ccore commited on
Commit
e126367
1 Parent(s): 892e1e9

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +2 -4
  2. all_results.json +5 -5
  3. checkpoint-1000/optimizer.pt +1 -1
  4. checkpoint-1000/pytorch_model.bin +1 -1
  5. checkpoint-1000/rng_state.pth +1 -1
  6. checkpoint-1000/scheduler.pt +1 -1
  7. checkpoint-1000/trainer_state.json +604 -604
  8. checkpoint-1000/training_args.bin +1 -1
  9. checkpoint-2000/config.json +26 -0
  10. checkpoint-2000/generation_config.json +6 -0
  11. checkpoint-2000/optimizer.pt +3 -0
  12. checkpoint-2000/pytorch_model.bin +3 -0
  13. checkpoint-2000/rng_state.pth +3 -0
  14. checkpoint-2000/scheduler.pt +3 -0
  15. checkpoint-2000/special_tokens_map.json +5 -0
  16. checkpoint-2000/tokenizer.json +0 -0
  17. checkpoint-2000/tokenizer.model +3 -0
  18. checkpoint-2000/tokenizer_config.json +38 -0
  19. checkpoint-2000/trainer_state.json +2419 -0
  20. checkpoint-2000/training_args.bin +3 -0
  21. checkpoint-3000/config.json +26 -0
  22. checkpoint-3000/generation_config.json +6 -0
  23. checkpoint-3000/optimizer.pt +3 -0
  24. checkpoint-3000/pytorch_model.bin +3 -0
  25. checkpoint-3000/rng_state.pth +3 -0
  26. checkpoint-3000/scheduler.pt +3 -0
  27. checkpoint-3000/special_tokens_map.json +5 -0
  28. checkpoint-3000/tokenizer.json +0 -0
  29. checkpoint-3000/tokenizer.model +3 -0
  30. checkpoint-3000/tokenizer_config.json +38 -0
  31. checkpoint-3000/trainer_state.json +3619 -0
  32. checkpoint-3000/training_args.bin +3 -0
  33. checkpoint-4000/config.json +26 -0
  34. checkpoint-4000/generation_config.json +6 -0
  35. checkpoint-4000/optimizer.pt +3 -0
  36. checkpoint-4000/pytorch_model.bin +3 -0
  37. checkpoint-4000/rng_state.pth +3 -0
  38. checkpoint-4000/scheduler.pt +3 -0
  39. checkpoint-4000/special_tokens_map.json +5 -0
  40. checkpoint-4000/tokenizer.json +0 -0
  41. checkpoint-4000/tokenizer.model +3 -0
  42. checkpoint-4000/tokenizer_config.json +38 -0
  43. checkpoint-4000/trainer_state.json +4819 -0
  44. checkpoint-4000/training_args.bin +3 -0
  45. checkpoint-5000/config.json +26 -0
  46. checkpoint-5000/generation_config.json +6 -0
  47. checkpoint-5000/optimizer.pt +3 -0
  48. checkpoint-5000/pytorch_model.bin +3 -0
  49. checkpoint-5000/rng_state.pth +3 -0
  50. checkpoint-5000/scheduler.pt +3 -0
README.md CHANGED
@@ -31,15 +31,13 @@ More information needed
31
  ### Training hyperparameters
32
 
33
  The following hyperparameters were used during training:
34
- - learning_rate: 0.0001
35
  - train_batch_size: 1
36
  - eval_batch_size: 1
37
  - seed: 42
38
- - gradient_accumulation_steps: 128
39
- - total_train_batch_size: 128
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: constant
42
- - num_epochs: 25.0
43
 
44
  ### Training results
45
 
 
31
  ### Training hyperparameters
32
 
33
  The following hyperparameters were used during training:
34
+ - learning_rate: 0.001
35
  - train_batch_size: 1
36
  - eval_batch_size: 1
37
  - seed: 42
 
 
38
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
  - lr_scheduler_type: constant
40
+ - num_epochs: 5.0
41
 
42
  ### Training results
43
 
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 23.04,
3
- "train_loss": 1.0600377412275834,
4
- "train_runtime": 1128.0648,
5
  "train_samples": 1528,
6
- "train_samples_per_second": 33.863,
7
- "train_steps_per_second": 0.244
8
  }
 
1
  {
2
+ "epoch": 5.0,
3
+ "train_loss": 1.999870525792007,
4
+ "train_runtime": 268.6642,
5
  "train_samples": 1528,
6
+ "train_samples_per_second": 28.437,
7
+ "train_steps_per_second": 28.437
8
  }
checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff915a4035235786ff34aca643fbdb2a4ef583f6fa0790194e53ec78ac7eb34e
3
  size 141585770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d9e2af855228dddbe0658b3aca8fceb49da183db44df0f8f6e98b8b81f5e76
3
  size 141585770
checkpoint-1000/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f00c657f63a7216e25e186f2d29946dac0ba91a74376974df8944e985170d76b
3
  size 70790896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb42b85976a37ecf6745788717d8c16a2c224e77a5574c54a93294058563d9de
3
  size 70790896
checkpoint-1000/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5432f961e7c82cbe7b6ec30d027cf3db4d17372f65774be8cf037a208cbc1ac
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
3
  size 14575
checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85885c3e5d3b4f84b750255dee6648c79d4c44369e80f9253531ad7ae88a6336
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28af83c57f2cddb6d735f7c816ebd9f24f4448153c24c61a1a5b5a0bd3955a9
3
  size 627
checkpoint-1000/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 20.94240837696335,
5
  "eval_steps": 500,
6
  "global_step": 1000,
7
  "is_hyper_param_search": false,
@@ -9,1211 +9,1211 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.1,
13
- "learning_rate": 0.0001,
14
- "loss": 1.7979,
15
  "step": 5
16
  },
17
  {
18
- "epoch": 0.21,
19
- "learning_rate": 0.0001,
20
- "loss": 1.7693,
21
  "step": 10
22
  },
23
  {
24
- "epoch": 0.31,
25
- "learning_rate": 0.0001,
26
- "loss": 1.7635,
27
  "step": 15
28
  },
29
  {
30
- "epoch": 0.42,
31
- "learning_rate": 0.0001,
32
- "loss": 1.7587,
33
  "step": 20
34
  },
35
  {
36
- "epoch": 0.52,
37
- "learning_rate": 0.0001,
38
- "loss": 1.7384,
39
  "step": 25
40
  },
41
  {
42
- "epoch": 0.63,
43
- "learning_rate": 0.0001,
44
- "loss": 1.7832,
45
  "step": 30
46
  },
47
  {
48
- "epoch": 0.73,
49
- "learning_rate": 0.0001,
50
- "loss": 1.7652,
51
  "step": 35
52
  },
53
  {
54
- "epoch": 0.84,
55
- "learning_rate": 0.0001,
56
- "loss": 1.7417,
57
  "step": 40
58
  },
59
  {
60
- "epoch": 0.94,
61
- "learning_rate": 0.0001,
62
- "loss": 1.7321,
63
  "step": 45
64
  },
65
  {
66
- "epoch": 1.05,
67
- "learning_rate": 0.0001,
68
- "loss": 1.6915,
69
  "step": 50
70
  },
71
  {
72
- "epoch": 1.15,
73
- "learning_rate": 0.0001,
74
- "loss": 1.6773,
75
  "step": 55
76
  },
77
  {
78
- "epoch": 1.26,
79
- "learning_rate": 0.0001,
80
- "loss": 1.6713,
81
  "step": 60
82
  },
83
  {
84
- "epoch": 1.36,
85
- "learning_rate": 0.0001,
86
- "loss": 1.6701,
87
  "step": 65
88
  },
89
  {
90
- "epoch": 1.47,
91
- "learning_rate": 0.0001,
92
- "loss": 1.6941,
93
  "step": 70
94
  },
95
  {
96
- "epoch": 1.57,
97
- "learning_rate": 0.0001,
98
- "loss": 1.6116,
99
  "step": 75
100
  },
101
  {
102
- "epoch": 1.68,
103
- "learning_rate": 0.0001,
104
- "loss": 1.7088,
105
  "step": 80
106
  },
107
  {
108
- "epoch": 1.78,
109
- "learning_rate": 0.0001,
110
- "loss": 1.661,
111
  "step": 85
112
  },
113
  {
114
- "epoch": 1.88,
115
- "learning_rate": 0.0001,
116
- "loss": 1.7321,
117
  "step": 90
118
  },
119
  {
120
- "epoch": 1.99,
121
- "learning_rate": 0.0001,
122
- "loss": 1.6995,
123
  "step": 95
124
  },
125
  {
126
- "epoch": 2.09,
127
- "learning_rate": 0.0001,
128
- "loss": 1.6298,
129
  "step": 100
130
  },
131
  {
132
- "epoch": 2.2,
133
- "learning_rate": 0.0001,
134
- "loss": 1.6231,
135
  "step": 105
136
  },
137
  {
138
- "epoch": 2.3,
139
- "learning_rate": 0.0001,
140
- "loss": 1.6427,
141
  "step": 110
142
  },
143
  {
144
- "epoch": 2.41,
145
- "learning_rate": 0.0001,
146
- "loss": 1.5985,
147
  "step": 115
148
  },
149
  {
150
- "epoch": 2.51,
151
- "learning_rate": 0.0001,
152
- "loss": 1.6267,
153
  "step": 120
154
  },
155
  {
156
- "epoch": 2.62,
157
- "learning_rate": 0.0001,
158
- "loss": 1.5373,
159
  "step": 125
160
  },
161
  {
162
- "epoch": 2.72,
163
- "learning_rate": 0.0001,
164
- "loss": 1.6516,
165
  "step": 130
166
  },
167
  {
168
- "epoch": 2.83,
169
- "learning_rate": 0.0001,
170
- "loss": 1.6861,
171
  "step": 135
172
  },
173
  {
174
- "epoch": 2.93,
175
- "learning_rate": 0.0001,
176
- "loss": 1.6746,
177
  "step": 140
178
  },
179
  {
180
- "epoch": 3.04,
181
- "learning_rate": 0.0001,
182
- "loss": 1.6478,
183
  "step": 145
184
  },
185
  {
186
- "epoch": 3.14,
187
- "learning_rate": 0.0001,
188
- "loss": 1.6206,
189
  "step": 150
190
  },
191
  {
192
- "epoch": 3.25,
193
- "learning_rate": 0.0001,
194
- "loss": 1.5848,
195
  "step": 155
196
  },
197
  {
198
- "epoch": 3.35,
199
- "learning_rate": 0.0001,
200
- "loss": 1.5988,
201
  "step": 160
202
  },
203
  {
204
- "epoch": 3.46,
205
- "learning_rate": 0.0001,
206
- "loss": 1.6014,
207
  "step": 165
208
  },
209
  {
210
- "epoch": 3.56,
211
- "learning_rate": 0.0001,
212
- "loss": 1.5327,
213
  "step": 170
214
  },
215
  {
216
- "epoch": 3.66,
217
- "learning_rate": 0.0001,
218
- "loss": 1.5811,
219
  "step": 175
220
  },
221
  {
222
- "epoch": 3.77,
223
- "learning_rate": 0.0001,
224
- "loss": 1.6202,
225
  "step": 180
226
  },
227
  {
228
- "epoch": 3.87,
229
- "learning_rate": 0.0001,
230
- "loss": 1.5986,
231
  "step": 185
232
  },
233
  {
234
- "epoch": 3.98,
235
- "learning_rate": 0.0001,
236
- "loss": 1.6548,
237
  "step": 190
238
  },
239
  {
240
- "epoch": 4.08,
241
- "learning_rate": 0.0001,
242
- "loss": 1.5288,
243
  "step": 195
244
  },
245
  {
246
- "epoch": 4.19,
247
- "learning_rate": 0.0001,
248
- "loss": 1.5604,
249
  "step": 200
250
  },
251
  {
252
- "epoch": 4.29,
253
- "learning_rate": 0.0001,
254
- "loss": 1.5302,
255
  "step": 205
256
  },
257
  {
258
- "epoch": 4.4,
259
- "learning_rate": 0.0001,
260
- "loss": 1.5751,
261
  "step": 210
262
  },
263
  {
264
- "epoch": 4.5,
265
- "learning_rate": 0.0001,
266
- "loss": 1.5865,
267
  "step": 215
268
  },
269
  {
270
- "epoch": 4.61,
271
- "learning_rate": 0.0001,
272
- "loss": 1.5476,
273
  "step": 220
274
  },
275
  {
276
- "epoch": 4.71,
277
- "learning_rate": 0.0001,
278
- "loss": 1.5636,
279
  "step": 225
280
  },
281
  {
282
- "epoch": 4.82,
283
- "learning_rate": 0.0001,
284
- "loss": 1.5472,
285
  "step": 230
286
  },
287
  {
288
- "epoch": 4.92,
289
- "learning_rate": 0.0001,
290
- "loss": 1.598,
291
  "step": 235
292
  },
293
  {
294
- "epoch": 5.03,
295
- "learning_rate": 0.0001,
296
- "loss": 1.6288,
297
  "step": 240
298
  },
299
  {
300
- "epoch": 5.13,
301
- "learning_rate": 0.0001,
302
- "loss": 1.4983,
303
  "step": 245
304
  },
305
  {
306
- "epoch": 5.24,
307
- "learning_rate": 0.0001,
308
- "loss": 1.5407,
309
  "step": 250
310
  },
311
  {
312
- "epoch": 5.34,
313
- "learning_rate": 0.0001,
314
- "loss": 1.486,
315
  "step": 255
316
  },
317
  {
318
- "epoch": 5.45,
319
- "learning_rate": 0.0001,
320
- "loss": 1.575,
321
  "step": 260
322
  },
323
  {
324
- "epoch": 5.55,
325
- "learning_rate": 0.0001,
326
- "loss": 1.4745,
327
  "step": 265
328
  },
329
  {
330
- "epoch": 5.65,
331
- "learning_rate": 0.0001,
332
- "loss": 1.5294,
333
  "step": 270
334
  },
335
  {
336
- "epoch": 5.76,
337
- "learning_rate": 0.0001,
338
- "loss": 1.5501,
339
  "step": 275
340
  },
341
  {
342
- "epoch": 5.86,
343
- "learning_rate": 0.0001,
344
- "loss": 1.5791,
345
  "step": 280
346
  },
347
  {
348
- "epoch": 5.97,
349
- "learning_rate": 0.0001,
350
- "loss": 1.5737,
351
  "step": 285
352
  },
353
  {
354
- "epoch": 6.07,
355
- "learning_rate": 0.0001,
356
- "loss": 1.5181,
357
  "step": 290
358
  },
359
  {
360
- "epoch": 6.18,
361
- "learning_rate": 0.0001,
362
- "loss": 1.4805,
363
  "step": 295
364
  },
365
  {
366
- "epoch": 6.28,
367
- "learning_rate": 0.0001,
368
- "loss": 1.5105,
369
  "step": 300
370
  },
371
  {
372
- "epoch": 6.39,
373
- "learning_rate": 0.0001,
374
- "loss": 1.5258,
375
  "step": 305
376
  },
377
  {
378
- "epoch": 6.49,
379
- "learning_rate": 0.0001,
380
- "loss": 1.5081,
381
  "step": 310
382
  },
383
  {
384
- "epoch": 6.6,
385
- "learning_rate": 0.0001,
386
- "loss": 1.4754,
387
  "step": 315
388
  },
389
  {
390
- "epoch": 6.7,
391
- "learning_rate": 0.0001,
392
- "loss": 1.5619,
393
  "step": 320
394
  },
395
  {
396
- "epoch": 6.81,
397
- "learning_rate": 0.0001,
398
- "loss": 1.5239,
399
  "step": 325
400
  },
401
  {
402
- "epoch": 6.91,
403
- "learning_rate": 0.0001,
404
- "loss": 1.4911,
405
  "step": 330
406
  },
407
  {
408
- "epoch": 7.02,
409
- "learning_rate": 0.0001,
410
- "loss": 1.5315,
411
  "step": 335
412
  },
413
  {
414
- "epoch": 7.12,
415
- "learning_rate": 0.0001,
416
- "loss": 1.477,
417
  "step": 340
418
  },
419
  {
420
- "epoch": 7.23,
421
- "learning_rate": 0.0001,
422
- "loss": 1.4767,
423
  "step": 345
424
  },
425
  {
426
- "epoch": 7.33,
427
- "learning_rate": 0.0001,
428
- "loss": 1.4628,
429
  "step": 350
430
  },
431
  {
432
- "epoch": 7.43,
433
- "learning_rate": 0.0001,
434
- "loss": 1.4545,
435
  "step": 355
436
  },
437
  {
438
- "epoch": 7.54,
439
- "learning_rate": 0.0001,
440
- "loss": 1.4682,
441
  "step": 360
442
  },
443
  {
444
- "epoch": 7.64,
445
- "learning_rate": 0.0001,
446
- "loss": 1.4623,
447
  "step": 365
448
  },
449
  {
450
- "epoch": 7.75,
451
- "learning_rate": 0.0001,
452
- "loss": 1.5164,
453
  "step": 370
454
  },
455
  {
456
- "epoch": 7.85,
457
- "learning_rate": 0.0001,
458
- "loss": 1.5296,
459
  "step": 375
460
  },
461
  {
462
- "epoch": 7.96,
463
- "learning_rate": 0.0001,
464
- "loss": 1.4896,
465
  "step": 380
466
  },
467
  {
468
- "epoch": 8.06,
469
- "learning_rate": 0.0001,
470
- "loss": 1.4365,
471
  "step": 385
472
  },
473
  {
474
- "epoch": 8.17,
475
- "learning_rate": 0.0001,
476
- "loss": 1.4186,
477
  "step": 390
478
  },
479
  {
480
- "epoch": 8.27,
481
- "learning_rate": 0.0001,
482
- "loss": 1.4972,
483
  "step": 395
484
  },
485
  {
486
- "epoch": 8.38,
487
- "learning_rate": 0.0001,
488
- "loss": 1.4749,
489
  "step": 400
490
  },
491
  {
492
- "epoch": 8.48,
493
- "learning_rate": 0.0001,
494
- "loss": 1.4914,
495
  "step": 405
496
  },
497
  {
498
- "epoch": 8.59,
499
- "learning_rate": 0.0001,
500
- "loss": 1.4091,
501
  "step": 410
502
  },
503
  {
504
- "epoch": 8.69,
505
- "learning_rate": 0.0001,
506
- "loss": 1.4599,
507
  "step": 415
508
  },
509
  {
510
- "epoch": 8.8,
511
- "learning_rate": 0.0001,
512
- "loss": 1.4714,
513
  "step": 420
514
  },
515
  {
516
- "epoch": 8.9,
517
- "learning_rate": 0.0001,
518
- "loss": 1.4636,
519
  "step": 425
520
  },
521
  {
522
- "epoch": 9.01,
523
- "learning_rate": 0.0001,
524
- "loss": 1.4848,
525
  "step": 430
526
  },
527
  {
528
- "epoch": 9.11,
529
- "learning_rate": 0.0001,
530
- "loss": 1.4412,
531
  "step": 435
532
  },
533
  {
534
- "epoch": 9.21,
535
- "learning_rate": 0.0001,
536
- "loss": 1.4057,
537
  "step": 440
538
  },
539
  {
540
- "epoch": 9.32,
541
- "learning_rate": 0.0001,
542
- "loss": 1.4464,
543
  "step": 445
544
  },
545
  {
546
- "epoch": 9.42,
547
- "learning_rate": 0.0001,
548
- "loss": 1.4228,
549
  "step": 450
550
  },
551
  {
552
- "epoch": 9.53,
553
- "learning_rate": 0.0001,
554
- "loss": 1.4315,
555
  "step": 455
556
  },
557
  {
558
- "epoch": 9.63,
559
- "learning_rate": 0.0001,
560
- "loss": 1.442,
561
  "step": 460
562
  },
563
  {
564
- "epoch": 9.74,
565
- "learning_rate": 0.0001,
566
- "loss": 1.4008,
567
  "step": 465
568
  },
569
  {
570
- "epoch": 9.84,
571
- "learning_rate": 0.0001,
572
- "loss": 1.4473,
573
  "step": 470
574
  },
575
  {
576
- "epoch": 9.95,
577
- "learning_rate": 0.0001,
578
- "loss": 1.4487,
579
  "step": 475
580
  },
581
  {
582
- "epoch": 10.05,
583
- "learning_rate": 0.0001,
584
- "loss": 1.476,
585
  "step": 480
586
  },
587
  {
588
- "epoch": 10.16,
589
- "learning_rate": 0.0001,
590
- "loss": 1.3862,
591
  "step": 485
592
  },
593
  {
594
- "epoch": 10.26,
595
- "learning_rate": 0.0001,
596
- "loss": 1.4721,
597
  "step": 490
598
  },
599
  {
600
- "epoch": 10.37,
601
- "learning_rate": 0.0001,
602
- "loss": 1.3839,
603
  "step": 495
604
  },
605
  {
606
- "epoch": 10.47,
607
- "learning_rate": 0.0001,
608
- "loss": 1.3948,
609
  "step": 500
610
  },
611
  {
612
- "epoch": 10.58,
613
- "learning_rate": 0.0001,
614
- "loss": 1.4057,
615
  "step": 505
616
  },
617
  {
618
- "epoch": 10.68,
619
- "learning_rate": 0.0001,
620
- "loss": 1.4158,
621
  "step": 510
622
  },
623
  {
624
- "epoch": 10.79,
625
- "learning_rate": 0.0001,
626
- "loss": 1.4162,
627
  "step": 515
628
  },
629
  {
630
- "epoch": 10.89,
631
- "learning_rate": 0.0001,
632
- "loss": 1.468,
633
  "step": 520
634
  },
635
  {
636
- "epoch": 10.99,
637
- "learning_rate": 0.0001,
638
- "loss": 1.3958,
639
  "step": 525
640
  },
641
  {
642
- "epoch": 11.1,
643
- "learning_rate": 0.0001,
644
- "loss": 1.4011,
645
  "step": 530
646
  },
647
  {
648
- "epoch": 11.2,
649
- "learning_rate": 0.0001,
650
- "loss": 1.3536,
651
  "step": 535
652
  },
653
  {
654
- "epoch": 11.31,
655
- "learning_rate": 0.0001,
656
- "loss": 1.4058,
657
  "step": 540
658
  },
659
  {
660
- "epoch": 11.41,
661
- "learning_rate": 0.0001,
662
- "loss": 1.4246,
663
  "step": 545
664
  },
665
  {
666
- "epoch": 11.52,
667
- "learning_rate": 0.0001,
668
- "loss": 1.3732,
669
  "step": 550
670
  },
671
  {
672
- "epoch": 11.62,
673
- "learning_rate": 0.0001,
674
- "loss": 1.4389,
675
  "step": 555
676
  },
677
  {
678
- "epoch": 11.73,
679
- "learning_rate": 0.0001,
680
- "loss": 1.3583,
681
  "step": 560
682
  },
683
  {
684
- "epoch": 11.83,
685
- "learning_rate": 0.0001,
686
- "loss": 1.383,
687
  "step": 565
688
  },
689
  {
690
- "epoch": 11.94,
691
- "learning_rate": 0.0001,
692
- "loss": 1.3902,
693
  "step": 570
694
  },
695
  {
696
- "epoch": 12.04,
697
- "learning_rate": 0.0001,
698
- "loss": 1.3814,
699
  "step": 575
700
  },
701
  {
702
- "epoch": 12.15,
703
- "learning_rate": 0.0001,
704
- "loss": 1.3598,
705
  "step": 580
706
  },
707
  {
708
- "epoch": 12.25,
709
- "learning_rate": 0.0001,
710
- "loss": 1.3826,
711
  "step": 585
712
  },
713
  {
714
- "epoch": 12.36,
715
- "learning_rate": 0.0001,
716
- "loss": 1.3724,
717
  "step": 590
718
  },
719
  {
720
- "epoch": 12.46,
721
- "learning_rate": 0.0001,
722
- "loss": 1.3413,
723
  "step": 595
724
  },
725
  {
726
- "epoch": 12.57,
727
- "learning_rate": 0.0001,
728
- "loss": 1.3661,
729
  "step": 600
730
  },
731
  {
732
- "epoch": 12.67,
733
- "learning_rate": 0.0001,
734
- "loss": 1.3633,
735
  "step": 605
736
  },
737
  {
738
- "epoch": 12.77,
739
- "learning_rate": 0.0001,
740
- "loss": 1.3524,
741
  "step": 610
742
  },
743
  {
744
- "epoch": 12.88,
745
- "learning_rate": 0.0001,
746
- "loss": 1.4059,
747
  "step": 615
748
  },
749
  {
750
- "epoch": 12.98,
751
- "learning_rate": 0.0001,
752
- "loss": 1.3891,
753
  "step": 620
754
  },
755
  {
756
- "epoch": 13.09,
757
- "learning_rate": 0.0001,
758
- "loss": 1.4142,
759
  "step": 625
760
  },
761
  {
762
- "epoch": 13.19,
763
- "learning_rate": 0.0001,
764
- "loss": 1.2695,
765
  "step": 630
766
  },
767
  {
768
- "epoch": 13.3,
769
- "learning_rate": 0.0001,
770
- "loss": 1.3521,
771
  "step": 635
772
  },
773
  {
774
- "epoch": 13.4,
775
- "learning_rate": 0.0001,
776
- "loss": 1.264,
777
  "step": 640
778
  },
779
  {
780
- "epoch": 13.51,
781
- "learning_rate": 0.0001,
782
- "loss": 1.3551,
783
  "step": 645
784
  },
785
  {
786
- "epoch": 13.61,
787
- "learning_rate": 0.0001,
788
- "loss": 1.4012,
789
  "step": 650
790
  },
791
  {
792
- "epoch": 13.72,
793
- "learning_rate": 0.0001,
794
- "loss": 1.3733,
795
  "step": 655
796
  },
797
  {
798
- "epoch": 13.82,
799
- "learning_rate": 0.0001,
800
- "loss": 1.3957,
801
  "step": 660
802
  },
803
  {
804
- "epoch": 13.93,
805
- "learning_rate": 0.0001,
806
- "loss": 1.3557,
807
  "step": 665
808
  },
809
  {
810
- "epoch": 14.03,
811
- "learning_rate": 0.0001,
812
- "loss": 1.3732,
813
  "step": 670
814
  },
815
  {
816
- "epoch": 14.14,
817
- "learning_rate": 0.0001,
818
- "loss": 1.248,
819
  "step": 675
820
  },
821
  {
822
- "epoch": 14.24,
823
- "learning_rate": 0.0001,
824
- "loss": 1.352,
825
  "step": 680
826
  },
827
  {
828
- "epoch": 14.35,
829
- "learning_rate": 0.0001,
830
- "loss": 1.3024,
831
  "step": 685
832
  },
833
  {
834
- "epoch": 14.45,
835
- "learning_rate": 0.0001,
836
- "loss": 1.3343,
837
  "step": 690
838
  },
839
  {
840
- "epoch": 14.55,
841
- "learning_rate": 0.0001,
842
- "loss": 1.3487,
843
  "step": 695
844
  },
845
  {
846
- "epoch": 14.66,
847
- "learning_rate": 0.0001,
848
- "loss": 1.3051,
849
  "step": 700
850
  },
851
  {
852
- "epoch": 14.76,
853
- "learning_rate": 0.0001,
854
- "loss": 1.3331,
855
  "step": 705
856
  },
857
  {
858
- "epoch": 14.87,
859
- "learning_rate": 0.0001,
860
- "loss": 1.371,
861
  "step": 710
862
  },
863
  {
864
- "epoch": 14.97,
865
- "learning_rate": 0.0001,
866
- "loss": 1.3779,
867
  "step": 715
868
  },
869
  {
870
- "epoch": 15.08,
871
- "learning_rate": 0.0001,
872
- "loss": 1.3086,
873
  "step": 720
874
  },
875
  {
876
- "epoch": 15.18,
877
- "learning_rate": 0.0001,
878
- "loss": 1.2871,
879
  "step": 725
880
  },
881
  {
882
- "epoch": 15.29,
883
- "learning_rate": 0.0001,
884
- "loss": 1.2899,
885
  "step": 730
886
  },
887
  {
888
- "epoch": 15.39,
889
- "learning_rate": 0.0001,
890
- "loss": 1.3205,
891
  "step": 735
892
  },
893
  {
894
- "epoch": 15.5,
895
- "learning_rate": 0.0001,
896
- "loss": 1.3799,
897
  "step": 740
898
  },
899
  {
900
- "epoch": 15.6,
901
- "learning_rate": 0.0001,
902
- "loss": 1.3251,
903
  "step": 745
904
  },
905
  {
906
- "epoch": 15.71,
907
- "learning_rate": 0.0001,
908
- "loss": 1.3209,
909
  "step": 750
910
  },
911
  {
912
- "epoch": 15.81,
913
- "learning_rate": 0.0001,
914
- "loss": 1.3015,
915
  "step": 755
916
  },
917
  {
918
- "epoch": 15.92,
919
- "learning_rate": 0.0001,
920
- "loss": 1.2979,
921
  "step": 760
922
  },
923
  {
924
- "epoch": 16.02,
925
- "learning_rate": 0.0001,
926
- "loss": 1.3355,
927
  "step": 765
928
  },
929
  {
930
- "epoch": 16.13,
931
- "learning_rate": 0.0001,
932
- "loss": 1.2764,
933
  "step": 770
934
  },
935
  {
936
- "epoch": 16.23,
937
- "learning_rate": 0.0001,
938
- "loss": 1.319,
939
  "step": 775
940
  },
941
  {
942
- "epoch": 16.34,
943
- "learning_rate": 0.0001,
944
- "loss": 1.2541,
945
  "step": 780
946
  },
947
  {
948
- "epoch": 16.44,
949
- "learning_rate": 0.0001,
950
- "loss": 1.3251,
951
  "step": 785
952
  },
953
  {
954
- "epoch": 16.54,
955
- "learning_rate": 0.0001,
956
- "loss": 1.2479,
957
  "step": 790
958
  },
959
  {
960
- "epoch": 16.65,
961
- "learning_rate": 0.0001,
962
- "loss": 1.2912,
963
  "step": 795
964
  },
965
  {
966
- "epoch": 16.75,
967
- "learning_rate": 0.0001,
968
- "loss": 1.3064,
969
  "step": 800
970
  },
971
  {
972
- "epoch": 16.86,
973
- "learning_rate": 0.0001,
974
- "loss": 1.3029,
975
  "step": 805
976
  },
977
  {
978
- "epoch": 16.96,
979
- "learning_rate": 0.0001,
980
- "loss": 1.3103,
981
  "step": 810
982
  },
983
  {
984
- "epoch": 17.07,
985
- "learning_rate": 0.0001,
986
- "loss": 1.2733,
987
  "step": 815
988
  },
989
  {
990
- "epoch": 17.17,
991
- "learning_rate": 0.0001,
992
- "loss": 1.3373,
993
  "step": 820
994
  },
995
  {
996
- "epoch": 17.28,
997
- "learning_rate": 0.0001,
998
- "loss": 1.2371,
999
  "step": 825
1000
  },
1001
  {
1002
- "epoch": 17.38,
1003
- "learning_rate": 0.0001,
1004
- "loss": 1.2919,
1005
  "step": 830
1006
  },
1007
  {
1008
- "epoch": 17.49,
1009
- "learning_rate": 0.0001,
1010
- "loss": 1.2806,
1011
  "step": 835
1012
  },
1013
  {
1014
- "epoch": 17.59,
1015
- "learning_rate": 0.0001,
1016
- "loss": 1.2925,
1017
  "step": 840
1018
  },
1019
  {
1020
- "epoch": 17.7,
1021
- "learning_rate": 0.0001,
1022
- "loss": 1.2465,
1023
  "step": 845
1024
  },
1025
  {
1026
- "epoch": 17.8,
1027
- "learning_rate": 0.0001,
1028
- "loss": 1.2417,
1029
  "step": 850
1030
  },
1031
  {
1032
- "epoch": 17.91,
1033
- "learning_rate": 0.0001,
1034
- "loss": 1.3069,
1035
  "step": 855
1036
  },
1037
  {
1038
- "epoch": 18.01,
1039
- "learning_rate": 0.0001,
1040
- "loss": 1.2598,
1041
  "step": 860
1042
  },
1043
  {
1044
- "epoch": 18.12,
1045
- "learning_rate": 0.0001,
1046
- "loss": 1.2807,
1047
  "step": 865
1048
  },
1049
  {
1050
- "epoch": 18.22,
1051
- "learning_rate": 0.0001,
1052
- "loss": 1.2548,
1053
  "step": 870
1054
  },
1055
  {
1056
- "epoch": 18.32,
1057
- "learning_rate": 0.0001,
1058
- "loss": 1.2531,
1059
  "step": 875
1060
  },
1061
  {
1062
- "epoch": 18.43,
1063
- "learning_rate": 0.0001,
1064
- "loss": 1.1707,
1065
  "step": 880
1066
  },
1067
  {
1068
- "epoch": 18.53,
1069
- "learning_rate": 0.0001,
1070
- "loss": 1.2652,
1071
  "step": 885
1072
  },
1073
  {
1074
- "epoch": 18.64,
1075
- "learning_rate": 0.0001,
1076
- "loss": 1.2448,
1077
  "step": 890
1078
  },
1079
  {
1080
- "epoch": 18.74,
1081
- "learning_rate": 0.0001,
1082
- "loss": 1.2969,
1083
  "step": 895
1084
  },
1085
  {
1086
- "epoch": 18.85,
1087
- "learning_rate": 0.0001,
1088
- "loss": 1.279,
1089
  "step": 900
1090
  },
1091
  {
1092
- "epoch": 18.95,
1093
- "learning_rate": 0.0001,
1094
- "loss": 1.2714,
1095
  "step": 905
1096
  },
1097
  {
1098
- "epoch": 19.06,
1099
- "learning_rate": 0.0001,
1100
- "loss": 1.277,
1101
  "step": 910
1102
  },
1103
  {
1104
- "epoch": 19.16,
1105
- "learning_rate": 0.0001,
1106
- "loss": 1.2272,
1107
  "step": 915
1108
  },
1109
  {
1110
- "epoch": 19.27,
1111
- "learning_rate": 0.0001,
1112
- "loss": 1.2387,
1113
  "step": 920
1114
  },
1115
  {
1116
- "epoch": 19.37,
1117
- "learning_rate": 0.0001,
1118
- "loss": 1.2494,
1119
  "step": 925
1120
  },
1121
  {
1122
- "epoch": 19.48,
1123
- "learning_rate": 0.0001,
1124
- "loss": 1.3238,
1125
  "step": 930
1126
  },
1127
  {
1128
- "epoch": 19.58,
1129
- "learning_rate": 0.0001,
1130
- "loss": 1.258,
1131
  "step": 935
1132
  },
1133
  {
1134
- "epoch": 19.69,
1135
- "learning_rate": 0.0001,
1136
- "loss": 1.2089,
1137
  "step": 940
1138
  },
1139
  {
1140
- "epoch": 19.79,
1141
- "learning_rate": 0.0001,
1142
- "loss": 1.2216,
1143
  "step": 945
1144
  },
1145
  {
1146
- "epoch": 19.9,
1147
- "learning_rate": 0.0001,
1148
- "loss": 1.2264,
1149
  "step": 950
1150
  },
1151
  {
1152
- "epoch": 20.0,
1153
- "learning_rate": 0.0001,
1154
- "loss": 1.2316,
1155
  "step": 955
1156
  },
1157
  {
1158
- "epoch": 20.1,
1159
- "learning_rate": 0.0001,
1160
- "loss": 1.2038,
1161
  "step": 960
1162
  },
1163
  {
1164
- "epoch": 20.21,
1165
- "learning_rate": 0.0001,
1166
- "loss": 1.2001,
1167
  "step": 965
1168
  },
1169
  {
1170
- "epoch": 20.31,
1171
- "learning_rate": 0.0001,
1172
- "loss": 1.2475,
1173
  "step": 970
1174
  },
1175
  {
1176
- "epoch": 20.42,
1177
- "learning_rate": 0.0001,
1178
- "loss": 1.2513,
1179
  "step": 975
1180
  },
1181
  {
1182
- "epoch": 20.52,
1183
- "learning_rate": 0.0001,
1184
- "loss": 1.2635,
1185
  "step": 980
1186
  },
1187
  {
1188
- "epoch": 20.63,
1189
- "learning_rate": 0.0001,
1190
- "loss": 1.1817,
1191
  "step": 985
1192
  },
1193
  {
1194
- "epoch": 20.73,
1195
- "learning_rate": 0.0001,
1196
- "loss": 1.2474,
1197
  "step": 990
1198
  },
1199
  {
1200
- "epoch": 20.84,
1201
- "learning_rate": 0.0001,
1202
- "loss": 1.2309,
1203
  "step": 995
1204
  },
1205
  {
1206
- "epoch": 20.94,
1207
- "learning_rate": 0.0001,
1208
- "loss": 1.1871,
1209
  "step": 1000
1210
  }
1211
  ],
1212
  "logging_steps": 5,
1213
- "max_steps": 1175,
1214
- "num_train_epochs": 25,
1215
  "save_steps": 1000,
1216
- "total_flos": 3737124864000000.0,
1217
  "trial_name": null,
1218
  "trial_params": null
1219
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.6544502617801047,
5
  "eval_steps": 500,
6
  "global_step": 1000,
7
  "is_hyper_param_search": false,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.001,
14
+ "loss": 1.3845,
15
  "step": 5
16
  },
17
  {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.001,
20
+ "loss": 1.6284,
21
  "step": 10
22
  },
23
  {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.001,
26
+ "loss": 1.3152,
27
  "step": 15
28
  },
29
  {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.001,
32
+ "loss": 1.6192,
33
  "step": 20
34
  },
35
  {
36
+ "epoch": 0.02,
37
+ "learning_rate": 0.001,
38
+ "loss": 1.7394,
39
  "step": 25
40
  },
41
  {
42
+ "epoch": 0.02,
43
+ "learning_rate": 0.001,
44
+ "loss": 1.9925,
45
  "step": 30
46
  },
47
  {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.001,
50
+ "loss": 1.902,
51
  "step": 35
52
  },
53
  {
54
+ "epoch": 0.03,
55
+ "learning_rate": 0.001,
56
+ "loss": 1.822,
57
  "step": 40
58
  },
59
  {
60
+ "epoch": 0.03,
61
+ "learning_rate": 0.001,
62
+ "loss": 2.137,
63
  "step": 45
64
  },
65
  {
66
+ "epoch": 0.03,
67
+ "learning_rate": 0.001,
68
+ "loss": 2.2556,
69
  "step": 50
70
  },
71
  {
72
+ "epoch": 0.04,
73
+ "learning_rate": 0.001,
74
+ "loss": 2.2468,
75
  "step": 55
76
  },
77
  {
78
+ "epoch": 0.04,
79
+ "learning_rate": 0.001,
80
+ "loss": 2.0746,
81
  "step": 60
82
  },
83
  {
84
+ "epoch": 0.04,
85
+ "learning_rate": 0.001,
86
+ "loss": 2.1092,
87
  "step": 65
88
  },
89
  {
90
+ "epoch": 0.05,
91
+ "learning_rate": 0.001,
92
+ "loss": 1.9553,
93
  "step": 70
94
  },
95
  {
96
+ "epoch": 0.05,
97
+ "learning_rate": 0.001,
98
+ "loss": 2.121,
99
  "step": 75
100
  },
101
  {
102
+ "epoch": 0.05,
103
+ "learning_rate": 0.001,
104
+ "loss": 2.1722,
105
  "step": 80
106
  },
107
  {
108
+ "epoch": 0.06,
109
+ "learning_rate": 0.001,
110
+ "loss": 2.1552,
111
  "step": 85
112
  },
113
  {
114
+ "epoch": 0.06,
115
+ "learning_rate": 0.001,
116
+ "loss": 2.5971,
117
  "step": 90
118
  },
119
  {
120
+ "epoch": 0.06,
121
+ "learning_rate": 0.001,
122
+ "loss": 2.4684,
123
  "step": 95
124
  },
125
  {
126
+ "epoch": 0.07,
127
+ "learning_rate": 0.001,
128
+ "loss": 2.0248,
129
  "step": 100
130
  },
131
  {
132
+ "epoch": 0.07,
133
+ "learning_rate": 0.001,
134
+ "loss": 2.5156,
135
  "step": 105
136
  },
137
  {
138
+ "epoch": 0.07,
139
+ "learning_rate": 0.001,
140
+ "loss": 2.3322,
141
  "step": 110
142
  },
143
  {
144
+ "epoch": 0.08,
145
+ "learning_rate": 0.001,
146
+ "loss": 1.7698,
147
  "step": 115
148
  },
149
  {
150
+ "epoch": 0.08,
151
+ "learning_rate": 0.001,
152
+ "loss": 2.3363,
153
  "step": 120
154
  },
155
  {
156
+ "epoch": 0.08,
157
+ "learning_rate": 0.001,
158
+ "loss": 2.1079,
159
  "step": 125
160
  },
161
  {
162
+ "epoch": 0.09,
163
+ "learning_rate": 0.001,
164
+ "loss": 2.0998,
165
  "step": 130
166
  },
167
  {
168
+ "epoch": 0.09,
169
+ "learning_rate": 0.001,
170
+ "loss": 2.8265,
171
  "step": 135
172
  },
173
  {
174
+ "epoch": 0.09,
175
+ "learning_rate": 0.001,
176
+ "loss": 2.6611,
177
  "step": 140
178
  },
179
  {
180
+ "epoch": 0.09,
181
+ "learning_rate": 0.001,
182
+ "loss": 2.2187,
183
  "step": 145
184
  },
185
  {
186
+ "epoch": 0.1,
187
+ "learning_rate": 0.001,
188
+ "loss": 2.33,
189
  "step": 150
190
  },
191
  {
192
+ "epoch": 0.1,
193
+ "learning_rate": 0.001,
194
+ "loss": 2.6119,
195
  "step": 155
196
  },
197
  {
198
+ "epoch": 0.1,
199
+ "learning_rate": 0.001,
200
+ "loss": 2.2203,
201
  "step": 160
202
  },
203
  {
204
+ "epoch": 0.11,
205
+ "learning_rate": 0.001,
206
+ "loss": 2.5474,
207
  "step": 165
208
  },
209
  {
210
+ "epoch": 0.11,
211
+ "learning_rate": 0.001,
212
+ "loss": 2.4763,
213
  "step": 170
214
  },
215
  {
216
+ "epoch": 0.11,
217
+ "learning_rate": 0.001,
218
+ "loss": 2.6068,
219
  "step": 175
220
  },
221
  {
222
+ "epoch": 0.12,
223
+ "learning_rate": 0.001,
224
+ "loss": 2.1221,
225
  "step": 180
226
  },
227
  {
228
+ "epoch": 0.12,
229
+ "learning_rate": 0.001,
230
+ "loss": 2.1185,
231
  "step": 185
232
  },
233
  {
234
+ "epoch": 0.12,
235
+ "learning_rate": 0.001,
236
+ "loss": 1.9481,
237
  "step": 190
238
  },
239
  {
240
+ "epoch": 0.13,
241
+ "learning_rate": 0.001,
242
+ "loss": 2.823,
243
  "step": 195
244
  },
245
  {
246
+ "epoch": 0.13,
247
+ "learning_rate": 0.001,
248
+ "loss": 2.4702,
249
  "step": 200
250
  },
251
  {
252
+ "epoch": 0.13,
253
+ "learning_rate": 0.001,
254
+ "loss": 2.3721,
255
  "step": 205
256
  },
257
  {
258
+ "epoch": 0.14,
259
+ "learning_rate": 0.001,
260
+ "loss": 2.4932,
261
  "step": 210
262
  },
263
  {
264
+ "epoch": 0.14,
265
+ "learning_rate": 0.001,
266
+ "loss": 2.3977,
267
  "step": 215
268
  },
269
  {
270
+ "epoch": 0.14,
271
+ "learning_rate": 0.001,
272
+ "loss": 2.5299,
273
  "step": 220
274
  },
275
  {
276
+ "epoch": 0.15,
277
+ "learning_rate": 0.001,
278
+ "loss": 2.4818,
279
  "step": 225
280
  },
281
  {
282
+ "epoch": 0.15,
283
+ "learning_rate": 0.001,
284
+ "loss": 2.3404,
285
  "step": 230
286
  },
287
  {
288
+ "epoch": 0.15,
289
+ "learning_rate": 0.001,
290
+ "loss": 2.3614,
291
  "step": 235
292
  },
293
  {
294
+ "epoch": 0.16,
295
+ "learning_rate": 0.001,
296
+ "loss": 2.1509,
297
  "step": 240
298
  },
299
  {
300
+ "epoch": 0.16,
301
+ "learning_rate": 0.001,
302
+ "loss": 2.5301,
303
  "step": 245
304
  },
305
  {
306
+ "epoch": 0.16,
307
+ "learning_rate": 0.001,
308
+ "loss": 2.3328,
309
  "step": 250
310
  },
311
  {
312
+ "epoch": 0.17,
313
+ "learning_rate": 0.001,
314
+ "loss": 2.412,
315
  "step": 255
316
  },
317
  {
318
+ "epoch": 0.17,
319
+ "learning_rate": 0.001,
320
+ "loss": 2.5923,
321
  "step": 260
322
  },
323
  {
324
+ "epoch": 0.17,
325
+ "learning_rate": 0.001,
326
+ "loss": 2.2655,
327
  "step": 265
328
  },
329
  {
330
+ "epoch": 0.18,
331
+ "learning_rate": 0.001,
332
+ "loss": 2.7524,
333
  "step": 270
334
  },
335
  {
336
+ "epoch": 0.18,
337
+ "learning_rate": 0.001,
338
+ "loss": 2.6456,
339
  "step": 275
340
  },
341
  {
342
+ "epoch": 0.18,
343
+ "learning_rate": 0.001,
344
+ "loss": 2.3814,
345
  "step": 280
346
  },
347
  {
348
+ "epoch": 0.19,
349
+ "learning_rate": 0.001,
350
+ "loss": 2.3805,
351
  "step": 285
352
  },
353
  {
354
+ "epoch": 0.19,
355
+ "learning_rate": 0.001,
356
+ "loss": 2.6727,
357
  "step": 290
358
  },
359
  {
360
+ "epoch": 0.19,
361
+ "learning_rate": 0.001,
362
+ "loss": 2.3931,
363
  "step": 295
364
  },
365
  {
366
+ "epoch": 0.2,
367
+ "learning_rate": 0.001,
368
+ "loss": 1.9526,
369
  "step": 300
370
  },
371
  {
372
+ "epoch": 0.2,
373
+ "learning_rate": 0.001,
374
+ "loss": 2.7219,
375
  "step": 305
376
  },
377
  {
378
+ "epoch": 0.2,
379
+ "learning_rate": 0.001,
380
+ "loss": 2.4869,
381
  "step": 310
382
  },
383
  {
384
+ "epoch": 0.21,
385
+ "learning_rate": 0.001,
386
+ "loss": 2.4303,
387
  "step": 315
388
  },
389
  {
390
+ "epoch": 0.21,
391
+ "learning_rate": 0.001,
392
+ "loss": 2.5916,
393
  "step": 320
394
  },
395
  {
396
+ "epoch": 0.21,
397
+ "learning_rate": 0.001,
398
+ "loss": 2.3917,
399
  "step": 325
400
  },
401
  {
402
+ "epoch": 0.22,
403
+ "learning_rate": 0.001,
404
+ "loss": 2.4881,
405
  "step": 330
406
  },
407
  {
408
+ "epoch": 0.22,
409
+ "learning_rate": 0.001,
410
+ "loss": 2.3369,
411
  "step": 335
412
  },
413
  {
414
+ "epoch": 0.22,
415
+ "learning_rate": 0.001,
416
+ "loss": 2.45,
417
  "step": 340
418
  },
419
  {
420
+ "epoch": 0.23,
421
+ "learning_rate": 0.001,
422
+ "loss": 2.1916,
423
  "step": 345
424
  },
425
  {
426
+ "epoch": 0.23,
427
+ "learning_rate": 0.001,
428
+ "loss": 2.2606,
429
  "step": 350
430
  },
431
  {
432
+ "epoch": 0.23,
433
+ "learning_rate": 0.001,
434
+ "loss": 2.5533,
435
  "step": 355
436
  },
437
  {
438
+ "epoch": 0.24,
439
+ "learning_rate": 0.001,
440
+ "loss": 2.1873,
441
  "step": 360
442
  },
443
  {
444
+ "epoch": 0.24,
445
+ "learning_rate": 0.001,
446
+ "loss": 2.6057,
447
  "step": 365
448
  },
449
  {
450
+ "epoch": 0.24,
451
+ "learning_rate": 0.001,
452
+ "loss": 2.4611,
453
  "step": 370
454
  },
455
  {
456
+ "epoch": 0.25,
457
+ "learning_rate": 0.001,
458
+ "loss": 2.606,
459
  "step": 375
460
  },
461
  {
462
+ "epoch": 0.25,
463
+ "learning_rate": 0.001,
464
+ "loss": 2.5645,
465
  "step": 380
466
  },
467
  {
468
+ "epoch": 0.25,
469
+ "learning_rate": 0.001,
470
+ "loss": 2.7591,
471
  "step": 385
472
  },
473
  {
474
+ "epoch": 0.26,
475
+ "learning_rate": 0.001,
476
+ "loss": 2.3399,
477
  "step": 390
478
  },
479
  {
480
+ "epoch": 0.26,
481
+ "learning_rate": 0.001,
482
+ "loss": 2.3675,
483
  "step": 395
484
  },
485
  {
486
+ "epoch": 0.26,
487
+ "learning_rate": 0.001,
488
+ "loss": 2.5141,
489
  "step": 400
490
  },
491
  {
492
+ "epoch": 0.27,
493
+ "learning_rate": 0.001,
494
+ "loss": 2.2407,
495
  "step": 405
496
  },
497
  {
498
+ "epoch": 0.27,
499
+ "learning_rate": 0.001,
500
+ "loss": 2.6321,
501
  "step": 410
502
  },
503
  {
504
+ "epoch": 0.27,
505
+ "learning_rate": 0.001,
506
+ "loss": 2.6431,
507
  "step": 415
508
  },
509
  {
510
+ "epoch": 0.27,
511
+ "learning_rate": 0.001,
512
+ "loss": 2.4707,
513
  "step": 420
514
  },
515
  {
516
+ "epoch": 0.28,
517
+ "learning_rate": 0.001,
518
+ "loss": 2.3744,
519
  "step": 425
520
  },
521
  {
522
+ "epoch": 0.28,
523
+ "learning_rate": 0.001,
524
+ "loss": 2.5658,
525
  "step": 430
526
  },
527
  {
528
+ "epoch": 0.28,
529
+ "learning_rate": 0.001,
530
+ "loss": 1.9922,
531
  "step": 435
532
  },
533
  {
534
+ "epoch": 0.29,
535
+ "learning_rate": 0.001,
536
+ "loss": 2.5948,
537
  "step": 440
538
  },
539
  {
540
+ "epoch": 0.29,
541
+ "learning_rate": 0.001,
542
+ "loss": 2.2519,
543
  "step": 445
544
  },
545
  {
546
+ "epoch": 0.29,
547
+ "learning_rate": 0.001,
548
+ "loss": 2.6248,
549
  "step": 450
550
  },
551
  {
552
+ "epoch": 0.3,
553
+ "learning_rate": 0.001,
554
+ "loss": 2.5877,
555
  "step": 455
556
  },
557
  {
558
+ "epoch": 0.3,
559
+ "learning_rate": 0.001,
560
+ "loss": 2.1311,
561
  "step": 460
562
  },
563
  {
564
+ "epoch": 0.3,
565
+ "learning_rate": 0.001,
566
+ "loss": 2.6091,
567
  "step": 465
568
  },
569
  {
570
+ "epoch": 0.31,
571
+ "learning_rate": 0.001,
572
+ "loss": 2.5488,
573
  "step": 470
574
  },
575
  {
576
+ "epoch": 0.31,
577
+ "learning_rate": 0.001,
578
+ "loss": 2.499,
579
  "step": 475
580
  },
581
  {
582
+ "epoch": 0.31,
583
+ "learning_rate": 0.001,
584
+ "loss": 2.5031,
585
  "step": 480
586
  },
587
  {
588
+ "epoch": 0.32,
589
+ "learning_rate": 0.001,
590
+ "loss": 2.5783,
591
  "step": 485
592
  },
593
  {
594
+ "epoch": 0.32,
595
+ "learning_rate": 0.001,
596
+ "loss": 2.6303,
597
  "step": 490
598
  },
599
  {
600
+ "epoch": 0.32,
601
+ "learning_rate": 0.001,
602
+ "loss": 2.6344,
603
  "step": 495
604
  },
605
  {
606
+ "epoch": 0.33,
607
+ "learning_rate": 0.001,
608
+ "loss": 2.7031,
609
  "step": 500
610
  },
611
  {
612
+ "epoch": 0.33,
613
+ "learning_rate": 0.001,
614
+ "loss": 2.6677,
615
  "step": 505
616
  },
617
  {
618
+ "epoch": 0.33,
619
+ "learning_rate": 0.001,
620
+ "loss": 2.7617,
621
  "step": 510
622
  },
623
  {
624
+ "epoch": 0.34,
625
+ "learning_rate": 0.001,
626
+ "loss": 2.3122,
627
  "step": 515
628
  },
629
  {
630
+ "epoch": 0.34,
631
+ "learning_rate": 0.001,
632
+ "loss": 2.3887,
633
  "step": 520
634
  },
635
  {
636
+ "epoch": 0.34,
637
+ "learning_rate": 0.001,
638
+ "loss": 2.5569,
639
  "step": 525
640
  },
641
  {
642
+ "epoch": 0.35,
643
+ "learning_rate": 0.001,
644
+ "loss": 2.4038,
645
  "step": 530
646
  },
647
  {
648
+ "epoch": 0.35,
649
+ "learning_rate": 0.001,
650
+ "loss": 2.7413,
651
  "step": 535
652
  },
653
  {
654
+ "epoch": 0.35,
655
+ "learning_rate": 0.001,
656
+ "loss": 2.5264,
657
  "step": 540
658
  },
659
  {
660
+ "epoch": 0.36,
661
+ "learning_rate": 0.001,
662
+ "loss": 2.335,
663
  "step": 545
664
  },
665
  {
666
+ "epoch": 0.36,
667
+ "learning_rate": 0.001,
668
+ "loss": 2.7574,
669
  "step": 550
670
  },
671
  {
672
+ "epoch": 0.36,
673
+ "learning_rate": 0.001,
674
+ "loss": 2.4542,
675
  "step": 555
676
  },
677
  {
678
+ "epoch": 0.37,
679
+ "learning_rate": 0.001,
680
+ "loss": 2.0885,
681
  "step": 560
682
  },
683
  {
684
+ "epoch": 0.37,
685
+ "learning_rate": 0.001,
686
+ "loss": 2.6057,
687
  "step": 565
688
  },
689
  {
690
+ "epoch": 0.37,
691
+ "learning_rate": 0.001,
692
+ "loss": 2.4971,
693
  "step": 570
694
  },
695
  {
696
+ "epoch": 0.38,
697
+ "learning_rate": 0.001,
698
+ "loss": 2.6251,
699
  "step": 575
700
  },
701
  {
702
+ "epoch": 0.38,
703
+ "learning_rate": 0.001,
704
+ "loss": 2.5784,
705
  "step": 580
706
  },
707
  {
708
+ "epoch": 0.38,
709
+ "learning_rate": 0.001,
710
+ "loss": 2.3878,
711
  "step": 585
712
  },
713
  {
714
+ "epoch": 0.39,
715
+ "learning_rate": 0.001,
716
+ "loss": 2.4271,
717
  "step": 590
718
  },
719
  {
720
+ "epoch": 0.39,
721
+ "learning_rate": 0.001,
722
+ "loss": 2.6751,
723
  "step": 595
724
  },
725
  {
726
+ "epoch": 0.39,
727
+ "learning_rate": 0.001,
728
+ "loss": 2.17,
729
  "step": 600
730
  },
731
  {
732
+ "epoch": 0.4,
733
+ "learning_rate": 0.001,
734
+ "loss": 2.0794,
735
  "step": 605
736
  },
737
  {
738
+ "epoch": 0.4,
739
+ "learning_rate": 0.001,
740
+ "loss": 2.6073,
741
  "step": 610
742
  },
743
  {
744
+ "epoch": 0.4,
745
+ "learning_rate": 0.001,
746
+ "loss": 2.6717,
747
  "step": 615
748
  },
749
  {
750
+ "epoch": 0.41,
751
+ "learning_rate": 0.001,
752
+ "loss": 2.8236,
753
  "step": 620
754
  },
755
  {
756
+ "epoch": 0.41,
757
+ "learning_rate": 0.001,
758
+ "loss": 2.4193,
759
  "step": 625
760
  },
761
  {
762
+ "epoch": 0.41,
763
+ "learning_rate": 0.001,
764
+ "loss": 2.7181,
765
  "step": 630
766
  },
767
  {
768
+ "epoch": 0.42,
769
+ "learning_rate": 0.001,
770
+ "loss": 2.6567,
771
  "step": 635
772
  },
773
  {
774
+ "epoch": 0.42,
775
+ "learning_rate": 0.001,
776
+ "loss": 2.1919,
777
  "step": 640
778
  },
779
  {
780
+ "epoch": 0.42,
781
+ "learning_rate": 0.001,
782
+ "loss": 2.5645,
783
  "step": 645
784
  },
785
  {
786
+ "epoch": 0.43,
787
+ "learning_rate": 0.001,
788
+ "loss": 2.3313,
789
  "step": 650
790
  },
791
  {
792
+ "epoch": 0.43,
793
+ "learning_rate": 0.001,
794
+ "loss": 2.533,
795
  "step": 655
796
  },
797
  {
798
+ "epoch": 0.43,
799
+ "learning_rate": 0.001,
800
+ "loss": 2.621,
801
  "step": 660
802
  },
803
  {
804
+ "epoch": 0.44,
805
+ "learning_rate": 0.001,
806
+ "loss": 2.5693,
807
  "step": 665
808
  },
809
  {
810
+ "epoch": 0.44,
811
+ "learning_rate": 0.001,
812
+ "loss": 2.6943,
813
  "step": 670
814
  },
815
  {
816
+ "epoch": 0.44,
817
+ "learning_rate": 0.001,
818
+ "loss": 2.2715,
819
  "step": 675
820
  },
821
  {
822
+ "epoch": 0.45,
823
+ "learning_rate": 0.001,
824
+ "loss": 2.5614,
825
  "step": 680
826
  },
827
  {
828
+ "epoch": 0.45,
829
+ "learning_rate": 0.001,
830
+ "loss": 2.5784,
831
  "step": 685
832
  },
833
  {
834
+ "epoch": 0.45,
835
+ "learning_rate": 0.001,
836
+ "loss": 2.0613,
837
  "step": 690
838
  },
839
  {
840
+ "epoch": 0.45,
841
+ "learning_rate": 0.001,
842
+ "loss": 2.582,
843
  "step": 695
844
  },
845
  {
846
+ "epoch": 0.46,
847
+ "learning_rate": 0.001,
848
+ "loss": 2.5178,
849
  "step": 700
850
  },
851
  {
852
+ "epoch": 0.46,
853
+ "learning_rate": 0.001,
854
+ "loss": 2.432,
855
  "step": 705
856
  },
857
  {
858
+ "epoch": 0.46,
859
+ "learning_rate": 0.001,
860
+ "loss": 2.1979,
861
  "step": 710
862
  },
863
  {
864
+ "epoch": 0.47,
865
+ "learning_rate": 0.001,
866
+ "loss": 2.4317,
867
  "step": 715
868
  },
869
  {
870
+ "epoch": 0.47,
871
+ "learning_rate": 0.001,
872
+ "loss": 2.285,
873
  "step": 720
874
  },
875
  {
876
+ "epoch": 0.47,
877
+ "learning_rate": 0.001,
878
+ "loss": 2.6127,
879
  "step": 725
880
  },
881
  {
882
+ "epoch": 0.48,
883
+ "learning_rate": 0.001,
884
+ "loss": 2.6221,
885
  "step": 730
886
  },
887
  {
888
+ "epoch": 0.48,
889
+ "learning_rate": 0.001,
890
+ "loss": 2.7519,
891
  "step": 735
892
  },
893
  {
894
+ "epoch": 0.48,
895
+ "learning_rate": 0.001,
896
+ "loss": 2.7351,
897
  "step": 740
898
  },
899
  {
900
+ "epoch": 0.49,
901
+ "learning_rate": 0.001,
902
+ "loss": 2.5224,
903
  "step": 745
904
  },
905
  {
906
+ "epoch": 0.49,
907
+ "learning_rate": 0.001,
908
+ "loss": 2.5145,
909
  "step": 750
910
  },
911
  {
912
+ "epoch": 0.49,
913
+ "learning_rate": 0.001,
914
+ "loss": 2.5122,
915
  "step": 755
916
  },
917
  {
918
+ "epoch": 0.5,
919
+ "learning_rate": 0.001,
920
+ "loss": 2.2971,
921
  "step": 760
922
  },
923
  {
924
+ "epoch": 0.5,
925
+ "learning_rate": 0.001,
926
+ "loss": 2.5628,
927
  "step": 765
928
  },
929
  {
930
+ "epoch": 0.5,
931
+ "learning_rate": 0.001,
932
+ "loss": 2.5803,
933
  "step": 770
934
  },
935
  {
936
+ "epoch": 0.51,
937
+ "learning_rate": 0.001,
938
+ "loss": 2.5209,
939
  "step": 775
940
  },
941
  {
942
+ "epoch": 0.51,
943
+ "learning_rate": 0.001,
944
+ "loss": 2.5051,
945
  "step": 780
946
  },
947
  {
948
+ "epoch": 0.51,
949
+ "learning_rate": 0.001,
950
+ "loss": 2.5275,
951
  "step": 785
952
  },
953
  {
954
+ "epoch": 0.52,
955
+ "learning_rate": 0.001,
956
+ "loss": 2.5019,
957
  "step": 790
958
  },
959
  {
960
+ "epoch": 0.52,
961
+ "learning_rate": 0.001,
962
+ "loss": 2.1714,
963
  "step": 795
964
  },
965
  {
966
+ "epoch": 0.52,
967
+ "learning_rate": 0.001,
968
+ "loss": 2.87,
969
  "step": 800
970
  },
971
  {
972
+ "epoch": 0.53,
973
+ "learning_rate": 0.001,
974
+ "loss": 2.6468,
975
  "step": 805
976
  },
977
  {
978
+ "epoch": 0.53,
979
+ "learning_rate": 0.001,
980
+ "loss": 2.4115,
981
  "step": 810
982
  },
983
  {
984
+ "epoch": 0.53,
985
+ "learning_rate": 0.001,
986
+ "loss": 2.5377,
987
  "step": 815
988
  },
989
  {
990
+ "epoch": 0.54,
991
+ "learning_rate": 0.001,
992
+ "loss": 2.4986,
993
  "step": 820
994
  },
995
  {
996
+ "epoch": 0.54,
997
+ "learning_rate": 0.001,
998
+ "loss": 2.6485,
999
  "step": 825
1000
  },
1001
  {
1002
+ "epoch": 0.54,
1003
+ "learning_rate": 0.001,
1004
+ "loss": 2.6314,
1005
  "step": 830
1006
  },
1007
  {
1008
+ "epoch": 0.55,
1009
+ "learning_rate": 0.001,
1010
+ "loss": 2.3516,
1011
  "step": 835
1012
  },
1013
  {
1014
+ "epoch": 0.55,
1015
+ "learning_rate": 0.001,
1016
+ "loss": 2.39,
1017
  "step": 840
1018
  },
1019
  {
1020
+ "epoch": 0.55,
1021
+ "learning_rate": 0.001,
1022
+ "loss": 2.3759,
1023
  "step": 845
1024
  },
1025
  {
1026
+ "epoch": 0.56,
1027
+ "learning_rate": 0.001,
1028
+ "loss": 2.5348,
1029
  "step": 850
1030
  },
1031
  {
1032
+ "epoch": 0.56,
1033
+ "learning_rate": 0.001,
1034
+ "loss": 2.6843,
1035
  "step": 855
1036
  },
1037
  {
1038
+ "epoch": 0.56,
1039
+ "learning_rate": 0.001,
1040
+ "loss": 2.6289,
1041
  "step": 860
1042
  },
1043
  {
1044
+ "epoch": 0.57,
1045
+ "learning_rate": 0.001,
1046
+ "loss": 2.4023,
1047
  "step": 865
1048
  },
1049
  {
1050
+ "epoch": 0.57,
1051
+ "learning_rate": 0.001,
1052
+ "loss": 2.5979,
1053
  "step": 870
1054
  },
1055
  {
1056
+ "epoch": 0.57,
1057
+ "learning_rate": 0.001,
1058
+ "loss": 2.4683,
1059
  "step": 875
1060
  },
1061
  {
1062
+ "epoch": 0.58,
1063
+ "learning_rate": 0.001,
1064
+ "loss": 2.7099,
1065
  "step": 880
1066
  },
1067
  {
1068
+ "epoch": 0.58,
1069
+ "learning_rate": 0.001,
1070
+ "loss": 2.3129,
1071
  "step": 885
1072
  },
1073
  {
1074
+ "epoch": 0.58,
1075
+ "learning_rate": 0.001,
1076
+ "loss": 2.4508,
1077
  "step": 890
1078
  },
1079
  {
1080
+ "epoch": 0.59,
1081
+ "learning_rate": 0.001,
1082
+ "loss": 2.6484,
1083
  "step": 895
1084
  },
1085
  {
1086
+ "epoch": 0.59,
1087
+ "learning_rate": 0.001,
1088
+ "loss": 2.4541,
1089
  "step": 900
1090
  },
1091
  {
1092
+ "epoch": 0.59,
1093
+ "learning_rate": 0.001,
1094
+ "loss": 2.5101,
1095
  "step": 905
1096
  },
1097
  {
1098
+ "epoch": 0.6,
1099
+ "learning_rate": 0.001,
1100
+ "loss": 2.6002,
1101
  "step": 910
1102
  },
1103
  {
1104
+ "epoch": 0.6,
1105
+ "learning_rate": 0.001,
1106
+ "loss": 2.742,
1107
  "step": 915
1108
  },
1109
  {
1110
+ "epoch": 0.6,
1111
+ "learning_rate": 0.001,
1112
+ "loss": 2.4772,
1113
  "step": 920
1114
  },
1115
  {
1116
+ "epoch": 0.61,
1117
+ "learning_rate": 0.001,
1118
+ "loss": 2.4328,
1119
  "step": 925
1120
  },
1121
  {
1122
+ "epoch": 0.61,
1123
+ "learning_rate": 0.001,
1124
+ "loss": 2.7404,
1125
  "step": 930
1126
  },
1127
  {
1128
+ "epoch": 0.61,
1129
+ "learning_rate": 0.001,
1130
+ "loss": 2.5969,
1131
  "step": 935
1132
  },
1133
  {
1134
+ "epoch": 0.62,
1135
+ "learning_rate": 0.001,
1136
+ "loss": 2.1367,
1137
  "step": 940
1138
  },
1139
  {
1140
+ "epoch": 0.62,
1141
+ "learning_rate": 0.001,
1142
+ "loss": 2.703,
1143
  "step": 945
1144
  },
1145
  {
1146
+ "epoch": 0.62,
1147
+ "learning_rate": 0.001,
1148
+ "loss": 2.5638,
1149
  "step": 950
1150
  },
1151
  {
1152
+ "epoch": 0.62,
1153
+ "learning_rate": 0.001,
1154
+ "loss": 1.8322,
1155
  "step": 955
1156
  },
1157
  {
1158
+ "epoch": 0.63,
1159
+ "learning_rate": 0.001,
1160
+ "loss": 2.5764,
1161
  "step": 960
1162
  },
1163
  {
1164
+ "epoch": 0.63,
1165
+ "learning_rate": 0.001,
1166
+ "loss": 2.4679,
1167
  "step": 965
1168
  },
1169
  {
1170
+ "epoch": 0.63,
1171
+ "learning_rate": 0.001,
1172
+ "loss": 2.1691,
1173
  "step": 970
1174
  },
1175
  {
1176
+ "epoch": 0.64,
1177
+ "learning_rate": 0.001,
1178
+ "loss": 2.3252,
1179
  "step": 975
1180
  },
1181
  {
1182
+ "epoch": 0.64,
1183
+ "learning_rate": 0.001,
1184
+ "loss": 2.3988,
1185
  "step": 980
1186
  },
1187
  {
1188
+ "epoch": 0.64,
1189
+ "learning_rate": 0.001,
1190
+ "loss": 2.221,
1191
  "step": 985
1192
  },
1193
  {
1194
+ "epoch": 0.65,
1195
+ "learning_rate": 0.001,
1196
+ "loss": 2.4715,
1197
  "step": 990
1198
  },
1199
  {
1200
+ "epoch": 0.65,
1201
+ "learning_rate": 0.001,
1202
+ "loss": 2.2479,
1203
  "step": 995
1204
  },
1205
  {
1206
+ "epoch": 0.65,
1207
+ "learning_rate": 0.001,
1208
+ "loss": 2.3859,
1209
  "step": 1000
1210
  }
1211
  ],
1212
  "logging_steps": 5,
1213
+ "max_steps": 7640,
1214
+ "num_train_epochs": 5,
1215
  "save_steps": 1000,
1216
+ "total_flos": 116785152000000.0,
1217
  "trial_name": null,
1218
  "trial_params": null
1219
  }
checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99eae4f19c67acd3f95af7fb6d5de5d000413bb16589081d407c5b736dcd91ad
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026a40a22d79b976af4f05a529a919434f1a1af96981147d87e1c857264d40d7
3
  size 4027
checkpoint-2000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 512,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 4,
15
+ "num_hidden_layers": 2,
16
+ "num_key_value_heads": 4,
17
+ "pretraining_tp": 2,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.34.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
checkpoint-2000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d23839f74f4c0b55aa103ef4325b320be97d8ed3a36d7f169466be1fe4d939
3
+ size 141585770
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b249f59fa15e8178603af8fdd7dd35fb8013199d4f657f6db2cbb5d965295041
3
+ size 70790896
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
+ size 14575
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1c6356a269fb96046eef13597862a100fa292babf825b85a856f1048c67ca0
3
+ size 627
checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "model_max_length": 8192,
33
+ "pad_token": null,
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,2419 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3089005235602094,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.001,
14
+ "loss": 1.3845,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.001,
20
+ "loss": 1.6284,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.001,
26
+ "loss": 1.3152,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.001,
32
+ "loss": 1.6192,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 0.001,
38
+ "loss": 1.7394,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 0.001,
44
+ "loss": 1.9925,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.001,
50
+ "loss": 1.902,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 0.001,
56
+ "loss": 1.822,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 0.001,
62
+ "loss": 2.137,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "learning_rate": 0.001,
68
+ "loss": 2.2556,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 0.04,
73
+ "learning_rate": 0.001,
74
+ "loss": 2.2468,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 0.04,
79
+ "learning_rate": 0.001,
80
+ "loss": 2.0746,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "learning_rate": 0.001,
86
+ "loss": 2.1092,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 0.05,
91
+ "learning_rate": 0.001,
92
+ "loss": 1.9553,
93
+ "step": 70
94
+ },
95
+ {
96
+ "epoch": 0.05,
97
+ "learning_rate": 0.001,
98
+ "loss": 2.121,
99
+ "step": 75
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "learning_rate": 0.001,
104
+ "loss": 2.1722,
105
+ "step": 80
106
+ },
107
+ {
108
+ "epoch": 0.06,
109
+ "learning_rate": 0.001,
110
+ "loss": 2.1552,
111
+ "step": 85
112
+ },
113
+ {
114
+ "epoch": 0.06,
115
+ "learning_rate": 0.001,
116
+ "loss": 2.5971,
117
+ "step": 90
118
+ },
119
+ {
120
+ "epoch": 0.06,
121
+ "learning_rate": 0.001,
122
+ "loss": 2.4684,
123
+ "step": 95
124
+ },
125
+ {
126
+ "epoch": 0.07,
127
+ "learning_rate": 0.001,
128
+ "loss": 2.0248,
129
+ "step": 100
130
+ },
131
+ {
132
+ "epoch": 0.07,
133
+ "learning_rate": 0.001,
134
+ "loss": 2.5156,
135
+ "step": 105
136
+ },
137
+ {
138
+ "epoch": 0.07,
139
+ "learning_rate": 0.001,
140
+ "loss": 2.3322,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.08,
145
+ "learning_rate": 0.001,
146
+ "loss": 1.7698,
147
+ "step": 115
148
+ },
149
+ {
150
+ "epoch": 0.08,
151
+ "learning_rate": 0.001,
152
+ "loss": 2.3363,
153
+ "step": 120
154
+ },
155
+ {
156
+ "epoch": 0.08,
157
+ "learning_rate": 0.001,
158
+ "loss": 2.1079,
159
+ "step": 125
160
+ },
161
+ {
162
+ "epoch": 0.09,
163
+ "learning_rate": 0.001,
164
+ "loss": 2.0998,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 0.09,
169
+ "learning_rate": 0.001,
170
+ "loss": 2.8265,
171
+ "step": 135
172
+ },
173
+ {
174
+ "epoch": 0.09,
175
+ "learning_rate": 0.001,
176
+ "loss": 2.6611,
177
+ "step": 140
178
+ },
179
+ {
180
+ "epoch": 0.09,
181
+ "learning_rate": 0.001,
182
+ "loss": 2.2187,
183
+ "step": 145
184
+ },
185
+ {
186
+ "epoch": 0.1,
187
+ "learning_rate": 0.001,
188
+ "loss": 2.33,
189
+ "step": 150
190
+ },
191
+ {
192
+ "epoch": 0.1,
193
+ "learning_rate": 0.001,
194
+ "loss": 2.6119,
195
+ "step": 155
196
+ },
197
+ {
198
+ "epoch": 0.1,
199
+ "learning_rate": 0.001,
200
+ "loss": 2.2203,
201
+ "step": 160
202
+ },
203
+ {
204
+ "epoch": 0.11,
205
+ "learning_rate": 0.001,
206
+ "loss": 2.5474,
207
+ "step": 165
208
+ },
209
+ {
210
+ "epoch": 0.11,
211
+ "learning_rate": 0.001,
212
+ "loss": 2.4763,
213
+ "step": 170
214
+ },
215
+ {
216
+ "epoch": 0.11,
217
+ "learning_rate": 0.001,
218
+ "loss": 2.6068,
219
+ "step": 175
220
+ },
221
+ {
222
+ "epoch": 0.12,
223
+ "learning_rate": 0.001,
224
+ "loss": 2.1221,
225
+ "step": 180
226
+ },
227
+ {
228
+ "epoch": 0.12,
229
+ "learning_rate": 0.001,
230
+ "loss": 2.1185,
231
+ "step": 185
232
+ },
233
+ {
234
+ "epoch": 0.12,
235
+ "learning_rate": 0.001,
236
+ "loss": 1.9481,
237
+ "step": 190
238
+ },
239
+ {
240
+ "epoch": 0.13,
241
+ "learning_rate": 0.001,
242
+ "loss": 2.823,
243
+ "step": 195
244
+ },
245
+ {
246
+ "epoch": 0.13,
247
+ "learning_rate": 0.001,
248
+ "loss": 2.4702,
249
+ "step": 200
250
+ },
251
+ {
252
+ "epoch": 0.13,
253
+ "learning_rate": 0.001,
254
+ "loss": 2.3721,
255
+ "step": 205
256
+ },
257
+ {
258
+ "epoch": 0.14,
259
+ "learning_rate": 0.001,
260
+ "loss": 2.4932,
261
+ "step": 210
262
+ },
263
+ {
264
+ "epoch": 0.14,
265
+ "learning_rate": 0.001,
266
+ "loss": 2.3977,
267
+ "step": 215
268
+ },
269
+ {
270
+ "epoch": 0.14,
271
+ "learning_rate": 0.001,
272
+ "loss": 2.5299,
273
+ "step": 220
274
+ },
275
+ {
276
+ "epoch": 0.15,
277
+ "learning_rate": 0.001,
278
+ "loss": 2.4818,
279
+ "step": 225
280
+ },
281
+ {
282
+ "epoch": 0.15,
283
+ "learning_rate": 0.001,
284
+ "loss": 2.3404,
285
+ "step": 230
286
+ },
287
+ {
288
+ "epoch": 0.15,
289
+ "learning_rate": 0.001,
290
+ "loss": 2.3614,
291
+ "step": 235
292
+ },
293
+ {
294
+ "epoch": 0.16,
295
+ "learning_rate": 0.001,
296
+ "loss": 2.1509,
297
+ "step": 240
298
+ },
299
+ {
300
+ "epoch": 0.16,
301
+ "learning_rate": 0.001,
302
+ "loss": 2.5301,
303
+ "step": 245
304
+ },
305
+ {
306
+ "epoch": 0.16,
307
+ "learning_rate": 0.001,
308
+ "loss": 2.3328,
309
+ "step": 250
310
+ },
311
+ {
312
+ "epoch": 0.17,
313
+ "learning_rate": 0.001,
314
+ "loss": 2.412,
315
+ "step": 255
316
+ },
317
+ {
318
+ "epoch": 0.17,
319
+ "learning_rate": 0.001,
320
+ "loss": 2.5923,
321
+ "step": 260
322
+ },
323
+ {
324
+ "epoch": 0.17,
325
+ "learning_rate": 0.001,
326
+ "loss": 2.2655,
327
+ "step": 265
328
+ },
329
+ {
330
+ "epoch": 0.18,
331
+ "learning_rate": 0.001,
332
+ "loss": 2.7524,
333
+ "step": 270
334
+ },
335
+ {
336
+ "epoch": 0.18,
337
+ "learning_rate": 0.001,
338
+ "loss": 2.6456,
339
+ "step": 275
340
+ },
341
+ {
342
+ "epoch": 0.18,
343
+ "learning_rate": 0.001,
344
+ "loss": 2.3814,
345
+ "step": 280
346
+ },
347
+ {
348
+ "epoch": 0.19,
349
+ "learning_rate": 0.001,
350
+ "loss": 2.3805,
351
+ "step": 285
352
+ },
353
+ {
354
+ "epoch": 0.19,
355
+ "learning_rate": 0.001,
356
+ "loss": 2.6727,
357
+ "step": 290
358
+ },
359
+ {
360
+ "epoch": 0.19,
361
+ "learning_rate": 0.001,
362
+ "loss": 2.3931,
363
+ "step": 295
364
+ },
365
+ {
366
+ "epoch": 0.2,
367
+ "learning_rate": 0.001,
368
+ "loss": 1.9526,
369
+ "step": 300
370
+ },
371
+ {
372
+ "epoch": 0.2,
373
+ "learning_rate": 0.001,
374
+ "loss": 2.7219,
375
+ "step": 305
376
+ },
377
+ {
378
+ "epoch": 0.2,
379
+ "learning_rate": 0.001,
380
+ "loss": 2.4869,
381
+ "step": 310
382
+ },
383
+ {
384
+ "epoch": 0.21,
385
+ "learning_rate": 0.001,
386
+ "loss": 2.4303,
387
+ "step": 315
388
+ },
389
+ {
390
+ "epoch": 0.21,
391
+ "learning_rate": 0.001,
392
+ "loss": 2.5916,
393
+ "step": 320
394
+ },
395
+ {
396
+ "epoch": 0.21,
397
+ "learning_rate": 0.001,
398
+ "loss": 2.3917,
399
+ "step": 325
400
+ },
401
+ {
402
+ "epoch": 0.22,
403
+ "learning_rate": 0.001,
404
+ "loss": 2.4881,
405
+ "step": 330
406
+ },
407
+ {
408
+ "epoch": 0.22,
409
+ "learning_rate": 0.001,
410
+ "loss": 2.3369,
411
+ "step": 335
412
+ },
413
+ {
414
+ "epoch": 0.22,
415
+ "learning_rate": 0.001,
416
+ "loss": 2.45,
417
+ "step": 340
418
+ },
419
+ {
420
+ "epoch": 0.23,
421
+ "learning_rate": 0.001,
422
+ "loss": 2.1916,
423
+ "step": 345
424
+ },
425
+ {
426
+ "epoch": 0.23,
427
+ "learning_rate": 0.001,
428
+ "loss": 2.2606,
429
+ "step": 350
430
+ },
431
+ {
432
+ "epoch": 0.23,
433
+ "learning_rate": 0.001,
434
+ "loss": 2.5533,
435
+ "step": 355
436
+ },
437
+ {
438
+ "epoch": 0.24,
439
+ "learning_rate": 0.001,
440
+ "loss": 2.1873,
441
+ "step": 360
442
+ },
443
+ {
444
+ "epoch": 0.24,
445
+ "learning_rate": 0.001,
446
+ "loss": 2.6057,
447
+ "step": 365
448
+ },
449
+ {
450
+ "epoch": 0.24,
451
+ "learning_rate": 0.001,
452
+ "loss": 2.4611,
453
+ "step": 370
454
+ },
455
+ {
456
+ "epoch": 0.25,
457
+ "learning_rate": 0.001,
458
+ "loss": 2.606,
459
+ "step": 375
460
+ },
461
+ {
462
+ "epoch": 0.25,
463
+ "learning_rate": 0.001,
464
+ "loss": 2.5645,
465
+ "step": 380
466
+ },
467
+ {
468
+ "epoch": 0.25,
469
+ "learning_rate": 0.001,
470
+ "loss": 2.7591,
471
+ "step": 385
472
+ },
473
+ {
474
+ "epoch": 0.26,
475
+ "learning_rate": 0.001,
476
+ "loss": 2.3399,
477
+ "step": 390
478
+ },
479
+ {
480
+ "epoch": 0.26,
481
+ "learning_rate": 0.001,
482
+ "loss": 2.3675,
483
+ "step": 395
484
+ },
485
+ {
486
+ "epoch": 0.26,
487
+ "learning_rate": 0.001,
488
+ "loss": 2.5141,
489
+ "step": 400
490
+ },
491
+ {
492
+ "epoch": 0.27,
493
+ "learning_rate": 0.001,
494
+ "loss": 2.2407,
495
+ "step": 405
496
+ },
497
+ {
498
+ "epoch": 0.27,
499
+ "learning_rate": 0.001,
500
+ "loss": 2.6321,
501
+ "step": 410
502
+ },
503
+ {
504
+ "epoch": 0.27,
505
+ "learning_rate": 0.001,
506
+ "loss": 2.6431,
507
+ "step": 415
508
+ },
509
+ {
510
+ "epoch": 0.27,
511
+ "learning_rate": 0.001,
512
+ "loss": 2.4707,
513
+ "step": 420
514
+ },
515
+ {
516
+ "epoch": 0.28,
517
+ "learning_rate": 0.001,
518
+ "loss": 2.3744,
519
+ "step": 425
520
+ },
521
+ {
522
+ "epoch": 0.28,
523
+ "learning_rate": 0.001,
524
+ "loss": 2.5658,
525
+ "step": 430
526
+ },
527
+ {
528
+ "epoch": 0.28,
529
+ "learning_rate": 0.001,
530
+ "loss": 1.9922,
531
+ "step": 435
532
+ },
533
+ {
534
+ "epoch": 0.29,
535
+ "learning_rate": 0.001,
536
+ "loss": 2.5948,
537
+ "step": 440
538
+ },
539
+ {
540
+ "epoch": 0.29,
541
+ "learning_rate": 0.001,
542
+ "loss": 2.2519,
543
+ "step": 445
544
+ },
545
+ {
546
+ "epoch": 0.29,
547
+ "learning_rate": 0.001,
548
+ "loss": 2.6248,
549
+ "step": 450
550
+ },
551
+ {
552
+ "epoch": 0.3,
553
+ "learning_rate": 0.001,
554
+ "loss": 2.5877,
555
+ "step": 455
556
+ },
557
+ {
558
+ "epoch": 0.3,
559
+ "learning_rate": 0.001,
560
+ "loss": 2.1311,
561
+ "step": 460
562
+ },
563
+ {
564
+ "epoch": 0.3,
565
+ "learning_rate": 0.001,
566
+ "loss": 2.6091,
567
+ "step": 465
568
+ },
569
+ {
570
+ "epoch": 0.31,
571
+ "learning_rate": 0.001,
572
+ "loss": 2.5488,
573
+ "step": 470
574
+ },
575
+ {
576
+ "epoch": 0.31,
577
+ "learning_rate": 0.001,
578
+ "loss": 2.499,
579
+ "step": 475
580
+ },
581
+ {
582
+ "epoch": 0.31,
583
+ "learning_rate": 0.001,
584
+ "loss": 2.5031,
585
+ "step": 480
586
+ },
587
+ {
588
+ "epoch": 0.32,
589
+ "learning_rate": 0.001,
590
+ "loss": 2.5783,
591
+ "step": 485
592
+ },
593
+ {
594
+ "epoch": 0.32,
595
+ "learning_rate": 0.001,
596
+ "loss": 2.6303,
597
+ "step": 490
598
+ },
599
+ {
600
+ "epoch": 0.32,
601
+ "learning_rate": 0.001,
602
+ "loss": 2.6344,
603
+ "step": 495
604
+ },
605
+ {
606
+ "epoch": 0.33,
607
+ "learning_rate": 0.001,
608
+ "loss": 2.7031,
609
+ "step": 500
610
+ },
611
+ {
612
+ "epoch": 0.33,
613
+ "learning_rate": 0.001,
614
+ "loss": 2.6677,
615
+ "step": 505
616
+ },
617
+ {
618
+ "epoch": 0.33,
619
+ "learning_rate": 0.001,
620
+ "loss": 2.7617,
621
+ "step": 510
622
+ },
623
+ {
624
+ "epoch": 0.34,
625
+ "learning_rate": 0.001,
626
+ "loss": 2.3122,
627
+ "step": 515
628
+ },
629
+ {
630
+ "epoch": 0.34,
631
+ "learning_rate": 0.001,
632
+ "loss": 2.3887,
633
+ "step": 520
634
+ },
635
+ {
636
+ "epoch": 0.34,
637
+ "learning_rate": 0.001,
638
+ "loss": 2.5569,
639
+ "step": 525
640
+ },
641
+ {
642
+ "epoch": 0.35,
643
+ "learning_rate": 0.001,
644
+ "loss": 2.4038,
645
+ "step": 530
646
+ },
647
+ {
648
+ "epoch": 0.35,
649
+ "learning_rate": 0.001,
650
+ "loss": 2.7413,
651
+ "step": 535
652
+ },
653
+ {
654
+ "epoch": 0.35,
655
+ "learning_rate": 0.001,
656
+ "loss": 2.5264,
657
+ "step": 540
658
+ },
659
+ {
660
+ "epoch": 0.36,
661
+ "learning_rate": 0.001,
662
+ "loss": 2.335,
663
+ "step": 545
664
+ },
665
+ {
666
+ "epoch": 0.36,
667
+ "learning_rate": 0.001,
668
+ "loss": 2.7574,
669
+ "step": 550
670
+ },
671
+ {
672
+ "epoch": 0.36,
673
+ "learning_rate": 0.001,
674
+ "loss": 2.4542,
675
+ "step": 555
676
+ },
677
+ {
678
+ "epoch": 0.37,
679
+ "learning_rate": 0.001,
680
+ "loss": 2.0885,
681
+ "step": 560
682
+ },
683
+ {
684
+ "epoch": 0.37,
685
+ "learning_rate": 0.001,
686
+ "loss": 2.6057,
687
+ "step": 565
688
+ },
689
+ {
690
+ "epoch": 0.37,
691
+ "learning_rate": 0.001,
692
+ "loss": 2.4971,
693
+ "step": 570
694
+ },
695
+ {
696
+ "epoch": 0.38,
697
+ "learning_rate": 0.001,
698
+ "loss": 2.6251,
699
+ "step": 575
700
+ },
701
+ {
702
+ "epoch": 0.38,
703
+ "learning_rate": 0.001,
704
+ "loss": 2.5784,
705
+ "step": 580
706
+ },
707
+ {
708
+ "epoch": 0.38,
709
+ "learning_rate": 0.001,
710
+ "loss": 2.3878,
711
+ "step": 585
712
+ },
713
+ {
714
+ "epoch": 0.39,
715
+ "learning_rate": 0.001,
716
+ "loss": 2.4271,
717
+ "step": 590
718
+ },
719
+ {
720
+ "epoch": 0.39,
721
+ "learning_rate": 0.001,
722
+ "loss": 2.6751,
723
+ "step": 595
724
+ },
725
+ {
726
+ "epoch": 0.39,
727
+ "learning_rate": 0.001,
728
+ "loss": 2.17,
729
+ "step": 600
730
+ },
731
+ {
732
+ "epoch": 0.4,
733
+ "learning_rate": 0.001,
734
+ "loss": 2.0794,
735
+ "step": 605
736
+ },
737
+ {
738
+ "epoch": 0.4,
739
+ "learning_rate": 0.001,
740
+ "loss": 2.6073,
741
+ "step": 610
742
+ },
743
+ {
744
+ "epoch": 0.4,
745
+ "learning_rate": 0.001,
746
+ "loss": 2.6717,
747
+ "step": 615
748
+ },
749
+ {
750
+ "epoch": 0.41,
751
+ "learning_rate": 0.001,
752
+ "loss": 2.8236,
753
+ "step": 620
754
+ },
755
+ {
756
+ "epoch": 0.41,
757
+ "learning_rate": 0.001,
758
+ "loss": 2.4193,
759
+ "step": 625
760
+ },
761
+ {
762
+ "epoch": 0.41,
763
+ "learning_rate": 0.001,
764
+ "loss": 2.7181,
765
+ "step": 630
766
+ },
767
+ {
768
+ "epoch": 0.42,
769
+ "learning_rate": 0.001,
770
+ "loss": 2.6567,
771
+ "step": 635
772
+ },
773
+ {
774
+ "epoch": 0.42,
775
+ "learning_rate": 0.001,
776
+ "loss": 2.1919,
777
+ "step": 640
778
+ },
779
+ {
780
+ "epoch": 0.42,
781
+ "learning_rate": 0.001,
782
+ "loss": 2.5645,
783
+ "step": 645
784
+ },
785
+ {
786
+ "epoch": 0.43,
787
+ "learning_rate": 0.001,
788
+ "loss": 2.3313,
789
+ "step": 650
790
+ },
791
+ {
792
+ "epoch": 0.43,
793
+ "learning_rate": 0.001,
794
+ "loss": 2.533,
795
+ "step": 655
796
+ },
797
+ {
798
+ "epoch": 0.43,
799
+ "learning_rate": 0.001,
800
+ "loss": 2.621,
801
+ "step": 660
802
+ },
803
+ {
804
+ "epoch": 0.44,
805
+ "learning_rate": 0.001,
806
+ "loss": 2.5693,
807
+ "step": 665
808
+ },
809
+ {
810
+ "epoch": 0.44,
811
+ "learning_rate": 0.001,
812
+ "loss": 2.6943,
813
+ "step": 670
814
+ },
815
+ {
816
+ "epoch": 0.44,
817
+ "learning_rate": 0.001,
818
+ "loss": 2.2715,
819
+ "step": 675
820
+ },
821
+ {
822
+ "epoch": 0.45,
823
+ "learning_rate": 0.001,
824
+ "loss": 2.5614,
825
+ "step": 680
826
+ },
827
+ {
828
+ "epoch": 0.45,
829
+ "learning_rate": 0.001,
830
+ "loss": 2.5784,
831
+ "step": 685
832
+ },
833
+ {
834
+ "epoch": 0.45,
835
+ "learning_rate": 0.001,
836
+ "loss": 2.0613,
837
+ "step": 690
838
+ },
839
+ {
840
+ "epoch": 0.45,
841
+ "learning_rate": 0.001,
842
+ "loss": 2.582,
843
+ "step": 695
844
+ },
845
+ {
846
+ "epoch": 0.46,
847
+ "learning_rate": 0.001,
848
+ "loss": 2.5178,
849
+ "step": 700
850
+ },
851
+ {
852
+ "epoch": 0.46,
853
+ "learning_rate": 0.001,
854
+ "loss": 2.432,
855
+ "step": 705
856
+ },
857
+ {
858
+ "epoch": 0.46,
859
+ "learning_rate": 0.001,
860
+ "loss": 2.1979,
861
+ "step": 710
862
+ },
863
+ {
864
+ "epoch": 0.47,
865
+ "learning_rate": 0.001,
866
+ "loss": 2.4317,
867
+ "step": 715
868
+ },
869
+ {
870
+ "epoch": 0.47,
871
+ "learning_rate": 0.001,
872
+ "loss": 2.285,
873
+ "step": 720
874
+ },
875
+ {
876
+ "epoch": 0.47,
877
+ "learning_rate": 0.001,
878
+ "loss": 2.6127,
879
+ "step": 725
880
+ },
881
+ {
882
+ "epoch": 0.48,
883
+ "learning_rate": 0.001,
884
+ "loss": 2.6221,
885
+ "step": 730
886
+ },
887
+ {
888
+ "epoch": 0.48,
889
+ "learning_rate": 0.001,
890
+ "loss": 2.7519,
891
+ "step": 735
892
+ },
893
+ {
894
+ "epoch": 0.48,
895
+ "learning_rate": 0.001,
896
+ "loss": 2.7351,
897
+ "step": 740
898
+ },
899
+ {
900
+ "epoch": 0.49,
901
+ "learning_rate": 0.001,
902
+ "loss": 2.5224,
903
+ "step": 745
904
+ },
905
+ {
906
+ "epoch": 0.49,
907
+ "learning_rate": 0.001,
908
+ "loss": 2.5145,
909
+ "step": 750
910
+ },
911
+ {
912
+ "epoch": 0.49,
913
+ "learning_rate": 0.001,
914
+ "loss": 2.5122,
915
+ "step": 755
916
+ },
917
+ {
918
+ "epoch": 0.5,
919
+ "learning_rate": 0.001,
920
+ "loss": 2.2971,
921
+ "step": 760
922
+ },
923
+ {
924
+ "epoch": 0.5,
925
+ "learning_rate": 0.001,
926
+ "loss": 2.5628,
927
+ "step": 765
928
+ },
929
+ {
930
+ "epoch": 0.5,
931
+ "learning_rate": 0.001,
932
+ "loss": 2.5803,
933
+ "step": 770
934
+ },
935
+ {
936
+ "epoch": 0.51,
937
+ "learning_rate": 0.001,
938
+ "loss": 2.5209,
939
+ "step": 775
940
+ },
941
+ {
942
+ "epoch": 0.51,
943
+ "learning_rate": 0.001,
944
+ "loss": 2.5051,
945
+ "step": 780
946
+ },
947
+ {
948
+ "epoch": 0.51,
949
+ "learning_rate": 0.001,
950
+ "loss": 2.5275,
951
+ "step": 785
952
+ },
953
+ {
954
+ "epoch": 0.52,
955
+ "learning_rate": 0.001,
956
+ "loss": 2.5019,
957
+ "step": 790
958
+ },
959
+ {
960
+ "epoch": 0.52,
961
+ "learning_rate": 0.001,
962
+ "loss": 2.1714,
963
+ "step": 795
964
+ },
965
+ {
966
+ "epoch": 0.52,
967
+ "learning_rate": 0.001,
968
+ "loss": 2.87,
969
+ "step": 800
970
+ },
971
+ {
972
+ "epoch": 0.53,
973
+ "learning_rate": 0.001,
974
+ "loss": 2.6468,
975
+ "step": 805
976
+ },
977
+ {
978
+ "epoch": 0.53,
979
+ "learning_rate": 0.001,
980
+ "loss": 2.4115,
981
+ "step": 810
982
+ },
983
+ {
984
+ "epoch": 0.53,
985
+ "learning_rate": 0.001,
986
+ "loss": 2.5377,
987
+ "step": 815
988
+ },
989
+ {
990
+ "epoch": 0.54,
991
+ "learning_rate": 0.001,
992
+ "loss": 2.4986,
993
+ "step": 820
994
+ },
995
+ {
996
+ "epoch": 0.54,
997
+ "learning_rate": 0.001,
998
+ "loss": 2.6485,
999
+ "step": 825
1000
+ },
1001
+ {
1002
+ "epoch": 0.54,
1003
+ "learning_rate": 0.001,
1004
+ "loss": 2.6314,
1005
+ "step": 830
1006
+ },
1007
+ {
1008
+ "epoch": 0.55,
1009
+ "learning_rate": 0.001,
1010
+ "loss": 2.3516,
1011
+ "step": 835
1012
+ },
1013
+ {
1014
+ "epoch": 0.55,
1015
+ "learning_rate": 0.001,
1016
+ "loss": 2.39,
1017
+ "step": 840
1018
+ },
1019
+ {
1020
+ "epoch": 0.55,
1021
+ "learning_rate": 0.001,
1022
+ "loss": 2.3759,
1023
+ "step": 845
1024
+ },
1025
+ {
1026
+ "epoch": 0.56,
1027
+ "learning_rate": 0.001,
1028
+ "loss": 2.5348,
1029
+ "step": 850
1030
+ },
1031
+ {
1032
+ "epoch": 0.56,
1033
+ "learning_rate": 0.001,
1034
+ "loss": 2.6843,
1035
+ "step": 855
1036
+ },
1037
+ {
1038
+ "epoch": 0.56,
1039
+ "learning_rate": 0.001,
1040
+ "loss": 2.6289,
1041
+ "step": 860
1042
+ },
1043
+ {
1044
+ "epoch": 0.57,
1045
+ "learning_rate": 0.001,
1046
+ "loss": 2.4023,
1047
+ "step": 865
1048
+ },
1049
+ {
1050
+ "epoch": 0.57,
1051
+ "learning_rate": 0.001,
1052
+ "loss": 2.5979,
1053
+ "step": 870
1054
+ },
1055
+ {
1056
+ "epoch": 0.57,
1057
+ "learning_rate": 0.001,
1058
+ "loss": 2.4683,
1059
+ "step": 875
1060
+ },
1061
+ {
1062
+ "epoch": 0.58,
1063
+ "learning_rate": 0.001,
1064
+ "loss": 2.7099,
1065
+ "step": 880
1066
+ },
1067
+ {
1068
+ "epoch": 0.58,
1069
+ "learning_rate": 0.001,
1070
+ "loss": 2.3129,
1071
+ "step": 885
1072
+ },
1073
+ {
1074
+ "epoch": 0.58,
1075
+ "learning_rate": 0.001,
1076
+ "loss": 2.4508,
1077
+ "step": 890
1078
+ },
1079
+ {
1080
+ "epoch": 0.59,
1081
+ "learning_rate": 0.001,
1082
+ "loss": 2.6484,
1083
+ "step": 895
1084
+ },
1085
+ {
1086
+ "epoch": 0.59,
1087
+ "learning_rate": 0.001,
1088
+ "loss": 2.4541,
1089
+ "step": 900
1090
+ },
1091
+ {
1092
+ "epoch": 0.59,
1093
+ "learning_rate": 0.001,
1094
+ "loss": 2.5101,
1095
+ "step": 905
1096
+ },
1097
+ {
1098
+ "epoch": 0.6,
1099
+ "learning_rate": 0.001,
1100
+ "loss": 2.6002,
1101
+ "step": 910
1102
+ },
1103
+ {
1104
+ "epoch": 0.6,
1105
+ "learning_rate": 0.001,
1106
+ "loss": 2.742,
1107
+ "step": 915
1108
+ },
1109
+ {
1110
+ "epoch": 0.6,
1111
+ "learning_rate": 0.001,
1112
+ "loss": 2.4772,
1113
+ "step": 920
1114
+ },
1115
+ {
1116
+ "epoch": 0.61,
1117
+ "learning_rate": 0.001,
1118
+ "loss": 2.4328,
1119
+ "step": 925
1120
+ },
1121
+ {
1122
+ "epoch": 0.61,
1123
+ "learning_rate": 0.001,
1124
+ "loss": 2.7404,
1125
+ "step": 930
1126
+ },
1127
+ {
1128
+ "epoch": 0.61,
1129
+ "learning_rate": 0.001,
1130
+ "loss": 2.5969,
1131
+ "step": 935
1132
+ },
1133
+ {
1134
+ "epoch": 0.62,
1135
+ "learning_rate": 0.001,
1136
+ "loss": 2.1367,
1137
+ "step": 940
1138
+ },
1139
+ {
1140
+ "epoch": 0.62,
1141
+ "learning_rate": 0.001,
1142
+ "loss": 2.703,
1143
+ "step": 945
1144
+ },
1145
+ {
1146
+ "epoch": 0.62,
1147
+ "learning_rate": 0.001,
1148
+ "loss": 2.5638,
1149
+ "step": 950
1150
+ },
1151
+ {
1152
+ "epoch": 0.62,
1153
+ "learning_rate": 0.001,
1154
+ "loss": 1.8322,
1155
+ "step": 955
1156
+ },
1157
+ {
1158
+ "epoch": 0.63,
1159
+ "learning_rate": 0.001,
1160
+ "loss": 2.5764,
1161
+ "step": 960
1162
+ },
1163
+ {
1164
+ "epoch": 0.63,
1165
+ "learning_rate": 0.001,
1166
+ "loss": 2.4679,
1167
+ "step": 965
1168
+ },
1169
+ {
1170
+ "epoch": 0.63,
1171
+ "learning_rate": 0.001,
1172
+ "loss": 2.1691,
1173
+ "step": 970
1174
+ },
1175
+ {
1176
+ "epoch": 0.64,
1177
+ "learning_rate": 0.001,
1178
+ "loss": 2.3252,
1179
+ "step": 975
1180
+ },
1181
+ {
1182
+ "epoch": 0.64,
1183
+ "learning_rate": 0.001,
1184
+ "loss": 2.3988,
1185
+ "step": 980
1186
+ },
1187
+ {
1188
+ "epoch": 0.64,
1189
+ "learning_rate": 0.001,
1190
+ "loss": 2.221,
1191
+ "step": 985
1192
+ },
1193
+ {
1194
+ "epoch": 0.65,
1195
+ "learning_rate": 0.001,
1196
+ "loss": 2.4715,
1197
+ "step": 990
1198
+ },
1199
+ {
1200
+ "epoch": 0.65,
1201
+ "learning_rate": 0.001,
1202
+ "loss": 2.2479,
1203
+ "step": 995
1204
+ },
1205
+ {
1206
+ "epoch": 0.65,
1207
+ "learning_rate": 0.001,
1208
+ "loss": 2.3859,
1209
+ "step": 1000
1210
+ },
1211
+ {
1212
+ "epoch": 0.66,
1213
+ "learning_rate": 0.001,
1214
+ "loss": 2.7889,
1215
+ "step": 1005
1216
+ },
1217
+ {
1218
+ "epoch": 0.66,
1219
+ "learning_rate": 0.001,
1220
+ "loss": 2.625,
1221
+ "step": 1010
1222
+ },
1223
+ {
1224
+ "epoch": 0.66,
1225
+ "learning_rate": 0.001,
1226
+ "loss": 2.324,
1227
+ "step": 1015
1228
+ },
1229
+ {
1230
+ "epoch": 0.67,
1231
+ "learning_rate": 0.001,
1232
+ "loss": 2.5879,
1233
+ "step": 1020
1234
+ },
1235
+ {
1236
+ "epoch": 0.67,
1237
+ "learning_rate": 0.001,
1238
+ "loss": 2.4721,
1239
+ "step": 1025
1240
+ },
1241
+ {
1242
+ "epoch": 0.67,
1243
+ "learning_rate": 0.001,
1244
+ "loss": 2.6365,
1245
+ "step": 1030
1246
+ },
1247
+ {
1248
+ "epoch": 0.68,
1249
+ "learning_rate": 0.001,
1250
+ "loss": 2.6356,
1251
+ "step": 1035
1252
+ },
1253
+ {
1254
+ "epoch": 0.68,
1255
+ "learning_rate": 0.001,
1256
+ "loss": 2.4022,
1257
+ "step": 1040
1258
+ },
1259
+ {
1260
+ "epoch": 0.68,
1261
+ "learning_rate": 0.001,
1262
+ "loss": 2.7109,
1263
+ "step": 1045
1264
+ },
1265
+ {
1266
+ "epoch": 0.69,
1267
+ "learning_rate": 0.001,
1268
+ "loss": 2.373,
1269
+ "step": 1050
1270
+ },
1271
+ {
1272
+ "epoch": 0.69,
1273
+ "learning_rate": 0.001,
1274
+ "loss": 2.523,
1275
+ "step": 1055
1276
+ },
1277
+ {
1278
+ "epoch": 0.69,
1279
+ "learning_rate": 0.001,
1280
+ "loss": 2.536,
1281
+ "step": 1060
1282
+ },
1283
+ {
1284
+ "epoch": 0.7,
1285
+ "learning_rate": 0.001,
1286
+ "loss": 2.6047,
1287
+ "step": 1065
1288
+ },
1289
+ {
1290
+ "epoch": 0.7,
1291
+ "learning_rate": 0.001,
1292
+ "loss": 2.5583,
1293
+ "step": 1070
1294
+ },
1295
+ {
1296
+ "epoch": 0.7,
1297
+ "learning_rate": 0.001,
1298
+ "loss": 2.7925,
1299
+ "step": 1075
1300
+ },
1301
+ {
1302
+ "epoch": 0.71,
1303
+ "learning_rate": 0.001,
1304
+ "loss": 2.0572,
1305
+ "step": 1080
1306
+ },
1307
+ {
1308
+ "epoch": 0.71,
1309
+ "learning_rate": 0.001,
1310
+ "loss": 2.3024,
1311
+ "step": 1085
1312
+ },
1313
+ {
1314
+ "epoch": 0.71,
1315
+ "learning_rate": 0.001,
1316
+ "loss": 2.0677,
1317
+ "step": 1090
1318
+ },
1319
+ {
1320
+ "epoch": 0.72,
1321
+ "learning_rate": 0.001,
1322
+ "loss": 2.5241,
1323
+ "step": 1095
1324
+ },
1325
+ {
1326
+ "epoch": 0.72,
1327
+ "learning_rate": 0.001,
1328
+ "loss": 2.7447,
1329
+ "step": 1100
1330
+ },
1331
+ {
1332
+ "epoch": 0.72,
1333
+ "learning_rate": 0.001,
1334
+ "loss": 2.6435,
1335
+ "step": 1105
1336
+ },
1337
+ {
1338
+ "epoch": 0.73,
1339
+ "learning_rate": 0.001,
1340
+ "loss": 2.4226,
1341
+ "step": 1110
1342
+ },
1343
+ {
1344
+ "epoch": 0.73,
1345
+ "learning_rate": 0.001,
1346
+ "loss": 2.6891,
1347
+ "step": 1115
1348
+ },
1349
+ {
1350
+ "epoch": 0.73,
1351
+ "learning_rate": 0.001,
1352
+ "loss": 2.458,
1353
+ "step": 1120
1354
+ },
1355
+ {
1356
+ "epoch": 0.74,
1357
+ "learning_rate": 0.001,
1358
+ "loss": 2.6884,
1359
+ "step": 1125
1360
+ },
1361
+ {
1362
+ "epoch": 0.74,
1363
+ "learning_rate": 0.001,
1364
+ "loss": 2.7058,
1365
+ "step": 1130
1366
+ },
1367
+ {
1368
+ "epoch": 0.74,
1369
+ "learning_rate": 0.001,
1370
+ "loss": 2.5828,
1371
+ "step": 1135
1372
+ },
1373
+ {
1374
+ "epoch": 0.75,
1375
+ "learning_rate": 0.001,
1376
+ "loss": 2.7107,
1377
+ "step": 1140
1378
+ },
1379
+ {
1380
+ "epoch": 0.75,
1381
+ "learning_rate": 0.001,
1382
+ "loss": 2.3635,
1383
+ "step": 1145
1384
+ },
1385
+ {
1386
+ "epoch": 0.75,
1387
+ "learning_rate": 0.001,
1388
+ "loss": 2.5258,
1389
+ "step": 1150
1390
+ },
1391
+ {
1392
+ "epoch": 0.76,
1393
+ "learning_rate": 0.001,
1394
+ "loss": 2.6046,
1395
+ "step": 1155
1396
+ },
1397
+ {
1398
+ "epoch": 0.76,
1399
+ "learning_rate": 0.001,
1400
+ "loss": 2.5215,
1401
+ "step": 1160
1402
+ },
1403
+ {
1404
+ "epoch": 0.76,
1405
+ "learning_rate": 0.001,
1406
+ "loss": 2.1417,
1407
+ "step": 1165
1408
+ },
1409
+ {
1410
+ "epoch": 0.77,
1411
+ "learning_rate": 0.001,
1412
+ "loss": 2.5903,
1413
+ "step": 1170
1414
+ },
1415
+ {
1416
+ "epoch": 0.77,
1417
+ "learning_rate": 0.001,
1418
+ "loss": 2.5376,
1419
+ "step": 1175
1420
+ },
1421
+ {
1422
+ "epoch": 0.77,
1423
+ "learning_rate": 0.001,
1424
+ "loss": 2.5716,
1425
+ "step": 1180
1426
+ },
1427
+ {
1428
+ "epoch": 0.78,
1429
+ "learning_rate": 0.001,
1430
+ "loss": 2.5904,
1431
+ "step": 1185
1432
+ },
1433
+ {
1434
+ "epoch": 0.78,
1435
+ "learning_rate": 0.001,
1436
+ "loss": 2.6511,
1437
+ "step": 1190
1438
+ },
1439
+ {
1440
+ "epoch": 0.78,
1441
+ "learning_rate": 0.001,
1442
+ "loss": 2.1679,
1443
+ "step": 1195
1444
+ },
1445
+ {
1446
+ "epoch": 0.79,
1447
+ "learning_rate": 0.001,
1448
+ "loss": 2.4169,
1449
+ "step": 1200
1450
+ },
1451
+ {
1452
+ "epoch": 0.79,
1453
+ "learning_rate": 0.001,
1454
+ "loss": 2.7519,
1455
+ "step": 1205
1456
+ },
1457
+ {
1458
+ "epoch": 0.79,
1459
+ "learning_rate": 0.001,
1460
+ "loss": 2.4385,
1461
+ "step": 1210
1462
+ },
1463
+ {
1464
+ "epoch": 0.8,
1465
+ "learning_rate": 0.001,
1466
+ "loss": 1.9145,
1467
+ "step": 1215
1468
+ },
1469
+ {
1470
+ "epoch": 0.8,
1471
+ "learning_rate": 0.001,
1472
+ "loss": 2.5898,
1473
+ "step": 1220
1474
+ },
1475
+ {
1476
+ "epoch": 0.8,
1477
+ "learning_rate": 0.001,
1478
+ "loss": 2.4768,
1479
+ "step": 1225
1480
+ },
1481
+ {
1482
+ "epoch": 0.8,
1483
+ "learning_rate": 0.001,
1484
+ "loss": 2.5546,
1485
+ "step": 1230
1486
+ },
1487
+ {
1488
+ "epoch": 0.81,
1489
+ "learning_rate": 0.001,
1490
+ "loss": 2.5279,
1491
+ "step": 1235
1492
+ },
1493
+ {
1494
+ "epoch": 0.81,
1495
+ "learning_rate": 0.001,
1496
+ "loss": 2.498,
1497
+ "step": 1240
1498
+ },
1499
+ {
1500
+ "epoch": 0.81,
1501
+ "learning_rate": 0.001,
1502
+ "loss": 2.4277,
1503
+ "step": 1245
1504
+ },
1505
+ {
1506
+ "epoch": 0.82,
1507
+ "learning_rate": 0.001,
1508
+ "loss": 2.9934,
1509
+ "step": 1250
1510
+ },
1511
+ {
1512
+ "epoch": 0.82,
1513
+ "learning_rate": 0.001,
1514
+ "loss": 2.3367,
1515
+ "step": 1255
1516
+ },
1517
+ {
1518
+ "epoch": 0.82,
1519
+ "learning_rate": 0.001,
1520
+ "loss": 2.012,
1521
+ "step": 1260
1522
+ },
1523
+ {
1524
+ "epoch": 0.83,
1525
+ "learning_rate": 0.001,
1526
+ "loss": 2.4148,
1527
+ "step": 1265
1528
+ },
1529
+ {
1530
+ "epoch": 0.83,
1531
+ "learning_rate": 0.001,
1532
+ "loss": 2.3207,
1533
+ "step": 1270
1534
+ },
1535
+ {
1536
+ "epoch": 0.83,
1537
+ "learning_rate": 0.001,
1538
+ "loss": 2.5629,
1539
+ "step": 1275
1540
+ },
1541
+ {
1542
+ "epoch": 0.84,
1543
+ "learning_rate": 0.001,
1544
+ "loss": 2.4338,
1545
+ "step": 1280
1546
+ },
1547
+ {
1548
+ "epoch": 0.84,
1549
+ "learning_rate": 0.001,
1550
+ "loss": 2.4612,
1551
+ "step": 1285
1552
+ },
1553
+ {
1554
+ "epoch": 0.84,
1555
+ "learning_rate": 0.001,
1556
+ "loss": 2.5406,
1557
+ "step": 1290
1558
+ },
1559
+ {
1560
+ "epoch": 0.85,
1561
+ "learning_rate": 0.001,
1562
+ "loss": 2.5438,
1563
+ "step": 1295
1564
+ },
1565
+ {
1566
+ "epoch": 0.85,
1567
+ "learning_rate": 0.001,
1568
+ "loss": 2.6348,
1569
+ "step": 1300
1570
+ },
1571
+ {
1572
+ "epoch": 0.85,
1573
+ "learning_rate": 0.001,
1574
+ "loss": 2.1436,
1575
+ "step": 1305
1576
+ },
1577
+ {
1578
+ "epoch": 0.86,
1579
+ "learning_rate": 0.001,
1580
+ "loss": 2.4825,
1581
+ "step": 1310
1582
+ },
1583
+ {
1584
+ "epoch": 0.86,
1585
+ "learning_rate": 0.001,
1586
+ "loss": 2.2579,
1587
+ "step": 1315
1588
+ },
1589
+ {
1590
+ "epoch": 0.86,
1591
+ "learning_rate": 0.001,
1592
+ "loss": 2.5234,
1593
+ "step": 1320
1594
+ },
1595
+ {
1596
+ "epoch": 0.87,
1597
+ "learning_rate": 0.001,
1598
+ "loss": 2.5127,
1599
+ "step": 1325
1600
+ },
1601
+ {
1602
+ "epoch": 0.87,
1603
+ "learning_rate": 0.001,
1604
+ "loss": 2.3415,
1605
+ "step": 1330
1606
+ },
1607
+ {
1608
+ "epoch": 0.87,
1609
+ "learning_rate": 0.001,
1610
+ "loss": 2.4005,
1611
+ "step": 1335
1612
+ },
1613
+ {
1614
+ "epoch": 0.88,
1615
+ "learning_rate": 0.001,
1616
+ "loss": 2.4731,
1617
+ "step": 1340
1618
+ },
1619
+ {
1620
+ "epoch": 0.88,
1621
+ "learning_rate": 0.001,
1622
+ "loss": 2.8025,
1623
+ "step": 1345
1624
+ },
1625
+ {
1626
+ "epoch": 0.88,
1627
+ "learning_rate": 0.001,
1628
+ "loss": 2.1733,
1629
+ "step": 1350
1630
+ },
1631
+ {
1632
+ "epoch": 0.89,
1633
+ "learning_rate": 0.001,
1634
+ "loss": 2.5599,
1635
+ "step": 1355
1636
+ },
1637
+ {
1638
+ "epoch": 0.89,
1639
+ "learning_rate": 0.001,
1640
+ "loss": 2.6287,
1641
+ "step": 1360
1642
+ },
1643
+ {
1644
+ "epoch": 0.89,
1645
+ "learning_rate": 0.001,
1646
+ "loss": 2.5367,
1647
+ "step": 1365
1648
+ },
1649
+ {
1650
+ "epoch": 0.9,
1651
+ "learning_rate": 0.001,
1652
+ "loss": 2.3331,
1653
+ "step": 1370
1654
+ },
1655
+ {
1656
+ "epoch": 0.9,
1657
+ "learning_rate": 0.001,
1658
+ "loss": 2.2061,
1659
+ "step": 1375
1660
+ },
1661
+ {
1662
+ "epoch": 0.9,
1663
+ "learning_rate": 0.001,
1664
+ "loss": 2.3905,
1665
+ "step": 1380
1666
+ },
1667
+ {
1668
+ "epoch": 0.91,
1669
+ "learning_rate": 0.001,
1670
+ "loss": 2.6162,
1671
+ "step": 1385
1672
+ },
1673
+ {
1674
+ "epoch": 0.91,
1675
+ "learning_rate": 0.001,
1676
+ "loss": 2.2712,
1677
+ "step": 1390
1678
+ },
1679
+ {
1680
+ "epoch": 0.91,
1681
+ "learning_rate": 0.001,
1682
+ "loss": 2.3674,
1683
+ "step": 1395
1684
+ },
1685
+ {
1686
+ "epoch": 0.92,
1687
+ "learning_rate": 0.001,
1688
+ "loss": 2.4791,
1689
+ "step": 1400
1690
+ },
1691
+ {
1692
+ "epoch": 0.92,
1693
+ "learning_rate": 0.001,
1694
+ "loss": 2.6425,
1695
+ "step": 1405
1696
+ },
1697
+ {
1698
+ "epoch": 0.92,
1699
+ "learning_rate": 0.001,
1700
+ "loss": 2.4496,
1701
+ "step": 1410
1702
+ },
1703
+ {
1704
+ "epoch": 0.93,
1705
+ "learning_rate": 0.001,
1706
+ "loss": 2.5499,
1707
+ "step": 1415
1708
+ },
1709
+ {
1710
+ "epoch": 0.93,
1711
+ "learning_rate": 0.001,
1712
+ "loss": 2.5993,
1713
+ "step": 1420
1714
+ },
1715
+ {
1716
+ "epoch": 0.93,
1717
+ "learning_rate": 0.001,
1718
+ "loss": 2.5543,
1719
+ "step": 1425
1720
+ },
1721
+ {
1722
+ "epoch": 0.94,
1723
+ "learning_rate": 0.001,
1724
+ "loss": 2.2981,
1725
+ "step": 1430
1726
+ },
1727
+ {
1728
+ "epoch": 0.94,
1729
+ "learning_rate": 0.001,
1730
+ "loss": 2.7974,
1731
+ "step": 1435
1732
+ },
1733
+ {
1734
+ "epoch": 0.94,
1735
+ "learning_rate": 0.001,
1736
+ "loss": 2.0898,
1737
+ "step": 1440
1738
+ },
1739
+ {
1740
+ "epoch": 0.95,
1741
+ "learning_rate": 0.001,
1742
+ "loss": 2.561,
1743
+ "step": 1445
1744
+ },
1745
+ {
1746
+ "epoch": 0.95,
1747
+ "learning_rate": 0.001,
1748
+ "loss": 2.2922,
1749
+ "step": 1450
1750
+ },
1751
+ {
1752
+ "epoch": 0.95,
1753
+ "learning_rate": 0.001,
1754
+ "loss": 2.3195,
1755
+ "step": 1455
1756
+ },
1757
+ {
1758
+ "epoch": 0.96,
1759
+ "learning_rate": 0.001,
1760
+ "loss": 2.4302,
1761
+ "step": 1460
1762
+ },
1763
+ {
1764
+ "epoch": 0.96,
1765
+ "learning_rate": 0.001,
1766
+ "loss": 2.6357,
1767
+ "step": 1465
1768
+ },
1769
+ {
1770
+ "epoch": 0.96,
1771
+ "learning_rate": 0.001,
1772
+ "loss": 2.1727,
1773
+ "step": 1470
1774
+ },
1775
+ {
1776
+ "epoch": 0.97,
1777
+ "learning_rate": 0.001,
1778
+ "loss": 2.5076,
1779
+ "step": 1475
1780
+ },
1781
+ {
1782
+ "epoch": 0.97,
1783
+ "learning_rate": 0.001,
1784
+ "loss": 2.7291,
1785
+ "step": 1480
1786
+ },
1787
+ {
1788
+ "epoch": 0.97,
1789
+ "learning_rate": 0.001,
1790
+ "loss": 2.443,
1791
+ "step": 1485
1792
+ },
1793
+ {
1794
+ "epoch": 0.98,
1795
+ "learning_rate": 0.001,
1796
+ "loss": 2.4889,
1797
+ "step": 1490
1798
+ },
1799
+ {
1800
+ "epoch": 0.98,
1801
+ "learning_rate": 0.001,
1802
+ "loss": 2.4709,
1803
+ "step": 1495
1804
+ },
1805
+ {
1806
+ "epoch": 0.98,
1807
+ "learning_rate": 0.001,
1808
+ "loss": 2.3124,
1809
+ "step": 1500
1810
+ },
1811
+ {
1812
+ "epoch": 0.98,
1813
+ "learning_rate": 0.001,
1814
+ "loss": 2.5515,
1815
+ "step": 1505
1816
+ },
1817
+ {
1818
+ "epoch": 0.99,
1819
+ "learning_rate": 0.001,
1820
+ "loss": 2.3861,
1821
+ "step": 1510
1822
+ },
1823
+ {
1824
+ "epoch": 0.99,
1825
+ "learning_rate": 0.001,
1826
+ "loss": 2.4269,
1827
+ "step": 1515
1828
+ },
1829
+ {
1830
+ "epoch": 0.99,
1831
+ "learning_rate": 0.001,
1832
+ "loss": 2.4074,
1833
+ "step": 1520
1834
+ },
1835
+ {
1836
+ "epoch": 1.0,
1837
+ "learning_rate": 0.001,
1838
+ "loss": 2.2783,
1839
+ "step": 1525
1840
+ },
1841
+ {
1842
+ "epoch": 1.0,
1843
+ "learning_rate": 0.001,
1844
+ "loss": 2.4139,
1845
+ "step": 1530
1846
+ },
1847
+ {
1848
+ "epoch": 1.0,
1849
+ "learning_rate": 0.001,
1850
+ "loss": 1.9251,
1851
+ "step": 1535
1852
+ },
1853
+ {
1854
+ "epoch": 1.01,
1855
+ "learning_rate": 0.001,
1856
+ "loss": 2.1038,
1857
+ "step": 1540
1858
+ },
1859
+ {
1860
+ "epoch": 1.01,
1861
+ "learning_rate": 0.001,
1862
+ "loss": 1.9436,
1863
+ "step": 1545
1864
+ },
1865
+ {
1866
+ "epoch": 1.01,
1867
+ "learning_rate": 0.001,
1868
+ "loss": 1.9581,
1869
+ "step": 1550
1870
+ },
1871
+ {
1872
+ "epoch": 1.02,
1873
+ "learning_rate": 0.001,
1874
+ "loss": 2.1705,
1875
+ "step": 1555
1876
+ },
1877
+ {
1878
+ "epoch": 1.02,
1879
+ "learning_rate": 0.001,
1880
+ "loss": 2.1393,
1881
+ "step": 1560
1882
+ },
1883
+ {
1884
+ "epoch": 1.02,
1885
+ "learning_rate": 0.001,
1886
+ "loss": 1.741,
1887
+ "step": 1565
1888
+ },
1889
+ {
1890
+ "epoch": 1.03,
1891
+ "learning_rate": 0.001,
1892
+ "loss": 1.9232,
1893
+ "step": 1570
1894
+ },
1895
+ {
1896
+ "epoch": 1.03,
1897
+ "learning_rate": 0.001,
1898
+ "loss": 1.9046,
1899
+ "step": 1575
1900
+ },
1901
+ {
1902
+ "epoch": 1.03,
1903
+ "learning_rate": 0.001,
1904
+ "loss": 1.8102,
1905
+ "step": 1580
1906
+ },
1907
+ {
1908
+ "epoch": 1.04,
1909
+ "learning_rate": 0.001,
1910
+ "loss": 1.7362,
1911
+ "step": 1585
1912
+ },
1913
+ {
1914
+ "epoch": 1.04,
1915
+ "learning_rate": 0.001,
1916
+ "loss": 1.8057,
1917
+ "step": 1590
1918
+ },
1919
+ {
1920
+ "epoch": 1.04,
1921
+ "learning_rate": 0.001,
1922
+ "loss": 2.0777,
1923
+ "step": 1595
1924
+ },
1925
+ {
1926
+ "epoch": 1.05,
1927
+ "learning_rate": 0.001,
1928
+ "loss": 2.1163,
1929
+ "step": 1600
1930
+ },
1931
+ {
1932
+ "epoch": 1.05,
1933
+ "learning_rate": 0.001,
1934
+ "loss": 1.8468,
1935
+ "step": 1605
1936
+ },
1937
+ {
1938
+ "epoch": 1.05,
1939
+ "learning_rate": 0.001,
1940
+ "loss": 2.3334,
1941
+ "step": 1610
1942
+ },
1943
+ {
1944
+ "epoch": 1.06,
1945
+ "learning_rate": 0.001,
1946
+ "loss": 2.1232,
1947
+ "step": 1615
1948
+ },
1949
+ {
1950
+ "epoch": 1.06,
1951
+ "learning_rate": 0.001,
1952
+ "loss": 1.7049,
1953
+ "step": 1620
1954
+ },
1955
+ {
1956
+ "epoch": 1.06,
1957
+ "learning_rate": 0.001,
1958
+ "loss": 2.1545,
1959
+ "step": 1625
1960
+ },
1961
+ {
1962
+ "epoch": 1.07,
1963
+ "learning_rate": 0.001,
1964
+ "loss": 2.3166,
1965
+ "step": 1630
1966
+ },
1967
+ {
1968
+ "epoch": 1.07,
1969
+ "learning_rate": 0.001,
1970
+ "loss": 2.103,
1971
+ "step": 1635
1972
+ },
1973
+ {
1974
+ "epoch": 1.07,
1975
+ "learning_rate": 0.001,
1976
+ "loss": 1.9295,
1977
+ "step": 1640
1978
+ },
1979
+ {
1980
+ "epoch": 1.08,
1981
+ "learning_rate": 0.001,
1982
+ "loss": 2.0598,
1983
+ "step": 1645
1984
+ },
1985
+ {
1986
+ "epoch": 1.08,
1987
+ "learning_rate": 0.001,
1988
+ "loss": 2.3646,
1989
+ "step": 1650
1990
+ },
1991
+ {
1992
+ "epoch": 1.08,
1993
+ "learning_rate": 0.001,
1994
+ "loss": 2.1853,
1995
+ "step": 1655
1996
+ },
1997
+ {
1998
+ "epoch": 1.09,
1999
+ "learning_rate": 0.001,
2000
+ "loss": 2.0635,
2001
+ "step": 1660
2002
+ },
2003
+ {
2004
+ "epoch": 1.09,
2005
+ "learning_rate": 0.001,
2006
+ "loss": 1.9439,
2007
+ "step": 1665
2008
+ },
2009
+ {
2010
+ "epoch": 1.09,
2011
+ "learning_rate": 0.001,
2012
+ "loss": 2.469,
2013
+ "step": 1670
2014
+ },
2015
+ {
2016
+ "epoch": 1.1,
2017
+ "learning_rate": 0.001,
2018
+ "loss": 2.1583,
2019
+ "step": 1675
2020
+ },
2021
+ {
2022
+ "epoch": 1.1,
2023
+ "learning_rate": 0.001,
2024
+ "loss": 2.079,
2025
+ "step": 1680
2026
+ },
2027
+ {
2028
+ "epoch": 1.1,
2029
+ "learning_rate": 0.001,
2030
+ "loss": 2.0118,
2031
+ "step": 1685
2032
+ },
2033
+ {
2034
+ "epoch": 1.11,
2035
+ "learning_rate": 0.001,
2036
+ "loss": 2.011,
2037
+ "step": 1690
2038
+ },
2039
+ {
2040
+ "epoch": 1.11,
2041
+ "learning_rate": 0.001,
2042
+ "loss": 2.3133,
2043
+ "step": 1695
2044
+ },
2045
+ {
2046
+ "epoch": 1.11,
2047
+ "learning_rate": 0.001,
2048
+ "loss": 2.1873,
2049
+ "step": 1700
2050
+ },
2051
+ {
2052
+ "epoch": 1.12,
2053
+ "learning_rate": 0.001,
2054
+ "loss": 1.7311,
2055
+ "step": 1705
2056
+ },
2057
+ {
2058
+ "epoch": 1.12,
2059
+ "learning_rate": 0.001,
2060
+ "loss": 1.7269,
2061
+ "step": 1710
2062
+ },
2063
+ {
2064
+ "epoch": 1.12,
2065
+ "learning_rate": 0.001,
2066
+ "loss": 2.3935,
2067
+ "step": 1715
2068
+ },
2069
+ {
2070
+ "epoch": 1.13,
2071
+ "learning_rate": 0.001,
2072
+ "loss": 2.1104,
2073
+ "step": 1720
2074
+ },
2075
+ {
2076
+ "epoch": 1.13,
2077
+ "learning_rate": 0.001,
2078
+ "loss": 2.2349,
2079
+ "step": 1725
2080
+ },
2081
+ {
2082
+ "epoch": 1.13,
2083
+ "learning_rate": 0.001,
2084
+ "loss": 1.6555,
2085
+ "step": 1730
2086
+ },
2087
+ {
2088
+ "epoch": 1.14,
2089
+ "learning_rate": 0.001,
2090
+ "loss": 1.9011,
2091
+ "step": 1735
2092
+ },
2093
+ {
2094
+ "epoch": 1.14,
2095
+ "learning_rate": 0.001,
2096
+ "loss": 2.2142,
2097
+ "step": 1740
2098
+ },
2099
+ {
2100
+ "epoch": 1.14,
2101
+ "learning_rate": 0.001,
2102
+ "loss": 2.1273,
2103
+ "step": 1745
2104
+ },
2105
+ {
2106
+ "epoch": 1.15,
2107
+ "learning_rate": 0.001,
2108
+ "loss": 2.4855,
2109
+ "step": 1750
2110
+ },
2111
+ {
2112
+ "epoch": 1.15,
2113
+ "learning_rate": 0.001,
2114
+ "loss": 2.3025,
2115
+ "step": 1755
2116
+ },
2117
+ {
2118
+ "epoch": 1.15,
2119
+ "learning_rate": 0.001,
2120
+ "loss": 1.9496,
2121
+ "step": 1760
2122
+ },
2123
+ {
2124
+ "epoch": 1.16,
2125
+ "learning_rate": 0.001,
2126
+ "loss": 1.9856,
2127
+ "step": 1765
2128
+ },
2129
+ {
2130
+ "epoch": 1.16,
2131
+ "learning_rate": 0.001,
2132
+ "loss": 2.1494,
2133
+ "step": 1770
2134
+ },
2135
+ {
2136
+ "epoch": 1.16,
2137
+ "learning_rate": 0.001,
2138
+ "loss": 1.9905,
2139
+ "step": 1775
2140
+ },
2141
+ {
2142
+ "epoch": 1.16,
2143
+ "learning_rate": 0.001,
2144
+ "loss": 2.1177,
2145
+ "step": 1780
2146
+ },
2147
+ {
2148
+ "epoch": 1.17,
2149
+ "learning_rate": 0.001,
2150
+ "loss": 1.9396,
2151
+ "step": 1785
2152
+ },
2153
+ {
2154
+ "epoch": 1.17,
2155
+ "learning_rate": 0.001,
2156
+ "loss": 1.8821,
2157
+ "step": 1790
2158
+ },
2159
+ {
2160
+ "epoch": 1.17,
2161
+ "learning_rate": 0.001,
2162
+ "loss": 2.1909,
2163
+ "step": 1795
2164
+ },
2165
+ {
2166
+ "epoch": 1.18,
2167
+ "learning_rate": 0.001,
2168
+ "loss": 1.9459,
2169
+ "step": 1800
2170
+ },
2171
+ {
2172
+ "epoch": 1.18,
2173
+ "learning_rate": 0.001,
2174
+ "loss": 2.1047,
2175
+ "step": 1805
2176
+ },
2177
+ {
2178
+ "epoch": 1.18,
2179
+ "learning_rate": 0.001,
2180
+ "loss": 1.833,
2181
+ "step": 1810
2182
+ },
2183
+ {
2184
+ "epoch": 1.19,
2185
+ "learning_rate": 0.001,
2186
+ "loss": 2.0839,
2187
+ "step": 1815
2188
+ },
2189
+ {
2190
+ "epoch": 1.19,
2191
+ "learning_rate": 0.001,
2192
+ "loss": 2.0736,
2193
+ "step": 1820
2194
+ },
2195
+ {
2196
+ "epoch": 1.19,
2197
+ "learning_rate": 0.001,
2198
+ "loss": 2.0034,
2199
+ "step": 1825
2200
+ },
2201
+ {
2202
+ "epoch": 1.2,
2203
+ "learning_rate": 0.001,
2204
+ "loss": 2.0788,
2205
+ "step": 1830
2206
+ },
2207
+ {
2208
+ "epoch": 1.2,
2209
+ "learning_rate": 0.001,
2210
+ "loss": 2.1903,
2211
+ "step": 1835
2212
+ },
2213
+ {
2214
+ "epoch": 1.2,
2215
+ "learning_rate": 0.001,
2216
+ "loss": 2.0829,
2217
+ "step": 1840
2218
+ },
2219
+ {
2220
+ "epoch": 1.21,
2221
+ "learning_rate": 0.001,
2222
+ "loss": 2.2449,
2223
+ "step": 1845
2224
+ },
2225
+ {
2226
+ "epoch": 1.21,
2227
+ "learning_rate": 0.001,
2228
+ "loss": 2.1561,
2229
+ "step": 1850
2230
+ },
2231
+ {
2232
+ "epoch": 1.21,
2233
+ "learning_rate": 0.001,
2234
+ "loss": 2.1827,
2235
+ "step": 1855
2236
+ },
2237
+ {
2238
+ "epoch": 1.22,
2239
+ "learning_rate": 0.001,
2240
+ "loss": 2.1885,
2241
+ "step": 1860
2242
+ },
2243
+ {
2244
+ "epoch": 1.22,
2245
+ "learning_rate": 0.001,
2246
+ "loss": 2.049,
2247
+ "step": 1865
2248
+ },
2249
+ {
2250
+ "epoch": 1.22,
2251
+ "learning_rate": 0.001,
2252
+ "loss": 2.2107,
2253
+ "step": 1870
2254
+ },
2255
+ {
2256
+ "epoch": 1.23,
2257
+ "learning_rate": 0.001,
2258
+ "loss": 2.0679,
2259
+ "step": 1875
2260
+ },
2261
+ {
2262
+ "epoch": 1.23,
2263
+ "learning_rate": 0.001,
2264
+ "loss": 2.2887,
2265
+ "step": 1880
2266
+ },
2267
+ {
2268
+ "epoch": 1.23,
2269
+ "learning_rate": 0.001,
2270
+ "loss": 2.2472,
2271
+ "step": 1885
2272
+ },
2273
+ {
2274
+ "epoch": 1.24,
2275
+ "learning_rate": 0.001,
2276
+ "loss": 2.1993,
2277
+ "step": 1890
2278
+ },
2279
+ {
2280
+ "epoch": 1.24,
2281
+ "learning_rate": 0.001,
2282
+ "loss": 2.1636,
2283
+ "step": 1895
2284
+ },
2285
+ {
2286
+ "epoch": 1.24,
2287
+ "learning_rate": 0.001,
2288
+ "loss": 1.9547,
2289
+ "step": 1900
2290
+ },
2291
+ {
2292
+ "epoch": 1.25,
2293
+ "learning_rate": 0.001,
2294
+ "loss": 2.3164,
2295
+ "step": 1905
2296
+ },
2297
+ {
2298
+ "epoch": 1.25,
2299
+ "learning_rate": 0.001,
2300
+ "loss": 2.2847,
2301
+ "step": 1910
2302
+ },
2303
+ {
2304
+ "epoch": 1.25,
2305
+ "learning_rate": 0.001,
2306
+ "loss": 2.2196,
2307
+ "step": 1915
2308
+ },
2309
+ {
2310
+ "epoch": 1.26,
2311
+ "learning_rate": 0.001,
2312
+ "loss": 2.1823,
2313
+ "step": 1920
2314
+ },
2315
+ {
2316
+ "epoch": 1.26,
2317
+ "learning_rate": 0.001,
2318
+ "loss": 2.2532,
2319
+ "step": 1925
2320
+ },
2321
+ {
2322
+ "epoch": 1.26,
2323
+ "learning_rate": 0.001,
2324
+ "loss": 2.2451,
2325
+ "step": 1930
2326
+ },
2327
+ {
2328
+ "epoch": 1.27,
2329
+ "learning_rate": 0.001,
2330
+ "loss": 1.984,
2331
+ "step": 1935
2332
+ },
2333
+ {
2334
+ "epoch": 1.27,
2335
+ "learning_rate": 0.001,
2336
+ "loss": 2.0976,
2337
+ "step": 1940
2338
+ },
2339
+ {
2340
+ "epoch": 1.27,
2341
+ "learning_rate": 0.001,
2342
+ "loss": 2.0658,
2343
+ "step": 1945
2344
+ },
2345
+ {
2346
+ "epoch": 1.28,
2347
+ "learning_rate": 0.001,
2348
+ "loss": 2.316,
2349
+ "step": 1950
2350
+ },
2351
+ {
2352
+ "epoch": 1.28,
2353
+ "learning_rate": 0.001,
2354
+ "loss": 2.2036,
2355
+ "step": 1955
2356
+ },
2357
+ {
2358
+ "epoch": 1.28,
2359
+ "learning_rate": 0.001,
2360
+ "loss": 2.0602,
2361
+ "step": 1960
2362
+ },
2363
+ {
2364
+ "epoch": 1.29,
2365
+ "learning_rate": 0.001,
2366
+ "loss": 1.971,
2367
+ "step": 1965
2368
+ },
2369
+ {
2370
+ "epoch": 1.29,
2371
+ "learning_rate": 0.001,
2372
+ "loss": 2.1463,
2373
+ "step": 1970
2374
+ },
2375
+ {
2376
+ "epoch": 1.29,
2377
+ "learning_rate": 0.001,
2378
+ "loss": 1.7689,
2379
+ "step": 1975
2380
+ },
2381
+ {
2382
+ "epoch": 1.3,
2383
+ "learning_rate": 0.001,
2384
+ "loss": 2.014,
2385
+ "step": 1980
2386
+ },
2387
+ {
2388
+ "epoch": 1.3,
2389
+ "learning_rate": 0.001,
2390
+ "loss": 2.3631,
2391
+ "step": 1985
2392
+ },
2393
+ {
2394
+ "epoch": 1.3,
2395
+ "learning_rate": 0.001,
2396
+ "loss": 2.2294,
2397
+ "step": 1990
2398
+ },
2399
+ {
2400
+ "epoch": 1.31,
2401
+ "learning_rate": 0.001,
2402
+ "loss": 1.8407,
2403
+ "step": 1995
2404
+ },
2405
+ {
2406
+ "epoch": 1.31,
2407
+ "learning_rate": 0.001,
2408
+ "loss": 1.9365,
2409
+ "step": 2000
2410
+ }
2411
+ ],
2412
+ "logging_steps": 5,
2413
+ "max_steps": 7640,
2414
+ "num_train_epochs": 5,
2415
+ "save_steps": 1000,
2416
+ "total_flos": 233570304000000.0,
2417
+ "trial_name": null,
2418
+ "trial_params": null
2419
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026a40a22d79b976af4f05a529a919434f1a1af96981147d87e1c857264d40d7
3
+ size 4027
checkpoint-3000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 512,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 4,
15
+ "num_hidden_layers": 2,
16
+ "num_key_value_heads": 4,
17
+ "pretraining_tp": 2,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.34.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
checkpoint-3000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0fe3b80ee45b84e88027bba1b73636c5a3de920d432788cdd22b00f9a02a43
3
+ size 141585770
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a764fb25b4caba123439351228ef0f661b7ef15e456d10f0cf47cff8f4477e
3
+ size 70790896
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
+ size 14575
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4426f223cff34ac6337acfdadb67959035e63ea16cd85636158703275bdacac9
3
+ size 627
checkpoint-3000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-3000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-3000/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "model_max_length": 8192,
33
+ "pad_token": null,
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,3619 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9633507853403143,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.001,
14
+ "loss": 1.3845,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.001,
20
+ "loss": 1.6284,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.001,
26
+ "loss": 1.3152,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.001,
32
+ "loss": 1.6192,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 0.001,
38
+ "loss": 1.7394,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 0.001,
44
+ "loss": 1.9925,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.001,
50
+ "loss": 1.902,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 0.001,
56
+ "loss": 1.822,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 0.001,
62
+ "loss": 2.137,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "learning_rate": 0.001,
68
+ "loss": 2.2556,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 0.04,
73
+ "learning_rate": 0.001,
74
+ "loss": 2.2468,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 0.04,
79
+ "learning_rate": 0.001,
80
+ "loss": 2.0746,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "learning_rate": 0.001,
86
+ "loss": 2.1092,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 0.05,
91
+ "learning_rate": 0.001,
92
+ "loss": 1.9553,
93
+ "step": 70
94
+ },
95
+ {
96
+ "epoch": 0.05,
97
+ "learning_rate": 0.001,
98
+ "loss": 2.121,
99
+ "step": 75
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "learning_rate": 0.001,
104
+ "loss": 2.1722,
105
+ "step": 80
106
+ },
107
+ {
108
+ "epoch": 0.06,
109
+ "learning_rate": 0.001,
110
+ "loss": 2.1552,
111
+ "step": 85
112
+ },
113
+ {
114
+ "epoch": 0.06,
115
+ "learning_rate": 0.001,
116
+ "loss": 2.5971,
117
+ "step": 90
118
+ },
119
+ {
120
+ "epoch": 0.06,
121
+ "learning_rate": 0.001,
122
+ "loss": 2.4684,
123
+ "step": 95
124
+ },
125
+ {
126
+ "epoch": 0.07,
127
+ "learning_rate": 0.001,
128
+ "loss": 2.0248,
129
+ "step": 100
130
+ },
131
+ {
132
+ "epoch": 0.07,
133
+ "learning_rate": 0.001,
134
+ "loss": 2.5156,
135
+ "step": 105
136
+ },
137
+ {
138
+ "epoch": 0.07,
139
+ "learning_rate": 0.001,
140
+ "loss": 2.3322,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.08,
145
+ "learning_rate": 0.001,
146
+ "loss": 1.7698,
147
+ "step": 115
148
+ },
149
+ {
150
+ "epoch": 0.08,
151
+ "learning_rate": 0.001,
152
+ "loss": 2.3363,
153
+ "step": 120
154
+ },
155
+ {
156
+ "epoch": 0.08,
157
+ "learning_rate": 0.001,
158
+ "loss": 2.1079,
159
+ "step": 125
160
+ },
161
+ {
162
+ "epoch": 0.09,
163
+ "learning_rate": 0.001,
164
+ "loss": 2.0998,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 0.09,
169
+ "learning_rate": 0.001,
170
+ "loss": 2.8265,
171
+ "step": 135
172
+ },
173
+ {
174
+ "epoch": 0.09,
175
+ "learning_rate": 0.001,
176
+ "loss": 2.6611,
177
+ "step": 140
178
+ },
179
+ {
180
+ "epoch": 0.09,
181
+ "learning_rate": 0.001,
182
+ "loss": 2.2187,
183
+ "step": 145
184
+ },
185
+ {
186
+ "epoch": 0.1,
187
+ "learning_rate": 0.001,
188
+ "loss": 2.33,
189
+ "step": 150
190
+ },
191
+ {
192
+ "epoch": 0.1,
193
+ "learning_rate": 0.001,
194
+ "loss": 2.6119,
195
+ "step": 155
196
+ },
197
+ {
198
+ "epoch": 0.1,
199
+ "learning_rate": 0.001,
200
+ "loss": 2.2203,
201
+ "step": 160
202
+ },
203
+ {
204
+ "epoch": 0.11,
205
+ "learning_rate": 0.001,
206
+ "loss": 2.5474,
207
+ "step": 165
208
+ },
209
+ {
210
+ "epoch": 0.11,
211
+ "learning_rate": 0.001,
212
+ "loss": 2.4763,
213
+ "step": 170
214
+ },
215
+ {
216
+ "epoch": 0.11,
217
+ "learning_rate": 0.001,
218
+ "loss": 2.6068,
219
+ "step": 175
220
+ },
221
+ {
222
+ "epoch": 0.12,
223
+ "learning_rate": 0.001,
224
+ "loss": 2.1221,
225
+ "step": 180
226
+ },
227
+ {
228
+ "epoch": 0.12,
229
+ "learning_rate": 0.001,
230
+ "loss": 2.1185,
231
+ "step": 185
232
+ },
233
+ {
234
+ "epoch": 0.12,
235
+ "learning_rate": 0.001,
236
+ "loss": 1.9481,
237
+ "step": 190
238
+ },
239
+ {
240
+ "epoch": 0.13,
241
+ "learning_rate": 0.001,
242
+ "loss": 2.823,
243
+ "step": 195
244
+ },
245
+ {
246
+ "epoch": 0.13,
247
+ "learning_rate": 0.001,
248
+ "loss": 2.4702,
249
+ "step": 200
250
+ },
251
+ {
252
+ "epoch": 0.13,
253
+ "learning_rate": 0.001,
254
+ "loss": 2.3721,
255
+ "step": 205
256
+ },
257
+ {
258
+ "epoch": 0.14,
259
+ "learning_rate": 0.001,
260
+ "loss": 2.4932,
261
+ "step": 210
262
+ },
263
+ {
264
+ "epoch": 0.14,
265
+ "learning_rate": 0.001,
266
+ "loss": 2.3977,
267
+ "step": 215
268
+ },
269
+ {
270
+ "epoch": 0.14,
271
+ "learning_rate": 0.001,
272
+ "loss": 2.5299,
273
+ "step": 220
274
+ },
275
+ {
276
+ "epoch": 0.15,
277
+ "learning_rate": 0.001,
278
+ "loss": 2.4818,
279
+ "step": 225
280
+ },
281
+ {
282
+ "epoch": 0.15,
283
+ "learning_rate": 0.001,
284
+ "loss": 2.3404,
285
+ "step": 230
286
+ },
287
+ {
288
+ "epoch": 0.15,
289
+ "learning_rate": 0.001,
290
+ "loss": 2.3614,
291
+ "step": 235
292
+ },
293
+ {
294
+ "epoch": 0.16,
295
+ "learning_rate": 0.001,
296
+ "loss": 2.1509,
297
+ "step": 240
298
+ },
299
+ {
300
+ "epoch": 0.16,
301
+ "learning_rate": 0.001,
302
+ "loss": 2.5301,
303
+ "step": 245
304
+ },
305
+ {
306
+ "epoch": 0.16,
307
+ "learning_rate": 0.001,
308
+ "loss": 2.3328,
309
+ "step": 250
310
+ },
311
+ {
312
+ "epoch": 0.17,
313
+ "learning_rate": 0.001,
314
+ "loss": 2.412,
315
+ "step": 255
316
+ },
317
+ {
318
+ "epoch": 0.17,
319
+ "learning_rate": 0.001,
320
+ "loss": 2.5923,
321
+ "step": 260
322
+ },
323
+ {
324
+ "epoch": 0.17,
325
+ "learning_rate": 0.001,
326
+ "loss": 2.2655,
327
+ "step": 265
328
+ },
329
+ {
330
+ "epoch": 0.18,
331
+ "learning_rate": 0.001,
332
+ "loss": 2.7524,
333
+ "step": 270
334
+ },
335
+ {
336
+ "epoch": 0.18,
337
+ "learning_rate": 0.001,
338
+ "loss": 2.6456,
339
+ "step": 275
340
+ },
341
+ {
342
+ "epoch": 0.18,
343
+ "learning_rate": 0.001,
344
+ "loss": 2.3814,
345
+ "step": 280
346
+ },
347
+ {
348
+ "epoch": 0.19,
349
+ "learning_rate": 0.001,
350
+ "loss": 2.3805,
351
+ "step": 285
352
+ },
353
+ {
354
+ "epoch": 0.19,
355
+ "learning_rate": 0.001,
356
+ "loss": 2.6727,
357
+ "step": 290
358
+ },
359
+ {
360
+ "epoch": 0.19,
361
+ "learning_rate": 0.001,
362
+ "loss": 2.3931,
363
+ "step": 295
364
+ },
365
+ {
366
+ "epoch": 0.2,
367
+ "learning_rate": 0.001,
368
+ "loss": 1.9526,
369
+ "step": 300
370
+ },
371
+ {
372
+ "epoch": 0.2,
373
+ "learning_rate": 0.001,
374
+ "loss": 2.7219,
375
+ "step": 305
376
+ },
377
+ {
378
+ "epoch": 0.2,
379
+ "learning_rate": 0.001,
380
+ "loss": 2.4869,
381
+ "step": 310
382
+ },
383
+ {
384
+ "epoch": 0.21,
385
+ "learning_rate": 0.001,
386
+ "loss": 2.4303,
387
+ "step": 315
388
+ },
389
+ {
390
+ "epoch": 0.21,
391
+ "learning_rate": 0.001,
392
+ "loss": 2.5916,
393
+ "step": 320
394
+ },
395
+ {
396
+ "epoch": 0.21,
397
+ "learning_rate": 0.001,
398
+ "loss": 2.3917,
399
+ "step": 325
400
+ },
401
+ {
402
+ "epoch": 0.22,
403
+ "learning_rate": 0.001,
404
+ "loss": 2.4881,
405
+ "step": 330
406
+ },
407
+ {
408
+ "epoch": 0.22,
409
+ "learning_rate": 0.001,
410
+ "loss": 2.3369,
411
+ "step": 335
412
+ },
413
+ {
414
+ "epoch": 0.22,
415
+ "learning_rate": 0.001,
416
+ "loss": 2.45,
417
+ "step": 340
418
+ },
419
+ {
420
+ "epoch": 0.23,
421
+ "learning_rate": 0.001,
422
+ "loss": 2.1916,
423
+ "step": 345
424
+ },
425
+ {
426
+ "epoch": 0.23,
427
+ "learning_rate": 0.001,
428
+ "loss": 2.2606,
429
+ "step": 350
430
+ },
431
+ {
432
+ "epoch": 0.23,
433
+ "learning_rate": 0.001,
434
+ "loss": 2.5533,
435
+ "step": 355
436
+ },
437
+ {
438
+ "epoch": 0.24,
439
+ "learning_rate": 0.001,
440
+ "loss": 2.1873,
441
+ "step": 360
442
+ },
443
+ {
444
+ "epoch": 0.24,
445
+ "learning_rate": 0.001,
446
+ "loss": 2.6057,
447
+ "step": 365
448
+ },
449
+ {
450
+ "epoch": 0.24,
451
+ "learning_rate": 0.001,
452
+ "loss": 2.4611,
453
+ "step": 370
454
+ },
455
+ {
456
+ "epoch": 0.25,
457
+ "learning_rate": 0.001,
458
+ "loss": 2.606,
459
+ "step": 375
460
+ },
461
+ {
462
+ "epoch": 0.25,
463
+ "learning_rate": 0.001,
464
+ "loss": 2.5645,
465
+ "step": 380
466
+ },
467
+ {
468
+ "epoch": 0.25,
469
+ "learning_rate": 0.001,
470
+ "loss": 2.7591,
471
+ "step": 385
472
+ },
473
+ {
474
+ "epoch": 0.26,
475
+ "learning_rate": 0.001,
476
+ "loss": 2.3399,
477
+ "step": 390
478
+ },
479
+ {
480
+ "epoch": 0.26,
481
+ "learning_rate": 0.001,
482
+ "loss": 2.3675,
483
+ "step": 395
484
+ },
485
+ {
486
+ "epoch": 0.26,
487
+ "learning_rate": 0.001,
488
+ "loss": 2.5141,
489
+ "step": 400
490
+ },
491
+ {
492
+ "epoch": 0.27,
493
+ "learning_rate": 0.001,
494
+ "loss": 2.2407,
495
+ "step": 405
496
+ },
497
+ {
498
+ "epoch": 0.27,
499
+ "learning_rate": 0.001,
500
+ "loss": 2.6321,
501
+ "step": 410
502
+ },
503
+ {
504
+ "epoch": 0.27,
505
+ "learning_rate": 0.001,
506
+ "loss": 2.6431,
507
+ "step": 415
508
+ },
509
+ {
510
+ "epoch": 0.27,
511
+ "learning_rate": 0.001,
512
+ "loss": 2.4707,
513
+ "step": 420
514
+ },
515
+ {
516
+ "epoch": 0.28,
517
+ "learning_rate": 0.001,
518
+ "loss": 2.3744,
519
+ "step": 425
520
+ },
521
+ {
522
+ "epoch": 0.28,
523
+ "learning_rate": 0.001,
524
+ "loss": 2.5658,
525
+ "step": 430
526
+ },
527
+ {
528
+ "epoch": 0.28,
529
+ "learning_rate": 0.001,
530
+ "loss": 1.9922,
531
+ "step": 435
532
+ },
533
+ {
534
+ "epoch": 0.29,
535
+ "learning_rate": 0.001,
536
+ "loss": 2.5948,
537
+ "step": 440
538
+ },
539
+ {
540
+ "epoch": 0.29,
541
+ "learning_rate": 0.001,
542
+ "loss": 2.2519,
543
+ "step": 445
544
+ },
545
+ {
546
+ "epoch": 0.29,
547
+ "learning_rate": 0.001,
548
+ "loss": 2.6248,
549
+ "step": 450
550
+ },
551
+ {
552
+ "epoch": 0.3,
553
+ "learning_rate": 0.001,
554
+ "loss": 2.5877,
555
+ "step": 455
556
+ },
557
+ {
558
+ "epoch": 0.3,
559
+ "learning_rate": 0.001,
560
+ "loss": 2.1311,
561
+ "step": 460
562
+ },
563
+ {
564
+ "epoch": 0.3,
565
+ "learning_rate": 0.001,
566
+ "loss": 2.6091,
567
+ "step": 465
568
+ },
569
+ {
570
+ "epoch": 0.31,
571
+ "learning_rate": 0.001,
572
+ "loss": 2.5488,
573
+ "step": 470
574
+ },
575
+ {
576
+ "epoch": 0.31,
577
+ "learning_rate": 0.001,
578
+ "loss": 2.499,
579
+ "step": 475
580
+ },
581
+ {
582
+ "epoch": 0.31,
583
+ "learning_rate": 0.001,
584
+ "loss": 2.5031,
585
+ "step": 480
586
+ },
587
+ {
588
+ "epoch": 0.32,
589
+ "learning_rate": 0.001,
590
+ "loss": 2.5783,
591
+ "step": 485
592
+ },
593
+ {
594
+ "epoch": 0.32,
595
+ "learning_rate": 0.001,
596
+ "loss": 2.6303,
597
+ "step": 490
598
+ },
599
+ {
600
+ "epoch": 0.32,
601
+ "learning_rate": 0.001,
602
+ "loss": 2.6344,
603
+ "step": 495
604
+ },
605
+ {
606
+ "epoch": 0.33,
607
+ "learning_rate": 0.001,
608
+ "loss": 2.7031,
609
+ "step": 500
610
+ },
611
+ {
612
+ "epoch": 0.33,
613
+ "learning_rate": 0.001,
614
+ "loss": 2.6677,
615
+ "step": 505
616
+ },
617
+ {
618
+ "epoch": 0.33,
619
+ "learning_rate": 0.001,
620
+ "loss": 2.7617,
621
+ "step": 510
622
+ },
623
+ {
624
+ "epoch": 0.34,
625
+ "learning_rate": 0.001,
626
+ "loss": 2.3122,
627
+ "step": 515
628
+ },
629
+ {
630
+ "epoch": 0.34,
631
+ "learning_rate": 0.001,
632
+ "loss": 2.3887,
633
+ "step": 520
634
+ },
635
+ {
636
+ "epoch": 0.34,
637
+ "learning_rate": 0.001,
638
+ "loss": 2.5569,
639
+ "step": 525
640
+ },
641
+ {
642
+ "epoch": 0.35,
643
+ "learning_rate": 0.001,
644
+ "loss": 2.4038,
645
+ "step": 530
646
+ },
647
+ {
648
+ "epoch": 0.35,
649
+ "learning_rate": 0.001,
650
+ "loss": 2.7413,
651
+ "step": 535
652
+ },
653
+ {
654
+ "epoch": 0.35,
655
+ "learning_rate": 0.001,
656
+ "loss": 2.5264,
657
+ "step": 540
658
+ },
659
+ {
660
+ "epoch": 0.36,
661
+ "learning_rate": 0.001,
662
+ "loss": 2.335,
663
+ "step": 545
664
+ },
665
+ {
666
+ "epoch": 0.36,
667
+ "learning_rate": 0.001,
668
+ "loss": 2.7574,
669
+ "step": 550
670
+ },
671
+ {
672
+ "epoch": 0.36,
673
+ "learning_rate": 0.001,
674
+ "loss": 2.4542,
675
+ "step": 555
676
+ },
677
+ {
678
+ "epoch": 0.37,
679
+ "learning_rate": 0.001,
680
+ "loss": 2.0885,
681
+ "step": 560
682
+ },
683
+ {
684
+ "epoch": 0.37,
685
+ "learning_rate": 0.001,
686
+ "loss": 2.6057,
687
+ "step": 565
688
+ },
689
+ {
690
+ "epoch": 0.37,
691
+ "learning_rate": 0.001,
692
+ "loss": 2.4971,
693
+ "step": 570
694
+ },
695
+ {
696
+ "epoch": 0.38,
697
+ "learning_rate": 0.001,
698
+ "loss": 2.6251,
699
+ "step": 575
700
+ },
701
+ {
702
+ "epoch": 0.38,
703
+ "learning_rate": 0.001,
704
+ "loss": 2.5784,
705
+ "step": 580
706
+ },
707
+ {
708
+ "epoch": 0.38,
709
+ "learning_rate": 0.001,
710
+ "loss": 2.3878,
711
+ "step": 585
712
+ },
713
+ {
714
+ "epoch": 0.39,
715
+ "learning_rate": 0.001,
716
+ "loss": 2.4271,
717
+ "step": 590
718
+ },
719
+ {
720
+ "epoch": 0.39,
721
+ "learning_rate": 0.001,
722
+ "loss": 2.6751,
723
+ "step": 595
724
+ },
725
+ {
726
+ "epoch": 0.39,
727
+ "learning_rate": 0.001,
728
+ "loss": 2.17,
729
+ "step": 600
730
+ },
731
+ {
732
+ "epoch": 0.4,
733
+ "learning_rate": 0.001,
734
+ "loss": 2.0794,
735
+ "step": 605
736
+ },
737
+ {
738
+ "epoch": 0.4,
739
+ "learning_rate": 0.001,
740
+ "loss": 2.6073,
741
+ "step": 610
742
+ },
743
+ {
744
+ "epoch": 0.4,
745
+ "learning_rate": 0.001,
746
+ "loss": 2.6717,
747
+ "step": 615
748
+ },
749
+ {
750
+ "epoch": 0.41,
751
+ "learning_rate": 0.001,
752
+ "loss": 2.8236,
753
+ "step": 620
754
+ },
755
+ {
756
+ "epoch": 0.41,
757
+ "learning_rate": 0.001,
758
+ "loss": 2.4193,
759
+ "step": 625
760
+ },
761
+ {
762
+ "epoch": 0.41,
763
+ "learning_rate": 0.001,
764
+ "loss": 2.7181,
765
+ "step": 630
766
+ },
767
+ {
768
+ "epoch": 0.42,
769
+ "learning_rate": 0.001,
770
+ "loss": 2.6567,
771
+ "step": 635
772
+ },
773
+ {
774
+ "epoch": 0.42,
775
+ "learning_rate": 0.001,
776
+ "loss": 2.1919,
777
+ "step": 640
778
+ },
779
+ {
780
+ "epoch": 0.42,
781
+ "learning_rate": 0.001,
782
+ "loss": 2.5645,
783
+ "step": 645
784
+ },
785
+ {
786
+ "epoch": 0.43,
787
+ "learning_rate": 0.001,
788
+ "loss": 2.3313,
789
+ "step": 650
790
+ },
791
+ {
792
+ "epoch": 0.43,
793
+ "learning_rate": 0.001,
794
+ "loss": 2.533,
795
+ "step": 655
796
+ },
797
+ {
798
+ "epoch": 0.43,
799
+ "learning_rate": 0.001,
800
+ "loss": 2.621,
801
+ "step": 660
802
+ },
803
+ {
804
+ "epoch": 0.44,
805
+ "learning_rate": 0.001,
806
+ "loss": 2.5693,
807
+ "step": 665
808
+ },
809
+ {
810
+ "epoch": 0.44,
811
+ "learning_rate": 0.001,
812
+ "loss": 2.6943,
813
+ "step": 670
814
+ },
815
+ {
816
+ "epoch": 0.44,
817
+ "learning_rate": 0.001,
818
+ "loss": 2.2715,
819
+ "step": 675
820
+ },
821
+ {
822
+ "epoch": 0.45,
823
+ "learning_rate": 0.001,
824
+ "loss": 2.5614,
825
+ "step": 680
826
+ },
827
+ {
828
+ "epoch": 0.45,
829
+ "learning_rate": 0.001,
830
+ "loss": 2.5784,
831
+ "step": 685
832
+ },
833
+ {
834
+ "epoch": 0.45,
835
+ "learning_rate": 0.001,
836
+ "loss": 2.0613,
837
+ "step": 690
838
+ },
839
+ {
840
+ "epoch": 0.45,
841
+ "learning_rate": 0.001,
842
+ "loss": 2.582,
843
+ "step": 695
844
+ },
845
+ {
846
+ "epoch": 0.46,
847
+ "learning_rate": 0.001,
848
+ "loss": 2.5178,
849
+ "step": 700
850
+ },
851
+ {
852
+ "epoch": 0.46,
853
+ "learning_rate": 0.001,
854
+ "loss": 2.432,
855
+ "step": 705
856
+ },
857
+ {
858
+ "epoch": 0.46,
859
+ "learning_rate": 0.001,
860
+ "loss": 2.1979,
861
+ "step": 710
862
+ },
863
+ {
864
+ "epoch": 0.47,
865
+ "learning_rate": 0.001,
866
+ "loss": 2.4317,
867
+ "step": 715
868
+ },
869
+ {
870
+ "epoch": 0.47,
871
+ "learning_rate": 0.001,
872
+ "loss": 2.285,
873
+ "step": 720
874
+ },
875
+ {
876
+ "epoch": 0.47,
877
+ "learning_rate": 0.001,
878
+ "loss": 2.6127,
879
+ "step": 725
880
+ },
881
+ {
882
+ "epoch": 0.48,
883
+ "learning_rate": 0.001,
884
+ "loss": 2.6221,
885
+ "step": 730
886
+ },
887
+ {
888
+ "epoch": 0.48,
889
+ "learning_rate": 0.001,
890
+ "loss": 2.7519,
891
+ "step": 735
892
+ },
893
+ {
894
+ "epoch": 0.48,
895
+ "learning_rate": 0.001,
896
+ "loss": 2.7351,
897
+ "step": 740
898
+ },
899
+ {
900
+ "epoch": 0.49,
901
+ "learning_rate": 0.001,
902
+ "loss": 2.5224,
903
+ "step": 745
904
+ },
905
+ {
906
+ "epoch": 0.49,
907
+ "learning_rate": 0.001,
908
+ "loss": 2.5145,
909
+ "step": 750
910
+ },
911
+ {
912
+ "epoch": 0.49,
913
+ "learning_rate": 0.001,
914
+ "loss": 2.5122,
915
+ "step": 755
916
+ },
917
+ {
918
+ "epoch": 0.5,
919
+ "learning_rate": 0.001,
920
+ "loss": 2.2971,
921
+ "step": 760
922
+ },
923
+ {
924
+ "epoch": 0.5,
925
+ "learning_rate": 0.001,
926
+ "loss": 2.5628,
927
+ "step": 765
928
+ },
929
+ {
930
+ "epoch": 0.5,
931
+ "learning_rate": 0.001,
932
+ "loss": 2.5803,
933
+ "step": 770
934
+ },
935
+ {
936
+ "epoch": 0.51,
937
+ "learning_rate": 0.001,
938
+ "loss": 2.5209,
939
+ "step": 775
940
+ },
941
+ {
942
+ "epoch": 0.51,
943
+ "learning_rate": 0.001,
944
+ "loss": 2.5051,
945
+ "step": 780
946
+ },
947
+ {
948
+ "epoch": 0.51,
949
+ "learning_rate": 0.001,
950
+ "loss": 2.5275,
951
+ "step": 785
952
+ },
953
+ {
954
+ "epoch": 0.52,
955
+ "learning_rate": 0.001,
956
+ "loss": 2.5019,
957
+ "step": 790
958
+ },
959
+ {
960
+ "epoch": 0.52,
961
+ "learning_rate": 0.001,
962
+ "loss": 2.1714,
963
+ "step": 795
964
+ },
965
+ {
966
+ "epoch": 0.52,
967
+ "learning_rate": 0.001,
968
+ "loss": 2.87,
969
+ "step": 800
970
+ },
971
+ {
972
+ "epoch": 0.53,
973
+ "learning_rate": 0.001,
974
+ "loss": 2.6468,
975
+ "step": 805
976
+ },
977
+ {
978
+ "epoch": 0.53,
979
+ "learning_rate": 0.001,
980
+ "loss": 2.4115,
981
+ "step": 810
982
+ },
983
+ {
984
+ "epoch": 0.53,
985
+ "learning_rate": 0.001,
986
+ "loss": 2.5377,
987
+ "step": 815
988
+ },
989
+ {
990
+ "epoch": 0.54,
991
+ "learning_rate": 0.001,
992
+ "loss": 2.4986,
993
+ "step": 820
994
+ },
995
+ {
996
+ "epoch": 0.54,
997
+ "learning_rate": 0.001,
998
+ "loss": 2.6485,
999
+ "step": 825
1000
+ },
1001
+ {
1002
+ "epoch": 0.54,
1003
+ "learning_rate": 0.001,
1004
+ "loss": 2.6314,
1005
+ "step": 830
1006
+ },
1007
+ {
1008
+ "epoch": 0.55,
1009
+ "learning_rate": 0.001,
1010
+ "loss": 2.3516,
1011
+ "step": 835
1012
+ },
1013
+ {
1014
+ "epoch": 0.55,
1015
+ "learning_rate": 0.001,
1016
+ "loss": 2.39,
1017
+ "step": 840
1018
+ },
1019
+ {
1020
+ "epoch": 0.55,
1021
+ "learning_rate": 0.001,
1022
+ "loss": 2.3759,
1023
+ "step": 845
1024
+ },
1025
+ {
1026
+ "epoch": 0.56,
1027
+ "learning_rate": 0.001,
1028
+ "loss": 2.5348,
1029
+ "step": 850
1030
+ },
1031
+ {
1032
+ "epoch": 0.56,
1033
+ "learning_rate": 0.001,
1034
+ "loss": 2.6843,
1035
+ "step": 855
1036
+ },
1037
+ {
1038
+ "epoch": 0.56,
1039
+ "learning_rate": 0.001,
1040
+ "loss": 2.6289,
1041
+ "step": 860
1042
+ },
1043
+ {
1044
+ "epoch": 0.57,
1045
+ "learning_rate": 0.001,
1046
+ "loss": 2.4023,
1047
+ "step": 865
1048
+ },
1049
+ {
1050
+ "epoch": 0.57,
1051
+ "learning_rate": 0.001,
1052
+ "loss": 2.5979,
1053
+ "step": 870
1054
+ },
1055
+ {
1056
+ "epoch": 0.57,
1057
+ "learning_rate": 0.001,
1058
+ "loss": 2.4683,
1059
+ "step": 875
1060
+ },
1061
+ {
1062
+ "epoch": 0.58,
1063
+ "learning_rate": 0.001,
1064
+ "loss": 2.7099,
1065
+ "step": 880
1066
+ },
1067
+ {
1068
+ "epoch": 0.58,
1069
+ "learning_rate": 0.001,
1070
+ "loss": 2.3129,
1071
+ "step": 885
1072
+ },
1073
+ {
1074
+ "epoch": 0.58,
1075
+ "learning_rate": 0.001,
1076
+ "loss": 2.4508,
1077
+ "step": 890
1078
+ },
1079
+ {
1080
+ "epoch": 0.59,
1081
+ "learning_rate": 0.001,
1082
+ "loss": 2.6484,
1083
+ "step": 895
1084
+ },
1085
+ {
1086
+ "epoch": 0.59,
1087
+ "learning_rate": 0.001,
1088
+ "loss": 2.4541,
1089
+ "step": 900
1090
+ },
1091
+ {
1092
+ "epoch": 0.59,
1093
+ "learning_rate": 0.001,
1094
+ "loss": 2.5101,
1095
+ "step": 905
1096
+ },
1097
+ {
1098
+ "epoch": 0.6,
1099
+ "learning_rate": 0.001,
1100
+ "loss": 2.6002,
1101
+ "step": 910
1102
+ },
1103
+ {
1104
+ "epoch": 0.6,
1105
+ "learning_rate": 0.001,
1106
+ "loss": 2.742,
1107
+ "step": 915
1108
+ },
1109
+ {
1110
+ "epoch": 0.6,
1111
+ "learning_rate": 0.001,
1112
+ "loss": 2.4772,
1113
+ "step": 920
1114
+ },
1115
+ {
1116
+ "epoch": 0.61,
1117
+ "learning_rate": 0.001,
1118
+ "loss": 2.4328,
1119
+ "step": 925
1120
+ },
1121
+ {
1122
+ "epoch": 0.61,
1123
+ "learning_rate": 0.001,
1124
+ "loss": 2.7404,
1125
+ "step": 930
1126
+ },
1127
+ {
1128
+ "epoch": 0.61,
1129
+ "learning_rate": 0.001,
1130
+ "loss": 2.5969,
1131
+ "step": 935
1132
+ },
1133
+ {
1134
+ "epoch": 0.62,
1135
+ "learning_rate": 0.001,
1136
+ "loss": 2.1367,
1137
+ "step": 940
1138
+ },
1139
+ {
1140
+ "epoch": 0.62,
1141
+ "learning_rate": 0.001,
1142
+ "loss": 2.703,
1143
+ "step": 945
1144
+ },
1145
+ {
1146
+ "epoch": 0.62,
1147
+ "learning_rate": 0.001,
1148
+ "loss": 2.5638,
1149
+ "step": 950
1150
+ },
1151
+ {
1152
+ "epoch": 0.62,
1153
+ "learning_rate": 0.001,
1154
+ "loss": 1.8322,
1155
+ "step": 955
1156
+ },
1157
+ {
1158
+ "epoch": 0.63,
1159
+ "learning_rate": 0.001,
1160
+ "loss": 2.5764,
1161
+ "step": 960
1162
+ },
1163
+ {
1164
+ "epoch": 0.63,
1165
+ "learning_rate": 0.001,
1166
+ "loss": 2.4679,
1167
+ "step": 965
1168
+ },
1169
+ {
1170
+ "epoch": 0.63,
1171
+ "learning_rate": 0.001,
1172
+ "loss": 2.1691,
1173
+ "step": 970
1174
+ },
1175
+ {
1176
+ "epoch": 0.64,
1177
+ "learning_rate": 0.001,
1178
+ "loss": 2.3252,
1179
+ "step": 975
1180
+ },
1181
+ {
1182
+ "epoch": 0.64,
1183
+ "learning_rate": 0.001,
1184
+ "loss": 2.3988,
1185
+ "step": 980
1186
+ },
1187
+ {
1188
+ "epoch": 0.64,
1189
+ "learning_rate": 0.001,
1190
+ "loss": 2.221,
1191
+ "step": 985
1192
+ },
1193
+ {
1194
+ "epoch": 0.65,
1195
+ "learning_rate": 0.001,
1196
+ "loss": 2.4715,
1197
+ "step": 990
1198
+ },
1199
+ {
1200
+ "epoch": 0.65,
1201
+ "learning_rate": 0.001,
1202
+ "loss": 2.2479,
1203
+ "step": 995
1204
+ },
1205
+ {
1206
+ "epoch": 0.65,
1207
+ "learning_rate": 0.001,
1208
+ "loss": 2.3859,
1209
+ "step": 1000
1210
+ },
1211
+ {
1212
+ "epoch": 0.66,
1213
+ "learning_rate": 0.001,
1214
+ "loss": 2.7889,
1215
+ "step": 1005
1216
+ },
1217
+ {
1218
+ "epoch": 0.66,
1219
+ "learning_rate": 0.001,
1220
+ "loss": 2.625,
1221
+ "step": 1010
1222
+ },
1223
+ {
1224
+ "epoch": 0.66,
1225
+ "learning_rate": 0.001,
1226
+ "loss": 2.324,
1227
+ "step": 1015
1228
+ },
1229
+ {
1230
+ "epoch": 0.67,
1231
+ "learning_rate": 0.001,
1232
+ "loss": 2.5879,
1233
+ "step": 1020
1234
+ },
1235
+ {
1236
+ "epoch": 0.67,
1237
+ "learning_rate": 0.001,
1238
+ "loss": 2.4721,
1239
+ "step": 1025
1240
+ },
1241
+ {
1242
+ "epoch": 0.67,
1243
+ "learning_rate": 0.001,
1244
+ "loss": 2.6365,
1245
+ "step": 1030
1246
+ },
1247
+ {
1248
+ "epoch": 0.68,
1249
+ "learning_rate": 0.001,
1250
+ "loss": 2.6356,
1251
+ "step": 1035
1252
+ },
1253
+ {
1254
+ "epoch": 0.68,
1255
+ "learning_rate": 0.001,
1256
+ "loss": 2.4022,
1257
+ "step": 1040
1258
+ },
1259
+ {
1260
+ "epoch": 0.68,
1261
+ "learning_rate": 0.001,
1262
+ "loss": 2.7109,
1263
+ "step": 1045
1264
+ },
1265
+ {
1266
+ "epoch": 0.69,
1267
+ "learning_rate": 0.001,
1268
+ "loss": 2.373,
1269
+ "step": 1050
1270
+ },
1271
+ {
1272
+ "epoch": 0.69,
1273
+ "learning_rate": 0.001,
1274
+ "loss": 2.523,
1275
+ "step": 1055
1276
+ },
1277
+ {
1278
+ "epoch": 0.69,
1279
+ "learning_rate": 0.001,
1280
+ "loss": 2.536,
1281
+ "step": 1060
1282
+ },
1283
+ {
1284
+ "epoch": 0.7,
1285
+ "learning_rate": 0.001,
1286
+ "loss": 2.6047,
1287
+ "step": 1065
1288
+ },
1289
+ {
1290
+ "epoch": 0.7,
1291
+ "learning_rate": 0.001,
1292
+ "loss": 2.5583,
1293
+ "step": 1070
1294
+ },
1295
+ {
1296
+ "epoch": 0.7,
1297
+ "learning_rate": 0.001,
1298
+ "loss": 2.7925,
1299
+ "step": 1075
1300
+ },
1301
+ {
1302
+ "epoch": 0.71,
1303
+ "learning_rate": 0.001,
1304
+ "loss": 2.0572,
1305
+ "step": 1080
1306
+ },
1307
+ {
1308
+ "epoch": 0.71,
1309
+ "learning_rate": 0.001,
1310
+ "loss": 2.3024,
1311
+ "step": 1085
1312
+ },
1313
+ {
1314
+ "epoch": 0.71,
1315
+ "learning_rate": 0.001,
1316
+ "loss": 2.0677,
1317
+ "step": 1090
1318
+ },
1319
+ {
1320
+ "epoch": 0.72,
1321
+ "learning_rate": 0.001,
1322
+ "loss": 2.5241,
1323
+ "step": 1095
1324
+ },
1325
+ {
1326
+ "epoch": 0.72,
1327
+ "learning_rate": 0.001,
1328
+ "loss": 2.7447,
1329
+ "step": 1100
1330
+ },
1331
+ {
1332
+ "epoch": 0.72,
1333
+ "learning_rate": 0.001,
1334
+ "loss": 2.6435,
1335
+ "step": 1105
1336
+ },
1337
+ {
1338
+ "epoch": 0.73,
1339
+ "learning_rate": 0.001,
1340
+ "loss": 2.4226,
1341
+ "step": 1110
1342
+ },
1343
+ {
1344
+ "epoch": 0.73,
1345
+ "learning_rate": 0.001,
1346
+ "loss": 2.6891,
1347
+ "step": 1115
1348
+ },
1349
+ {
1350
+ "epoch": 0.73,
1351
+ "learning_rate": 0.001,
1352
+ "loss": 2.458,
1353
+ "step": 1120
1354
+ },
1355
+ {
1356
+ "epoch": 0.74,
1357
+ "learning_rate": 0.001,
1358
+ "loss": 2.6884,
1359
+ "step": 1125
1360
+ },
1361
+ {
1362
+ "epoch": 0.74,
1363
+ "learning_rate": 0.001,
1364
+ "loss": 2.7058,
1365
+ "step": 1130
1366
+ },
1367
+ {
1368
+ "epoch": 0.74,
1369
+ "learning_rate": 0.001,
1370
+ "loss": 2.5828,
1371
+ "step": 1135
1372
+ },
1373
+ {
1374
+ "epoch": 0.75,
1375
+ "learning_rate": 0.001,
1376
+ "loss": 2.7107,
1377
+ "step": 1140
1378
+ },
1379
+ {
1380
+ "epoch": 0.75,
1381
+ "learning_rate": 0.001,
1382
+ "loss": 2.3635,
1383
+ "step": 1145
1384
+ },
1385
+ {
1386
+ "epoch": 0.75,
1387
+ "learning_rate": 0.001,
1388
+ "loss": 2.5258,
1389
+ "step": 1150
1390
+ },
1391
+ {
1392
+ "epoch": 0.76,
1393
+ "learning_rate": 0.001,
1394
+ "loss": 2.6046,
1395
+ "step": 1155
1396
+ },
1397
+ {
1398
+ "epoch": 0.76,
1399
+ "learning_rate": 0.001,
1400
+ "loss": 2.5215,
1401
+ "step": 1160
1402
+ },
1403
+ {
1404
+ "epoch": 0.76,
1405
+ "learning_rate": 0.001,
1406
+ "loss": 2.1417,
1407
+ "step": 1165
1408
+ },
1409
+ {
1410
+ "epoch": 0.77,
1411
+ "learning_rate": 0.001,
1412
+ "loss": 2.5903,
1413
+ "step": 1170
1414
+ },
1415
+ {
1416
+ "epoch": 0.77,
1417
+ "learning_rate": 0.001,
1418
+ "loss": 2.5376,
1419
+ "step": 1175
1420
+ },
1421
+ {
1422
+ "epoch": 0.77,
1423
+ "learning_rate": 0.001,
1424
+ "loss": 2.5716,
1425
+ "step": 1180
1426
+ },
1427
+ {
1428
+ "epoch": 0.78,
1429
+ "learning_rate": 0.001,
1430
+ "loss": 2.5904,
1431
+ "step": 1185
1432
+ },
1433
+ {
1434
+ "epoch": 0.78,
1435
+ "learning_rate": 0.001,
1436
+ "loss": 2.6511,
1437
+ "step": 1190
1438
+ },
1439
+ {
1440
+ "epoch": 0.78,
1441
+ "learning_rate": 0.001,
1442
+ "loss": 2.1679,
1443
+ "step": 1195
1444
+ },
1445
+ {
1446
+ "epoch": 0.79,
1447
+ "learning_rate": 0.001,
1448
+ "loss": 2.4169,
1449
+ "step": 1200
1450
+ },
1451
+ {
1452
+ "epoch": 0.79,
1453
+ "learning_rate": 0.001,
1454
+ "loss": 2.7519,
1455
+ "step": 1205
1456
+ },
1457
+ {
1458
+ "epoch": 0.79,
1459
+ "learning_rate": 0.001,
1460
+ "loss": 2.4385,
1461
+ "step": 1210
1462
+ },
1463
+ {
1464
+ "epoch": 0.8,
1465
+ "learning_rate": 0.001,
1466
+ "loss": 1.9145,
1467
+ "step": 1215
1468
+ },
1469
+ {
1470
+ "epoch": 0.8,
1471
+ "learning_rate": 0.001,
1472
+ "loss": 2.5898,
1473
+ "step": 1220
1474
+ },
1475
+ {
1476
+ "epoch": 0.8,
1477
+ "learning_rate": 0.001,
1478
+ "loss": 2.4768,
1479
+ "step": 1225
1480
+ },
1481
+ {
1482
+ "epoch": 0.8,
1483
+ "learning_rate": 0.001,
1484
+ "loss": 2.5546,
1485
+ "step": 1230
1486
+ },
1487
+ {
1488
+ "epoch": 0.81,
1489
+ "learning_rate": 0.001,
1490
+ "loss": 2.5279,
1491
+ "step": 1235
1492
+ },
1493
+ {
1494
+ "epoch": 0.81,
1495
+ "learning_rate": 0.001,
1496
+ "loss": 2.498,
1497
+ "step": 1240
1498
+ },
1499
+ {
1500
+ "epoch": 0.81,
1501
+ "learning_rate": 0.001,
1502
+ "loss": 2.4277,
1503
+ "step": 1245
1504
+ },
1505
+ {
1506
+ "epoch": 0.82,
1507
+ "learning_rate": 0.001,
1508
+ "loss": 2.9934,
1509
+ "step": 1250
1510
+ },
1511
+ {
1512
+ "epoch": 0.82,
1513
+ "learning_rate": 0.001,
1514
+ "loss": 2.3367,
1515
+ "step": 1255
1516
+ },
1517
+ {
1518
+ "epoch": 0.82,
1519
+ "learning_rate": 0.001,
1520
+ "loss": 2.012,
1521
+ "step": 1260
1522
+ },
1523
+ {
1524
+ "epoch": 0.83,
1525
+ "learning_rate": 0.001,
1526
+ "loss": 2.4148,
1527
+ "step": 1265
1528
+ },
1529
+ {
1530
+ "epoch": 0.83,
1531
+ "learning_rate": 0.001,
1532
+ "loss": 2.3207,
1533
+ "step": 1270
1534
+ },
1535
+ {
1536
+ "epoch": 0.83,
1537
+ "learning_rate": 0.001,
1538
+ "loss": 2.5629,
1539
+ "step": 1275
1540
+ },
1541
+ {
1542
+ "epoch": 0.84,
1543
+ "learning_rate": 0.001,
1544
+ "loss": 2.4338,
1545
+ "step": 1280
1546
+ },
1547
+ {
1548
+ "epoch": 0.84,
1549
+ "learning_rate": 0.001,
1550
+ "loss": 2.4612,
1551
+ "step": 1285
1552
+ },
1553
+ {
1554
+ "epoch": 0.84,
1555
+ "learning_rate": 0.001,
1556
+ "loss": 2.5406,
1557
+ "step": 1290
1558
+ },
1559
+ {
1560
+ "epoch": 0.85,
1561
+ "learning_rate": 0.001,
1562
+ "loss": 2.5438,
1563
+ "step": 1295
1564
+ },
1565
+ {
1566
+ "epoch": 0.85,
1567
+ "learning_rate": 0.001,
1568
+ "loss": 2.6348,
1569
+ "step": 1300
1570
+ },
1571
+ {
1572
+ "epoch": 0.85,
1573
+ "learning_rate": 0.001,
1574
+ "loss": 2.1436,
1575
+ "step": 1305
1576
+ },
1577
+ {
1578
+ "epoch": 0.86,
1579
+ "learning_rate": 0.001,
1580
+ "loss": 2.4825,
1581
+ "step": 1310
1582
+ },
1583
+ {
1584
+ "epoch": 0.86,
1585
+ "learning_rate": 0.001,
1586
+ "loss": 2.2579,
1587
+ "step": 1315
1588
+ },
1589
+ {
1590
+ "epoch": 0.86,
1591
+ "learning_rate": 0.001,
1592
+ "loss": 2.5234,
1593
+ "step": 1320
1594
+ },
1595
+ {
1596
+ "epoch": 0.87,
1597
+ "learning_rate": 0.001,
1598
+ "loss": 2.5127,
1599
+ "step": 1325
1600
+ },
1601
+ {
1602
+ "epoch": 0.87,
1603
+ "learning_rate": 0.001,
1604
+ "loss": 2.3415,
1605
+ "step": 1330
1606
+ },
1607
+ {
1608
+ "epoch": 0.87,
1609
+ "learning_rate": 0.001,
1610
+ "loss": 2.4005,
1611
+ "step": 1335
1612
+ },
1613
+ {
1614
+ "epoch": 0.88,
1615
+ "learning_rate": 0.001,
1616
+ "loss": 2.4731,
1617
+ "step": 1340
1618
+ },
1619
+ {
1620
+ "epoch": 0.88,
1621
+ "learning_rate": 0.001,
1622
+ "loss": 2.8025,
1623
+ "step": 1345
1624
+ },
1625
+ {
1626
+ "epoch": 0.88,
1627
+ "learning_rate": 0.001,
1628
+ "loss": 2.1733,
1629
+ "step": 1350
1630
+ },
1631
+ {
1632
+ "epoch": 0.89,
1633
+ "learning_rate": 0.001,
1634
+ "loss": 2.5599,
1635
+ "step": 1355
1636
+ },
1637
+ {
1638
+ "epoch": 0.89,
1639
+ "learning_rate": 0.001,
1640
+ "loss": 2.6287,
1641
+ "step": 1360
1642
+ },
1643
+ {
1644
+ "epoch": 0.89,
1645
+ "learning_rate": 0.001,
1646
+ "loss": 2.5367,
1647
+ "step": 1365
1648
+ },
1649
+ {
1650
+ "epoch": 0.9,
1651
+ "learning_rate": 0.001,
1652
+ "loss": 2.3331,
1653
+ "step": 1370
1654
+ },
1655
+ {
1656
+ "epoch": 0.9,
1657
+ "learning_rate": 0.001,
1658
+ "loss": 2.2061,
1659
+ "step": 1375
1660
+ },
1661
+ {
1662
+ "epoch": 0.9,
1663
+ "learning_rate": 0.001,
1664
+ "loss": 2.3905,
1665
+ "step": 1380
1666
+ },
1667
+ {
1668
+ "epoch": 0.91,
1669
+ "learning_rate": 0.001,
1670
+ "loss": 2.6162,
1671
+ "step": 1385
1672
+ },
1673
+ {
1674
+ "epoch": 0.91,
1675
+ "learning_rate": 0.001,
1676
+ "loss": 2.2712,
1677
+ "step": 1390
1678
+ },
1679
+ {
1680
+ "epoch": 0.91,
1681
+ "learning_rate": 0.001,
1682
+ "loss": 2.3674,
1683
+ "step": 1395
1684
+ },
1685
+ {
1686
+ "epoch": 0.92,
1687
+ "learning_rate": 0.001,
1688
+ "loss": 2.4791,
1689
+ "step": 1400
1690
+ },
1691
+ {
1692
+ "epoch": 0.92,
1693
+ "learning_rate": 0.001,
1694
+ "loss": 2.6425,
1695
+ "step": 1405
1696
+ },
1697
+ {
1698
+ "epoch": 0.92,
1699
+ "learning_rate": 0.001,
1700
+ "loss": 2.4496,
1701
+ "step": 1410
1702
+ },
1703
+ {
1704
+ "epoch": 0.93,
1705
+ "learning_rate": 0.001,
1706
+ "loss": 2.5499,
1707
+ "step": 1415
1708
+ },
1709
+ {
1710
+ "epoch": 0.93,
1711
+ "learning_rate": 0.001,
1712
+ "loss": 2.5993,
1713
+ "step": 1420
1714
+ },
1715
+ {
1716
+ "epoch": 0.93,
1717
+ "learning_rate": 0.001,
1718
+ "loss": 2.5543,
1719
+ "step": 1425
1720
+ },
1721
+ {
1722
+ "epoch": 0.94,
1723
+ "learning_rate": 0.001,
1724
+ "loss": 2.2981,
1725
+ "step": 1430
1726
+ },
1727
+ {
1728
+ "epoch": 0.94,
1729
+ "learning_rate": 0.001,
1730
+ "loss": 2.7974,
1731
+ "step": 1435
1732
+ },
1733
+ {
1734
+ "epoch": 0.94,
1735
+ "learning_rate": 0.001,
1736
+ "loss": 2.0898,
1737
+ "step": 1440
1738
+ },
1739
+ {
1740
+ "epoch": 0.95,
1741
+ "learning_rate": 0.001,
1742
+ "loss": 2.561,
1743
+ "step": 1445
1744
+ },
1745
+ {
1746
+ "epoch": 0.95,
1747
+ "learning_rate": 0.001,
1748
+ "loss": 2.2922,
1749
+ "step": 1450
1750
+ },
1751
+ {
1752
+ "epoch": 0.95,
1753
+ "learning_rate": 0.001,
1754
+ "loss": 2.3195,
1755
+ "step": 1455
1756
+ },
1757
+ {
1758
+ "epoch": 0.96,
1759
+ "learning_rate": 0.001,
1760
+ "loss": 2.4302,
1761
+ "step": 1460
1762
+ },
1763
+ {
1764
+ "epoch": 0.96,
1765
+ "learning_rate": 0.001,
1766
+ "loss": 2.6357,
1767
+ "step": 1465
1768
+ },
1769
+ {
1770
+ "epoch": 0.96,
1771
+ "learning_rate": 0.001,
1772
+ "loss": 2.1727,
1773
+ "step": 1470
1774
+ },
1775
+ {
1776
+ "epoch": 0.97,
1777
+ "learning_rate": 0.001,
1778
+ "loss": 2.5076,
1779
+ "step": 1475
1780
+ },
1781
+ {
1782
+ "epoch": 0.97,
1783
+ "learning_rate": 0.001,
1784
+ "loss": 2.7291,
1785
+ "step": 1480
1786
+ },
1787
+ {
1788
+ "epoch": 0.97,
1789
+ "learning_rate": 0.001,
1790
+ "loss": 2.443,
1791
+ "step": 1485
1792
+ },
1793
+ {
1794
+ "epoch": 0.98,
1795
+ "learning_rate": 0.001,
1796
+ "loss": 2.4889,
1797
+ "step": 1490
1798
+ },
1799
+ {
1800
+ "epoch": 0.98,
1801
+ "learning_rate": 0.001,
1802
+ "loss": 2.4709,
1803
+ "step": 1495
1804
+ },
1805
+ {
1806
+ "epoch": 0.98,
1807
+ "learning_rate": 0.001,
1808
+ "loss": 2.3124,
1809
+ "step": 1500
1810
+ },
1811
+ {
1812
+ "epoch": 0.98,
1813
+ "learning_rate": 0.001,
1814
+ "loss": 2.5515,
1815
+ "step": 1505
1816
+ },
1817
+ {
1818
+ "epoch": 0.99,
1819
+ "learning_rate": 0.001,
1820
+ "loss": 2.3861,
1821
+ "step": 1510
1822
+ },
1823
+ {
1824
+ "epoch": 0.99,
1825
+ "learning_rate": 0.001,
1826
+ "loss": 2.4269,
1827
+ "step": 1515
1828
+ },
1829
+ {
1830
+ "epoch": 0.99,
1831
+ "learning_rate": 0.001,
1832
+ "loss": 2.4074,
1833
+ "step": 1520
1834
+ },
1835
+ {
1836
+ "epoch": 1.0,
1837
+ "learning_rate": 0.001,
1838
+ "loss": 2.2783,
1839
+ "step": 1525
1840
+ },
1841
+ {
1842
+ "epoch": 1.0,
1843
+ "learning_rate": 0.001,
1844
+ "loss": 2.4139,
1845
+ "step": 1530
1846
+ },
1847
+ {
1848
+ "epoch": 1.0,
1849
+ "learning_rate": 0.001,
1850
+ "loss": 1.9251,
1851
+ "step": 1535
1852
+ },
1853
+ {
1854
+ "epoch": 1.01,
1855
+ "learning_rate": 0.001,
1856
+ "loss": 2.1038,
1857
+ "step": 1540
1858
+ },
1859
+ {
1860
+ "epoch": 1.01,
1861
+ "learning_rate": 0.001,
1862
+ "loss": 1.9436,
1863
+ "step": 1545
1864
+ },
1865
+ {
1866
+ "epoch": 1.01,
1867
+ "learning_rate": 0.001,
1868
+ "loss": 1.9581,
1869
+ "step": 1550
1870
+ },
1871
+ {
1872
+ "epoch": 1.02,
1873
+ "learning_rate": 0.001,
1874
+ "loss": 2.1705,
1875
+ "step": 1555
1876
+ },
1877
+ {
1878
+ "epoch": 1.02,
1879
+ "learning_rate": 0.001,
1880
+ "loss": 2.1393,
1881
+ "step": 1560
1882
+ },
1883
+ {
1884
+ "epoch": 1.02,
1885
+ "learning_rate": 0.001,
1886
+ "loss": 1.741,
1887
+ "step": 1565
1888
+ },
1889
+ {
1890
+ "epoch": 1.03,
1891
+ "learning_rate": 0.001,
1892
+ "loss": 1.9232,
1893
+ "step": 1570
1894
+ },
1895
+ {
1896
+ "epoch": 1.03,
1897
+ "learning_rate": 0.001,
1898
+ "loss": 1.9046,
1899
+ "step": 1575
1900
+ },
1901
+ {
1902
+ "epoch": 1.03,
1903
+ "learning_rate": 0.001,
1904
+ "loss": 1.8102,
1905
+ "step": 1580
1906
+ },
1907
+ {
1908
+ "epoch": 1.04,
1909
+ "learning_rate": 0.001,
1910
+ "loss": 1.7362,
1911
+ "step": 1585
1912
+ },
1913
+ {
1914
+ "epoch": 1.04,
1915
+ "learning_rate": 0.001,
1916
+ "loss": 1.8057,
1917
+ "step": 1590
1918
+ },
1919
+ {
1920
+ "epoch": 1.04,
1921
+ "learning_rate": 0.001,
1922
+ "loss": 2.0777,
1923
+ "step": 1595
1924
+ },
1925
+ {
1926
+ "epoch": 1.05,
1927
+ "learning_rate": 0.001,
1928
+ "loss": 2.1163,
1929
+ "step": 1600
1930
+ },
1931
+ {
1932
+ "epoch": 1.05,
1933
+ "learning_rate": 0.001,
1934
+ "loss": 1.8468,
1935
+ "step": 1605
1936
+ },
1937
+ {
1938
+ "epoch": 1.05,
1939
+ "learning_rate": 0.001,
1940
+ "loss": 2.3334,
1941
+ "step": 1610
1942
+ },
1943
+ {
1944
+ "epoch": 1.06,
1945
+ "learning_rate": 0.001,
1946
+ "loss": 2.1232,
1947
+ "step": 1615
1948
+ },
1949
+ {
1950
+ "epoch": 1.06,
1951
+ "learning_rate": 0.001,
1952
+ "loss": 1.7049,
1953
+ "step": 1620
1954
+ },
1955
+ {
1956
+ "epoch": 1.06,
1957
+ "learning_rate": 0.001,
1958
+ "loss": 2.1545,
1959
+ "step": 1625
1960
+ },
1961
+ {
1962
+ "epoch": 1.07,
1963
+ "learning_rate": 0.001,
1964
+ "loss": 2.3166,
1965
+ "step": 1630
1966
+ },
1967
+ {
1968
+ "epoch": 1.07,
1969
+ "learning_rate": 0.001,
1970
+ "loss": 2.103,
1971
+ "step": 1635
1972
+ },
1973
+ {
1974
+ "epoch": 1.07,
1975
+ "learning_rate": 0.001,
1976
+ "loss": 1.9295,
1977
+ "step": 1640
1978
+ },
1979
+ {
1980
+ "epoch": 1.08,
1981
+ "learning_rate": 0.001,
1982
+ "loss": 2.0598,
1983
+ "step": 1645
1984
+ },
1985
+ {
1986
+ "epoch": 1.08,
1987
+ "learning_rate": 0.001,
1988
+ "loss": 2.3646,
1989
+ "step": 1650
1990
+ },
1991
+ {
1992
+ "epoch": 1.08,
1993
+ "learning_rate": 0.001,
1994
+ "loss": 2.1853,
1995
+ "step": 1655
1996
+ },
1997
+ {
1998
+ "epoch": 1.09,
1999
+ "learning_rate": 0.001,
2000
+ "loss": 2.0635,
2001
+ "step": 1660
2002
+ },
2003
+ {
2004
+ "epoch": 1.09,
2005
+ "learning_rate": 0.001,
2006
+ "loss": 1.9439,
2007
+ "step": 1665
2008
+ },
2009
+ {
2010
+ "epoch": 1.09,
2011
+ "learning_rate": 0.001,
2012
+ "loss": 2.469,
2013
+ "step": 1670
2014
+ },
2015
+ {
2016
+ "epoch": 1.1,
2017
+ "learning_rate": 0.001,
2018
+ "loss": 2.1583,
2019
+ "step": 1675
2020
+ },
2021
+ {
2022
+ "epoch": 1.1,
2023
+ "learning_rate": 0.001,
2024
+ "loss": 2.079,
2025
+ "step": 1680
2026
+ },
2027
+ {
2028
+ "epoch": 1.1,
2029
+ "learning_rate": 0.001,
2030
+ "loss": 2.0118,
2031
+ "step": 1685
2032
+ },
2033
+ {
2034
+ "epoch": 1.11,
2035
+ "learning_rate": 0.001,
2036
+ "loss": 2.011,
2037
+ "step": 1690
2038
+ },
2039
+ {
2040
+ "epoch": 1.11,
2041
+ "learning_rate": 0.001,
2042
+ "loss": 2.3133,
2043
+ "step": 1695
2044
+ },
2045
+ {
2046
+ "epoch": 1.11,
2047
+ "learning_rate": 0.001,
2048
+ "loss": 2.1873,
2049
+ "step": 1700
2050
+ },
2051
+ {
2052
+ "epoch": 1.12,
2053
+ "learning_rate": 0.001,
2054
+ "loss": 1.7311,
2055
+ "step": 1705
2056
+ },
2057
+ {
2058
+ "epoch": 1.12,
2059
+ "learning_rate": 0.001,
2060
+ "loss": 1.7269,
2061
+ "step": 1710
2062
+ },
2063
+ {
2064
+ "epoch": 1.12,
2065
+ "learning_rate": 0.001,
2066
+ "loss": 2.3935,
2067
+ "step": 1715
2068
+ },
2069
+ {
2070
+ "epoch": 1.13,
2071
+ "learning_rate": 0.001,
2072
+ "loss": 2.1104,
2073
+ "step": 1720
2074
+ },
2075
+ {
2076
+ "epoch": 1.13,
2077
+ "learning_rate": 0.001,
2078
+ "loss": 2.2349,
2079
+ "step": 1725
2080
+ },
2081
+ {
2082
+ "epoch": 1.13,
2083
+ "learning_rate": 0.001,
2084
+ "loss": 1.6555,
2085
+ "step": 1730
2086
+ },
2087
+ {
2088
+ "epoch": 1.14,
2089
+ "learning_rate": 0.001,
2090
+ "loss": 1.9011,
2091
+ "step": 1735
2092
+ },
2093
+ {
2094
+ "epoch": 1.14,
2095
+ "learning_rate": 0.001,
2096
+ "loss": 2.2142,
2097
+ "step": 1740
2098
+ },
2099
+ {
2100
+ "epoch": 1.14,
2101
+ "learning_rate": 0.001,
2102
+ "loss": 2.1273,
2103
+ "step": 1745
2104
+ },
2105
+ {
2106
+ "epoch": 1.15,
2107
+ "learning_rate": 0.001,
2108
+ "loss": 2.4855,
2109
+ "step": 1750
2110
+ },
2111
+ {
2112
+ "epoch": 1.15,
2113
+ "learning_rate": 0.001,
2114
+ "loss": 2.3025,
2115
+ "step": 1755
2116
+ },
2117
+ {
2118
+ "epoch": 1.15,
2119
+ "learning_rate": 0.001,
2120
+ "loss": 1.9496,
2121
+ "step": 1760
2122
+ },
2123
+ {
2124
+ "epoch": 1.16,
2125
+ "learning_rate": 0.001,
2126
+ "loss": 1.9856,
2127
+ "step": 1765
2128
+ },
2129
+ {
2130
+ "epoch": 1.16,
2131
+ "learning_rate": 0.001,
2132
+ "loss": 2.1494,
2133
+ "step": 1770
2134
+ },
2135
+ {
2136
+ "epoch": 1.16,
2137
+ "learning_rate": 0.001,
2138
+ "loss": 1.9905,
2139
+ "step": 1775
2140
+ },
2141
+ {
2142
+ "epoch": 1.16,
2143
+ "learning_rate": 0.001,
2144
+ "loss": 2.1177,
2145
+ "step": 1780
2146
+ },
2147
+ {
2148
+ "epoch": 1.17,
2149
+ "learning_rate": 0.001,
2150
+ "loss": 1.9396,
2151
+ "step": 1785
2152
+ },
2153
+ {
2154
+ "epoch": 1.17,
2155
+ "learning_rate": 0.001,
2156
+ "loss": 1.8821,
2157
+ "step": 1790
2158
+ },
2159
+ {
2160
+ "epoch": 1.17,
2161
+ "learning_rate": 0.001,
2162
+ "loss": 2.1909,
2163
+ "step": 1795
2164
+ },
2165
+ {
2166
+ "epoch": 1.18,
2167
+ "learning_rate": 0.001,
2168
+ "loss": 1.9459,
2169
+ "step": 1800
2170
+ },
2171
+ {
2172
+ "epoch": 1.18,
2173
+ "learning_rate": 0.001,
2174
+ "loss": 2.1047,
2175
+ "step": 1805
2176
+ },
2177
+ {
2178
+ "epoch": 1.18,
2179
+ "learning_rate": 0.001,
2180
+ "loss": 1.833,
2181
+ "step": 1810
2182
+ },
2183
+ {
2184
+ "epoch": 1.19,
2185
+ "learning_rate": 0.001,
2186
+ "loss": 2.0839,
2187
+ "step": 1815
2188
+ },
2189
+ {
2190
+ "epoch": 1.19,
2191
+ "learning_rate": 0.001,
2192
+ "loss": 2.0736,
2193
+ "step": 1820
2194
+ },
2195
+ {
2196
+ "epoch": 1.19,
2197
+ "learning_rate": 0.001,
2198
+ "loss": 2.0034,
2199
+ "step": 1825
2200
+ },
2201
+ {
2202
+ "epoch": 1.2,
2203
+ "learning_rate": 0.001,
2204
+ "loss": 2.0788,
2205
+ "step": 1830
2206
+ },
2207
+ {
2208
+ "epoch": 1.2,
2209
+ "learning_rate": 0.001,
2210
+ "loss": 2.1903,
2211
+ "step": 1835
2212
+ },
2213
+ {
2214
+ "epoch": 1.2,
2215
+ "learning_rate": 0.001,
2216
+ "loss": 2.0829,
2217
+ "step": 1840
2218
+ },
2219
+ {
2220
+ "epoch": 1.21,
2221
+ "learning_rate": 0.001,
2222
+ "loss": 2.2449,
2223
+ "step": 1845
2224
+ },
2225
+ {
2226
+ "epoch": 1.21,
2227
+ "learning_rate": 0.001,
2228
+ "loss": 2.1561,
2229
+ "step": 1850
2230
+ },
2231
+ {
2232
+ "epoch": 1.21,
2233
+ "learning_rate": 0.001,
2234
+ "loss": 2.1827,
2235
+ "step": 1855
2236
+ },
2237
+ {
2238
+ "epoch": 1.22,
2239
+ "learning_rate": 0.001,
2240
+ "loss": 2.1885,
2241
+ "step": 1860
2242
+ },
2243
+ {
2244
+ "epoch": 1.22,
2245
+ "learning_rate": 0.001,
2246
+ "loss": 2.049,
2247
+ "step": 1865
2248
+ },
2249
+ {
2250
+ "epoch": 1.22,
2251
+ "learning_rate": 0.001,
2252
+ "loss": 2.2107,
2253
+ "step": 1870
2254
+ },
2255
+ {
2256
+ "epoch": 1.23,
2257
+ "learning_rate": 0.001,
2258
+ "loss": 2.0679,
2259
+ "step": 1875
2260
+ },
2261
+ {
2262
+ "epoch": 1.23,
2263
+ "learning_rate": 0.001,
2264
+ "loss": 2.2887,
2265
+ "step": 1880
2266
+ },
2267
+ {
2268
+ "epoch": 1.23,
2269
+ "learning_rate": 0.001,
2270
+ "loss": 2.2472,
2271
+ "step": 1885
2272
+ },
2273
+ {
2274
+ "epoch": 1.24,
2275
+ "learning_rate": 0.001,
2276
+ "loss": 2.1993,
2277
+ "step": 1890
2278
+ },
2279
+ {
2280
+ "epoch": 1.24,
2281
+ "learning_rate": 0.001,
2282
+ "loss": 2.1636,
2283
+ "step": 1895
2284
+ },
2285
+ {
2286
+ "epoch": 1.24,
2287
+ "learning_rate": 0.001,
2288
+ "loss": 1.9547,
2289
+ "step": 1900
2290
+ },
2291
+ {
2292
+ "epoch": 1.25,
2293
+ "learning_rate": 0.001,
2294
+ "loss": 2.3164,
2295
+ "step": 1905
2296
+ },
2297
+ {
2298
+ "epoch": 1.25,
2299
+ "learning_rate": 0.001,
2300
+ "loss": 2.2847,
2301
+ "step": 1910
2302
+ },
2303
+ {
2304
+ "epoch": 1.25,
2305
+ "learning_rate": 0.001,
2306
+ "loss": 2.2196,
2307
+ "step": 1915
2308
+ },
2309
+ {
2310
+ "epoch": 1.26,
2311
+ "learning_rate": 0.001,
2312
+ "loss": 2.1823,
2313
+ "step": 1920
2314
+ },
2315
+ {
2316
+ "epoch": 1.26,
2317
+ "learning_rate": 0.001,
2318
+ "loss": 2.2532,
2319
+ "step": 1925
2320
+ },
2321
+ {
2322
+ "epoch": 1.26,
2323
+ "learning_rate": 0.001,
2324
+ "loss": 2.2451,
2325
+ "step": 1930
2326
+ },
2327
+ {
2328
+ "epoch": 1.27,
2329
+ "learning_rate": 0.001,
2330
+ "loss": 1.984,
2331
+ "step": 1935
2332
+ },
2333
+ {
2334
+ "epoch": 1.27,
2335
+ "learning_rate": 0.001,
2336
+ "loss": 2.0976,
2337
+ "step": 1940
2338
+ },
2339
+ {
2340
+ "epoch": 1.27,
2341
+ "learning_rate": 0.001,
2342
+ "loss": 2.0658,
2343
+ "step": 1945
2344
+ },
2345
+ {
2346
+ "epoch": 1.28,
2347
+ "learning_rate": 0.001,
2348
+ "loss": 2.316,
2349
+ "step": 1950
2350
+ },
2351
+ {
2352
+ "epoch": 1.28,
2353
+ "learning_rate": 0.001,
2354
+ "loss": 2.2036,
2355
+ "step": 1955
2356
+ },
2357
+ {
2358
+ "epoch": 1.28,
2359
+ "learning_rate": 0.001,
2360
+ "loss": 2.0602,
2361
+ "step": 1960
2362
+ },
2363
+ {
2364
+ "epoch": 1.29,
2365
+ "learning_rate": 0.001,
2366
+ "loss": 1.971,
2367
+ "step": 1965
2368
+ },
2369
+ {
2370
+ "epoch": 1.29,
2371
+ "learning_rate": 0.001,
2372
+ "loss": 2.1463,
2373
+ "step": 1970
2374
+ },
2375
+ {
2376
+ "epoch": 1.29,
2377
+ "learning_rate": 0.001,
2378
+ "loss": 1.7689,
2379
+ "step": 1975
2380
+ },
2381
+ {
2382
+ "epoch": 1.3,
2383
+ "learning_rate": 0.001,
2384
+ "loss": 2.014,
2385
+ "step": 1980
2386
+ },
2387
+ {
2388
+ "epoch": 1.3,
2389
+ "learning_rate": 0.001,
2390
+ "loss": 2.3631,
2391
+ "step": 1985
2392
+ },
2393
+ {
2394
+ "epoch": 1.3,
2395
+ "learning_rate": 0.001,
2396
+ "loss": 2.2294,
2397
+ "step": 1990
2398
+ },
2399
+ {
2400
+ "epoch": 1.31,
2401
+ "learning_rate": 0.001,
2402
+ "loss": 1.8407,
2403
+ "step": 1995
2404
+ },
2405
+ {
2406
+ "epoch": 1.31,
2407
+ "learning_rate": 0.001,
2408
+ "loss": 1.9365,
2409
+ "step": 2000
2410
+ },
2411
+ {
2412
+ "epoch": 1.31,
2413
+ "learning_rate": 0.001,
2414
+ "loss": 2.0895,
2415
+ "step": 2005
2416
+ },
2417
+ {
2418
+ "epoch": 1.32,
2419
+ "learning_rate": 0.001,
2420
+ "loss": 2.1625,
2421
+ "step": 2010
2422
+ },
2423
+ {
2424
+ "epoch": 1.32,
2425
+ "learning_rate": 0.001,
2426
+ "loss": 2.053,
2427
+ "step": 2015
2428
+ },
2429
+ {
2430
+ "epoch": 1.32,
2431
+ "learning_rate": 0.001,
2432
+ "loss": 2.0925,
2433
+ "step": 2020
2434
+ },
2435
+ {
2436
+ "epoch": 1.33,
2437
+ "learning_rate": 0.001,
2438
+ "loss": 1.9764,
2439
+ "step": 2025
2440
+ },
2441
+ {
2442
+ "epoch": 1.33,
2443
+ "learning_rate": 0.001,
2444
+ "loss": 2.1212,
2445
+ "step": 2030
2446
+ },
2447
+ {
2448
+ "epoch": 1.33,
2449
+ "learning_rate": 0.001,
2450
+ "loss": 1.923,
2451
+ "step": 2035
2452
+ },
2453
+ {
2454
+ "epoch": 1.34,
2455
+ "learning_rate": 0.001,
2456
+ "loss": 2.2899,
2457
+ "step": 2040
2458
+ },
2459
+ {
2460
+ "epoch": 1.34,
2461
+ "learning_rate": 0.001,
2462
+ "loss": 2.3056,
2463
+ "step": 2045
2464
+ },
2465
+ {
2466
+ "epoch": 1.34,
2467
+ "learning_rate": 0.001,
2468
+ "loss": 2.0217,
2469
+ "step": 2050
2470
+ },
2471
+ {
2472
+ "epoch": 1.34,
2473
+ "learning_rate": 0.001,
2474
+ "loss": 2.1757,
2475
+ "step": 2055
2476
+ },
2477
+ {
2478
+ "epoch": 1.35,
2479
+ "learning_rate": 0.001,
2480
+ "loss": 1.7524,
2481
+ "step": 2060
2482
+ },
2483
+ {
2484
+ "epoch": 1.35,
2485
+ "learning_rate": 0.001,
2486
+ "loss": 2.3042,
2487
+ "step": 2065
2488
+ },
2489
+ {
2490
+ "epoch": 1.35,
2491
+ "learning_rate": 0.001,
2492
+ "loss": 2.164,
2493
+ "step": 2070
2494
+ },
2495
+ {
2496
+ "epoch": 1.36,
2497
+ "learning_rate": 0.001,
2498
+ "loss": 2.3265,
2499
+ "step": 2075
2500
+ },
2501
+ {
2502
+ "epoch": 1.36,
2503
+ "learning_rate": 0.001,
2504
+ "loss": 2.4762,
2505
+ "step": 2080
2506
+ },
2507
+ {
2508
+ "epoch": 1.36,
2509
+ "learning_rate": 0.001,
2510
+ "loss": 2.2577,
2511
+ "step": 2085
2512
+ },
2513
+ {
2514
+ "epoch": 1.37,
2515
+ "learning_rate": 0.001,
2516
+ "loss": 2.4857,
2517
+ "step": 2090
2518
+ },
2519
+ {
2520
+ "epoch": 1.37,
2521
+ "learning_rate": 0.001,
2522
+ "loss": 2.1887,
2523
+ "step": 2095
2524
+ },
2525
+ {
2526
+ "epoch": 1.37,
2527
+ "learning_rate": 0.001,
2528
+ "loss": 2.3144,
2529
+ "step": 2100
2530
+ },
2531
+ {
2532
+ "epoch": 1.38,
2533
+ "learning_rate": 0.001,
2534
+ "loss": 2.2387,
2535
+ "step": 2105
2536
+ },
2537
+ {
2538
+ "epoch": 1.38,
2539
+ "learning_rate": 0.001,
2540
+ "loss": 2.5008,
2541
+ "step": 2110
2542
+ },
2543
+ {
2544
+ "epoch": 1.38,
2545
+ "learning_rate": 0.001,
2546
+ "loss": 2.0604,
2547
+ "step": 2115
2548
+ },
2549
+ {
2550
+ "epoch": 1.39,
2551
+ "learning_rate": 0.001,
2552
+ "loss": 2.414,
2553
+ "step": 2120
2554
+ },
2555
+ {
2556
+ "epoch": 1.39,
2557
+ "learning_rate": 0.001,
2558
+ "loss": 2.2392,
2559
+ "step": 2125
2560
+ },
2561
+ {
2562
+ "epoch": 1.39,
2563
+ "learning_rate": 0.001,
2564
+ "loss": 2.1842,
2565
+ "step": 2130
2566
+ },
2567
+ {
2568
+ "epoch": 1.4,
2569
+ "learning_rate": 0.001,
2570
+ "loss": 2.0674,
2571
+ "step": 2135
2572
+ },
2573
+ {
2574
+ "epoch": 1.4,
2575
+ "learning_rate": 0.001,
2576
+ "loss": 2.2088,
2577
+ "step": 2140
2578
+ },
2579
+ {
2580
+ "epoch": 1.4,
2581
+ "learning_rate": 0.001,
2582
+ "loss": 2.363,
2583
+ "step": 2145
2584
+ },
2585
+ {
2586
+ "epoch": 1.41,
2587
+ "learning_rate": 0.001,
2588
+ "loss": 2.1834,
2589
+ "step": 2150
2590
+ },
2591
+ {
2592
+ "epoch": 1.41,
2593
+ "learning_rate": 0.001,
2594
+ "loss": 2.1047,
2595
+ "step": 2155
2596
+ },
2597
+ {
2598
+ "epoch": 1.41,
2599
+ "learning_rate": 0.001,
2600
+ "loss": 1.8624,
2601
+ "step": 2160
2602
+ },
2603
+ {
2604
+ "epoch": 1.42,
2605
+ "learning_rate": 0.001,
2606
+ "loss": 2.0746,
2607
+ "step": 2165
2608
+ },
2609
+ {
2610
+ "epoch": 1.42,
2611
+ "learning_rate": 0.001,
2612
+ "loss": 2.4054,
2613
+ "step": 2170
2614
+ },
2615
+ {
2616
+ "epoch": 1.42,
2617
+ "learning_rate": 0.001,
2618
+ "loss": 2.326,
2619
+ "step": 2175
2620
+ },
2621
+ {
2622
+ "epoch": 1.43,
2623
+ "learning_rate": 0.001,
2624
+ "loss": 2.1054,
2625
+ "step": 2180
2626
+ },
2627
+ {
2628
+ "epoch": 1.43,
2629
+ "learning_rate": 0.001,
2630
+ "loss": 1.7848,
2631
+ "step": 2185
2632
+ },
2633
+ {
2634
+ "epoch": 1.43,
2635
+ "learning_rate": 0.001,
2636
+ "loss": 2.2795,
2637
+ "step": 2190
2638
+ },
2639
+ {
2640
+ "epoch": 1.44,
2641
+ "learning_rate": 0.001,
2642
+ "loss": 1.9866,
2643
+ "step": 2195
2644
+ },
2645
+ {
2646
+ "epoch": 1.44,
2647
+ "learning_rate": 0.001,
2648
+ "loss": 2.5626,
2649
+ "step": 2200
2650
+ },
2651
+ {
2652
+ "epoch": 1.44,
2653
+ "learning_rate": 0.001,
2654
+ "loss": 2.2101,
2655
+ "step": 2205
2656
+ },
2657
+ {
2658
+ "epoch": 1.45,
2659
+ "learning_rate": 0.001,
2660
+ "loss": 2.286,
2661
+ "step": 2210
2662
+ },
2663
+ {
2664
+ "epoch": 1.45,
2665
+ "learning_rate": 0.001,
2666
+ "loss": 1.8204,
2667
+ "step": 2215
2668
+ },
2669
+ {
2670
+ "epoch": 1.45,
2671
+ "learning_rate": 0.001,
2672
+ "loss": 2.1886,
2673
+ "step": 2220
2674
+ },
2675
+ {
2676
+ "epoch": 1.46,
2677
+ "learning_rate": 0.001,
2678
+ "loss": 2.0936,
2679
+ "step": 2225
2680
+ },
2681
+ {
2682
+ "epoch": 1.46,
2683
+ "learning_rate": 0.001,
2684
+ "loss": 2.5121,
2685
+ "step": 2230
2686
+ },
2687
+ {
2688
+ "epoch": 1.46,
2689
+ "learning_rate": 0.001,
2690
+ "loss": 2.2165,
2691
+ "step": 2235
2692
+ },
2693
+ {
2694
+ "epoch": 1.47,
2695
+ "learning_rate": 0.001,
2696
+ "loss": 1.8987,
2697
+ "step": 2240
2698
+ },
2699
+ {
2700
+ "epoch": 1.47,
2701
+ "learning_rate": 0.001,
2702
+ "loss": 1.8333,
2703
+ "step": 2245
2704
+ },
2705
+ {
2706
+ "epoch": 1.47,
2707
+ "learning_rate": 0.001,
2708
+ "loss": 2.2611,
2709
+ "step": 2250
2710
+ },
2711
+ {
2712
+ "epoch": 1.48,
2713
+ "learning_rate": 0.001,
2714
+ "loss": 2.2649,
2715
+ "step": 2255
2716
+ },
2717
+ {
2718
+ "epoch": 1.48,
2719
+ "learning_rate": 0.001,
2720
+ "loss": 2.0907,
2721
+ "step": 2260
2722
+ },
2723
+ {
2724
+ "epoch": 1.48,
2725
+ "learning_rate": 0.001,
2726
+ "loss": 2.2594,
2727
+ "step": 2265
2728
+ },
2729
+ {
2730
+ "epoch": 1.49,
2731
+ "learning_rate": 0.001,
2732
+ "loss": 2.1826,
2733
+ "step": 2270
2734
+ },
2735
+ {
2736
+ "epoch": 1.49,
2737
+ "learning_rate": 0.001,
2738
+ "loss": 2.0087,
2739
+ "step": 2275
2740
+ },
2741
+ {
2742
+ "epoch": 1.49,
2743
+ "learning_rate": 0.001,
2744
+ "loss": 2.0936,
2745
+ "step": 2280
2746
+ },
2747
+ {
2748
+ "epoch": 1.5,
2749
+ "learning_rate": 0.001,
2750
+ "loss": 2.1456,
2751
+ "step": 2285
2752
+ },
2753
+ {
2754
+ "epoch": 1.5,
2755
+ "learning_rate": 0.001,
2756
+ "loss": 2.3667,
2757
+ "step": 2290
2758
+ },
2759
+ {
2760
+ "epoch": 1.5,
2761
+ "learning_rate": 0.001,
2762
+ "loss": 1.9434,
2763
+ "step": 2295
2764
+ },
2765
+ {
2766
+ "epoch": 1.51,
2767
+ "learning_rate": 0.001,
2768
+ "loss": 2.2934,
2769
+ "step": 2300
2770
+ },
2771
+ {
2772
+ "epoch": 1.51,
2773
+ "learning_rate": 0.001,
2774
+ "loss": 2.2615,
2775
+ "step": 2305
2776
+ },
2777
+ {
2778
+ "epoch": 1.51,
2779
+ "learning_rate": 0.001,
2780
+ "loss": 2.0636,
2781
+ "step": 2310
2782
+ },
2783
+ {
2784
+ "epoch": 1.52,
2785
+ "learning_rate": 0.001,
2786
+ "loss": 2.0307,
2787
+ "step": 2315
2788
+ },
2789
+ {
2790
+ "epoch": 1.52,
2791
+ "learning_rate": 0.001,
2792
+ "loss": 2.0033,
2793
+ "step": 2320
2794
+ },
2795
+ {
2796
+ "epoch": 1.52,
2797
+ "learning_rate": 0.001,
2798
+ "loss": 2.0915,
2799
+ "step": 2325
2800
+ },
2801
+ {
2802
+ "epoch": 1.52,
2803
+ "learning_rate": 0.001,
2804
+ "loss": 2.0934,
2805
+ "step": 2330
2806
+ },
2807
+ {
2808
+ "epoch": 1.53,
2809
+ "learning_rate": 0.001,
2810
+ "loss": 2.2811,
2811
+ "step": 2335
2812
+ },
2813
+ {
2814
+ "epoch": 1.53,
2815
+ "learning_rate": 0.001,
2816
+ "loss": 1.962,
2817
+ "step": 2340
2818
+ },
2819
+ {
2820
+ "epoch": 1.53,
2821
+ "learning_rate": 0.001,
2822
+ "loss": 1.8715,
2823
+ "step": 2345
2824
+ },
2825
+ {
2826
+ "epoch": 1.54,
2827
+ "learning_rate": 0.001,
2828
+ "loss": 2.2623,
2829
+ "step": 2350
2830
+ },
2831
+ {
2832
+ "epoch": 1.54,
2833
+ "learning_rate": 0.001,
2834
+ "loss": 2.1543,
2835
+ "step": 2355
2836
+ },
2837
+ {
2838
+ "epoch": 1.54,
2839
+ "learning_rate": 0.001,
2840
+ "loss": 2.1026,
2841
+ "step": 2360
2842
+ },
2843
+ {
2844
+ "epoch": 1.55,
2845
+ "learning_rate": 0.001,
2846
+ "loss": 2.4501,
2847
+ "step": 2365
2848
+ },
2849
+ {
2850
+ "epoch": 1.55,
2851
+ "learning_rate": 0.001,
2852
+ "loss": 2.1931,
2853
+ "step": 2370
2854
+ },
2855
+ {
2856
+ "epoch": 1.55,
2857
+ "learning_rate": 0.001,
2858
+ "loss": 2.0309,
2859
+ "step": 2375
2860
+ },
2861
+ {
2862
+ "epoch": 1.56,
2863
+ "learning_rate": 0.001,
2864
+ "loss": 2.0723,
2865
+ "step": 2380
2866
+ },
2867
+ {
2868
+ "epoch": 1.56,
2869
+ "learning_rate": 0.001,
2870
+ "loss": 2.3666,
2871
+ "step": 2385
2872
+ },
2873
+ {
2874
+ "epoch": 1.56,
2875
+ "learning_rate": 0.001,
2876
+ "loss": 2.1858,
2877
+ "step": 2390
2878
+ },
2879
+ {
2880
+ "epoch": 1.57,
2881
+ "learning_rate": 0.001,
2882
+ "loss": 2.031,
2883
+ "step": 2395
2884
+ },
2885
+ {
2886
+ "epoch": 1.57,
2887
+ "learning_rate": 0.001,
2888
+ "loss": 1.6752,
2889
+ "step": 2400
2890
+ },
2891
+ {
2892
+ "epoch": 1.57,
2893
+ "learning_rate": 0.001,
2894
+ "loss": 2.1003,
2895
+ "step": 2405
2896
+ },
2897
+ {
2898
+ "epoch": 1.58,
2899
+ "learning_rate": 0.001,
2900
+ "loss": 2.4007,
2901
+ "step": 2410
2902
+ },
2903
+ {
2904
+ "epoch": 1.58,
2905
+ "learning_rate": 0.001,
2906
+ "loss": 2.2498,
2907
+ "step": 2415
2908
+ },
2909
+ {
2910
+ "epoch": 1.58,
2911
+ "learning_rate": 0.001,
2912
+ "loss": 2.2472,
2913
+ "step": 2420
2914
+ },
2915
+ {
2916
+ "epoch": 1.59,
2917
+ "learning_rate": 0.001,
2918
+ "loss": 2.202,
2919
+ "step": 2425
2920
+ },
2921
+ {
2922
+ "epoch": 1.59,
2923
+ "learning_rate": 0.001,
2924
+ "loss": 2.4824,
2925
+ "step": 2430
2926
+ },
2927
+ {
2928
+ "epoch": 1.59,
2929
+ "learning_rate": 0.001,
2930
+ "loss": 2.1637,
2931
+ "step": 2435
2932
+ },
2933
+ {
2934
+ "epoch": 1.6,
2935
+ "learning_rate": 0.001,
2936
+ "loss": 2.4039,
2937
+ "step": 2440
2938
+ },
2939
+ {
2940
+ "epoch": 1.6,
2941
+ "learning_rate": 0.001,
2942
+ "loss": 2.1053,
2943
+ "step": 2445
2944
+ },
2945
+ {
2946
+ "epoch": 1.6,
2947
+ "learning_rate": 0.001,
2948
+ "loss": 1.9858,
2949
+ "step": 2450
2950
+ },
2951
+ {
2952
+ "epoch": 1.61,
2953
+ "learning_rate": 0.001,
2954
+ "loss": 2.2371,
2955
+ "step": 2455
2956
+ },
2957
+ {
2958
+ "epoch": 1.61,
2959
+ "learning_rate": 0.001,
2960
+ "loss": 1.8063,
2961
+ "step": 2460
2962
+ },
2963
+ {
2964
+ "epoch": 1.61,
2965
+ "learning_rate": 0.001,
2966
+ "loss": 2.2199,
2967
+ "step": 2465
2968
+ },
2969
+ {
2970
+ "epoch": 1.62,
2971
+ "learning_rate": 0.001,
2972
+ "loss": 2.2837,
2973
+ "step": 2470
2974
+ },
2975
+ {
2976
+ "epoch": 1.62,
2977
+ "learning_rate": 0.001,
2978
+ "loss": 2.2889,
2979
+ "step": 2475
2980
+ },
2981
+ {
2982
+ "epoch": 1.62,
2983
+ "learning_rate": 0.001,
2984
+ "loss": 2.1687,
2985
+ "step": 2480
2986
+ },
2987
+ {
2988
+ "epoch": 1.63,
2989
+ "learning_rate": 0.001,
2990
+ "loss": 2.2346,
2991
+ "step": 2485
2992
+ },
2993
+ {
2994
+ "epoch": 1.63,
2995
+ "learning_rate": 0.001,
2996
+ "loss": 2.3059,
2997
+ "step": 2490
2998
+ },
2999
+ {
3000
+ "epoch": 1.63,
3001
+ "learning_rate": 0.001,
3002
+ "loss": 2.3096,
3003
+ "step": 2495
3004
+ },
3005
+ {
3006
+ "epoch": 1.64,
3007
+ "learning_rate": 0.001,
3008
+ "loss": 2.4252,
3009
+ "step": 2500
3010
+ },
3011
+ {
3012
+ "epoch": 1.64,
3013
+ "learning_rate": 0.001,
3014
+ "loss": 1.9604,
3015
+ "step": 2505
3016
+ },
3017
+ {
3018
+ "epoch": 1.64,
3019
+ "learning_rate": 0.001,
3020
+ "loss": 2.154,
3021
+ "step": 2510
3022
+ },
3023
+ {
3024
+ "epoch": 1.65,
3025
+ "learning_rate": 0.001,
3026
+ "loss": 2.3648,
3027
+ "step": 2515
3028
+ },
3029
+ {
3030
+ "epoch": 1.65,
3031
+ "learning_rate": 0.001,
3032
+ "loss": 2.3436,
3033
+ "step": 2520
3034
+ },
3035
+ {
3036
+ "epoch": 1.65,
3037
+ "learning_rate": 0.001,
3038
+ "loss": 2.3471,
3039
+ "step": 2525
3040
+ },
3041
+ {
3042
+ "epoch": 1.66,
3043
+ "learning_rate": 0.001,
3044
+ "loss": 2.1766,
3045
+ "step": 2530
3046
+ },
3047
+ {
3048
+ "epoch": 1.66,
3049
+ "learning_rate": 0.001,
3050
+ "loss": 2.1967,
3051
+ "step": 2535
3052
+ },
3053
+ {
3054
+ "epoch": 1.66,
3055
+ "learning_rate": 0.001,
3056
+ "loss": 2.1945,
3057
+ "step": 2540
3058
+ },
3059
+ {
3060
+ "epoch": 1.67,
3061
+ "learning_rate": 0.001,
3062
+ "loss": 2.1473,
3063
+ "step": 2545
3064
+ },
3065
+ {
3066
+ "epoch": 1.67,
3067
+ "learning_rate": 0.001,
3068
+ "loss": 2.4883,
3069
+ "step": 2550
3070
+ },
3071
+ {
3072
+ "epoch": 1.67,
3073
+ "learning_rate": 0.001,
3074
+ "loss": 1.9596,
3075
+ "step": 2555
3076
+ },
3077
+ {
3078
+ "epoch": 1.68,
3079
+ "learning_rate": 0.001,
3080
+ "loss": 2.3908,
3081
+ "step": 2560
3082
+ },
3083
+ {
3084
+ "epoch": 1.68,
3085
+ "learning_rate": 0.001,
3086
+ "loss": 2.2533,
3087
+ "step": 2565
3088
+ },
3089
+ {
3090
+ "epoch": 1.68,
3091
+ "learning_rate": 0.001,
3092
+ "loss": 2.0808,
3093
+ "step": 2570
3094
+ },
3095
+ {
3096
+ "epoch": 1.69,
3097
+ "learning_rate": 0.001,
3098
+ "loss": 2.028,
3099
+ "step": 2575
3100
+ },
3101
+ {
3102
+ "epoch": 1.69,
3103
+ "learning_rate": 0.001,
3104
+ "loss": 2.2471,
3105
+ "step": 2580
3106
+ },
3107
+ {
3108
+ "epoch": 1.69,
3109
+ "learning_rate": 0.001,
3110
+ "loss": 2.1975,
3111
+ "step": 2585
3112
+ },
3113
+ {
3114
+ "epoch": 1.7,
3115
+ "learning_rate": 0.001,
3116
+ "loss": 2.404,
3117
+ "step": 2590
3118
+ },
3119
+ {
3120
+ "epoch": 1.7,
3121
+ "learning_rate": 0.001,
3122
+ "loss": 2.4238,
3123
+ "step": 2595
3124
+ },
3125
+ {
3126
+ "epoch": 1.7,
3127
+ "learning_rate": 0.001,
3128
+ "loss": 2.2742,
3129
+ "step": 2600
3130
+ },
3131
+ {
3132
+ "epoch": 1.7,
3133
+ "learning_rate": 0.001,
3134
+ "loss": 2.3284,
3135
+ "step": 2605
3136
+ },
3137
+ {
3138
+ "epoch": 1.71,
3139
+ "learning_rate": 0.001,
3140
+ "loss": 2.0517,
3141
+ "step": 2610
3142
+ },
3143
+ {
3144
+ "epoch": 1.71,
3145
+ "learning_rate": 0.001,
3146
+ "loss": 2.488,
3147
+ "step": 2615
3148
+ },
3149
+ {
3150
+ "epoch": 1.71,
3151
+ "learning_rate": 0.001,
3152
+ "loss": 2.1215,
3153
+ "step": 2620
3154
+ },
3155
+ {
3156
+ "epoch": 1.72,
3157
+ "learning_rate": 0.001,
3158
+ "loss": 2.1813,
3159
+ "step": 2625
3160
+ },
3161
+ {
3162
+ "epoch": 1.72,
3163
+ "learning_rate": 0.001,
3164
+ "loss": 1.9404,
3165
+ "step": 2630
3166
+ },
3167
+ {
3168
+ "epoch": 1.72,
3169
+ "learning_rate": 0.001,
3170
+ "loss": 2.1978,
3171
+ "step": 2635
3172
+ },
3173
+ {
3174
+ "epoch": 1.73,
3175
+ "learning_rate": 0.001,
3176
+ "loss": 2.1462,
3177
+ "step": 2640
3178
+ },
3179
+ {
3180
+ "epoch": 1.73,
3181
+ "learning_rate": 0.001,
3182
+ "loss": 1.9796,
3183
+ "step": 2645
3184
+ },
3185
+ {
3186
+ "epoch": 1.73,
3187
+ "learning_rate": 0.001,
3188
+ "loss": 2.267,
3189
+ "step": 2650
3190
+ },
3191
+ {
3192
+ "epoch": 1.74,
3193
+ "learning_rate": 0.001,
3194
+ "loss": 2.0169,
3195
+ "step": 2655
3196
+ },
3197
+ {
3198
+ "epoch": 1.74,
3199
+ "learning_rate": 0.001,
3200
+ "loss": 2.1779,
3201
+ "step": 2660
3202
+ },
3203
+ {
3204
+ "epoch": 1.74,
3205
+ "learning_rate": 0.001,
3206
+ "loss": 2.2851,
3207
+ "step": 2665
3208
+ },
3209
+ {
3210
+ "epoch": 1.75,
3211
+ "learning_rate": 0.001,
3212
+ "loss": 2.5845,
3213
+ "step": 2670
3214
+ },
3215
+ {
3216
+ "epoch": 1.75,
3217
+ "learning_rate": 0.001,
3218
+ "loss": 2.006,
3219
+ "step": 2675
3220
+ },
3221
+ {
3222
+ "epoch": 1.75,
3223
+ "learning_rate": 0.001,
3224
+ "loss": 2.0386,
3225
+ "step": 2680
3226
+ },
3227
+ {
3228
+ "epoch": 1.76,
3229
+ "learning_rate": 0.001,
3230
+ "loss": 2.2271,
3231
+ "step": 2685
3232
+ },
3233
+ {
3234
+ "epoch": 1.76,
3235
+ "learning_rate": 0.001,
3236
+ "loss": 2.1557,
3237
+ "step": 2690
3238
+ },
3239
+ {
3240
+ "epoch": 1.76,
3241
+ "learning_rate": 0.001,
3242
+ "loss": 2.0532,
3243
+ "step": 2695
3244
+ },
3245
+ {
3246
+ "epoch": 1.77,
3247
+ "learning_rate": 0.001,
3248
+ "loss": 2.14,
3249
+ "step": 2700
3250
+ },
3251
+ {
3252
+ "epoch": 1.77,
3253
+ "learning_rate": 0.001,
3254
+ "loss": 1.995,
3255
+ "step": 2705
3256
+ },
3257
+ {
3258
+ "epoch": 1.77,
3259
+ "learning_rate": 0.001,
3260
+ "loss": 1.9508,
3261
+ "step": 2710
3262
+ },
3263
+ {
3264
+ "epoch": 1.78,
3265
+ "learning_rate": 0.001,
3266
+ "loss": 2.4736,
3267
+ "step": 2715
3268
+ },
3269
+ {
3270
+ "epoch": 1.78,
3271
+ "learning_rate": 0.001,
3272
+ "loss": 2.0145,
3273
+ "step": 2720
3274
+ },
3275
+ {
3276
+ "epoch": 1.78,
3277
+ "learning_rate": 0.001,
3278
+ "loss": 2.1276,
3279
+ "step": 2725
3280
+ },
3281
+ {
3282
+ "epoch": 1.79,
3283
+ "learning_rate": 0.001,
3284
+ "loss": 2.1232,
3285
+ "step": 2730
3286
+ },
3287
+ {
3288
+ "epoch": 1.79,
3289
+ "learning_rate": 0.001,
3290
+ "loss": 2.3248,
3291
+ "step": 2735
3292
+ },
3293
+ {
3294
+ "epoch": 1.79,
3295
+ "learning_rate": 0.001,
3296
+ "loss": 2.0148,
3297
+ "step": 2740
3298
+ },
3299
+ {
3300
+ "epoch": 1.8,
3301
+ "learning_rate": 0.001,
3302
+ "loss": 1.974,
3303
+ "step": 2745
3304
+ },
3305
+ {
3306
+ "epoch": 1.8,
3307
+ "learning_rate": 0.001,
3308
+ "loss": 2.2313,
3309
+ "step": 2750
3310
+ },
3311
+ {
3312
+ "epoch": 1.8,
3313
+ "learning_rate": 0.001,
3314
+ "loss": 2.0893,
3315
+ "step": 2755
3316
+ },
3317
+ {
3318
+ "epoch": 1.81,
3319
+ "learning_rate": 0.001,
3320
+ "loss": 2.1423,
3321
+ "step": 2760
3322
+ },
3323
+ {
3324
+ "epoch": 1.81,
3325
+ "learning_rate": 0.001,
3326
+ "loss": 2.2085,
3327
+ "step": 2765
3328
+ },
3329
+ {
3330
+ "epoch": 1.81,
3331
+ "learning_rate": 0.001,
3332
+ "loss": 2.2314,
3333
+ "step": 2770
3334
+ },
3335
+ {
3336
+ "epoch": 1.82,
3337
+ "learning_rate": 0.001,
3338
+ "loss": 2.1122,
3339
+ "step": 2775
3340
+ },
3341
+ {
3342
+ "epoch": 1.82,
3343
+ "learning_rate": 0.001,
3344
+ "loss": 2.0739,
3345
+ "step": 2780
3346
+ },
3347
+ {
3348
+ "epoch": 1.82,
3349
+ "learning_rate": 0.001,
3350
+ "loss": 2.2233,
3351
+ "step": 2785
3352
+ },
3353
+ {
3354
+ "epoch": 1.83,
3355
+ "learning_rate": 0.001,
3356
+ "loss": 2.2696,
3357
+ "step": 2790
3358
+ },
3359
+ {
3360
+ "epoch": 1.83,
3361
+ "learning_rate": 0.001,
3362
+ "loss": 1.9375,
3363
+ "step": 2795
3364
+ },
3365
+ {
3366
+ "epoch": 1.83,
3367
+ "learning_rate": 0.001,
3368
+ "loss": 2.2126,
3369
+ "step": 2800
3370
+ },
3371
+ {
3372
+ "epoch": 1.84,
3373
+ "learning_rate": 0.001,
3374
+ "loss": 2.2643,
3375
+ "step": 2805
3376
+ },
3377
+ {
3378
+ "epoch": 1.84,
3379
+ "learning_rate": 0.001,
3380
+ "loss": 1.881,
3381
+ "step": 2810
3382
+ },
3383
+ {
3384
+ "epoch": 1.84,
3385
+ "learning_rate": 0.001,
3386
+ "loss": 2.427,
3387
+ "step": 2815
3388
+ },
3389
+ {
3390
+ "epoch": 1.85,
3391
+ "learning_rate": 0.001,
3392
+ "loss": 2.419,
3393
+ "step": 2820
3394
+ },
3395
+ {
3396
+ "epoch": 1.85,
3397
+ "learning_rate": 0.001,
3398
+ "loss": 2.2486,
3399
+ "step": 2825
3400
+ },
3401
+ {
3402
+ "epoch": 1.85,
3403
+ "learning_rate": 0.001,
3404
+ "loss": 2.6872,
3405
+ "step": 2830
3406
+ },
3407
+ {
3408
+ "epoch": 1.86,
3409
+ "learning_rate": 0.001,
3410
+ "loss": 2.0539,
3411
+ "step": 2835
3412
+ },
3413
+ {
3414
+ "epoch": 1.86,
3415
+ "learning_rate": 0.001,
3416
+ "loss": 2.4746,
3417
+ "step": 2840
3418
+ },
3419
+ {
3420
+ "epoch": 1.86,
3421
+ "learning_rate": 0.001,
3422
+ "loss": 2.2573,
3423
+ "step": 2845
3424
+ },
3425
+ {
3426
+ "epoch": 1.87,
3427
+ "learning_rate": 0.001,
3428
+ "loss": 2.0748,
3429
+ "step": 2850
3430
+ },
3431
+ {
3432
+ "epoch": 1.87,
3433
+ "learning_rate": 0.001,
3434
+ "loss": 2.2958,
3435
+ "step": 2855
3436
+ },
3437
+ {
3438
+ "epoch": 1.87,
3439
+ "learning_rate": 0.001,
3440
+ "loss": 1.8544,
3441
+ "step": 2860
3442
+ },
3443
+ {
3444
+ "epoch": 1.88,
3445
+ "learning_rate": 0.001,
3446
+ "loss": 2.4232,
3447
+ "step": 2865
3448
+ },
3449
+ {
3450
+ "epoch": 1.88,
3451
+ "learning_rate": 0.001,
3452
+ "loss": 2.3381,
3453
+ "step": 2870
3454
+ },
3455
+ {
3456
+ "epoch": 1.88,
3457
+ "learning_rate": 0.001,
3458
+ "loss": 2.276,
3459
+ "step": 2875
3460
+ },
3461
+ {
3462
+ "epoch": 1.88,
3463
+ "learning_rate": 0.001,
3464
+ "loss": 2.3278,
3465
+ "step": 2880
3466
+ },
3467
+ {
3468
+ "epoch": 1.89,
3469
+ "learning_rate": 0.001,
3470
+ "loss": 2.3119,
3471
+ "step": 2885
3472
+ },
3473
+ {
3474
+ "epoch": 1.89,
3475
+ "learning_rate": 0.001,
3476
+ "loss": 2.2123,
3477
+ "step": 2890
3478
+ },
3479
+ {
3480
+ "epoch": 1.89,
3481
+ "learning_rate": 0.001,
3482
+ "loss": 2.1596,
3483
+ "step": 2895
3484
+ },
3485
+ {
3486
+ "epoch": 1.9,
3487
+ "learning_rate": 0.001,
3488
+ "loss": 2.04,
3489
+ "step": 2900
3490
+ },
3491
+ {
3492
+ "epoch": 1.9,
3493
+ "learning_rate": 0.001,
3494
+ "loss": 2.3909,
3495
+ "step": 2905
3496
+ },
3497
+ {
3498
+ "epoch": 1.9,
3499
+ "learning_rate": 0.001,
3500
+ "loss": 2.1027,
3501
+ "step": 2910
3502
+ },
3503
+ {
3504
+ "epoch": 1.91,
3505
+ "learning_rate": 0.001,
3506
+ "loss": 2.1365,
3507
+ "step": 2915
3508
+ },
3509
+ {
3510
+ "epoch": 1.91,
3511
+ "learning_rate": 0.001,
3512
+ "loss": 2.2151,
3513
+ "step": 2920
3514
+ },
3515
+ {
3516
+ "epoch": 1.91,
3517
+ "learning_rate": 0.001,
3518
+ "loss": 2.2469,
3519
+ "step": 2925
3520
+ },
3521
+ {
3522
+ "epoch": 1.92,
3523
+ "learning_rate": 0.001,
3524
+ "loss": 2.1939,
3525
+ "step": 2930
3526
+ },
3527
+ {
3528
+ "epoch": 1.92,
3529
+ "learning_rate": 0.001,
3530
+ "loss": 2.0386,
3531
+ "step": 2935
3532
+ },
3533
+ {
3534
+ "epoch": 1.92,
3535
+ "learning_rate": 0.001,
3536
+ "loss": 2.094,
3537
+ "step": 2940
3538
+ },
3539
+ {
3540
+ "epoch": 1.93,
3541
+ "learning_rate": 0.001,
3542
+ "loss": 2.3225,
3543
+ "step": 2945
3544
+ },
3545
+ {
3546
+ "epoch": 1.93,
3547
+ "learning_rate": 0.001,
3548
+ "loss": 2.1019,
3549
+ "step": 2950
3550
+ },
3551
+ {
3552
+ "epoch": 1.93,
3553
+ "learning_rate": 0.001,
3554
+ "loss": 2.3213,
3555
+ "step": 2955
3556
+ },
3557
+ {
3558
+ "epoch": 1.94,
3559
+ "learning_rate": 0.001,
3560
+ "loss": 2.4173,
3561
+ "step": 2960
3562
+ },
3563
+ {
3564
+ "epoch": 1.94,
3565
+ "learning_rate": 0.001,
3566
+ "loss": 2.1919,
3567
+ "step": 2965
3568
+ },
3569
+ {
3570
+ "epoch": 1.94,
3571
+ "learning_rate": 0.001,
3572
+ "loss": 2.1733,
3573
+ "step": 2970
3574
+ },
3575
+ {
3576
+ "epoch": 1.95,
3577
+ "learning_rate": 0.001,
3578
+ "loss": 2.3576,
3579
+ "step": 2975
3580
+ },
3581
+ {
3582
+ "epoch": 1.95,
3583
+ "learning_rate": 0.001,
3584
+ "loss": 2.0042,
3585
+ "step": 2980
3586
+ },
3587
+ {
3588
+ "epoch": 1.95,
3589
+ "learning_rate": 0.001,
3590
+ "loss": 2.0977,
3591
+ "step": 2985
3592
+ },
3593
+ {
3594
+ "epoch": 1.96,
3595
+ "learning_rate": 0.001,
3596
+ "loss": 2.2674,
3597
+ "step": 2990
3598
+ },
3599
+ {
3600
+ "epoch": 1.96,
3601
+ "learning_rate": 0.001,
3602
+ "loss": 1.9316,
3603
+ "step": 2995
3604
+ },
3605
+ {
3606
+ "epoch": 1.96,
3607
+ "learning_rate": 0.001,
3608
+ "loss": 2.2472,
3609
+ "step": 3000
3610
+ }
3611
+ ],
3612
+ "logging_steps": 5,
3613
+ "max_steps": 7640,
3614
+ "num_train_epochs": 5,
3615
+ "save_steps": 1000,
3616
+ "total_flos": 350355456000000.0,
3617
+ "trial_name": null,
3618
+ "trial_params": null
3619
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026a40a22d79b976af4f05a529a919434f1a1af96981147d87e1c857264d40d7
3
+ size 4027
checkpoint-4000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 512,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 4,
15
+ "num_hidden_layers": 2,
16
+ "num_key_value_heads": 4,
17
+ "pretraining_tp": 2,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.34.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
checkpoint-4000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ef0dc8787de18f7a71345e92976845f2336048062f9f270d600c15dded0259
3
+ size 141585770
checkpoint-4000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b31dbbe85d80b08135e7e6576e31b1fbda6f1771922cfb9f315838ffcb09a75
3
+ size 70790896
checkpoint-4000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
3
+ size 14575
checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0453986a30df5c399672292dda61b3344d1cacf352c203ac7a1055e9e21b3b71
3
+ size 627
checkpoint-4000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-4000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-4000/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "model_max_length": 8192,
33
+ "pad_token": null,
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,4819 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.6178010471204187,
5
+ "eval_steps": 500,
6
+ "global_step": 4000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.001,
14
+ "loss": 1.3845,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.001,
20
+ "loss": 1.6284,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.001,
26
+ "loss": 1.3152,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.001,
32
+ "loss": 1.6192,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 0.001,
38
+ "loss": 1.7394,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 0.001,
44
+ "loss": 1.9925,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.001,
50
+ "loss": 1.902,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 0.001,
56
+ "loss": 1.822,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 0.001,
62
+ "loss": 2.137,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "learning_rate": 0.001,
68
+ "loss": 2.2556,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 0.04,
73
+ "learning_rate": 0.001,
74
+ "loss": 2.2468,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 0.04,
79
+ "learning_rate": 0.001,
80
+ "loss": 2.0746,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "learning_rate": 0.001,
86
+ "loss": 2.1092,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 0.05,
91
+ "learning_rate": 0.001,
92
+ "loss": 1.9553,
93
+ "step": 70
94
+ },
95
+ {
96
+ "epoch": 0.05,
97
+ "learning_rate": 0.001,
98
+ "loss": 2.121,
99
+ "step": 75
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "learning_rate": 0.001,
104
+ "loss": 2.1722,
105
+ "step": 80
106
+ },
107
+ {
108
+ "epoch": 0.06,
109
+ "learning_rate": 0.001,
110
+ "loss": 2.1552,
111
+ "step": 85
112
+ },
113
+ {
114
+ "epoch": 0.06,
115
+ "learning_rate": 0.001,
116
+ "loss": 2.5971,
117
+ "step": 90
118
+ },
119
+ {
120
+ "epoch": 0.06,
121
+ "learning_rate": 0.001,
122
+ "loss": 2.4684,
123
+ "step": 95
124
+ },
125
+ {
126
+ "epoch": 0.07,
127
+ "learning_rate": 0.001,
128
+ "loss": 2.0248,
129
+ "step": 100
130
+ },
131
+ {
132
+ "epoch": 0.07,
133
+ "learning_rate": 0.001,
134
+ "loss": 2.5156,
135
+ "step": 105
136
+ },
137
+ {
138
+ "epoch": 0.07,
139
+ "learning_rate": 0.001,
140
+ "loss": 2.3322,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.08,
145
+ "learning_rate": 0.001,
146
+ "loss": 1.7698,
147
+ "step": 115
148
+ },
149
+ {
150
+ "epoch": 0.08,
151
+ "learning_rate": 0.001,
152
+ "loss": 2.3363,
153
+ "step": 120
154
+ },
155
+ {
156
+ "epoch": 0.08,
157
+ "learning_rate": 0.001,
158
+ "loss": 2.1079,
159
+ "step": 125
160
+ },
161
+ {
162
+ "epoch": 0.09,
163
+ "learning_rate": 0.001,
164
+ "loss": 2.0998,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 0.09,
169
+ "learning_rate": 0.001,
170
+ "loss": 2.8265,
171
+ "step": 135
172
+ },
173
+ {
174
+ "epoch": 0.09,
175
+ "learning_rate": 0.001,
176
+ "loss": 2.6611,
177
+ "step": 140
178
+ },
179
+ {
180
+ "epoch": 0.09,
181
+ "learning_rate": 0.001,
182
+ "loss": 2.2187,
183
+ "step": 145
184
+ },
185
+ {
186
+ "epoch": 0.1,
187
+ "learning_rate": 0.001,
188
+ "loss": 2.33,
189
+ "step": 150
190
+ },
191
+ {
192
+ "epoch": 0.1,
193
+ "learning_rate": 0.001,
194
+ "loss": 2.6119,
195
+ "step": 155
196
+ },
197
+ {
198
+ "epoch": 0.1,
199
+ "learning_rate": 0.001,
200
+ "loss": 2.2203,
201
+ "step": 160
202
+ },
203
+ {
204
+ "epoch": 0.11,
205
+ "learning_rate": 0.001,
206
+ "loss": 2.5474,
207
+ "step": 165
208
+ },
209
+ {
210
+ "epoch": 0.11,
211
+ "learning_rate": 0.001,
212
+ "loss": 2.4763,
213
+ "step": 170
214
+ },
215
+ {
216
+ "epoch": 0.11,
217
+ "learning_rate": 0.001,
218
+ "loss": 2.6068,
219
+ "step": 175
220
+ },
221
+ {
222
+ "epoch": 0.12,
223
+ "learning_rate": 0.001,
224
+ "loss": 2.1221,
225
+ "step": 180
226
+ },
227
+ {
228
+ "epoch": 0.12,
229
+ "learning_rate": 0.001,
230
+ "loss": 2.1185,
231
+ "step": 185
232
+ },
233
+ {
234
+ "epoch": 0.12,
235
+ "learning_rate": 0.001,
236
+ "loss": 1.9481,
237
+ "step": 190
238
+ },
239
+ {
240
+ "epoch": 0.13,
241
+ "learning_rate": 0.001,
242
+ "loss": 2.823,
243
+ "step": 195
244
+ },
245
+ {
246
+ "epoch": 0.13,
247
+ "learning_rate": 0.001,
248
+ "loss": 2.4702,
249
+ "step": 200
250
+ },
251
+ {
252
+ "epoch": 0.13,
253
+ "learning_rate": 0.001,
254
+ "loss": 2.3721,
255
+ "step": 205
256
+ },
257
+ {
258
+ "epoch": 0.14,
259
+ "learning_rate": 0.001,
260
+ "loss": 2.4932,
261
+ "step": 210
262
+ },
263
+ {
264
+ "epoch": 0.14,
265
+ "learning_rate": 0.001,
266
+ "loss": 2.3977,
267
+ "step": 215
268
+ },
269
+ {
270
+ "epoch": 0.14,
271
+ "learning_rate": 0.001,
272
+ "loss": 2.5299,
273
+ "step": 220
274
+ },
275
+ {
276
+ "epoch": 0.15,
277
+ "learning_rate": 0.001,
278
+ "loss": 2.4818,
279
+ "step": 225
280
+ },
281
+ {
282
+ "epoch": 0.15,
283
+ "learning_rate": 0.001,
284
+ "loss": 2.3404,
285
+ "step": 230
286
+ },
287
+ {
288
+ "epoch": 0.15,
289
+ "learning_rate": 0.001,
290
+ "loss": 2.3614,
291
+ "step": 235
292
+ },
293
+ {
294
+ "epoch": 0.16,
295
+ "learning_rate": 0.001,
296
+ "loss": 2.1509,
297
+ "step": 240
298
+ },
299
+ {
300
+ "epoch": 0.16,
301
+ "learning_rate": 0.001,
302
+ "loss": 2.5301,
303
+ "step": 245
304
+ },
305
+ {
306
+ "epoch": 0.16,
307
+ "learning_rate": 0.001,
308
+ "loss": 2.3328,
309
+ "step": 250
310
+ },
311
+ {
312
+ "epoch": 0.17,
313
+ "learning_rate": 0.001,
314
+ "loss": 2.412,
315
+ "step": 255
316
+ },
317
+ {
318
+ "epoch": 0.17,
319
+ "learning_rate": 0.001,
320
+ "loss": 2.5923,
321
+ "step": 260
322
+ },
323
+ {
324
+ "epoch": 0.17,
325
+ "learning_rate": 0.001,
326
+ "loss": 2.2655,
327
+ "step": 265
328
+ },
329
+ {
330
+ "epoch": 0.18,
331
+ "learning_rate": 0.001,
332
+ "loss": 2.7524,
333
+ "step": 270
334
+ },
335
+ {
336
+ "epoch": 0.18,
337
+ "learning_rate": 0.001,
338
+ "loss": 2.6456,
339
+ "step": 275
340
+ },
341
+ {
342
+ "epoch": 0.18,
343
+ "learning_rate": 0.001,
344
+ "loss": 2.3814,
345
+ "step": 280
346
+ },
347
+ {
348
+ "epoch": 0.19,
349
+ "learning_rate": 0.001,
350
+ "loss": 2.3805,
351
+ "step": 285
352
+ },
353
+ {
354
+ "epoch": 0.19,
355
+ "learning_rate": 0.001,
356
+ "loss": 2.6727,
357
+ "step": 290
358
+ },
359
+ {
360
+ "epoch": 0.19,
361
+ "learning_rate": 0.001,
362
+ "loss": 2.3931,
363
+ "step": 295
364
+ },
365
+ {
366
+ "epoch": 0.2,
367
+ "learning_rate": 0.001,
368
+ "loss": 1.9526,
369
+ "step": 300
370
+ },
371
+ {
372
+ "epoch": 0.2,
373
+ "learning_rate": 0.001,
374
+ "loss": 2.7219,
375
+ "step": 305
376
+ },
377
+ {
378
+ "epoch": 0.2,
379
+ "learning_rate": 0.001,
380
+ "loss": 2.4869,
381
+ "step": 310
382
+ },
383
+ {
384
+ "epoch": 0.21,
385
+ "learning_rate": 0.001,
386
+ "loss": 2.4303,
387
+ "step": 315
388
+ },
389
+ {
390
+ "epoch": 0.21,
391
+ "learning_rate": 0.001,
392
+ "loss": 2.5916,
393
+ "step": 320
394
+ },
395
+ {
396
+ "epoch": 0.21,
397
+ "learning_rate": 0.001,
398
+ "loss": 2.3917,
399
+ "step": 325
400
+ },
401
+ {
402
+ "epoch": 0.22,
403
+ "learning_rate": 0.001,
404
+ "loss": 2.4881,
405
+ "step": 330
406
+ },
407
+ {
408
+ "epoch": 0.22,
409
+ "learning_rate": 0.001,
410
+ "loss": 2.3369,
411
+ "step": 335
412
+ },
413
+ {
414
+ "epoch": 0.22,
415
+ "learning_rate": 0.001,
416
+ "loss": 2.45,
417
+ "step": 340
418
+ },
419
+ {
420
+ "epoch": 0.23,
421
+ "learning_rate": 0.001,
422
+ "loss": 2.1916,
423
+ "step": 345
424
+ },
425
+ {
426
+ "epoch": 0.23,
427
+ "learning_rate": 0.001,
428
+ "loss": 2.2606,
429
+ "step": 350
430
+ },
431
+ {
432
+ "epoch": 0.23,
433
+ "learning_rate": 0.001,
434
+ "loss": 2.5533,
435
+ "step": 355
436
+ },
437
+ {
438
+ "epoch": 0.24,
439
+ "learning_rate": 0.001,
440
+ "loss": 2.1873,
441
+ "step": 360
442
+ },
443
+ {
444
+ "epoch": 0.24,
445
+ "learning_rate": 0.001,
446
+ "loss": 2.6057,
447
+ "step": 365
448
+ },
449
+ {
450
+ "epoch": 0.24,
451
+ "learning_rate": 0.001,
452
+ "loss": 2.4611,
453
+ "step": 370
454
+ },
455
+ {
456
+ "epoch": 0.25,
457
+ "learning_rate": 0.001,
458
+ "loss": 2.606,
459
+ "step": 375
460
+ },
461
+ {
462
+ "epoch": 0.25,
463
+ "learning_rate": 0.001,
464
+ "loss": 2.5645,
465
+ "step": 380
466
+ },
467
+ {
468
+ "epoch": 0.25,
469
+ "learning_rate": 0.001,
470
+ "loss": 2.7591,
471
+ "step": 385
472
+ },
473
+ {
474
+ "epoch": 0.26,
475
+ "learning_rate": 0.001,
476
+ "loss": 2.3399,
477
+ "step": 390
478
+ },
479
+ {
480
+ "epoch": 0.26,
481
+ "learning_rate": 0.001,
482
+ "loss": 2.3675,
483
+ "step": 395
484
+ },
485
+ {
486
+ "epoch": 0.26,
487
+ "learning_rate": 0.001,
488
+ "loss": 2.5141,
489
+ "step": 400
490
+ },
491
+ {
492
+ "epoch": 0.27,
493
+ "learning_rate": 0.001,
494
+ "loss": 2.2407,
495
+ "step": 405
496
+ },
497
+ {
498
+ "epoch": 0.27,
499
+ "learning_rate": 0.001,
500
+ "loss": 2.6321,
501
+ "step": 410
502
+ },
503
+ {
504
+ "epoch": 0.27,
505
+ "learning_rate": 0.001,
506
+ "loss": 2.6431,
507
+ "step": 415
508
+ },
509
+ {
510
+ "epoch": 0.27,
511
+ "learning_rate": 0.001,
512
+ "loss": 2.4707,
513
+ "step": 420
514
+ },
515
+ {
516
+ "epoch": 0.28,
517
+ "learning_rate": 0.001,
518
+ "loss": 2.3744,
519
+ "step": 425
520
+ },
521
+ {
522
+ "epoch": 0.28,
523
+ "learning_rate": 0.001,
524
+ "loss": 2.5658,
525
+ "step": 430
526
+ },
527
+ {
528
+ "epoch": 0.28,
529
+ "learning_rate": 0.001,
530
+ "loss": 1.9922,
531
+ "step": 435
532
+ },
533
+ {
534
+ "epoch": 0.29,
535
+ "learning_rate": 0.001,
536
+ "loss": 2.5948,
537
+ "step": 440
538
+ },
539
+ {
540
+ "epoch": 0.29,
541
+ "learning_rate": 0.001,
542
+ "loss": 2.2519,
543
+ "step": 445
544
+ },
545
+ {
546
+ "epoch": 0.29,
547
+ "learning_rate": 0.001,
548
+ "loss": 2.6248,
549
+ "step": 450
550
+ },
551
+ {
552
+ "epoch": 0.3,
553
+ "learning_rate": 0.001,
554
+ "loss": 2.5877,
555
+ "step": 455
556
+ },
557
+ {
558
+ "epoch": 0.3,
559
+ "learning_rate": 0.001,
560
+ "loss": 2.1311,
561
+ "step": 460
562
+ },
563
+ {
564
+ "epoch": 0.3,
565
+ "learning_rate": 0.001,
566
+ "loss": 2.6091,
567
+ "step": 465
568
+ },
569
+ {
570
+ "epoch": 0.31,
571
+ "learning_rate": 0.001,
572
+ "loss": 2.5488,
573
+ "step": 470
574
+ },
575
+ {
576
+ "epoch": 0.31,
577
+ "learning_rate": 0.001,
578
+ "loss": 2.499,
579
+ "step": 475
580
+ },
581
+ {
582
+ "epoch": 0.31,
583
+ "learning_rate": 0.001,
584
+ "loss": 2.5031,
585
+ "step": 480
586
+ },
587
+ {
588
+ "epoch": 0.32,
589
+ "learning_rate": 0.001,
590
+ "loss": 2.5783,
591
+ "step": 485
592
+ },
593
+ {
594
+ "epoch": 0.32,
595
+ "learning_rate": 0.001,
596
+ "loss": 2.6303,
597
+ "step": 490
598
+ },
599
+ {
600
+ "epoch": 0.32,
601
+ "learning_rate": 0.001,
602
+ "loss": 2.6344,
603
+ "step": 495
604
+ },
605
+ {
606
+ "epoch": 0.33,
607
+ "learning_rate": 0.001,
608
+ "loss": 2.7031,
609
+ "step": 500
610
+ },
611
+ {
612
+ "epoch": 0.33,
613
+ "learning_rate": 0.001,
614
+ "loss": 2.6677,
615
+ "step": 505
616
+ },
617
+ {
618
+ "epoch": 0.33,
619
+ "learning_rate": 0.001,
620
+ "loss": 2.7617,
621
+ "step": 510
622
+ },
623
+ {
624
+ "epoch": 0.34,
625
+ "learning_rate": 0.001,
626
+ "loss": 2.3122,
627
+ "step": 515
628
+ },
629
+ {
630
+ "epoch": 0.34,
631
+ "learning_rate": 0.001,
632
+ "loss": 2.3887,
633
+ "step": 520
634
+ },
635
+ {
636
+ "epoch": 0.34,
637
+ "learning_rate": 0.001,
638
+ "loss": 2.5569,
639
+ "step": 525
640
+ },
641
+ {
642
+ "epoch": 0.35,
643
+ "learning_rate": 0.001,
644
+ "loss": 2.4038,
645
+ "step": 530
646
+ },
647
+ {
648
+ "epoch": 0.35,
649
+ "learning_rate": 0.001,
650
+ "loss": 2.7413,
651
+ "step": 535
652
+ },
653
+ {
654
+ "epoch": 0.35,
655
+ "learning_rate": 0.001,
656
+ "loss": 2.5264,
657
+ "step": 540
658
+ },
659
+ {
660
+ "epoch": 0.36,
661
+ "learning_rate": 0.001,
662
+ "loss": 2.335,
663
+ "step": 545
664
+ },
665
+ {
666
+ "epoch": 0.36,
667
+ "learning_rate": 0.001,
668
+ "loss": 2.7574,
669
+ "step": 550
670
+ },
671
+ {
672
+ "epoch": 0.36,
673
+ "learning_rate": 0.001,
674
+ "loss": 2.4542,
675
+ "step": 555
676
+ },
677
+ {
678
+ "epoch": 0.37,
679
+ "learning_rate": 0.001,
680
+ "loss": 2.0885,
681
+ "step": 560
682
+ },
683
+ {
684
+ "epoch": 0.37,
685
+ "learning_rate": 0.001,
686
+ "loss": 2.6057,
687
+ "step": 565
688
+ },
689
+ {
690
+ "epoch": 0.37,
691
+ "learning_rate": 0.001,
692
+ "loss": 2.4971,
693
+ "step": 570
694
+ },
695
+ {
696
+ "epoch": 0.38,
697
+ "learning_rate": 0.001,
698
+ "loss": 2.6251,
699
+ "step": 575
700
+ },
701
+ {
702
+ "epoch": 0.38,
703
+ "learning_rate": 0.001,
704
+ "loss": 2.5784,
705
+ "step": 580
706
+ },
707
+ {
708
+ "epoch": 0.38,
709
+ "learning_rate": 0.001,
710
+ "loss": 2.3878,
711
+ "step": 585
712
+ },
713
+ {
714
+ "epoch": 0.39,
715
+ "learning_rate": 0.001,
716
+ "loss": 2.4271,
717
+ "step": 590
718
+ },
719
+ {
720
+ "epoch": 0.39,
721
+ "learning_rate": 0.001,
722
+ "loss": 2.6751,
723
+ "step": 595
724
+ },
725
+ {
726
+ "epoch": 0.39,
727
+ "learning_rate": 0.001,
728
+ "loss": 2.17,
729
+ "step": 600
730
+ },
731
+ {
732
+ "epoch": 0.4,
733
+ "learning_rate": 0.001,
734
+ "loss": 2.0794,
735
+ "step": 605
736
+ },
737
+ {
738
+ "epoch": 0.4,
739
+ "learning_rate": 0.001,
740
+ "loss": 2.6073,
741
+ "step": 610
742
+ },
743
+ {
744
+ "epoch": 0.4,
745
+ "learning_rate": 0.001,
746
+ "loss": 2.6717,
747
+ "step": 615
748
+ },
749
+ {
750
+ "epoch": 0.41,
751
+ "learning_rate": 0.001,
752
+ "loss": 2.8236,
753
+ "step": 620
754
+ },
755
+ {
756
+ "epoch": 0.41,
757
+ "learning_rate": 0.001,
758
+ "loss": 2.4193,
759
+ "step": 625
760
+ },
761
+ {
762
+ "epoch": 0.41,
763
+ "learning_rate": 0.001,
764
+ "loss": 2.7181,
765
+ "step": 630
766
+ },
767
+ {
768
+ "epoch": 0.42,
769
+ "learning_rate": 0.001,
770
+ "loss": 2.6567,
771
+ "step": 635
772
+ },
773
+ {
774
+ "epoch": 0.42,
775
+ "learning_rate": 0.001,
776
+ "loss": 2.1919,
777
+ "step": 640
778
+ },
779
+ {
780
+ "epoch": 0.42,
781
+ "learning_rate": 0.001,
782
+ "loss": 2.5645,
783
+ "step": 645
784
+ },
785
+ {
786
+ "epoch": 0.43,
787
+ "learning_rate": 0.001,
788
+ "loss": 2.3313,
789
+ "step": 650
790
+ },
791
+ {
792
+ "epoch": 0.43,
793
+ "learning_rate": 0.001,
794
+ "loss": 2.533,
795
+ "step": 655
796
+ },
797
+ {
798
+ "epoch": 0.43,
799
+ "learning_rate": 0.001,
800
+ "loss": 2.621,
801
+ "step": 660
802
+ },
803
+ {
804
+ "epoch": 0.44,
805
+ "learning_rate": 0.001,
806
+ "loss": 2.5693,
807
+ "step": 665
808
+ },
809
+ {
810
+ "epoch": 0.44,
811
+ "learning_rate": 0.001,
812
+ "loss": 2.6943,
813
+ "step": 670
814
+ },
815
+ {
816
+ "epoch": 0.44,
817
+ "learning_rate": 0.001,
818
+ "loss": 2.2715,
819
+ "step": 675
820
+ },
821
+ {
822
+ "epoch": 0.45,
823
+ "learning_rate": 0.001,
824
+ "loss": 2.5614,
825
+ "step": 680
826
+ },
827
+ {
828
+ "epoch": 0.45,
829
+ "learning_rate": 0.001,
830
+ "loss": 2.5784,
831
+ "step": 685
832
+ },
833
+ {
834
+ "epoch": 0.45,
835
+ "learning_rate": 0.001,
836
+ "loss": 2.0613,
837
+ "step": 690
838
+ },
839
+ {
840
+ "epoch": 0.45,
841
+ "learning_rate": 0.001,
842
+ "loss": 2.582,
843
+ "step": 695
844
+ },
845
+ {
846
+ "epoch": 0.46,
847
+ "learning_rate": 0.001,
848
+ "loss": 2.5178,
849
+ "step": 700
850
+ },
851
+ {
852
+ "epoch": 0.46,
853
+ "learning_rate": 0.001,
854
+ "loss": 2.432,
855
+ "step": 705
856
+ },
857
+ {
858
+ "epoch": 0.46,
859
+ "learning_rate": 0.001,
860
+ "loss": 2.1979,
861
+ "step": 710
862
+ },
863
+ {
864
+ "epoch": 0.47,
865
+ "learning_rate": 0.001,
866
+ "loss": 2.4317,
867
+ "step": 715
868
+ },
869
+ {
870
+ "epoch": 0.47,
871
+ "learning_rate": 0.001,
872
+ "loss": 2.285,
873
+ "step": 720
874
+ },
875
+ {
876
+ "epoch": 0.47,
877
+ "learning_rate": 0.001,
878
+ "loss": 2.6127,
879
+ "step": 725
880
+ },
881
+ {
882
+ "epoch": 0.48,
883
+ "learning_rate": 0.001,
884
+ "loss": 2.6221,
885
+ "step": 730
886
+ },
887
+ {
888
+ "epoch": 0.48,
889
+ "learning_rate": 0.001,
890
+ "loss": 2.7519,
891
+ "step": 735
892
+ },
893
+ {
894
+ "epoch": 0.48,
895
+ "learning_rate": 0.001,
896
+ "loss": 2.7351,
897
+ "step": 740
898
+ },
899
+ {
900
+ "epoch": 0.49,
901
+ "learning_rate": 0.001,
902
+ "loss": 2.5224,
903
+ "step": 745
904
+ },
905
+ {
906
+ "epoch": 0.49,
907
+ "learning_rate": 0.001,
908
+ "loss": 2.5145,
909
+ "step": 750
910
+ },
911
+ {
912
+ "epoch": 0.49,
913
+ "learning_rate": 0.001,
914
+ "loss": 2.5122,
915
+ "step": 755
916
+ },
917
+ {
918
+ "epoch": 0.5,
919
+ "learning_rate": 0.001,
920
+ "loss": 2.2971,
921
+ "step": 760
922
+ },
923
+ {
924
+ "epoch": 0.5,
925
+ "learning_rate": 0.001,
926
+ "loss": 2.5628,
927
+ "step": 765
928
+ },
929
+ {
930
+ "epoch": 0.5,
931
+ "learning_rate": 0.001,
932
+ "loss": 2.5803,
933
+ "step": 770
934
+ },
935
+ {
936
+ "epoch": 0.51,
937
+ "learning_rate": 0.001,
938
+ "loss": 2.5209,
939
+ "step": 775
940
+ },
941
+ {
942
+ "epoch": 0.51,
943
+ "learning_rate": 0.001,
944
+ "loss": 2.5051,
945
+ "step": 780
946
+ },
947
+ {
948
+ "epoch": 0.51,
949
+ "learning_rate": 0.001,
950
+ "loss": 2.5275,
951
+ "step": 785
952
+ },
953
+ {
954
+ "epoch": 0.52,
955
+ "learning_rate": 0.001,
956
+ "loss": 2.5019,
957
+ "step": 790
958
+ },
959
+ {
960
+ "epoch": 0.52,
961
+ "learning_rate": 0.001,
962
+ "loss": 2.1714,
963
+ "step": 795
964
+ },
965
+ {
966
+ "epoch": 0.52,
967
+ "learning_rate": 0.001,
968
+ "loss": 2.87,
969
+ "step": 800
970
+ },
971
+ {
972
+ "epoch": 0.53,
973
+ "learning_rate": 0.001,
974
+ "loss": 2.6468,
975
+ "step": 805
976
+ },
977
+ {
978
+ "epoch": 0.53,
979
+ "learning_rate": 0.001,
980
+ "loss": 2.4115,
981
+ "step": 810
982
+ },
983
+ {
984
+ "epoch": 0.53,
985
+ "learning_rate": 0.001,
986
+ "loss": 2.5377,
987
+ "step": 815
988
+ },
989
+ {
990
+ "epoch": 0.54,
991
+ "learning_rate": 0.001,
992
+ "loss": 2.4986,
993
+ "step": 820
994
+ },
995
+ {
996
+ "epoch": 0.54,
997
+ "learning_rate": 0.001,
998
+ "loss": 2.6485,
999
+ "step": 825
1000
+ },
1001
+ {
1002
+ "epoch": 0.54,
1003
+ "learning_rate": 0.001,
1004
+ "loss": 2.6314,
1005
+ "step": 830
1006
+ },
1007
+ {
1008
+ "epoch": 0.55,
1009
+ "learning_rate": 0.001,
1010
+ "loss": 2.3516,
1011
+ "step": 835
1012
+ },
1013
+ {
1014
+ "epoch": 0.55,
1015
+ "learning_rate": 0.001,
1016
+ "loss": 2.39,
1017
+ "step": 840
1018
+ },
1019
+ {
1020
+ "epoch": 0.55,
1021
+ "learning_rate": 0.001,
1022
+ "loss": 2.3759,
1023
+ "step": 845
1024
+ },
1025
+ {
1026
+ "epoch": 0.56,
1027
+ "learning_rate": 0.001,
1028
+ "loss": 2.5348,
1029
+ "step": 850
1030
+ },
1031
+ {
1032
+ "epoch": 0.56,
1033
+ "learning_rate": 0.001,
1034
+ "loss": 2.6843,
1035
+ "step": 855
1036
+ },
1037
+ {
1038
+ "epoch": 0.56,
1039
+ "learning_rate": 0.001,
1040
+ "loss": 2.6289,
1041
+ "step": 860
1042
+ },
1043
+ {
1044
+ "epoch": 0.57,
1045
+ "learning_rate": 0.001,
1046
+ "loss": 2.4023,
1047
+ "step": 865
1048
+ },
1049
+ {
1050
+ "epoch": 0.57,
1051
+ "learning_rate": 0.001,
1052
+ "loss": 2.5979,
1053
+ "step": 870
1054
+ },
1055
+ {
1056
+ "epoch": 0.57,
1057
+ "learning_rate": 0.001,
1058
+ "loss": 2.4683,
1059
+ "step": 875
1060
+ },
1061
+ {
1062
+ "epoch": 0.58,
1063
+ "learning_rate": 0.001,
1064
+ "loss": 2.7099,
1065
+ "step": 880
1066
+ },
1067
+ {
1068
+ "epoch": 0.58,
1069
+ "learning_rate": 0.001,
1070
+ "loss": 2.3129,
1071
+ "step": 885
1072
+ },
1073
+ {
1074
+ "epoch": 0.58,
1075
+ "learning_rate": 0.001,
1076
+ "loss": 2.4508,
1077
+ "step": 890
1078
+ },
1079
+ {
1080
+ "epoch": 0.59,
1081
+ "learning_rate": 0.001,
1082
+ "loss": 2.6484,
1083
+ "step": 895
1084
+ },
1085
+ {
1086
+ "epoch": 0.59,
1087
+ "learning_rate": 0.001,
1088
+ "loss": 2.4541,
1089
+ "step": 900
1090
+ },
1091
+ {
1092
+ "epoch": 0.59,
1093
+ "learning_rate": 0.001,
1094
+ "loss": 2.5101,
1095
+ "step": 905
1096
+ },
1097
+ {
1098
+ "epoch": 0.6,
1099
+ "learning_rate": 0.001,
1100
+ "loss": 2.6002,
1101
+ "step": 910
1102
+ },
1103
+ {
1104
+ "epoch": 0.6,
1105
+ "learning_rate": 0.001,
1106
+ "loss": 2.742,
1107
+ "step": 915
1108
+ },
1109
+ {
1110
+ "epoch": 0.6,
1111
+ "learning_rate": 0.001,
1112
+ "loss": 2.4772,
1113
+ "step": 920
1114
+ },
1115
+ {
1116
+ "epoch": 0.61,
1117
+ "learning_rate": 0.001,
1118
+ "loss": 2.4328,
1119
+ "step": 925
1120
+ },
1121
+ {
1122
+ "epoch": 0.61,
1123
+ "learning_rate": 0.001,
1124
+ "loss": 2.7404,
1125
+ "step": 930
1126
+ },
1127
+ {
1128
+ "epoch": 0.61,
1129
+ "learning_rate": 0.001,
1130
+ "loss": 2.5969,
1131
+ "step": 935
1132
+ },
1133
+ {
1134
+ "epoch": 0.62,
1135
+ "learning_rate": 0.001,
1136
+ "loss": 2.1367,
1137
+ "step": 940
1138
+ },
1139
+ {
1140
+ "epoch": 0.62,
1141
+ "learning_rate": 0.001,
1142
+ "loss": 2.703,
1143
+ "step": 945
1144
+ },
1145
+ {
1146
+ "epoch": 0.62,
1147
+ "learning_rate": 0.001,
1148
+ "loss": 2.5638,
1149
+ "step": 950
1150
+ },
1151
+ {
1152
+ "epoch": 0.62,
1153
+ "learning_rate": 0.001,
1154
+ "loss": 1.8322,
1155
+ "step": 955
1156
+ },
1157
+ {
1158
+ "epoch": 0.63,
1159
+ "learning_rate": 0.001,
1160
+ "loss": 2.5764,
1161
+ "step": 960
1162
+ },
1163
+ {
1164
+ "epoch": 0.63,
1165
+ "learning_rate": 0.001,
1166
+ "loss": 2.4679,
1167
+ "step": 965
1168
+ },
1169
+ {
1170
+ "epoch": 0.63,
1171
+ "learning_rate": 0.001,
1172
+ "loss": 2.1691,
1173
+ "step": 970
1174
+ },
1175
+ {
1176
+ "epoch": 0.64,
1177
+ "learning_rate": 0.001,
1178
+ "loss": 2.3252,
1179
+ "step": 975
1180
+ },
1181
+ {
1182
+ "epoch": 0.64,
1183
+ "learning_rate": 0.001,
1184
+ "loss": 2.3988,
1185
+ "step": 980
1186
+ },
1187
+ {
1188
+ "epoch": 0.64,
1189
+ "learning_rate": 0.001,
1190
+ "loss": 2.221,
1191
+ "step": 985
1192
+ },
1193
+ {
1194
+ "epoch": 0.65,
1195
+ "learning_rate": 0.001,
1196
+ "loss": 2.4715,
1197
+ "step": 990
1198
+ },
1199
+ {
1200
+ "epoch": 0.65,
1201
+ "learning_rate": 0.001,
1202
+ "loss": 2.2479,
1203
+ "step": 995
1204
+ },
1205
+ {
1206
+ "epoch": 0.65,
1207
+ "learning_rate": 0.001,
1208
+ "loss": 2.3859,
1209
+ "step": 1000
1210
+ },
1211
+ {
1212
+ "epoch": 0.66,
1213
+ "learning_rate": 0.001,
1214
+ "loss": 2.7889,
1215
+ "step": 1005
1216
+ },
1217
+ {
1218
+ "epoch": 0.66,
1219
+ "learning_rate": 0.001,
1220
+ "loss": 2.625,
1221
+ "step": 1010
1222
+ },
1223
+ {
1224
+ "epoch": 0.66,
1225
+ "learning_rate": 0.001,
1226
+ "loss": 2.324,
1227
+ "step": 1015
1228
+ },
1229
+ {
1230
+ "epoch": 0.67,
1231
+ "learning_rate": 0.001,
1232
+ "loss": 2.5879,
1233
+ "step": 1020
1234
+ },
1235
+ {
1236
+ "epoch": 0.67,
1237
+ "learning_rate": 0.001,
1238
+ "loss": 2.4721,
1239
+ "step": 1025
1240
+ },
1241
+ {
1242
+ "epoch": 0.67,
1243
+ "learning_rate": 0.001,
1244
+ "loss": 2.6365,
1245
+ "step": 1030
1246
+ },
1247
+ {
1248
+ "epoch": 0.68,
1249
+ "learning_rate": 0.001,
1250
+ "loss": 2.6356,
1251
+ "step": 1035
1252
+ },
1253
+ {
1254
+ "epoch": 0.68,
1255
+ "learning_rate": 0.001,
1256
+ "loss": 2.4022,
1257
+ "step": 1040
1258
+ },
1259
+ {
1260
+ "epoch": 0.68,
1261
+ "learning_rate": 0.001,
1262
+ "loss": 2.7109,
1263
+ "step": 1045
1264
+ },
1265
+ {
1266
+ "epoch": 0.69,
1267
+ "learning_rate": 0.001,
1268
+ "loss": 2.373,
1269
+ "step": 1050
1270
+ },
1271
+ {
1272
+ "epoch": 0.69,
1273
+ "learning_rate": 0.001,
1274
+ "loss": 2.523,
1275
+ "step": 1055
1276
+ },
1277
+ {
1278
+ "epoch": 0.69,
1279
+ "learning_rate": 0.001,
1280
+ "loss": 2.536,
1281
+ "step": 1060
1282
+ },
1283
+ {
1284
+ "epoch": 0.7,
1285
+ "learning_rate": 0.001,
1286
+ "loss": 2.6047,
1287
+ "step": 1065
1288
+ },
1289
+ {
1290
+ "epoch": 0.7,
1291
+ "learning_rate": 0.001,
1292
+ "loss": 2.5583,
1293
+ "step": 1070
1294
+ },
1295
+ {
1296
+ "epoch": 0.7,
1297
+ "learning_rate": 0.001,
1298
+ "loss": 2.7925,
1299
+ "step": 1075
1300
+ },
1301
+ {
1302
+ "epoch": 0.71,
1303
+ "learning_rate": 0.001,
1304
+ "loss": 2.0572,
1305
+ "step": 1080
1306
+ },
1307
+ {
1308
+ "epoch": 0.71,
1309
+ "learning_rate": 0.001,
1310
+ "loss": 2.3024,
1311
+ "step": 1085
1312
+ },
1313
+ {
1314
+ "epoch": 0.71,
1315
+ "learning_rate": 0.001,
1316
+ "loss": 2.0677,
1317
+ "step": 1090
1318
+ },
1319
+ {
1320
+ "epoch": 0.72,
1321
+ "learning_rate": 0.001,
1322
+ "loss": 2.5241,
1323
+ "step": 1095
1324
+ },
1325
+ {
1326
+ "epoch": 0.72,
1327
+ "learning_rate": 0.001,
1328
+ "loss": 2.7447,
1329
+ "step": 1100
1330
+ },
1331
+ {
1332
+ "epoch": 0.72,
1333
+ "learning_rate": 0.001,
1334
+ "loss": 2.6435,
1335
+ "step": 1105
1336
+ },
1337
+ {
1338
+ "epoch": 0.73,
1339
+ "learning_rate": 0.001,
1340
+ "loss": 2.4226,
1341
+ "step": 1110
1342
+ },
1343
+ {
1344
+ "epoch": 0.73,
1345
+ "learning_rate": 0.001,
1346
+ "loss": 2.6891,
1347
+ "step": 1115
1348
+ },
1349
+ {
1350
+ "epoch": 0.73,
1351
+ "learning_rate": 0.001,
1352
+ "loss": 2.458,
1353
+ "step": 1120
1354
+ },
1355
+ {
1356
+ "epoch": 0.74,
1357
+ "learning_rate": 0.001,
1358
+ "loss": 2.6884,
1359
+ "step": 1125
1360
+ },
1361
+ {
1362
+ "epoch": 0.74,
1363
+ "learning_rate": 0.001,
1364
+ "loss": 2.7058,
1365
+ "step": 1130
1366
+ },
1367
+ {
1368
+ "epoch": 0.74,
1369
+ "learning_rate": 0.001,
1370
+ "loss": 2.5828,
1371
+ "step": 1135
1372
+ },
1373
+ {
1374
+ "epoch": 0.75,
1375
+ "learning_rate": 0.001,
1376
+ "loss": 2.7107,
1377
+ "step": 1140
1378
+ },
1379
+ {
1380
+ "epoch": 0.75,
1381
+ "learning_rate": 0.001,
1382
+ "loss": 2.3635,
1383
+ "step": 1145
1384
+ },
1385
+ {
1386
+ "epoch": 0.75,
1387
+ "learning_rate": 0.001,
1388
+ "loss": 2.5258,
1389
+ "step": 1150
1390
+ },
1391
+ {
1392
+ "epoch": 0.76,
1393
+ "learning_rate": 0.001,
1394
+ "loss": 2.6046,
1395
+ "step": 1155
1396
+ },
1397
+ {
1398
+ "epoch": 0.76,
1399
+ "learning_rate": 0.001,
1400
+ "loss": 2.5215,
1401
+ "step": 1160
1402
+ },
1403
+ {
1404
+ "epoch": 0.76,
1405
+ "learning_rate": 0.001,
1406
+ "loss": 2.1417,
1407
+ "step": 1165
1408
+ },
1409
+ {
1410
+ "epoch": 0.77,
1411
+ "learning_rate": 0.001,
1412
+ "loss": 2.5903,
1413
+ "step": 1170
1414
+ },
1415
+ {
1416
+ "epoch": 0.77,
1417
+ "learning_rate": 0.001,
1418
+ "loss": 2.5376,
1419
+ "step": 1175
1420
+ },
1421
+ {
1422
+ "epoch": 0.77,
1423
+ "learning_rate": 0.001,
1424
+ "loss": 2.5716,
1425
+ "step": 1180
1426
+ },
1427
+ {
1428
+ "epoch": 0.78,
1429
+ "learning_rate": 0.001,
1430
+ "loss": 2.5904,
1431
+ "step": 1185
1432
+ },
1433
+ {
1434
+ "epoch": 0.78,
1435
+ "learning_rate": 0.001,
1436
+ "loss": 2.6511,
1437
+ "step": 1190
1438
+ },
1439
+ {
1440
+ "epoch": 0.78,
1441
+ "learning_rate": 0.001,
1442
+ "loss": 2.1679,
1443
+ "step": 1195
1444
+ },
1445
+ {
1446
+ "epoch": 0.79,
1447
+ "learning_rate": 0.001,
1448
+ "loss": 2.4169,
1449
+ "step": 1200
1450
+ },
1451
+ {
1452
+ "epoch": 0.79,
1453
+ "learning_rate": 0.001,
1454
+ "loss": 2.7519,
1455
+ "step": 1205
1456
+ },
1457
+ {
1458
+ "epoch": 0.79,
1459
+ "learning_rate": 0.001,
1460
+ "loss": 2.4385,
1461
+ "step": 1210
1462
+ },
1463
+ {
1464
+ "epoch": 0.8,
1465
+ "learning_rate": 0.001,
1466
+ "loss": 1.9145,
1467
+ "step": 1215
1468
+ },
1469
+ {
1470
+ "epoch": 0.8,
1471
+ "learning_rate": 0.001,
1472
+ "loss": 2.5898,
1473
+ "step": 1220
1474
+ },
1475
+ {
1476
+ "epoch": 0.8,
1477
+ "learning_rate": 0.001,
1478
+ "loss": 2.4768,
1479
+ "step": 1225
1480
+ },
1481
+ {
1482
+ "epoch": 0.8,
1483
+ "learning_rate": 0.001,
1484
+ "loss": 2.5546,
1485
+ "step": 1230
1486
+ },
1487
+ {
1488
+ "epoch": 0.81,
1489
+ "learning_rate": 0.001,
1490
+ "loss": 2.5279,
1491
+ "step": 1235
1492
+ },
1493
+ {
1494
+ "epoch": 0.81,
1495
+ "learning_rate": 0.001,
1496
+ "loss": 2.498,
1497
+ "step": 1240
1498
+ },
1499
+ {
1500
+ "epoch": 0.81,
1501
+ "learning_rate": 0.001,
1502
+ "loss": 2.4277,
1503
+ "step": 1245
1504
+ },
1505
+ {
1506
+ "epoch": 0.82,
1507
+ "learning_rate": 0.001,
1508
+ "loss": 2.9934,
1509
+ "step": 1250
1510
+ },
1511
+ {
1512
+ "epoch": 0.82,
1513
+ "learning_rate": 0.001,
1514
+ "loss": 2.3367,
1515
+ "step": 1255
1516
+ },
1517
+ {
1518
+ "epoch": 0.82,
1519
+ "learning_rate": 0.001,
1520
+ "loss": 2.012,
1521
+ "step": 1260
1522
+ },
1523
+ {
1524
+ "epoch": 0.83,
1525
+ "learning_rate": 0.001,
1526
+ "loss": 2.4148,
1527
+ "step": 1265
1528
+ },
1529
+ {
1530
+ "epoch": 0.83,
1531
+ "learning_rate": 0.001,
1532
+ "loss": 2.3207,
1533
+ "step": 1270
1534
+ },
1535
+ {
1536
+ "epoch": 0.83,
1537
+ "learning_rate": 0.001,
1538
+ "loss": 2.5629,
1539
+ "step": 1275
1540
+ },
1541
+ {
1542
+ "epoch": 0.84,
1543
+ "learning_rate": 0.001,
1544
+ "loss": 2.4338,
1545
+ "step": 1280
1546
+ },
1547
+ {
1548
+ "epoch": 0.84,
1549
+ "learning_rate": 0.001,
1550
+ "loss": 2.4612,
1551
+ "step": 1285
1552
+ },
1553
+ {
1554
+ "epoch": 0.84,
1555
+ "learning_rate": 0.001,
1556
+ "loss": 2.5406,
1557
+ "step": 1290
1558
+ },
1559
+ {
1560
+ "epoch": 0.85,
1561
+ "learning_rate": 0.001,
1562
+ "loss": 2.5438,
1563
+ "step": 1295
1564
+ },
1565
+ {
1566
+ "epoch": 0.85,
1567
+ "learning_rate": 0.001,
1568
+ "loss": 2.6348,
1569
+ "step": 1300
1570
+ },
1571
+ {
1572
+ "epoch": 0.85,
1573
+ "learning_rate": 0.001,
1574
+ "loss": 2.1436,
1575
+ "step": 1305
1576
+ },
1577
+ {
1578
+ "epoch": 0.86,
1579
+ "learning_rate": 0.001,
1580
+ "loss": 2.4825,
1581
+ "step": 1310
1582
+ },
1583
+ {
1584
+ "epoch": 0.86,
1585
+ "learning_rate": 0.001,
1586
+ "loss": 2.2579,
1587
+ "step": 1315
1588
+ },
1589
+ {
1590
+ "epoch": 0.86,
1591
+ "learning_rate": 0.001,
1592
+ "loss": 2.5234,
1593
+ "step": 1320
1594
+ },
1595
+ {
1596
+ "epoch": 0.87,
1597
+ "learning_rate": 0.001,
1598
+ "loss": 2.5127,
1599
+ "step": 1325
1600
+ },
1601
+ {
1602
+ "epoch": 0.87,
1603
+ "learning_rate": 0.001,
1604
+ "loss": 2.3415,
1605
+ "step": 1330
1606
+ },
1607
+ {
1608
+ "epoch": 0.87,
1609
+ "learning_rate": 0.001,
1610
+ "loss": 2.4005,
1611
+ "step": 1335
1612
+ },
1613
+ {
1614
+ "epoch": 0.88,
1615
+ "learning_rate": 0.001,
1616
+ "loss": 2.4731,
1617
+ "step": 1340
1618
+ },
1619
+ {
1620
+ "epoch": 0.88,
1621
+ "learning_rate": 0.001,
1622
+ "loss": 2.8025,
1623
+ "step": 1345
1624
+ },
1625
+ {
1626
+ "epoch": 0.88,
1627
+ "learning_rate": 0.001,
1628
+ "loss": 2.1733,
1629
+ "step": 1350
1630
+ },
1631
+ {
1632
+ "epoch": 0.89,
1633
+ "learning_rate": 0.001,
1634
+ "loss": 2.5599,
1635
+ "step": 1355
1636
+ },
1637
+ {
1638
+ "epoch": 0.89,
1639
+ "learning_rate": 0.001,
1640
+ "loss": 2.6287,
1641
+ "step": 1360
1642
+ },
1643
+ {
1644
+ "epoch": 0.89,
1645
+ "learning_rate": 0.001,
1646
+ "loss": 2.5367,
1647
+ "step": 1365
1648
+ },
1649
+ {
1650
+ "epoch": 0.9,
1651
+ "learning_rate": 0.001,
1652
+ "loss": 2.3331,
1653
+ "step": 1370
1654
+ },
1655
+ {
1656
+ "epoch": 0.9,
1657
+ "learning_rate": 0.001,
1658
+ "loss": 2.2061,
1659
+ "step": 1375
1660
+ },
1661
+ {
1662
+ "epoch": 0.9,
1663
+ "learning_rate": 0.001,
1664
+ "loss": 2.3905,
1665
+ "step": 1380
1666
+ },
1667
+ {
1668
+ "epoch": 0.91,
1669
+ "learning_rate": 0.001,
1670
+ "loss": 2.6162,
1671
+ "step": 1385
1672
+ },
1673
+ {
1674
+ "epoch": 0.91,
1675
+ "learning_rate": 0.001,
1676
+ "loss": 2.2712,
1677
+ "step": 1390
1678
+ },
1679
+ {
1680
+ "epoch": 0.91,
1681
+ "learning_rate": 0.001,
1682
+ "loss": 2.3674,
1683
+ "step": 1395
1684
+ },
1685
+ {
1686
+ "epoch": 0.92,
1687
+ "learning_rate": 0.001,
1688
+ "loss": 2.4791,
1689
+ "step": 1400
1690
+ },
1691
+ {
1692
+ "epoch": 0.92,
1693
+ "learning_rate": 0.001,
1694
+ "loss": 2.6425,
1695
+ "step": 1405
1696
+ },
1697
+ {
1698
+ "epoch": 0.92,
1699
+ "learning_rate": 0.001,
1700
+ "loss": 2.4496,
1701
+ "step": 1410
1702
+ },
1703
+ {
1704
+ "epoch": 0.93,
1705
+ "learning_rate": 0.001,
1706
+ "loss": 2.5499,
1707
+ "step": 1415
1708
+ },
1709
+ {
1710
+ "epoch": 0.93,
1711
+ "learning_rate": 0.001,
1712
+ "loss": 2.5993,
1713
+ "step": 1420
1714
+ },
1715
+ {
1716
+ "epoch": 0.93,
1717
+ "learning_rate": 0.001,
1718
+ "loss": 2.5543,
1719
+ "step": 1425
1720
+ },
1721
+ {
1722
+ "epoch": 0.94,
1723
+ "learning_rate": 0.001,
1724
+ "loss": 2.2981,
1725
+ "step": 1430
1726
+ },
1727
+ {
1728
+ "epoch": 0.94,
1729
+ "learning_rate": 0.001,
1730
+ "loss": 2.7974,
1731
+ "step": 1435
1732
+ },
1733
+ {
1734
+ "epoch": 0.94,
1735
+ "learning_rate": 0.001,
1736
+ "loss": 2.0898,
1737
+ "step": 1440
1738
+ },
1739
+ {
1740
+ "epoch": 0.95,
1741
+ "learning_rate": 0.001,
1742
+ "loss": 2.561,
1743
+ "step": 1445
1744
+ },
1745
+ {
1746
+ "epoch": 0.95,
1747
+ "learning_rate": 0.001,
1748
+ "loss": 2.2922,
1749
+ "step": 1450
1750
+ },
1751
+ {
1752
+ "epoch": 0.95,
1753
+ "learning_rate": 0.001,
1754
+ "loss": 2.3195,
1755
+ "step": 1455
1756
+ },
1757
+ {
1758
+ "epoch": 0.96,
1759
+ "learning_rate": 0.001,
1760
+ "loss": 2.4302,
1761
+ "step": 1460
1762
+ },
1763
+ {
1764
+ "epoch": 0.96,
1765
+ "learning_rate": 0.001,
1766
+ "loss": 2.6357,
1767
+ "step": 1465
1768
+ },
1769
+ {
1770
+ "epoch": 0.96,
1771
+ "learning_rate": 0.001,
1772
+ "loss": 2.1727,
1773
+ "step": 1470
1774
+ },
1775
+ {
1776
+ "epoch": 0.97,
1777
+ "learning_rate": 0.001,
1778
+ "loss": 2.5076,
1779
+ "step": 1475
1780
+ },
1781
+ {
1782
+ "epoch": 0.97,
1783
+ "learning_rate": 0.001,
1784
+ "loss": 2.7291,
1785
+ "step": 1480
1786
+ },
1787
+ {
1788
+ "epoch": 0.97,
1789
+ "learning_rate": 0.001,
1790
+ "loss": 2.443,
1791
+ "step": 1485
1792
+ },
1793
+ {
1794
+ "epoch": 0.98,
1795
+ "learning_rate": 0.001,
1796
+ "loss": 2.4889,
1797
+ "step": 1490
1798
+ },
1799
+ {
1800
+ "epoch": 0.98,
1801
+ "learning_rate": 0.001,
1802
+ "loss": 2.4709,
1803
+ "step": 1495
1804
+ },
1805
+ {
1806
+ "epoch": 0.98,
1807
+ "learning_rate": 0.001,
1808
+ "loss": 2.3124,
1809
+ "step": 1500
1810
+ },
1811
+ {
1812
+ "epoch": 0.98,
1813
+ "learning_rate": 0.001,
1814
+ "loss": 2.5515,
1815
+ "step": 1505
1816
+ },
1817
+ {
1818
+ "epoch": 0.99,
1819
+ "learning_rate": 0.001,
1820
+ "loss": 2.3861,
1821
+ "step": 1510
1822
+ },
1823
+ {
1824
+ "epoch": 0.99,
1825
+ "learning_rate": 0.001,
1826
+ "loss": 2.4269,
1827
+ "step": 1515
1828
+ },
1829
+ {
1830
+ "epoch": 0.99,
1831
+ "learning_rate": 0.001,
1832
+ "loss": 2.4074,
1833
+ "step": 1520
1834
+ },
1835
+ {
1836
+ "epoch": 1.0,
1837
+ "learning_rate": 0.001,
1838
+ "loss": 2.2783,
1839
+ "step": 1525
1840
+ },
1841
+ {
1842
+ "epoch": 1.0,
1843
+ "learning_rate": 0.001,
1844
+ "loss": 2.4139,
1845
+ "step": 1530
1846
+ },
1847
+ {
1848
+ "epoch": 1.0,
1849
+ "learning_rate": 0.001,
1850
+ "loss": 1.9251,
1851
+ "step": 1535
1852
+ },
1853
+ {
1854
+ "epoch": 1.01,
1855
+ "learning_rate": 0.001,
1856
+ "loss": 2.1038,
1857
+ "step": 1540
1858
+ },
1859
+ {
1860
+ "epoch": 1.01,
1861
+ "learning_rate": 0.001,
1862
+ "loss": 1.9436,
1863
+ "step": 1545
1864
+ },
1865
+ {
1866
+ "epoch": 1.01,
1867
+ "learning_rate": 0.001,
1868
+ "loss": 1.9581,
1869
+ "step": 1550
1870
+ },
1871
+ {
1872
+ "epoch": 1.02,
1873
+ "learning_rate": 0.001,
1874
+ "loss": 2.1705,
1875
+ "step": 1555
1876
+ },
1877
+ {
1878
+ "epoch": 1.02,
1879
+ "learning_rate": 0.001,
1880
+ "loss": 2.1393,
1881
+ "step": 1560
1882
+ },
1883
+ {
1884
+ "epoch": 1.02,
1885
+ "learning_rate": 0.001,
1886
+ "loss": 1.741,
1887
+ "step": 1565
1888
+ },
1889
+ {
1890
+ "epoch": 1.03,
1891
+ "learning_rate": 0.001,
1892
+ "loss": 1.9232,
1893
+ "step": 1570
1894
+ },
1895
+ {
1896
+ "epoch": 1.03,
1897
+ "learning_rate": 0.001,
1898
+ "loss": 1.9046,
1899
+ "step": 1575
1900
+ },
1901
+ {
1902
+ "epoch": 1.03,
1903
+ "learning_rate": 0.001,
1904
+ "loss": 1.8102,
1905
+ "step": 1580
1906
+ },
1907
+ {
1908
+ "epoch": 1.04,
1909
+ "learning_rate": 0.001,
1910
+ "loss": 1.7362,
1911
+ "step": 1585
1912
+ },
1913
+ {
1914
+ "epoch": 1.04,
1915
+ "learning_rate": 0.001,
1916
+ "loss": 1.8057,
1917
+ "step": 1590
1918
+ },
1919
+ {
1920
+ "epoch": 1.04,
1921
+ "learning_rate": 0.001,
1922
+ "loss": 2.0777,
1923
+ "step": 1595
1924
+ },
1925
+ {
1926
+ "epoch": 1.05,
1927
+ "learning_rate": 0.001,
1928
+ "loss": 2.1163,
1929
+ "step": 1600
1930
+ },
1931
+ {
1932
+ "epoch": 1.05,
1933
+ "learning_rate": 0.001,
1934
+ "loss": 1.8468,
1935
+ "step": 1605
1936
+ },
1937
+ {
1938
+ "epoch": 1.05,
1939
+ "learning_rate": 0.001,
1940
+ "loss": 2.3334,
1941
+ "step": 1610
1942
+ },
1943
+ {
1944
+ "epoch": 1.06,
1945
+ "learning_rate": 0.001,
1946
+ "loss": 2.1232,
1947
+ "step": 1615
1948
+ },
1949
+ {
1950
+ "epoch": 1.06,
1951
+ "learning_rate": 0.001,
1952
+ "loss": 1.7049,
1953
+ "step": 1620
1954
+ },
1955
+ {
1956
+ "epoch": 1.06,
1957
+ "learning_rate": 0.001,
1958
+ "loss": 2.1545,
1959
+ "step": 1625
1960
+ },
1961
+ {
1962
+ "epoch": 1.07,
1963
+ "learning_rate": 0.001,
1964
+ "loss": 2.3166,
1965
+ "step": 1630
1966
+ },
1967
+ {
1968
+ "epoch": 1.07,
1969
+ "learning_rate": 0.001,
1970
+ "loss": 2.103,
1971
+ "step": 1635
1972
+ },
1973
+ {
1974
+ "epoch": 1.07,
1975
+ "learning_rate": 0.001,
1976
+ "loss": 1.9295,
1977
+ "step": 1640
1978
+ },
1979
+ {
1980
+ "epoch": 1.08,
1981
+ "learning_rate": 0.001,
1982
+ "loss": 2.0598,
1983
+ "step": 1645
1984
+ },
1985
+ {
1986
+ "epoch": 1.08,
1987
+ "learning_rate": 0.001,
1988
+ "loss": 2.3646,
1989
+ "step": 1650
1990
+ },
1991
+ {
1992
+ "epoch": 1.08,
1993
+ "learning_rate": 0.001,
1994
+ "loss": 2.1853,
1995
+ "step": 1655
1996
+ },
1997
+ {
1998
+ "epoch": 1.09,
1999
+ "learning_rate": 0.001,
2000
+ "loss": 2.0635,
2001
+ "step": 1660
2002
+ },
2003
+ {
2004
+ "epoch": 1.09,
2005
+ "learning_rate": 0.001,
2006
+ "loss": 1.9439,
2007
+ "step": 1665
2008
+ },
2009
+ {
2010
+ "epoch": 1.09,
2011
+ "learning_rate": 0.001,
2012
+ "loss": 2.469,
2013
+ "step": 1670
2014
+ },
2015
+ {
2016
+ "epoch": 1.1,
2017
+ "learning_rate": 0.001,
2018
+ "loss": 2.1583,
2019
+ "step": 1675
2020
+ },
2021
+ {
2022
+ "epoch": 1.1,
2023
+ "learning_rate": 0.001,
2024
+ "loss": 2.079,
2025
+ "step": 1680
2026
+ },
2027
+ {
2028
+ "epoch": 1.1,
2029
+ "learning_rate": 0.001,
2030
+ "loss": 2.0118,
2031
+ "step": 1685
2032
+ },
2033
+ {
2034
+ "epoch": 1.11,
2035
+ "learning_rate": 0.001,
2036
+ "loss": 2.011,
2037
+ "step": 1690
2038
+ },
2039
+ {
2040
+ "epoch": 1.11,
2041
+ "learning_rate": 0.001,
2042
+ "loss": 2.3133,
2043
+ "step": 1695
2044
+ },
2045
+ {
2046
+ "epoch": 1.11,
2047
+ "learning_rate": 0.001,
2048
+ "loss": 2.1873,
2049
+ "step": 1700
2050
+ },
2051
+ {
2052
+ "epoch": 1.12,
2053
+ "learning_rate": 0.001,
2054
+ "loss": 1.7311,
2055
+ "step": 1705
2056
+ },
2057
+ {
2058
+ "epoch": 1.12,
2059
+ "learning_rate": 0.001,
2060
+ "loss": 1.7269,
2061
+ "step": 1710
2062
+ },
2063
+ {
2064
+ "epoch": 1.12,
2065
+ "learning_rate": 0.001,
2066
+ "loss": 2.3935,
2067
+ "step": 1715
2068
+ },
2069
+ {
2070
+ "epoch": 1.13,
2071
+ "learning_rate": 0.001,
2072
+ "loss": 2.1104,
2073
+ "step": 1720
2074
+ },
2075
+ {
2076
+ "epoch": 1.13,
2077
+ "learning_rate": 0.001,
2078
+ "loss": 2.2349,
2079
+ "step": 1725
2080
+ },
2081
+ {
2082
+ "epoch": 1.13,
2083
+ "learning_rate": 0.001,
2084
+ "loss": 1.6555,
2085
+ "step": 1730
2086
+ },
2087
+ {
2088
+ "epoch": 1.14,
2089
+ "learning_rate": 0.001,
2090
+ "loss": 1.9011,
2091
+ "step": 1735
2092
+ },
2093
+ {
2094
+ "epoch": 1.14,
2095
+ "learning_rate": 0.001,
2096
+ "loss": 2.2142,
2097
+ "step": 1740
2098
+ },
2099
+ {
2100
+ "epoch": 1.14,
2101
+ "learning_rate": 0.001,
2102
+ "loss": 2.1273,
2103
+ "step": 1745
2104
+ },
2105
+ {
2106
+ "epoch": 1.15,
2107
+ "learning_rate": 0.001,
2108
+ "loss": 2.4855,
2109
+ "step": 1750
2110
+ },
2111
+ {
2112
+ "epoch": 1.15,
2113
+ "learning_rate": 0.001,
2114
+ "loss": 2.3025,
2115
+ "step": 1755
2116
+ },
2117
+ {
2118
+ "epoch": 1.15,
2119
+ "learning_rate": 0.001,
2120
+ "loss": 1.9496,
2121
+ "step": 1760
2122
+ },
2123
+ {
2124
+ "epoch": 1.16,
2125
+ "learning_rate": 0.001,
2126
+ "loss": 1.9856,
2127
+ "step": 1765
2128
+ },
2129
+ {
2130
+ "epoch": 1.16,
2131
+ "learning_rate": 0.001,
2132
+ "loss": 2.1494,
2133
+ "step": 1770
2134
+ },
2135
+ {
2136
+ "epoch": 1.16,
2137
+ "learning_rate": 0.001,
2138
+ "loss": 1.9905,
2139
+ "step": 1775
2140
+ },
2141
+ {
2142
+ "epoch": 1.16,
2143
+ "learning_rate": 0.001,
2144
+ "loss": 2.1177,
2145
+ "step": 1780
2146
+ },
2147
+ {
2148
+ "epoch": 1.17,
2149
+ "learning_rate": 0.001,
2150
+ "loss": 1.9396,
2151
+ "step": 1785
2152
+ },
2153
+ {
2154
+ "epoch": 1.17,
2155
+ "learning_rate": 0.001,
2156
+ "loss": 1.8821,
2157
+ "step": 1790
2158
+ },
2159
+ {
2160
+ "epoch": 1.17,
2161
+ "learning_rate": 0.001,
2162
+ "loss": 2.1909,
2163
+ "step": 1795
2164
+ },
2165
+ {
2166
+ "epoch": 1.18,
2167
+ "learning_rate": 0.001,
2168
+ "loss": 1.9459,
2169
+ "step": 1800
2170
+ },
2171
+ {
2172
+ "epoch": 1.18,
2173
+ "learning_rate": 0.001,
2174
+ "loss": 2.1047,
2175
+ "step": 1805
2176
+ },
2177
+ {
2178
+ "epoch": 1.18,
2179
+ "learning_rate": 0.001,
2180
+ "loss": 1.833,
2181
+ "step": 1810
2182
+ },
2183
+ {
2184
+ "epoch": 1.19,
2185
+ "learning_rate": 0.001,
2186
+ "loss": 2.0839,
2187
+ "step": 1815
2188
+ },
2189
+ {
2190
+ "epoch": 1.19,
2191
+ "learning_rate": 0.001,
2192
+ "loss": 2.0736,
2193
+ "step": 1820
2194
+ },
2195
+ {
2196
+ "epoch": 1.19,
2197
+ "learning_rate": 0.001,
2198
+ "loss": 2.0034,
2199
+ "step": 1825
2200
+ },
2201
+ {
2202
+ "epoch": 1.2,
2203
+ "learning_rate": 0.001,
2204
+ "loss": 2.0788,
2205
+ "step": 1830
2206
+ },
2207
+ {
2208
+ "epoch": 1.2,
2209
+ "learning_rate": 0.001,
2210
+ "loss": 2.1903,
2211
+ "step": 1835
2212
+ },
2213
+ {
2214
+ "epoch": 1.2,
2215
+ "learning_rate": 0.001,
2216
+ "loss": 2.0829,
2217
+ "step": 1840
2218
+ },
2219
+ {
2220
+ "epoch": 1.21,
2221
+ "learning_rate": 0.001,
2222
+ "loss": 2.2449,
2223
+ "step": 1845
2224
+ },
2225
+ {
2226
+ "epoch": 1.21,
2227
+ "learning_rate": 0.001,
2228
+ "loss": 2.1561,
2229
+ "step": 1850
2230
+ },
2231
+ {
2232
+ "epoch": 1.21,
2233
+ "learning_rate": 0.001,
2234
+ "loss": 2.1827,
2235
+ "step": 1855
2236
+ },
2237
+ {
2238
+ "epoch": 1.22,
2239
+ "learning_rate": 0.001,
2240
+ "loss": 2.1885,
2241
+ "step": 1860
2242
+ },
2243
+ {
2244
+ "epoch": 1.22,
2245
+ "learning_rate": 0.001,
2246
+ "loss": 2.049,
2247
+ "step": 1865
2248
+ },
2249
+ {
2250
+ "epoch": 1.22,
2251
+ "learning_rate": 0.001,
2252
+ "loss": 2.2107,
2253
+ "step": 1870
2254
+ },
2255
+ {
2256
+ "epoch": 1.23,
2257
+ "learning_rate": 0.001,
2258
+ "loss": 2.0679,
2259
+ "step": 1875
2260
+ },
2261
+ {
2262
+ "epoch": 1.23,
2263
+ "learning_rate": 0.001,
2264
+ "loss": 2.2887,
2265
+ "step": 1880
2266
+ },
2267
+ {
2268
+ "epoch": 1.23,
2269
+ "learning_rate": 0.001,
2270
+ "loss": 2.2472,
2271
+ "step": 1885
2272
+ },
2273
+ {
2274
+ "epoch": 1.24,
2275
+ "learning_rate": 0.001,
2276
+ "loss": 2.1993,
2277
+ "step": 1890
2278
+ },
2279
+ {
2280
+ "epoch": 1.24,
2281
+ "learning_rate": 0.001,
2282
+ "loss": 2.1636,
2283
+ "step": 1895
2284
+ },
2285
+ {
2286
+ "epoch": 1.24,
2287
+ "learning_rate": 0.001,
2288
+ "loss": 1.9547,
2289
+ "step": 1900
2290
+ },
2291
+ {
2292
+ "epoch": 1.25,
2293
+ "learning_rate": 0.001,
2294
+ "loss": 2.3164,
2295
+ "step": 1905
2296
+ },
2297
+ {
2298
+ "epoch": 1.25,
2299
+ "learning_rate": 0.001,
2300
+ "loss": 2.2847,
2301
+ "step": 1910
2302
+ },
2303
+ {
2304
+ "epoch": 1.25,
2305
+ "learning_rate": 0.001,
2306
+ "loss": 2.2196,
2307
+ "step": 1915
2308
+ },
2309
+ {
2310
+ "epoch": 1.26,
2311
+ "learning_rate": 0.001,
2312
+ "loss": 2.1823,
2313
+ "step": 1920
2314
+ },
2315
+ {
2316
+ "epoch": 1.26,
2317
+ "learning_rate": 0.001,
2318
+ "loss": 2.2532,
2319
+ "step": 1925
2320
+ },
2321
+ {
2322
+ "epoch": 1.26,
2323
+ "learning_rate": 0.001,
2324
+ "loss": 2.2451,
2325
+ "step": 1930
2326
+ },
2327
+ {
2328
+ "epoch": 1.27,
2329
+ "learning_rate": 0.001,
2330
+ "loss": 1.984,
2331
+ "step": 1935
2332
+ },
2333
+ {
2334
+ "epoch": 1.27,
2335
+ "learning_rate": 0.001,
2336
+ "loss": 2.0976,
2337
+ "step": 1940
2338
+ },
2339
+ {
2340
+ "epoch": 1.27,
2341
+ "learning_rate": 0.001,
2342
+ "loss": 2.0658,
2343
+ "step": 1945
2344
+ },
2345
+ {
2346
+ "epoch": 1.28,
2347
+ "learning_rate": 0.001,
2348
+ "loss": 2.316,
2349
+ "step": 1950
2350
+ },
2351
+ {
2352
+ "epoch": 1.28,
2353
+ "learning_rate": 0.001,
2354
+ "loss": 2.2036,
2355
+ "step": 1955
2356
+ },
2357
+ {
2358
+ "epoch": 1.28,
2359
+ "learning_rate": 0.001,
2360
+ "loss": 2.0602,
2361
+ "step": 1960
2362
+ },
2363
+ {
2364
+ "epoch": 1.29,
2365
+ "learning_rate": 0.001,
2366
+ "loss": 1.971,
2367
+ "step": 1965
2368
+ },
2369
+ {
2370
+ "epoch": 1.29,
2371
+ "learning_rate": 0.001,
2372
+ "loss": 2.1463,
2373
+ "step": 1970
2374
+ },
2375
+ {
2376
+ "epoch": 1.29,
2377
+ "learning_rate": 0.001,
2378
+ "loss": 1.7689,
2379
+ "step": 1975
2380
+ },
2381
+ {
2382
+ "epoch": 1.3,
2383
+ "learning_rate": 0.001,
2384
+ "loss": 2.014,
2385
+ "step": 1980
2386
+ },
2387
+ {
2388
+ "epoch": 1.3,
2389
+ "learning_rate": 0.001,
2390
+ "loss": 2.3631,
2391
+ "step": 1985
2392
+ },
2393
+ {
2394
+ "epoch": 1.3,
2395
+ "learning_rate": 0.001,
2396
+ "loss": 2.2294,
2397
+ "step": 1990
2398
+ },
2399
+ {
2400
+ "epoch": 1.31,
2401
+ "learning_rate": 0.001,
2402
+ "loss": 1.8407,
2403
+ "step": 1995
2404
+ },
2405
+ {
2406
+ "epoch": 1.31,
2407
+ "learning_rate": 0.001,
2408
+ "loss": 1.9365,
2409
+ "step": 2000
2410
+ },
2411
+ {
2412
+ "epoch": 1.31,
2413
+ "learning_rate": 0.001,
2414
+ "loss": 2.0895,
2415
+ "step": 2005
2416
+ },
2417
+ {
2418
+ "epoch": 1.32,
2419
+ "learning_rate": 0.001,
2420
+ "loss": 2.1625,
2421
+ "step": 2010
2422
+ },
2423
+ {
2424
+ "epoch": 1.32,
2425
+ "learning_rate": 0.001,
2426
+ "loss": 2.053,
2427
+ "step": 2015
2428
+ },
2429
+ {
2430
+ "epoch": 1.32,
2431
+ "learning_rate": 0.001,
2432
+ "loss": 2.0925,
2433
+ "step": 2020
2434
+ },
2435
+ {
2436
+ "epoch": 1.33,
2437
+ "learning_rate": 0.001,
2438
+ "loss": 1.9764,
2439
+ "step": 2025
2440
+ },
2441
+ {
2442
+ "epoch": 1.33,
2443
+ "learning_rate": 0.001,
2444
+ "loss": 2.1212,
2445
+ "step": 2030
2446
+ },
2447
+ {
2448
+ "epoch": 1.33,
2449
+ "learning_rate": 0.001,
2450
+ "loss": 1.923,
2451
+ "step": 2035
2452
+ },
2453
+ {
2454
+ "epoch": 1.34,
2455
+ "learning_rate": 0.001,
2456
+ "loss": 2.2899,
2457
+ "step": 2040
2458
+ },
2459
+ {
2460
+ "epoch": 1.34,
2461
+ "learning_rate": 0.001,
2462
+ "loss": 2.3056,
2463
+ "step": 2045
2464
+ },
2465
+ {
2466
+ "epoch": 1.34,
2467
+ "learning_rate": 0.001,
2468
+ "loss": 2.0217,
2469
+ "step": 2050
2470
+ },
2471
+ {
2472
+ "epoch": 1.34,
2473
+ "learning_rate": 0.001,
2474
+ "loss": 2.1757,
2475
+ "step": 2055
2476
+ },
2477
+ {
2478
+ "epoch": 1.35,
2479
+ "learning_rate": 0.001,
2480
+ "loss": 1.7524,
2481
+ "step": 2060
2482
+ },
2483
+ {
2484
+ "epoch": 1.35,
2485
+ "learning_rate": 0.001,
2486
+ "loss": 2.3042,
2487
+ "step": 2065
2488
+ },
2489
+ {
2490
+ "epoch": 1.35,
2491
+ "learning_rate": 0.001,
2492
+ "loss": 2.164,
2493
+ "step": 2070
2494
+ },
2495
+ {
2496
+ "epoch": 1.36,
2497
+ "learning_rate": 0.001,
2498
+ "loss": 2.3265,
2499
+ "step": 2075
2500
+ },
2501
+ {
2502
+ "epoch": 1.36,
2503
+ "learning_rate": 0.001,
2504
+ "loss": 2.4762,
2505
+ "step": 2080
2506
+ },
2507
+ {
2508
+ "epoch": 1.36,
2509
+ "learning_rate": 0.001,
2510
+ "loss": 2.2577,
2511
+ "step": 2085
2512
+ },
2513
+ {
2514
+ "epoch": 1.37,
2515
+ "learning_rate": 0.001,
2516
+ "loss": 2.4857,
2517
+ "step": 2090
2518
+ },
2519
+ {
2520
+ "epoch": 1.37,
2521
+ "learning_rate": 0.001,
2522
+ "loss": 2.1887,
2523
+ "step": 2095
2524
+ },
2525
+ {
2526
+ "epoch": 1.37,
2527
+ "learning_rate": 0.001,
2528
+ "loss": 2.3144,
2529
+ "step": 2100
2530
+ },
2531
+ {
2532
+ "epoch": 1.38,
2533
+ "learning_rate": 0.001,
2534
+ "loss": 2.2387,
2535
+ "step": 2105
2536
+ },
2537
+ {
2538
+ "epoch": 1.38,
2539
+ "learning_rate": 0.001,
2540
+ "loss": 2.5008,
2541
+ "step": 2110
2542
+ },
2543
+ {
2544
+ "epoch": 1.38,
2545
+ "learning_rate": 0.001,
2546
+ "loss": 2.0604,
2547
+ "step": 2115
2548
+ },
2549
+ {
2550
+ "epoch": 1.39,
2551
+ "learning_rate": 0.001,
2552
+ "loss": 2.414,
2553
+ "step": 2120
2554
+ },
2555
+ {
2556
+ "epoch": 1.39,
2557
+ "learning_rate": 0.001,
2558
+ "loss": 2.2392,
2559
+ "step": 2125
2560
+ },
2561
+ {
2562
+ "epoch": 1.39,
2563
+ "learning_rate": 0.001,
2564
+ "loss": 2.1842,
2565
+ "step": 2130
2566
+ },
2567
+ {
2568
+ "epoch": 1.4,
2569
+ "learning_rate": 0.001,
2570
+ "loss": 2.0674,
2571
+ "step": 2135
2572
+ },
2573
+ {
2574
+ "epoch": 1.4,
2575
+ "learning_rate": 0.001,
2576
+ "loss": 2.2088,
2577
+ "step": 2140
2578
+ },
2579
+ {
2580
+ "epoch": 1.4,
2581
+ "learning_rate": 0.001,
2582
+ "loss": 2.363,
2583
+ "step": 2145
2584
+ },
2585
+ {
2586
+ "epoch": 1.41,
2587
+ "learning_rate": 0.001,
2588
+ "loss": 2.1834,
2589
+ "step": 2150
2590
+ },
2591
+ {
2592
+ "epoch": 1.41,
2593
+ "learning_rate": 0.001,
2594
+ "loss": 2.1047,
2595
+ "step": 2155
2596
+ },
2597
+ {
2598
+ "epoch": 1.41,
2599
+ "learning_rate": 0.001,
2600
+ "loss": 1.8624,
2601
+ "step": 2160
2602
+ },
2603
+ {
2604
+ "epoch": 1.42,
2605
+ "learning_rate": 0.001,
2606
+ "loss": 2.0746,
2607
+ "step": 2165
2608
+ },
2609
+ {
2610
+ "epoch": 1.42,
2611
+ "learning_rate": 0.001,
2612
+ "loss": 2.4054,
2613
+ "step": 2170
2614
+ },
2615
+ {
2616
+ "epoch": 1.42,
2617
+ "learning_rate": 0.001,
2618
+ "loss": 2.326,
2619
+ "step": 2175
2620
+ },
2621
+ {
2622
+ "epoch": 1.43,
2623
+ "learning_rate": 0.001,
2624
+ "loss": 2.1054,
2625
+ "step": 2180
2626
+ },
2627
+ {
2628
+ "epoch": 1.43,
2629
+ "learning_rate": 0.001,
2630
+ "loss": 1.7848,
2631
+ "step": 2185
2632
+ },
2633
+ {
2634
+ "epoch": 1.43,
2635
+ "learning_rate": 0.001,
2636
+ "loss": 2.2795,
2637
+ "step": 2190
2638
+ },
2639
+ {
2640
+ "epoch": 1.44,
2641
+ "learning_rate": 0.001,
2642
+ "loss": 1.9866,
2643
+ "step": 2195
2644
+ },
2645
+ {
2646
+ "epoch": 1.44,
2647
+ "learning_rate": 0.001,
2648
+ "loss": 2.5626,
2649
+ "step": 2200
2650
+ },
2651
+ {
2652
+ "epoch": 1.44,
2653
+ "learning_rate": 0.001,
2654
+ "loss": 2.2101,
2655
+ "step": 2205
2656
+ },
2657
+ {
2658
+ "epoch": 1.45,
2659
+ "learning_rate": 0.001,
2660
+ "loss": 2.286,
2661
+ "step": 2210
2662
+ },
2663
+ {
2664
+ "epoch": 1.45,
2665
+ "learning_rate": 0.001,
2666
+ "loss": 1.8204,
2667
+ "step": 2215
2668
+ },
2669
+ {
2670
+ "epoch": 1.45,
2671
+ "learning_rate": 0.001,
2672
+ "loss": 2.1886,
2673
+ "step": 2220
2674
+ },
2675
+ {
2676
+ "epoch": 1.46,
2677
+ "learning_rate": 0.001,
2678
+ "loss": 2.0936,
2679
+ "step": 2225
2680
+ },
2681
+ {
2682
+ "epoch": 1.46,
2683
+ "learning_rate": 0.001,
2684
+ "loss": 2.5121,
2685
+ "step": 2230
2686
+ },
2687
+ {
2688
+ "epoch": 1.46,
2689
+ "learning_rate": 0.001,
2690
+ "loss": 2.2165,
2691
+ "step": 2235
2692
+ },
2693
+ {
2694
+ "epoch": 1.47,
2695
+ "learning_rate": 0.001,
2696
+ "loss": 1.8987,
2697
+ "step": 2240
2698
+ },
2699
+ {
2700
+ "epoch": 1.47,
2701
+ "learning_rate": 0.001,
2702
+ "loss": 1.8333,
2703
+ "step": 2245
2704
+ },
2705
+ {
2706
+ "epoch": 1.47,
2707
+ "learning_rate": 0.001,
2708
+ "loss": 2.2611,
2709
+ "step": 2250
2710
+ },
2711
+ {
2712
+ "epoch": 1.48,
2713
+ "learning_rate": 0.001,
2714
+ "loss": 2.2649,
2715
+ "step": 2255
2716
+ },
2717
+ {
2718
+ "epoch": 1.48,
2719
+ "learning_rate": 0.001,
2720
+ "loss": 2.0907,
2721
+ "step": 2260
2722
+ },
2723
+ {
2724
+ "epoch": 1.48,
2725
+ "learning_rate": 0.001,
2726
+ "loss": 2.2594,
2727
+ "step": 2265
2728
+ },
2729
+ {
2730
+ "epoch": 1.49,
2731
+ "learning_rate": 0.001,
2732
+ "loss": 2.1826,
2733
+ "step": 2270
2734
+ },
2735
+ {
2736
+ "epoch": 1.49,
2737
+ "learning_rate": 0.001,
2738
+ "loss": 2.0087,
2739
+ "step": 2275
2740
+ },
2741
+ {
2742
+ "epoch": 1.49,
2743
+ "learning_rate": 0.001,
2744
+ "loss": 2.0936,
2745
+ "step": 2280
2746
+ },
2747
+ {
2748
+ "epoch": 1.5,
2749
+ "learning_rate": 0.001,
2750
+ "loss": 2.1456,
2751
+ "step": 2285
2752
+ },
2753
+ {
2754
+ "epoch": 1.5,
2755
+ "learning_rate": 0.001,
2756
+ "loss": 2.3667,
2757
+ "step": 2290
2758
+ },
2759
+ {
2760
+ "epoch": 1.5,
2761
+ "learning_rate": 0.001,
2762
+ "loss": 1.9434,
2763
+ "step": 2295
2764
+ },
2765
+ {
2766
+ "epoch": 1.51,
2767
+ "learning_rate": 0.001,
2768
+ "loss": 2.2934,
2769
+ "step": 2300
2770
+ },
2771
+ {
2772
+ "epoch": 1.51,
2773
+ "learning_rate": 0.001,
2774
+ "loss": 2.2615,
2775
+ "step": 2305
2776
+ },
2777
+ {
2778
+ "epoch": 1.51,
2779
+ "learning_rate": 0.001,
2780
+ "loss": 2.0636,
2781
+ "step": 2310
2782
+ },
2783
+ {
2784
+ "epoch": 1.52,
2785
+ "learning_rate": 0.001,
2786
+ "loss": 2.0307,
2787
+ "step": 2315
2788
+ },
2789
+ {
2790
+ "epoch": 1.52,
2791
+ "learning_rate": 0.001,
2792
+ "loss": 2.0033,
2793
+ "step": 2320
2794
+ },
2795
+ {
2796
+ "epoch": 1.52,
2797
+ "learning_rate": 0.001,
2798
+ "loss": 2.0915,
2799
+ "step": 2325
2800
+ },
2801
+ {
2802
+ "epoch": 1.52,
2803
+ "learning_rate": 0.001,
2804
+ "loss": 2.0934,
2805
+ "step": 2330
2806
+ },
2807
+ {
2808
+ "epoch": 1.53,
2809
+ "learning_rate": 0.001,
2810
+ "loss": 2.2811,
2811
+ "step": 2335
2812
+ },
2813
+ {
2814
+ "epoch": 1.53,
2815
+ "learning_rate": 0.001,
2816
+ "loss": 1.962,
2817
+ "step": 2340
2818
+ },
2819
+ {
2820
+ "epoch": 1.53,
2821
+ "learning_rate": 0.001,
2822
+ "loss": 1.8715,
2823
+ "step": 2345
2824
+ },
2825
+ {
2826
+ "epoch": 1.54,
2827
+ "learning_rate": 0.001,
2828
+ "loss": 2.2623,
2829
+ "step": 2350
2830
+ },
2831
+ {
2832
+ "epoch": 1.54,
2833
+ "learning_rate": 0.001,
2834
+ "loss": 2.1543,
2835
+ "step": 2355
2836
+ },
2837
+ {
2838
+ "epoch": 1.54,
2839
+ "learning_rate": 0.001,
2840
+ "loss": 2.1026,
2841
+ "step": 2360
2842
+ },
2843
+ {
2844
+ "epoch": 1.55,
2845
+ "learning_rate": 0.001,
2846
+ "loss": 2.4501,
2847
+ "step": 2365
2848
+ },
2849
+ {
2850
+ "epoch": 1.55,
2851
+ "learning_rate": 0.001,
2852
+ "loss": 2.1931,
2853
+ "step": 2370
2854
+ },
2855
+ {
2856
+ "epoch": 1.55,
2857
+ "learning_rate": 0.001,
2858
+ "loss": 2.0309,
2859
+ "step": 2375
2860
+ },
2861
+ {
2862
+ "epoch": 1.56,
2863
+ "learning_rate": 0.001,
2864
+ "loss": 2.0723,
2865
+ "step": 2380
2866
+ },
2867
+ {
2868
+ "epoch": 1.56,
2869
+ "learning_rate": 0.001,
2870
+ "loss": 2.3666,
2871
+ "step": 2385
2872
+ },
2873
+ {
2874
+ "epoch": 1.56,
2875
+ "learning_rate": 0.001,
2876
+ "loss": 2.1858,
2877
+ "step": 2390
2878
+ },
2879
+ {
2880
+ "epoch": 1.57,
2881
+ "learning_rate": 0.001,
2882
+ "loss": 2.031,
2883
+ "step": 2395
2884
+ },
2885
+ {
2886
+ "epoch": 1.57,
2887
+ "learning_rate": 0.001,
2888
+ "loss": 1.6752,
2889
+ "step": 2400
2890
+ },
2891
+ {
2892
+ "epoch": 1.57,
2893
+ "learning_rate": 0.001,
2894
+ "loss": 2.1003,
2895
+ "step": 2405
2896
+ },
2897
+ {
2898
+ "epoch": 1.58,
2899
+ "learning_rate": 0.001,
2900
+ "loss": 2.4007,
2901
+ "step": 2410
2902
+ },
2903
+ {
2904
+ "epoch": 1.58,
2905
+ "learning_rate": 0.001,
2906
+ "loss": 2.2498,
2907
+ "step": 2415
2908
+ },
2909
+ {
2910
+ "epoch": 1.58,
2911
+ "learning_rate": 0.001,
2912
+ "loss": 2.2472,
2913
+ "step": 2420
2914
+ },
2915
+ {
2916
+ "epoch": 1.59,
2917
+ "learning_rate": 0.001,
2918
+ "loss": 2.202,
2919
+ "step": 2425
2920
+ },
2921
+ {
2922
+ "epoch": 1.59,
2923
+ "learning_rate": 0.001,
2924
+ "loss": 2.4824,
2925
+ "step": 2430
2926
+ },
2927
+ {
2928
+ "epoch": 1.59,
2929
+ "learning_rate": 0.001,
2930
+ "loss": 2.1637,
2931
+ "step": 2435
2932
+ },
2933
+ {
2934
+ "epoch": 1.6,
2935
+ "learning_rate": 0.001,
2936
+ "loss": 2.4039,
2937
+ "step": 2440
2938
+ },
2939
+ {
2940
+ "epoch": 1.6,
2941
+ "learning_rate": 0.001,
2942
+ "loss": 2.1053,
2943
+ "step": 2445
2944
+ },
2945
+ {
2946
+ "epoch": 1.6,
2947
+ "learning_rate": 0.001,
2948
+ "loss": 1.9858,
2949
+ "step": 2450
2950
+ },
2951
+ {
2952
+ "epoch": 1.61,
2953
+ "learning_rate": 0.001,
2954
+ "loss": 2.2371,
2955
+ "step": 2455
2956
+ },
2957
+ {
2958
+ "epoch": 1.61,
2959
+ "learning_rate": 0.001,
2960
+ "loss": 1.8063,
2961
+ "step": 2460
2962
+ },
2963
+ {
2964
+ "epoch": 1.61,
2965
+ "learning_rate": 0.001,
2966
+ "loss": 2.2199,
2967
+ "step": 2465
2968
+ },
2969
+ {
2970
+ "epoch": 1.62,
2971
+ "learning_rate": 0.001,
2972
+ "loss": 2.2837,
2973
+ "step": 2470
2974
+ },
2975
+ {
2976
+ "epoch": 1.62,
2977
+ "learning_rate": 0.001,
2978
+ "loss": 2.2889,
2979
+ "step": 2475
2980
+ },
2981
+ {
2982
+ "epoch": 1.62,
2983
+ "learning_rate": 0.001,
2984
+ "loss": 2.1687,
2985
+ "step": 2480
2986
+ },
2987
+ {
2988
+ "epoch": 1.63,
2989
+ "learning_rate": 0.001,
2990
+ "loss": 2.2346,
2991
+ "step": 2485
2992
+ },
2993
+ {
2994
+ "epoch": 1.63,
2995
+ "learning_rate": 0.001,
2996
+ "loss": 2.3059,
2997
+ "step": 2490
2998
+ },
2999
+ {
3000
+ "epoch": 1.63,
3001
+ "learning_rate": 0.001,
3002
+ "loss": 2.3096,
3003
+ "step": 2495
3004
+ },
3005
+ {
3006
+ "epoch": 1.64,
3007
+ "learning_rate": 0.001,
3008
+ "loss": 2.4252,
3009
+ "step": 2500
3010
+ },
3011
+ {
3012
+ "epoch": 1.64,
3013
+ "learning_rate": 0.001,
3014
+ "loss": 1.9604,
3015
+ "step": 2505
3016
+ },
3017
+ {
3018
+ "epoch": 1.64,
3019
+ "learning_rate": 0.001,
3020
+ "loss": 2.154,
3021
+ "step": 2510
3022
+ },
3023
+ {
3024
+ "epoch": 1.65,
3025
+ "learning_rate": 0.001,
3026
+ "loss": 2.3648,
3027
+ "step": 2515
3028
+ },
3029
+ {
3030
+ "epoch": 1.65,
3031
+ "learning_rate": 0.001,
3032
+ "loss": 2.3436,
3033
+ "step": 2520
3034
+ },
3035
+ {
3036
+ "epoch": 1.65,
3037
+ "learning_rate": 0.001,
3038
+ "loss": 2.3471,
3039
+ "step": 2525
3040
+ },
3041
+ {
3042
+ "epoch": 1.66,
3043
+ "learning_rate": 0.001,
3044
+ "loss": 2.1766,
3045
+ "step": 2530
3046
+ },
3047
+ {
3048
+ "epoch": 1.66,
3049
+ "learning_rate": 0.001,
3050
+ "loss": 2.1967,
3051
+ "step": 2535
3052
+ },
3053
+ {
3054
+ "epoch": 1.66,
3055
+ "learning_rate": 0.001,
3056
+ "loss": 2.1945,
3057
+ "step": 2540
3058
+ },
3059
+ {
3060
+ "epoch": 1.67,
3061
+ "learning_rate": 0.001,
3062
+ "loss": 2.1473,
3063
+ "step": 2545
3064
+ },
3065
+ {
3066
+ "epoch": 1.67,
3067
+ "learning_rate": 0.001,
3068
+ "loss": 2.4883,
3069
+ "step": 2550
3070
+ },
3071
+ {
3072
+ "epoch": 1.67,
3073
+ "learning_rate": 0.001,
3074
+ "loss": 1.9596,
3075
+ "step": 2555
3076
+ },
3077
+ {
3078
+ "epoch": 1.68,
3079
+ "learning_rate": 0.001,
3080
+ "loss": 2.3908,
3081
+ "step": 2560
3082
+ },
3083
+ {
3084
+ "epoch": 1.68,
3085
+ "learning_rate": 0.001,
3086
+ "loss": 2.2533,
3087
+ "step": 2565
3088
+ },
3089
+ {
3090
+ "epoch": 1.68,
3091
+ "learning_rate": 0.001,
3092
+ "loss": 2.0808,
3093
+ "step": 2570
3094
+ },
3095
+ {
3096
+ "epoch": 1.69,
3097
+ "learning_rate": 0.001,
3098
+ "loss": 2.028,
3099
+ "step": 2575
3100
+ },
3101
+ {
3102
+ "epoch": 1.69,
3103
+ "learning_rate": 0.001,
3104
+ "loss": 2.2471,
3105
+ "step": 2580
3106
+ },
3107
+ {
3108
+ "epoch": 1.69,
3109
+ "learning_rate": 0.001,
3110
+ "loss": 2.1975,
3111
+ "step": 2585
3112
+ },
3113
+ {
3114
+ "epoch": 1.7,
3115
+ "learning_rate": 0.001,
3116
+ "loss": 2.404,
3117
+ "step": 2590
3118
+ },
3119
+ {
3120
+ "epoch": 1.7,
3121
+ "learning_rate": 0.001,
3122
+ "loss": 2.4238,
3123
+ "step": 2595
3124
+ },
3125
+ {
3126
+ "epoch": 1.7,
3127
+ "learning_rate": 0.001,
3128
+ "loss": 2.2742,
3129
+ "step": 2600
3130
+ },
3131
+ {
3132
+ "epoch": 1.7,
3133
+ "learning_rate": 0.001,
3134
+ "loss": 2.3284,
3135
+ "step": 2605
3136
+ },
3137
+ {
3138
+ "epoch": 1.71,
3139
+ "learning_rate": 0.001,
3140
+ "loss": 2.0517,
3141
+ "step": 2610
3142
+ },
3143
+ {
3144
+ "epoch": 1.71,
3145
+ "learning_rate": 0.001,
3146
+ "loss": 2.488,
3147
+ "step": 2615
3148
+ },
3149
+ {
3150
+ "epoch": 1.71,
3151
+ "learning_rate": 0.001,
3152
+ "loss": 2.1215,
3153
+ "step": 2620
3154
+ },
3155
+ {
3156
+ "epoch": 1.72,
3157
+ "learning_rate": 0.001,
3158
+ "loss": 2.1813,
3159
+ "step": 2625
3160
+ },
3161
+ {
3162
+ "epoch": 1.72,
3163
+ "learning_rate": 0.001,
3164
+ "loss": 1.9404,
3165
+ "step": 2630
3166
+ },
3167
+ {
3168
+ "epoch": 1.72,
3169
+ "learning_rate": 0.001,
3170
+ "loss": 2.1978,
3171
+ "step": 2635
3172
+ },
3173
+ {
3174
+ "epoch": 1.73,
3175
+ "learning_rate": 0.001,
3176
+ "loss": 2.1462,
3177
+ "step": 2640
3178
+ },
3179
+ {
3180
+ "epoch": 1.73,
3181
+ "learning_rate": 0.001,
3182
+ "loss": 1.9796,
3183
+ "step": 2645
3184
+ },
3185
+ {
3186
+ "epoch": 1.73,
3187
+ "learning_rate": 0.001,
3188
+ "loss": 2.267,
3189
+ "step": 2650
3190
+ },
3191
+ {
3192
+ "epoch": 1.74,
3193
+ "learning_rate": 0.001,
3194
+ "loss": 2.0169,
3195
+ "step": 2655
3196
+ },
3197
+ {
3198
+ "epoch": 1.74,
3199
+ "learning_rate": 0.001,
3200
+ "loss": 2.1779,
3201
+ "step": 2660
3202
+ },
3203
+ {
3204
+ "epoch": 1.74,
3205
+ "learning_rate": 0.001,
3206
+ "loss": 2.2851,
3207
+ "step": 2665
3208
+ },
3209
+ {
3210
+ "epoch": 1.75,
3211
+ "learning_rate": 0.001,
3212
+ "loss": 2.5845,
3213
+ "step": 2670
3214
+ },
3215
+ {
3216
+ "epoch": 1.75,
3217
+ "learning_rate": 0.001,
3218
+ "loss": 2.006,
3219
+ "step": 2675
3220
+ },
3221
+ {
3222
+ "epoch": 1.75,
3223
+ "learning_rate": 0.001,
3224
+ "loss": 2.0386,
3225
+ "step": 2680
3226
+ },
3227
+ {
3228
+ "epoch": 1.76,
3229
+ "learning_rate": 0.001,
3230
+ "loss": 2.2271,
3231
+ "step": 2685
3232
+ },
3233
+ {
3234
+ "epoch": 1.76,
3235
+ "learning_rate": 0.001,
3236
+ "loss": 2.1557,
3237
+ "step": 2690
3238
+ },
3239
+ {
3240
+ "epoch": 1.76,
3241
+ "learning_rate": 0.001,
3242
+ "loss": 2.0532,
3243
+ "step": 2695
3244
+ },
3245
+ {
3246
+ "epoch": 1.77,
3247
+ "learning_rate": 0.001,
3248
+ "loss": 2.14,
3249
+ "step": 2700
3250
+ },
3251
+ {
3252
+ "epoch": 1.77,
3253
+ "learning_rate": 0.001,
3254
+ "loss": 1.995,
3255
+ "step": 2705
3256
+ },
3257
+ {
3258
+ "epoch": 1.77,
3259
+ "learning_rate": 0.001,
3260
+ "loss": 1.9508,
3261
+ "step": 2710
3262
+ },
3263
+ {
3264
+ "epoch": 1.78,
3265
+ "learning_rate": 0.001,
3266
+ "loss": 2.4736,
3267
+ "step": 2715
3268
+ },
3269
+ {
3270
+ "epoch": 1.78,
3271
+ "learning_rate": 0.001,
3272
+ "loss": 2.0145,
3273
+ "step": 2720
3274
+ },
3275
+ {
3276
+ "epoch": 1.78,
3277
+ "learning_rate": 0.001,
3278
+ "loss": 2.1276,
3279
+ "step": 2725
3280
+ },
3281
+ {
3282
+ "epoch": 1.79,
3283
+ "learning_rate": 0.001,
3284
+ "loss": 2.1232,
3285
+ "step": 2730
3286
+ },
3287
+ {
3288
+ "epoch": 1.79,
3289
+ "learning_rate": 0.001,
3290
+ "loss": 2.3248,
3291
+ "step": 2735
3292
+ },
3293
+ {
3294
+ "epoch": 1.79,
3295
+ "learning_rate": 0.001,
3296
+ "loss": 2.0148,
3297
+ "step": 2740
3298
+ },
3299
+ {
3300
+ "epoch": 1.8,
3301
+ "learning_rate": 0.001,
3302
+ "loss": 1.974,
3303
+ "step": 2745
3304
+ },
3305
+ {
3306
+ "epoch": 1.8,
3307
+ "learning_rate": 0.001,
3308
+ "loss": 2.2313,
3309
+ "step": 2750
3310
+ },
3311
+ {
3312
+ "epoch": 1.8,
3313
+ "learning_rate": 0.001,
3314
+ "loss": 2.0893,
3315
+ "step": 2755
3316
+ },
3317
+ {
3318
+ "epoch": 1.81,
3319
+ "learning_rate": 0.001,
3320
+ "loss": 2.1423,
3321
+ "step": 2760
3322
+ },
3323
+ {
3324
+ "epoch": 1.81,
3325
+ "learning_rate": 0.001,
3326
+ "loss": 2.2085,
3327
+ "step": 2765
3328
+ },
3329
+ {
3330
+ "epoch": 1.81,
3331
+ "learning_rate": 0.001,
3332
+ "loss": 2.2314,
3333
+ "step": 2770
3334
+ },
3335
+ {
3336
+ "epoch": 1.82,
3337
+ "learning_rate": 0.001,
3338
+ "loss": 2.1122,
3339
+ "step": 2775
3340
+ },
3341
+ {
3342
+ "epoch": 1.82,
3343
+ "learning_rate": 0.001,
3344
+ "loss": 2.0739,
3345
+ "step": 2780
3346
+ },
3347
+ {
3348
+ "epoch": 1.82,
3349
+ "learning_rate": 0.001,
3350
+ "loss": 2.2233,
3351
+ "step": 2785
3352
+ },
3353
+ {
3354
+ "epoch": 1.83,
3355
+ "learning_rate": 0.001,
3356
+ "loss": 2.2696,
3357
+ "step": 2790
3358
+ },
3359
+ {
3360
+ "epoch": 1.83,
3361
+ "learning_rate": 0.001,
3362
+ "loss": 1.9375,
3363
+ "step": 2795
3364
+ },
3365
+ {
3366
+ "epoch": 1.83,
3367
+ "learning_rate": 0.001,
3368
+ "loss": 2.2126,
3369
+ "step": 2800
3370
+ },
3371
+ {
3372
+ "epoch": 1.84,
3373
+ "learning_rate": 0.001,
3374
+ "loss": 2.2643,
3375
+ "step": 2805
3376
+ },
3377
+ {
3378
+ "epoch": 1.84,
3379
+ "learning_rate": 0.001,
3380
+ "loss": 1.881,
3381
+ "step": 2810
3382
+ },
3383
+ {
3384
+ "epoch": 1.84,
3385
+ "learning_rate": 0.001,
3386
+ "loss": 2.427,
3387
+ "step": 2815
3388
+ },
3389
+ {
3390
+ "epoch": 1.85,
3391
+ "learning_rate": 0.001,
3392
+ "loss": 2.419,
3393
+ "step": 2820
3394
+ },
3395
+ {
3396
+ "epoch": 1.85,
3397
+ "learning_rate": 0.001,
3398
+ "loss": 2.2486,
3399
+ "step": 2825
3400
+ },
3401
+ {
3402
+ "epoch": 1.85,
3403
+ "learning_rate": 0.001,
3404
+ "loss": 2.6872,
3405
+ "step": 2830
3406
+ },
3407
+ {
3408
+ "epoch": 1.86,
3409
+ "learning_rate": 0.001,
3410
+ "loss": 2.0539,
3411
+ "step": 2835
3412
+ },
3413
+ {
3414
+ "epoch": 1.86,
3415
+ "learning_rate": 0.001,
3416
+ "loss": 2.4746,
3417
+ "step": 2840
3418
+ },
3419
+ {
3420
+ "epoch": 1.86,
3421
+ "learning_rate": 0.001,
3422
+ "loss": 2.2573,
3423
+ "step": 2845
3424
+ },
3425
+ {
3426
+ "epoch": 1.87,
3427
+ "learning_rate": 0.001,
3428
+ "loss": 2.0748,
3429
+ "step": 2850
3430
+ },
3431
+ {
3432
+ "epoch": 1.87,
3433
+ "learning_rate": 0.001,
3434
+ "loss": 2.2958,
3435
+ "step": 2855
3436
+ },
3437
+ {
3438
+ "epoch": 1.87,
3439
+ "learning_rate": 0.001,
3440
+ "loss": 1.8544,
3441
+ "step": 2860
3442
+ },
3443
+ {
3444
+ "epoch": 1.88,
3445
+ "learning_rate": 0.001,
3446
+ "loss": 2.4232,
3447
+ "step": 2865
3448
+ },
3449
+ {
3450
+ "epoch": 1.88,
3451
+ "learning_rate": 0.001,
3452
+ "loss": 2.3381,
3453
+ "step": 2870
3454
+ },
3455
+ {
3456
+ "epoch": 1.88,
3457
+ "learning_rate": 0.001,
3458
+ "loss": 2.276,
3459
+ "step": 2875
3460
+ },
3461
+ {
3462
+ "epoch": 1.88,
3463
+ "learning_rate": 0.001,
3464
+ "loss": 2.3278,
3465
+ "step": 2880
3466
+ },
3467
+ {
3468
+ "epoch": 1.89,
3469
+ "learning_rate": 0.001,
3470
+ "loss": 2.3119,
3471
+ "step": 2885
3472
+ },
3473
+ {
3474
+ "epoch": 1.89,
3475
+ "learning_rate": 0.001,
3476
+ "loss": 2.2123,
3477
+ "step": 2890
3478
+ },
3479
+ {
3480
+ "epoch": 1.89,
3481
+ "learning_rate": 0.001,
3482
+ "loss": 2.1596,
3483
+ "step": 2895
3484
+ },
3485
+ {
3486
+ "epoch": 1.9,
3487
+ "learning_rate": 0.001,
3488
+ "loss": 2.04,
3489
+ "step": 2900
3490
+ },
3491
+ {
3492
+ "epoch": 1.9,
3493
+ "learning_rate": 0.001,
3494
+ "loss": 2.3909,
3495
+ "step": 2905
3496
+ },
3497
+ {
3498
+ "epoch": 1.9,
3499
+ "learning_rate": 0.001,
3500
+ "loss": 2.1027,
3501
+ "step": 2910
3502
+ },
3503
+ {
3504
+ "epoch": 1.91,
3505
+ "learning_rate": 0.001,
3506
+ "loss": 2.1365,
3507
+ "step": 2915
3508
+ },
3509
+ {
3510
+ "epoch": 1.91,
3511
+ "learning_rate": 0.001,
3512
+ "loss": 2.2151,
3513
+ "step": 2920
3514
+ },
3515
+ {
3516
+ "epoch": 1.91,
3517
+ "learning_rate": 0.001,
3518
+ "loss": 2.2469,
3519
+ "step": 2925
3520
+ },
3521
+ {
3522
+ "epoch": 1.92,
3523
+ "learning_rate": 0.001,
3524
+ "loss": 2.1939,
3525
+ "step": 2930
3526
+ },
3527
+ {
3528
+ "epoch": 1.92,
3529
+ "learning_rate": 0.001,
3530
+ "loss": 2.0386,
3531
+ "step": 2935
3532
+ },
3533
+ {
3534
+ "epoch": 1.92,
3535
+ "learning_rate": 0.001,
3536
+ "loss": 2.094,
3537
+ "step": 2940
3538
+ },
3539
+ {
3540
+ "epoch": 1.93,
3541
+ "learning_rate": 0.001,
3542
+ "loss": 2.3225,
3543
+ "step": 2945
3544
+ },
3545
+ {
3546
+ "epoch": 1.93,
3547
+ "learning_rate": 0.001,
3548
+ "loss": 2.1019,
3549
+ "step": 2950
3550
+ },
3551
+ {
3552
+ "epoch": 1.93,
3553
+ "learning_rate": 0.001,
3554
+ "loss": 2.3213,
3555
+ "step": 2955
3556
+ },
3557
+ {
3558
+ "epoch": 1.94,
3559
+ "learning_rate": 0.001,
3560
+ "loss": 2.4173,
3561
+ "step": 2960
3562
+ },
3563
+ {
3564
+ "epoch": 1.94,
3565
+ "learning_rate": 0.001,
3566
+ "loss": 2.1919,
3567
+ "step": 2965
3568
+ },
3569
+ {
3570
+ "epoch": 1.94,
3571
+ "learning_rate": 0.001,
3572
+ "loss": 2.1733,
3573
+ "step": 2970
3574
+ },
3575
+ {
3576
+ "epoch": 1.95,
3577
+ "learning_rate": 0.001,
3578
+ "loss": 2.3576,
3579
+ "step": 2975
3580
+ },
3581
+ {
3582
+ "epoch": 1.95,
3583
+ "learning_rate": 0.001,
3584
+ "loss": 2.0042,
3585
+ "step": 2980
3586
+ },
3587
+ {
3588
+ "epoch": 1.95,
3589
+ "learning_rate": 0.001,
3590
+ "loss": 2.0977,
3591
+ "step": 2985
3592
+ },
3593
+ {
3594
+ "epoch": 1.96,
3595
+ "learning_rate": 0.001,
3596
+ "loss": 2.2674,
3597
+ "step": 2990
3598
+ },
3599
+ {
3600
+ "epoch": 1.96,
3601
+ "learning_rate": 0.001,
3602
+ "loss": 1.9316,
3603
+ "step": 2995
3604
+ },
3605
+ {
3606
+ "epoch": 1.96,
3607
+ "learning_rate": 0.001,
3608
+ "loss": 2.2472,
3609
+ "step": 3000
3610
+ },
3611
+ {
3612
+ "epoch": 1.97,
3613
+ "learning_rate": 0.001,
3614
+ "loss": 2.3264,
3615
+ "step": 3005
3616
+ },
3617
+ {
3618
+ "epoch": 1.97,
3619
+ "learning_rate": 0.001,
3620
+ "loss": 2.1732,
3621
+ "step": 3010
3622
+ },
3623
+ {
3624
+ "epoch": 1.97,
3625
+ "learning_rate": 0.001,
3626
+ "loss": 2.3932,
3627
+ "step": 3015
3628
+ },
3629
+ {
3630
+ "epoch": 1.98,
3631
+ "learning_rate": 0.001,
3632
+ "loss": 2.168,
3633
+ "step": 3020
3634
+ },
3635
+ {
3636
+ "epoch": 1.98,
3637
+ "learning_rate": 0.001,
3638
+ "loss": 2.2907,
3639
+ "step": 3025
3640
+ },
3641
+ {
3642
+ "epoch": 1.98,
3643
+ "learning_rate": 0.001,
3644
+ "loss": 2.1086,
3645
+ "step": 3030
3646
+ },
3647
+ {
3648
+ "epoch": 1.99,
3649
+ "learning_rate": 0.001,
3650
+ "loss": 2.2868,
3651
+ "step": 3035
3652
+ },
3653
+ {
3654
+ "epoch": 1.99,
3655
+ "learning_rate": 0.001,
3656
+ "loss": 1.9612,
3657
+ "step": 3040
3658
+ },
3659
+ {
3660
+ "epoch": 1.99,
3661
+ "learning_rate": 0.001,
3662
+ "loss": 2.1025,
3663
+ "step": 3045
3664
+ },
3665
+ {
3666
+ "epoch": 2.0,
3667
+ "learning_rate": 0.001,
3668
+ "loss": 2.1001,
3669
+ "step": 3050
3670
+ },
3671
+ {
3672
+ "epoch": 2.0,
3673
+ "learning_rate": 0.001,
3674
+ "loss": 2.0419,
3675
+ "step": 3055
3676
+ },
3677
+ {
3678
+ "epoch": 2.0,
3679
+ "learning_rate": 0.001,
3680
+ "loss": 2.1358,
3681
+ "step": 3060
3682
+ },
3683
+ {
3684
+ "epoch": 2.01,
3685
+ "learning_rate": 0.001,
3686
+ "loss": 1.762,
3687
+ "step": 3065
3688
+ },
3689
+ {
3690
+ "epoch": 2.01,
3691
+ "learning_rate": 0.001,
3692
+ "loss": 1.8736,
3693
+ "step": 3070
3694
+ },
3695
+ {
3696
+ "epoch": 2.01,
3697
+ "learning_rate": 0.001,
3698
+ "loss": 1.7017,
3699
+ "step": 3075
3700
+ },
3701
+ {
3702
+ "epoch": 2.02,
3703
+ "learning_rate": 0.001,
3704
+ "loss": 2.0051,
3705
+ "step": 3080
3706
+ },
3707
+ {
3708
+ "epoch": 2.02,
3709
+ "learning_rate": 0.001,
3710
+ "loss": 1.9062,
3711
+ "step": 3085
3712
+ },
3713
+ {
3714
+ "epoch": 2.02,
3715
+ "learning_rate": 0.001,
3716
+ "loss": 1.8619,
3717
+ "step": 3090
3718
+ },
3719
+ {
3720
+ "epoch": 2.03,
3721
+ "learning_rate": 0.001,
3722
+ "loss": 1.9188,
3723
+ "step": 3095
3724
+ },
3725
+ {
3726
+ "epoch": 2.03,
3727
+ "learning_rate": 0.001,
3728
+ "loss": 1.7303,
3729
+ "step": 3100
3730
+ },
3731
+ {
3732
+ "epoch": 2.03,
3733
+ "learning_rate": 0.001,
3734
+ "loss": 1.846,
3735
+ "step": 3105
3736
+ },
3737
+ {
3738
+ "epoch": 2.04,
3739
+ "learning_rate": 0.001,
3740
+ "loss": 1.8145,
3741
+ "step": 3110
3742
+ },
3743
+ {
3744
+ "epoch": 2.04,
3745
+ "learning_rate": 0.001,
3746
+ "loss": 1.8482,
3747
+ "step": 3115
3748
+ },
3749
+ {
3750
+ "epoch": 2.04,
3751
+ "learning_rate": 0.001,
3752
+ "loss": 1.5815,
3753
+ "step": 3120
3754
+ },
3755
+ {
3756
+ "epoch": 2.05,
3757
+ "learning_rate": 0.001,
3758
+ "loss": 1.5672,
3759
+ "step": 3125
3760
+ },
3761
+ {
3762
+ "epoch": 2.05,
3763
+ "learning_rate": 0.001,
3764
+ "loss": 1.7365,
3765
+ "step": 3130
3766
+ },
3767
+ {
3768
+ "epoch": 2.05,
3769
+ "learning_rate": 0.001,
3770
+ "loss": 1.971,
3771
+ "step": 3135
3772
+ },
3773
+ {
3774
+ "epoch": 2.05,
3775
+ "learning_rate": 0.001,
3776
+ "loss": 1.9756,
3777
+ "step": 3140
3778
+ },
3779
+ {
3780
+ "epoch": 2.06,
3781
+ "learning_rate": 0.001,
3782
+ "loss": 1.8266,
3783
+ "step": 3145
3784
+ },
3785
+ {
3786
+ "epoch": 2.06,
3787
+ "learning_rate": 0.001,
3788
+ "loss": 1.9481,
3789
+ "step": 3150
3790
+ },
3791
+ {
3792
+ "epoch": 2.06,
3793
+ "learning_rate": 0.001,
3794
+ "loss": 1.7729,
3795
+ "step": 3155
3796
+ },
3797
+ {
3798
+ "epoch": 2.07,
3799
+ "learning_rate": 0.001,
3800
+ "loss": 1.7883,
3801
+ "step": 3160
3802
+ },
3803
+ {
3804
+ "epoch": 2.07,
3805
+ "learning_rate": 0.001,
3806
+ "loss": 1.6513,
3807
+ "step": 3165
3808
+ },
3809
+ {
3810
+ "epoch": 2.07,
3811
+ "learning_rate": 0.001,
3812
+ "loss": 1.9425,
3813
+ "step": 3170
3814
+ },
3815
+ {
3816
+ "epoch": 2.08,
3817
+ "learning_rate": 0.001,
3818
+ "loss": 1.7869,
3819
+ "step": 3175
3820
+ },
3821
+ {
3822
+ "epoch": 2.08,
3823
+ "learning_rate": 0.001,
3824
+ "loss": 1.9321,
3825
+ "step": 3180
3826
+ },
3827
+ {
3828
+ "epoch": 2.08,
3829
+ "learning_rate": 0.001,
3830
+ "loss": 2.0544,
3831
+ "step": 3185
3832
+ },
3833
+ {
3834
+ "epoch": 2.09,
3835
+ "learning_rate": 0.001,
3836
+ "loss": 1.9293,
3837
+ "step": 3190
3838
+ },
3839
+ {
3840
+ "epoch": 2.09,
3841
+ "learning_rate": 0.001,
3842
+ "loss": 1.8088,
3843
+ "step": 3195
3844
+ },
3845
+ {
3846
+ "epoch": 2.09,
3847
+ "learning_rate": 0.001,
3848
+ "loss": 1.9035,
3849
+ "step": 3200
3850
+ },
3851
+ {
3852
+ "epoch": 2.1,
3853
+ "learning_rate": 0.001,
3854
+ "loss": 1.8003,
3855
+ "step": 3205
3856
+ },
3857
+ {
3858
+ "epoch": 2.1,
3859
+ "learning_rate": 0.001,
3860
+ "loss": 1.924,
3861
+ "step": 3210
3862
+ },
3863
+ {
3864
+ "epoch": 2.1,
3865
+ "learning_rate": 0.001,
3866
+ "loss": 1.5344,
3867
+ "step": 3215
3868
+ },
3869
+ {
3870
+ "epoch": 2.11,
3871
+ "learning_rate": 0.001,
3872
+ "loss": 1.7529,
3873
+ "step": 3220
3874
+ },
3875
+ {
3876
+ "epoch": 2.11,
3877
+ "learning_rate": 0.001,
3878
+ "loss": 1.9707,
3879
+ "step": 3225
3880
+ },
3881
+ {
3882
+ "epoch": 2.11,
3883
+ "learning_rate": 0.001,
3884
+ "loss": 2.1602,
3885
+ "step": 3230
3886
+ },
3887
+ {
3888
+ "epoch": 2.12,
3889
+ "learning_rate": 0.001,
3890
+ "loss": 2.0995,
3891
+ "step": 3235
3892
+ },
3893
+ {
3894
+ "epoch": 2.12,
3895
+ "learning_rate": 0.001,
3896
+ "loss": 1.7761,
3897
+ "step": 3240
3898
+ },
3899
+ {
3900
+ "epoch": 2.12,
3901
+ "learning_rate": 0.001,
3902
+ "loss": 1.7302,
3903
+ "step": 3245
3904
+ },
3905
+ {
3906
+ "epoch": 2.13,
3907
+ "learning_rate": 0.001,
3908
+ "loss": 2.0175,
3909
+ "step": 3250
3910
+ },
3911
+ {
3912
+ "epoch": 2.13,
3913
+ "learning_rate": 0.001,
3914
+ "loss": 1.9675,
3915
+ "step": 3255
3916
+ },
3917
+ {
3918
+ "epoch": 2.13,
3919
+ "learning_rate": 0.001,
3920
+ "loss": 1.7262,
3921
+ "step": 3260
3922
+ },
3923
+ {
3924
+ "epoch": 2.14,
3925
+ "learning_rate": 0.001,
3926
+ "loss": 1.8225,
3927
+ "step": 3265
3928
+ },
3929
+ {
3930
+ "epoch": 2.14,
3931
+ "learning_rate": 0.001,
3932
+ "loss": 1.9512,
3933
+ "step": 3270
3934
+ },
3935
+ {
3936
+ "epoch": 2.14,
3937
+ "learning_rate": 0.001,
3938
+ "loss": 1.8595,
3939
+ "step": 3275
3940
+ },
3941
+ {
3942
+ "epoch": 2.15,
3943
+ "learning_rate": 0.001,
3944
+ "loss": 1.8585,
3945
+ "step": 3280
3946
+ },
3947
+ {
3948
+ "epoch": 2.15,
3949
+ "learning_rate": 0.001,
3950
+ "loss": 1.8572,
3951
+ "step": 3285
3952
+ },
3953
+ {
3954
+ "epoch": 2.15,
3955
+ "learning_rate": 0.001,
3956
+ "loss": 1.9084,
3957
+ "step": 3290
3958
+ },
3959
+ {
3960
+ "epoch": 2.16,
3961
+ "learning_rate": 0.001,
3962
+ "loss": 1.9047,
3963
+ "step": 3295
3964
+ },
3965
+ {
3966
+ "epoch": 2.16,
3967
+ "learning_rate": 0.001,
3968
+ "loss": 2.0312,
3969
+ "step": 3300
3970
+ },
3971
+ {
3972
+ "epoch": 2.16,
3973
+ "learning_rate": 0.001,
3974
+ "loss": 1.7408,
3975
+ "step": 3305
3976
+ },
3977
+ {
3978
+ "epoch": 2.17,
3979
+ "learning_rate": 0.001,
3980
+ "loss": 1.9193,
3981
+ "step": 3310
3982
+ },
3983
+ {
3984
+ "epoch": 2.17,
3985
+ "learning_rate": 0.001,
3986
+ "loss": 1.8676,
3987
+ "step": 3315
3988
+ },
3989
+ {
3990
+ "epoch": 2.17,
3991
+ "learning_rate": 0.001,
3992
+ "loss": 1.9841,
3993
+ "step": 3320
3994
+ },
3995
+ {
3996
+ "epoch": 2.18,
3997
+ "learning_rate": 0.001,
3998
+ "loss": 2.0652,
3999
+ "step": 3325
4000
+ },
4001
+ {
4002
+ "epoch": 2.18,
4003
+ "learning_rate": 0.001,
4004
+ "loss": 1.7531,
4005
+ "step": 3330
4006
+ },
4007
+ {
4008
+ "epoch": 2.18,
4009
+ "learning_rate": 0.001,
4010
+ "loss": 1.8534,
4011
+ "step": 3335
4012
+ },
4013
+ {
4014
+ "epoch": 2.19,
4015
+ "learning_rate": 0.001,
4016
+ "loss": 1.9164,
4017
+ "step": 3340
4018
+ },
4019
+ {
4020
+ "epoch": 2.19,
4021
+ "learning_rate": 0.001,
4022
+ "loss": 2.1042,
4023
+ "step": 3345
4024
+ },
4025
+ {
4026
+ "epoch": 2.19,
4027
+ "learning_rate": 0.001,
4028
+ "loss": 1.7698,
4029
+ "step": 3350
4030
+ },
4031
+ {
4032
+ "epoch": 2.2,
4033
+ "learning_rate": 0.001,
4034
+ "loss": 1.9511,
4035
+ "step": 3355
4036
+ },
4037
+ {
4038
+ "epoch": 2.2,
4039
+ "learning_rate": 0.001,
4040
+ "loss": 1.7882,
4041
+ "step": 3360
4042
+ },
4043
+ {
4044
+ "epoch": 2.2,
4045
+ "learning_rate": 0.001,
4046
+ "loss": 2.0131,
4047
+ "step": 3365
4048
+ },
4049
+ {
4050
+ "epoch": 2.21,
4051
+ "learning_rate": 0.001,
4052
+ "loss": 1.8166,
4053
+ "step": 3370
4054
+ },
4055
+ {
4056
+ "epoch": 2.21,
4057
+ "learning_rate": 0.001,
4058
+ "loss": 1.7719,
4059
+ "step": 3375
4060
+ },
4061
+ {
4062
+ "epoch": 2.21,
4063
+ "learning_rate": 0.001,
4064
+ "loss": 1.7812,
4065
+ "step": 3380
4066
+ },
4067
+ {
4068
+ "epoch": 2.22,
4069
+ "learning_rate": 0.001,
4070
+ "loss": 1.8818,
4071
+ "step": 3385
4072
+ },
4073
+ {
4074
+ "epoch": 2.22,
4075
+ "learning_rate": 0.001,
4076
+ "loss": 1.8874,
4077
+ "step": 3390
4078
+ },
4079
+ {
4080
+ "epoch": 2.22,
4081
+ "learning_rate": 0.001,
4082
+ "loss": 1.8422,
4083
+ "step": 3395
4084
+ },
4085
+ {
4086
+ "epoch": 2.23,
4087
+ "learning_rate": 0.001,
4088
+ "loss": 2.1017,
4089
+ "step": 3400
4090
+ },
4091
+ {
4092
+ "epoch": 2.23,
4093
+ "learning_rate": 0.001,
4094
+ "loss": 1.8183,
4095
+ "step": 3405
4096
+ },
4097
+ {
4098
+ "epoch": 2.23,
4099
+ "learning_rate": 0.001,
4100
+ "loss": 1.9675,
4101
+ "step": 3410
4102
+ },
4103
+ {
4104
+ "epoch": 2.23,
4105
+ "learning_rate": 0.001,
4106
+ "loss": 1.7103,
4107
+ "step": 3415
4108
+ },
4109
+ {
4110
+ "epoch": 2.24,
4111
+ "learning_rate": 0.001,
4112
+ "loss": 1.9424,
4113
+ "step": 3420
4114
+ },
4115
+ {
4116
+ "epoch": 2.24,
4117
+ "learning_rate": 0.001,
4118
+ "loss": 1.6799,
4119
+ "step": 3425
4120
+ },
4121
+ {
4122
+ "epoch": 2.24,
4123
+ "learning_rate": 0.001,
4124
+ "loss": 1.6281,
4125
+ "step": 3430
4126
+ },
4127
+ {
4128
+ "epoch": 2.25,
4129
+ "learning_rate": 0.001,
4130
+ "loss": 1.9875,
4131
+ "step": 3435
4132
+ },
4133
+ {
4134
+ "epoch": 2.25,
4135
+ "learning_rate": 0.001,
4136
+ "loss": 1.6356,
4137
+ "step": 3440
4138
+ },
4139
+ {
4140
+ "epoch": 2.25,
4141
+ "learning_rate": 0.001,
4142
+ "loss": 1.8295,
4143
+ "step": 3445
4144
+ },
4145
+ {
4146
+ "epoch": 2.26,
4147
+ "learning_rate": 0.001,
4148
+ "loss": 2.1965,
4149
+ "step": 3450
4150
+ },
4151
+ {
4152
+ "epoch": 2.26,
4153
+ "learning_rate": 0.001,
4154
+ "loss": 1.8972,
4155
+ "step": 3455
4156
+ },
4157
+ {
4158
+ "epoch": 2.26,
4159
+ "learning_rate": 0.001,
4160
+ "loss": 2.1296,
4161
+ "step": 3460
4162
+ },
4163
+ {
4164
+ "epoch": 2.27,
4165
+ "learning_rate": 0.001,
4166
+ "loss": 1.987,
4167
+ "step": 3465
4168
+ },
4169
+ {
4170
+ "epoch": 2.27,
4171
+ "learning_rate": 0.001,
4172
+ "loss": 1.7851,
4173
+ "step": 3470
4174
+ },
4175
+ {
4176
+ "epoch": 2.27,
4177
+ "learning_rate": 0.001,
4178
+ "loss": 1.758,
4179
+ "step": 3475
4180
+ },
4181
+ {
4182
+ "epoch": 2.28,
4183
+ "learning_rate": 0.001,
4184
+ "loss": 1.752,
4185
+ "step": 3480
4186
+ },
4187
+ {
4188
+ "epoch": 2.28,
4189
+ "learning_rate": 0.001,
4190
+ "loss": 1.9093,
4191
+ "step": 3485
4192
+ },
4193
+ {
4194
+ "epoch": 2.28,
4195
+ "learning_rate": 0.001,
4196
+ "loss": 1.9931,
4197
+ "step": 3490
4198
+ },
4199
+ {
4200
+ "epoch": 2.29,
4201
+ "learning_rate": 0.001,
4202
+ "loss": 1.8762,
4203
+ "step": 3495
4204
+ },
4205
+ {
4206
+ "epoch": 2.29,
4207
+ "learning_rate": 0.001,
4208
+ "loss": 1.9769,
4209
+ "step": 3500
4210
+ },
4211
+ {
4212
+ "epoch": 2.29,
4213
+ "learning_rate": 0.001,
4214
+ "loss": 2.0007,
4215
+ "step": 3505
4216
+ },
4217
+ {
4218
+ "epoch": 2.3,
4219
+ "learning_rate": 0.001,
4220
+ "loss": 2.2291,
4221
+ "step": 3510
4222
+ },
4223
+ {
4224
+ "epoch": 2.3,
4225
+ "learning_rate": 0.001,
4226
+ "loss": 2.0776,
4227
+ "step": 3515
4228
+ },
4229
+ {
4230
+ "epoch": 2.3,
4231
+ "learning_rate": 0.001,
4232
+ "loss": 2.2868,
4233
+ "step": 3520
4234
+ },
4235
+ {
4236
+ "epoch": 2.31,
4237
+ "learning_rate": 0.001,
4238
+ "loss": 2.0916,
4239
+ "step": 3525
4240
+ },
4241
+ {
4242
+ "epoch": 2.31,
4243
+ "learning_rate": 0.001,
4244
+ "loss": 2.0035,
4245
+ "step": 3530
4246
+ },
4247
+ {
4248
+ "epoch": 2.31,
4249
+ "learning_rate": 0.001,
4250
+ "loss": 1.9706,
4251
+ "step": 3535
4252
+ },
4253
+ {
4254
+ "epoch": 2.32,
4255
+ "learning_rate": 0.001,
4256
+ "loss": 1.6881,
4257
+ "step": 3540
4258
+ },
4259
+ {
4260
+ "epoch": 2.32,
4261
+ "learning_rate": 0.001,
4262
+ "loss": 2.0781,
4263
+ "step": 3545
4264
+ },
4265
+ {
4266
+ "epoch": 2.32,
4267
+ "learning_rate": 0.001,
4268
+ "loss": 1.9761,
4269
+ "step": 3550
4270
+ },
4271
+ {
4272
+ "epoch": 2.33,
4273
+ "learning_rate": 0.001,
4274
+ "loss": 1.9865,
4275
+ "step": 3555
4276
+ },
4277
+ {
4278
+ "epoch": 2.33,
4279
+ "learning_rate": 0.001,
4280
+ "loss": 1.7636,
4281
+ "step": 3560
4282
+ },
4283
+ {
4284
+ "epoch": 2.33,
4285
+ "learning_rate": 0.001,
4286
+ "loss": 2.1409,
4287
+ "step": 3565
4288
+ },
4289
+ {
4290
+ "epoch": 2.34,
4291
+ "learning_rate": 0.001,
4292
+ "loss": 2.11,
4293
+ "step": 3570
4294
+ },
4295
+ {
4296
+ "epoch": 2.34,
4297
+ "learning_rate": 0.001,
4298
+ "loss": 1.7359,
4299
+ "step": 3575
4300
+ },
4301
+ {
4302
+ "epoch": 2.34,
4303
+ "learning_rate": 0.001,
4304
+ "loss": 1.9619,
4305
+ "step": 3580
4306
+ },
4307
+ {
4308
+ "epoch": 2.35,
4309
+ "learning_rate": 0.001,
4310
+ "loss": 2.0434,
4311
+ "step": 3585
4312
+ },
4313
+ {
4314
+ "epoch": 2.35,
4315
+ "learning_rate": 0.001,
4316
+ "loss": 1.8588,
4317
+ "step": 3590
4318
+ },
4319
+ {
4320
+ "epoch": 2.35,
4321
+ "learning_rate": 0.001,
4322
+ "loss": 2.0681,
4323
+ "step": 3595
4324
+ },
4325
+ {
4326
+ "epoch": 2.36,
4327
+ "learning_rate": 0.001,
4328
+ "loss": 1.8467,
4329
+ "step": 3600
4330
+ },
4331
+ {
4332
+ "epoch": 2.36,
4333
+ "learning_rate": 0.001,
4334
+ "loss": 1.5267,
4335
+ "step": 3605
4336
+ },
4337
+ {
4338
+ "epoch": 2.36,
4339
+ "learning_rate": 0.001,
4340
+ "loss": 1.9642,
4341
+ "step": 3610
4342
+ },
4343
+ {
4344
+ "epoch": 2.37,
4345
+ "learning_rate": 0.001,
4346
+ "loss": 1.9597,
4347
+ "step": 3615
4348
+ },
4349
+ {
4350
+ "epoch": 2.37,
4351
+ "learning_rate": 0.001,
4352
+ "loss": 1.8687,
4353
+ "step": 3620
4354
+ },
4355
+ {
4356
+ "epoch": 2.37,
4357
+ "learning_rate": 0.001,
4358
+ "loss": 2.0584,
4359
+ "step": 3625
4360
+ },
4361
+ {
4362
+ "epoch": 2.38,
4363
+ "learning_rate": 0.001,
4364
+ "loss": 2.0966,
4365
+ "step": 3630
4366
+ },
4367
+ {
4368
+ "epoch": 2.38,
4369
+ "learning_rate": 0.001,
4370
+ "loss": 2.0021,
4371
+ "step": 3635
4372
+ },
4373
+ {
4374
+ "epoch": 2.38,
4375
+ "learning_rate": 0.001,
4376
+ "loss": 1.8767,
4377
+ "step": 3640
4378
+ },
4379
+ {
4380
+ "epoch": 2.39,
4381
+ "learning_rate": 0.001,
4382
+ "loss": 1.713,
4383
+ "step": 3645
4384
+ },
4385
+ {
4386
+ "epoch": 2.39,
4387
+ "learning_rate": 0.001,
4388
+ "loss": 1.5825,
4389
+ "step": 3650
4390
+ },
4391
+ {
4392
+ "epoch": 2.39,
4393
+ "learning_rate": 0.001,
4394
+ "loss": 1.8617,
4395
+ "step": 3655
4396
+ },
4397
+ {
4398
+ "epoch": 2.4,
4399
+ "learning_rate": 0.001,
4400
+ "loss": 2.0615,
4401
+ "step": 3660
4402
+ },
4403
+ {
4404
+ "epoch": 2.4,
4405
+ "learning_rate": 0.001,
4406
+ "loss": 1.6553,
4407
+ "step": 3665
4408
+ },
4409
+ {
4410
+ "epoch": 2.4,
4411
+ "learning_rate": 0.001,
4412
+ "loss": 1.6166,
4413
+ "step": 3670
4414
+ },
4415
+ {
4416
+ "epoch": 2.41,
4417
+ "learning_rate": 0.001,
4418
+ "loss": 1.6974,
4419
+ "step": 3675
4420
+ },
4421
+ {
4422
+ "epoch": 2.41,
4423
+ "learning_rate": 0.001,
4424
+ "loss": 2.0093,
4425
+ "step": 3680
4426
+ },
4427
+ {
4428
+ "epoch": 2.41,
4429
+ "learning_rate": 0.001,
4430
+ "loss": 1.8497,
4431
+ "step": 3685
4432
+ },
4433
+ {
4434
+ "epoch": 2.41,
4435
+ "learning_rate": 0.001,
4436
+ "loss": 1.7226,
4437
+ "step": 3690
4438
+ },
4439
+ {
4440
+ "epoch": 2.42,
4441
+ "learning_rate": 0.001,
4442
+ "loss": 1.668,
4443
+ "step": 3695
4444
+ },
4445
+ {
4446
+ "epoch": 2.42,
4447
+ "learning_rate": 0.001,
4448
+ "loss": 2.115,
4449
+ "step": 3700
4450
+ },
4451
+ {
4452
+ "epoch": 2.42,
4453
+ "learning_rate": 0.001,
4454
+ "loss": 2.145,
4455
+ "step": 3705
4456
+ },
4457
+ {
4458
+ "epoch": 2.43,
4459
+ "learning_rate": 0.001,
4460
+ "loss": 1.7443,
4461
+ "step": 3710
4462
+ },
4463
+ {
4464
+ "epoch": 2.43,
4465
+ "learning_rate": 0.001,
4466
+ "loss": 1.7406,
4467
+ "step": 3715
4468
+ },
4469
+ {
4470
+ "epoch": 2.43,
4471
+ "learning_rate": 0.001,
4472
+ "loss": 1.8569,
4473
+ "step": 3720
4474
+ },
4475
+ {
4476
+ "epoch": 2.44,
4477
+ "learning_rate": 0.001,
4478
+ "loss": 2.0726,
4479
+ "step": 3725
4480
+ },
4481
+ {
4482
+ "epoch": 2.44,
4483
+ "learning_rate": 0.001,
4484
+ "loss": 2.1467,
4485
+ "step": 3730
4486
+ },
4487
+ {
4488
+ "epoch": 2.44,
4489
+ "learning_rate": 0.001,
4490
+ "loss": 2.019,
4491
+ "step": 3735
4492
+ },
4493
+ {
4494
+ "epoch": 2.45,
4495
+ "learning_rate": 0.001,
4496
+ "loss": 2.1104,
4497
+ "step": 3740
4498
+ },
4499
+ {
4500
+ "epoch": 2.45,
4501
+ "learning_rate": 0.001,
4502
+ "loss": 2.1444,
4503
+ "step": 3745
4504
+ },
4505
+ {
4506
+ "epoch": 2.45,
4507
+ "learning_rate": 0.001,
4508
+ "loss": 2.0757,
4509
+ "step": 3750
4510
+ },
4511
+ {
4512
+ "epoch": 2.46,
4513
+ "learning_rate": 0.001,
4514
+ "loss": 1.7169,
4515
+ "step": 3755
4516
+ },
4517
+ {
4518
+ "epoch": 2.46,
4519
+ "learning_rate": 0.001,
4520
+ "loss": 1.7558,
4521
+ "step": 3760
4522
+ },
4523
+ {
4524
+ "epoch": 2.46,
4525
+ "learning_rate": 0.001,
4526
+ "loss": 1.6213,
4527
+ "step": 3765
4528
+ },
4529
+ {
4530
+ "epoch": 2.47,
4531
+ "learning_rate": 0.001,
4532
+ "loss": 1.8306,
4533
+ "step": 3770
4534
+ },
4535
+ {
4536
+ "epoch": 2.47,
4537
+ "learning_rate": 0.001,
4538
+ "loss": 2.015,
4539
+ "step": 3775
4540
+ },
4541
+ {
4542
+ "epoch": 2.47,
4543
+ "learning_rate": 0.001,
4544
+ "loss": 2.0952,
4545
+ "step": 3780
4546
+ },
4547
+ {
4548
+ "epoch": 2.48,
4549
+ "learning_rate": 0.001,
4550
+ "loss": 1.6549,
4551
+ "step": 3785
4552
+ },
4553
+ {
4554
+ "epoch": 2.48,
4555
+ "learning_rate": 0.001,
4556
+ "loss": 1.8965,
4557
+ "step": 3790
4558
+ },
4559
+ {
4560
+ "epoch": 2.48,
4561
+ "learning_rate": 0.001,
4562
+ "loss": 2.0753,
4563
+ "step": 3795
4564
+ },
4565
+ {
4566
+ "epoch": 2.49,
4567
+ "learning_rate": 0.001,
4568
+ "loss": 2.135,
4569
+ "step": 3800
4570
+ },
4571
+ {
4572
+ "epoch": 2.49,
4573
+ "learning_rate": 0.001,
4574
+ "loss": 1.8428,
4575
+ "step": 3805
4576
+ },
4577
+ {
4578
+ "epoch": 2.49,
4579
+ "learning_rate": 0.001,
4580
+ "loss": 2.1602,
4581
+ "step": 3810
4582
+ },
4583
+ {
4584
+ "epoch": 2.5,
4585
+ "learning_rate": 0.001,
4586
+ "loss": 1.8219,
4587
+ "step": 3815
4588
+ },
4589
+ {
4590
+ "epoch": 2.5,
4591
+ "learning_rate": 0.001,
4592
+ "loss": 1.8266,
4593
+ "step": 3820
4594
+ },
4595
+ {
4596
+ "epoch": 2.5,
4597
+ "learning_rate": 0.001,
4598
+ "loss": 1.839,
4599
+ "step": 3825
4600
+ },
4601
+ {
4602
+ "epoch": 2.51,
4603
+ "learning_rate": 0.001,
4604
+ "loss": 1.8746,
4605
+ "step": 3830
4606
+ },
4607
+ {
4608
+ "epoch": 2.51,
4609
+ "learning_rate": 0.001,
4610
+ "loss": 2.1668,
4611
+ "step": 3835
4612
+ },
4613
+ {
4614
+ "epoch": 2.51,
4615
+ "learning_rate": 0.001,
4616
+ "loss": 2.1224,
4617
+ "step": 3840
4618
+ },
4619
+ {
4620
+ "epoch": 2.52,
4621
+ "learning_rate": 0.001,
4622
+ "loss": 2.0099,
4623
+ "step": 3845
4624
+ },
4625
+ {
4626
+ "epoch": 2.52,
4627
+ "learning_rate": 0.001,
4628
+ "loss": 2.2438,
4629
+ "step": 3850
4630
+ },
4631
+ {
4632
+ "epoch": 2.52,
4633
+ "learning_rate": 0.001,
4634
+ "loss": 1.8494,
4635
+ "step": 3855
4636
+ },
4637
+ {
4638
+ "epoch": 2.53,
4639
+ "learning_rate": 0.001,
4640
+ "loss": 1.8063,
4641
+ "step": 3860
4642
+ },
4643
+ {
4644
+ "epoch": 2.53,
4645
+ "learning_rate": 0.001,
4646
+ "loss": 1.7068,
4647
+ "step": 3865
4648
+ },
4649
+ {
4650
+ "epoch": 2.53,
4651
+ "learning_rate": 0.001,
4652
+ "loss": 1.8158,
4653
+ "step": 3870
4654
+ },
4655
+ {
4656
+ "epoch": 2.54,
4657
+ "learning_rate": 0.001,
4658
+ "loss": 1.6616,
4659
+ "step": 3875
4660
+ },
4661
+ {
4662
+ "epoch": 2.54,
4663
+ "learning_rate": 0.001,
4664
+ "loss": 1.9542,
4665
+ "step": 3880
4666
+ },
4667
+ {
4668
+ "epoch": 2.54,
4669
+ "learning_rate": 0.001,
4670
+ "loss": 1.9595,
4671
+ "step": 3885
4672
+ },
4673
+ {
4674
+ "epoch": 2.55,
4675
+ "learning_rate": 0.001,
4676
+ "loss": 2.1507,
4677
+ "step": 3890
4678
+ },
4679
+ {
4680
+ "epoch": 2.55,
4681
+ "learning_rate": 0.001,
4682
+ "loss": 1.883,
4683
+ "step": 3895
4684
+ },
4685
+ {
4686
+ "epoch": 2.55,
4687
+ "learning_rate": 0.001,
4688
+ "loss": 1.6634,
4689
+ "step": 3900
4690
+ },
4691
+ {
4692
+ "epoch": 2.56,
4693
+ "learning_rate": 0.001,
4694
+ "loss": 1.7621,
4695
+ "step": 3905
4696
+ },
4697
+ {
4698
+ "epoch": 2.56,
4699
+ "learning_rate": 0.001,
4700
+ "loss": 1.9474,
4701
+ "step": 3910
4702
+ },
4703
+ {
4704
+ "epoch": 2.56,
4705
+ "learning_rate": 0.001,
4706
+ "loss": 2.094,
4707
+ "step": 3915
4708
+ },
4709
+ {
4710
+ "epoch": 2.57,
4711
+ "learning_rate": 0.001,
4712
+ "loss": 2.0111,
4713
+ "step": 3920
4714
+ },
4715
+ {
4716
+ "epoch": 2.57,
4717
+ "learning_rate": 0.001,
4718
+ "loss": 1.872,
4719
+ "step": 3925
4720
+ },
4721
+ {
4722
+ "epoch": 2.57,
4723
+ "learning_rate": 0.001,
4724
+ "loss": 1.604,
4725
+ "step": 3930
4726
+ },
4727
+ {
4728
+ "epoch": 2.58,
4729
+ "learning_rate": 0.001,
4730
+ "loss": 1.8784,
4731
+ "step": 3935
4732
+ },
4733
+ {
4734
+ "epoch": 2.58,
4735
+ "learning_rate": 0.001,
4736
+ "loss": 1.9175,
4737
+ "step": 3940
4738
+ },
4739
+ {
4740
+ "epoch": 2.58,
4741
+ "learning_rate": 0.001,
4742
+ "loss": 1.8607,
4743
+ "step": 3945
4744
+ },
4745
+ {
4746
+ "epoch": 2.59,
4747
+ "learning_rate": 0.001,
4748
+ "loss": 1.9768,
4749
+ "step": 3950
4750
+ },
4751
+ {
4752
+ "epoch": 2.59,
4753
+ "learning_rate": 0.001,
4754
+ "loss": 1.9017,
4755
+ "step": 3955
4756
+ },
4757
+ {
4758
+ "epoch": 2.59,
4759
+ "learning_rate": 0.001,
4760
+ "loss": 1.6314,
4761
+ "step": 3960
4762
+ },
4763
+ {
4764
+ "epoch": 2.59,
4765
+ "learning_rate": 0.001,
4766
+ "loss": 1.8859,
4767
+ "step": 3965
4768
+ },
4769
+ {
4770
+ "epoch": 2.6,
4771
+ "learning_rate": 0.001,
4772
+ "loss": 2.0082,
4773
+ "step": 3970
4774
+ },
4775
+ {
4776
+ "epoch": 2.6,
4777
+ "learning_rate": 0.001,
4778
+ "loss": 1.7938,
4779
+ "step": 3975
4780
+ },
4781
+ {
4782
+ "epoch": 2.6,
4783
+ "learning_rate": 0.001,
4784
+ "loss": 2.0765,
4785
+ "step": 3980
4786
+ },
4787
+ {
4788
+ "epoch": 2.61,
4789
+ "learning_rate": 0.001,
4790
+ "loss": 2.0694,
4791
+ "step": 3985
4792
+ },
4793
+ {
4794
+ "epoch": 2.61,
4795
+ "learning_rate": 0.001,
4796
+ "loss": 1.8571,
4797
+ "step": 3990
4798
+ },
4799
+ {
4800
+ "epoch": 2.61,
4801
+ "learning_rate": 0.001,
4802
+ "loss": 1.6691,
4803
+ "step": 3995
4804
+ },
4805
+ {
4806
+ "epoch": 2.62,
4807
+ "learning_rate": 0.001,
4808
+ "loss": 2.1105,
4809
+ "step": 4000
4810
+ }
4811
+ ],
4812
+ "logging_steps": 5,
4813
+ "max_steps": 7640,
4814
+ "num_train_epochs": 5,
4815
+ "save_steps": 1000,
4816
+ "total_flos": 467140608000000.0,
4817
+ "trial_name": null,
4818
+ "trial_params": null
4819
+ }
checkpoint-4000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026a40a22d79b976af4f05a529a919434f1a1af96981147d87e1c857264d40d7
3
+ size 4027
checkpoint-5000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 512,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 4,
15
+ "num_hidden_layers": 2,
16
+ "num_key_value_heads": 4,
17
+ "pretraining_tp": 2,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.34.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
checkpoint-5000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72076ac2f74cc0ac4749f5e5d7c4decbb53c0f9382578b5b44174e58eb826000
3
+ size 141585770
checkpoint-5000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4711d194ca4729fa35adde6d09f17b2e0a4d365bfbd5ce8f2a83fc22880248a
3
+ size 70790896
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6869750f95a25c4e970298a33adf90e2d7ab52680bf3317239bff1b10103235
3
+ size 14575
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ebabb5b51c7a8df5077fe9fe3ff1e6fd2822beec18f71aadab0884bfb1a2ea
3
+ size 627