoch": 1.82,
4149
- "learning_rate": 4.1434316353887405e-05,
4150
- "loss": 0.1173,
4151
- "step": 689
4152
- },
4153
- {
4154
- "epoch": 1.83,
4155
- "learning_rate": 4.1420911528150134e-05,
4156
- "loss": 0.3217,
4157
- "step": 690
4158
- },
4159
- {
4160
- "epoch": 1.83,
4161
- "learning_rate": 4.140750670241287e-05,
4162
- "loss": 0.2358,
4163
- "step": 691
4164
- },
4165
- {
4166
- "epoch": 1.83,
4167
- "learning_rate": 4.1394101876675604e-05,
4168
- "loss": 0.7696,
4169
- "step": 692
4170
- },
4171
- {
4172
- "epoch": 1.83,
4173
- "learning_rate": 4.138069705093834e-05,
4174
- "loss": 0.2288,
4175
- "step": 693
4176
- },
4177
- {
4178
- "epoch": 1.84,
4179
- "learning_rate": 4.1367292225201074e-05,
4180
- "loss": 0.2575,
4181
- "step": 694
4182
- },
4183
- {
4184
- "epoch": 1.84,
4185
- "learning_rate": 4.135388739946381e-05,
4186
- "loss": 0.1201,
4187
- "step": 695
4188
- },
4189
- {
4190
- "epoch": 1.84,
4191
- "learning_rate": 4.1340482573726544e-05,
4192
- "loss": 0.2034,
4193
- "step": 696
4194
- },
4195
- {
4196
- "epoch": 1.84,
4197
- "learning_rate": 4.132707774798928e-05,
4198
- "loss": 0.1142,
4199
- "step": 697
4200
- },
4201
- {
4202
- "epoch": 1.85,
4203
- "learning_rate": 4.1313672922252015e-05,
4204
- "loss": 0.5671,
4205
- "step": 698
4206
- },
4207
- {
4208
- "epoch": 1.85,
4209
- "learning_rate": 4.130026809651475e-05,
4210
- "loss": 0.3132,
4211
- "step": 699
4212
- },
4213
- {
4214
- "epoch": 1.85,
4215
- "learning_rate": 4.1286863270777485e-05,
4216
- "loss": 0.4266,
4217
- "step": 700
4218
- },
4219
- {
4220
- "epoch": 1.85,
4221
- "learning_rate": 4.127345844504021e-05,
4222
- "loss": 0.1354,
4223
- "step": 701
4224
- },
4225
- {
4226
- "epoch": 1.86,
4227
- "learning_rate": 4.1260053619302955e-05,
4228
- "loss": 0.2867,
4229
- "step": 702
4230
- },
4231
- {
4232
- "epoch": 1.86,
4233
- "learning_rate": 4.1246648793565684e-05,
4234
- "loss": 0.1839,
4235
- "step": 703
4236
- },
4237
- {
4238
- "epoch": 1.86,
4239
- "learning_rate": 4.1233243967828425e-05,
4240
- "loss": 0.4741,
4241
- "step": 704
4242
- },
4243
- {
4244
- "epoch": 1.87,
4245
- "learning_rate": 4.1219839142091154e-05,
4246
- "loss": 0.2909,
4247
- "step": 705
4248
- },
4249
- {
4250
- "epoch": 1.87,
4251
- "learning_rate": 4.120643431635389e-05,
4252
- "loss": 0.2705,
4253
- "step": 706
4254
- },
4255
- {
4256
- "epoch": 1.87,
4257
- "learning_rate": 4.1193029490616624e-05,
4258
- "loss": 0.1354,
4259
- "step": 707
4260
- },
4261
- {
4262
- "epoch": 1.87,
4263
- "learning_rate": 4.117962466487936e-05,
4264
- "loss": 0.4801,
4265
- "step": 708
4266
- },
4267
- {
4268
- "epoch": 1.88,
4269
- "learning_rate": 4.1166219839142094e-05,
4270
- "loss": 0.189,
4271
- "step": 709
4272
- },
4273
- {
4274
- "epoch": 1.88,
4275
- "learning_rate": 4.115281501340483e-05,
4276
- "loss": 0.3204,
4277
- "step": 710
4278
- },
4279
- {
4280
- "epoch": 1.88,
4281
- "learning_rate": 4.113941018766756e-05,
4282
- "loss": 0.4358,
4283
- "step": 711
4284
- },
4285
- {
4286
- "epoch": 1.88,
4287
- "learning_rate": 4.11260053619303e-05,
4288
- "loss": 0.9474,
4289
- "step": 712
4290
- },
4291
- {
4292
- "epoch": 1.89,
4293
- "learning_rate": 4.111260053619303e-05,
4294
- "loss": 0.2102,
4295
- "step": 713
4296
- },
4297
- {
4298
- "epoch": 1.89,
4299
- "learning_rate": 4.109919571045577e-05,
4300
- "loss": 0.3927,
4301
- "step": 714
4302
- },
4303
- {
4304
- "epoch": 1.89,
4305
- "learning_rate": 4.10857908847185e-05,
4306
- "loss": 0.139,
4307
- "step": 715
4308
- },
4309
- {
4310
- "epoch": 1.89,
4311
- "learning_rate": 4.1072386058981233e-05,
4312
- "loss": 0.3575,
4313
- "step": 716
4314
- },
4315
- {
4316
- "epoch": 1.9,
4317
- "learning_rate": 4.105898123324397e-05,
4318
- "loss": 0.7534,
4319
- "step": 717
4320
- },
4321
- {
4322
- "epoch": 1.9,
4323
- "learning_rate": 4.1045576407506704e-05,
4324
- "loss": 0.1134,
4325
- "step": 718
4326
- },
4327
- {
4328
- "epoch": 1.9,
4329
- "learning_rate": 4.103217158176944e-05,
4330
- "loss": 0.2136,
4331
- "step": 719
4332
- },
4333
- {
4334
- "epoch": 1.9,
4335
- "learning_rate": 4.1018766756032174e-05,
4336
- "loss": 0.4344,
4337
- "step": 720
4338
- },
4339
- {
4340
- "epoch": 1.91,
4341
- "learning_rate": 4.10053619302949e-05,
4342
- "loss": 0.0695,
4343
- "step": 721
4344
- },
4345
- {
4346
- "epoch": 1.91,
4347
- "learning_rate": 4.0991957104557644e-05,
4348
- "loss": 0.2286,
4349
- "step": 722
4350
- },
4351
- {
4352
- "epoch": 1.91,
4353
- "learning_rate": 4.097855227882037e-05,
4354
- "loss": 0.1189,
4355
- "step": 723
4356
- },
4357
- {
4358
- "epoch": 1.92,
4359
- "learning_rate": 4.0965147453083115e-05,
4360
- "loss": 0.2882,
4361
- "step": 724
4362
- },
4363
- {
4364
- "epoch": 1.92,
4365
- "learning_rate": 4.095174262734584e-05,
4366
- "loss": 0.2623,
4367
- "step": 725
4368
- },
4369
- {
4370
- "epoch": 1.92,
4371
- "learning_rate": 4.093833780160858e-05,
4372
- "loss": 0.2473,
4373
- "step": 726
4374
- },
4375
- {
4376
- "epoch": 1.92,
4377
- "learning_rate": 4.092493297587131e-05,
4378
- "loss": 0.4846,
4379
- "step": 727
4380
- },
4381
- {
4382
- "epoch": 1.93,
4383
- "learning_rate": 4.091152815013405e-05,
4384
- "loss": 0.1689,
4385
- "step": 728
4386
- },
4387
- {
4388
- "epoch": 1.93,
4389
- "learning_rate": 4.0898123324396783e-05,
4390
- "loss": 0.3481,
4391
- "step": 729
4392
- },
4393
- {
4394
- "epoch": 1.93,
4395
- "learning_rate": 4.088471849865952e-05,
4396
- "loss": 0.3447,
4397
- "step": 730
4398
- },
4399
- {
4400
- "epoch": 1.93,
4401
- "learning_rate": 4.0871313672922254e-05,
4402
- "loss": 0.2959,
4403
- "step": 731
4404
- },
4405
- {
4406
- "epoch": 1.94,
4407
- "learning_rate": 4.085790884718499e-05,
4408
- "loss": 0.3387,
4409
- "step": 732
4410
- },
4411
- {
4412
- "epoch": 1.94,
4413
- "learning_rate": 4.0844504021447724e-05,
4414
- "loss": 0.3742,
4415
- "step": 733
4416
- },
4417
- {
4418
- "epoch": 1.94,
4419
- "learning_rate": 4.083109919571046e-05,
4420
- "loss": 0.3245,
4421
- "step": 734
4422
- },
4423
- {
4424
- "epoch": 1.94,
4425
- "learning_rate": 4.0817694369973194e-05,
4426
- "loss": 0.4891,
4427
- "step": 735
4428
- },
4429
- {
4430
- "epoch": 1.95,
4431
- "learning_rate": 4.080428954423593e-05,
4432
- "loss": 0.1444,
4433
- "step": 736
4434
- },
4435
- {
4436
- "epoch": 1.95,
4437
- "learning_rate": 4.0790884718498664e-05,
4438
- "loss": 0.3678,
4439
- "step": 737
4440
- },
4441
- {
4442
- "epoch": 1.95,
4443
- "learning_rate": 4.077747989276139e-05,
4444
- "loss": 0.3772,
4445
- "step": 738
4446
- },
4447
- {
4448
- "epoch": 1.96,
4449
- "learning_rate": 4.0764075067024135e-05,
4450
- "loss": 0.43,
4451
- "step": 739
4452
- },
4453
- {
4454
- "epoch": 1.96,
4455
- "learning_rate": 4.075067024128686e-05,
4456
- "loss": 0.2463,
4457
- "step": 740
4458
- },
4459
- {
4460
- "epoch": 1.96,
4461
- "learning_rate": 4.0737265415549605e-05,
4462
- "loss": 0.2277,
4463
- "step": 741
4464
- },
4465
- {
4466
- "epoch": 1.96,
4467
- "learning_rate": 4.072386058981233e-05,
4468
- "loss": 0.2153,
4469
- "step": 742
4470
- },
4471
- {
4472
- "epoch": 1.97,
4473
- "learning_rate": 4.071045576407507e-05,
4474
- "loss": 0.1052,
4475
- "step": 743
4476
- },
4477
- {
4478
- "epoch": 1.97,
4479
- "learning_rate": 4.0697050938337804e-05,
4480
- "loss": 0.5657,
4481
- "step": 744
4482
- },
4483
- {
4484
- "epoch": 1.97,
4485
- "learning_rate": 4.068364611260054e-05,
4486
- "loss": 0.2664,
4487
- "step": 745
4488
- },
4489
- {
4490
- "epoch": 1.97,
4491
- "learning_rate": 4.0670241286863274e-05,
4492
- "loss": 0.1369,
4493
- "step": 746
4494
- },
4495
- {
4496
- "epoch": 1.98,
4497
- "learning_rate": 4.065683646112601e-05,
4498
- "loss": 0.4972,
4499
- "step": 747
4500
- },
4501
- {
4502
- "epoch": 1.98,
4503
- "learning_rate": 4.064343163538874e-05,
4504
- "loss": 0.4131,
4505
- "step": 748
4506
- },
4507
- {
4508
- "epoch": 1.98,
4509
- "learning_rate": 4.063002680965148e-05,
4510
- "loss": 0.3824,
4511
- "step": 749
4512
- },
4513
- {
4514
- "epoch": 1.98,
4515
- "learning_rate": 4.061662198391421e-05,
4516
- "loss": 0.323,
4517
- "step": 750
4518
- },
4519
- {
4520
- "epoch": 1.99,
4521
- "learning_rate": 4.060321715817695e-05,
4522
- "loss": 0.3698,
4523
- "step": 751
4524
- },
4525
- {
4526
- "epoch": 1.99,
4527
- "learning_rate": 4.058981233243968e-05,
4528
- "loss": 0.1708,
4529
- "step": 752
4530
- },
4531
- {
4532
- "epoch": 1.99,
4533
- "learning_rate": 4.057640750670241e-05,
4534
- "loss": 0.2941,
4535
- "step": 753
4536
- },
4537
- {
4538
- "epoch": 1.99,
4539
- "learning_rate": 4.056300268096515e-05,
4540
- "loss": 0.3224,
4541
- "step": 754
4542
- },
4543
- {
4544
- "epoch": 2.0,
4545
- "learning_rate": 4.054959785522788e-05,
4546
- "loss": 0.0851,
4547
- "step": 755
4548
- },
4549
- {
4550
- "epoch": 2.0,
4551
- "learning_rate": 4.053619302949062e-05,
4552
- "loss": 0.4694,
4553
- "step": 756
4554
- },
4555
- {
4556
- "epoch": 2.0,
4557
- "eval_f1": 0.7882736156351792,
4558
- "eval_loss": 0.4484867751598358,
4559
- "eval_runtime": 1.8734,
4560
- "eval_samples_per_second": 807.638,
4561
- "eval_steps_per_second": 50.711,
4562
- "step": 756
4563
- }
4564
- ],
4565
- "max_steps": 3780,
4566
- "num_train_epochs": 10,
4567
- "total_flos": 194391767921472.0,
4568
- "trial_name": null,
4569
- "trial_params": null
4570
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-756/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7c01d8e107b4a20c0ba0f3692dae4e25d8f1dffe1d23d6e4f4bdf92b87ab5ea
3
- size 3899