TinyPixel commited on
Commit
6ac11d2
·
1 Parent(s): 07f4166

Upload folder using huggingface_hub

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b142003602f7f01ee05e6855c405f84646dff1a8e49668d88a6614f742d4e93
3
  size 121915776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbcf87564e012991ca47d4a0153da5158f67084919dfcb0bfe5f27cd6cc3031
3
  size 121915776
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:161d0cbe64e1872859d6cc7b6a021b960a4f2c3941d5b2dddbf9458ce07c20a0
3
  size 243883386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978bfce6e1e86c47e623d3ab426f4b5a602c31851c010587372757cdb50f0d68
3
  size 243883386
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a5d121795e588100bd33bc9edf9263368604c213bf6fb6c711266a0359aa1d1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b3f3176d085e03a49853887788f3adcaaef45778bbf815fe1240c6fb54bfea
3
  size 14244
trainer_state.json CHANGED
@@ -11,901 +11,901 @@
11
  {
12
  "epoch": 0.02,
13
  "learning_rate": 4.444444444444444e-06,
14
- "loss": 2.3725,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.04,
19
  "learning_rate": 8.888888888888888e-06,
20
- "loss": 2.2594,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.06,
25
  "learning_rate": 1.3333333333333333e-05,
26
- "loss": 2.2795,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.08,
31
  "learning_rate": 1.7777777777777777e-05,
32
- "loss": 2.2708,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.1,
37
  "learning_rate": 1.9999417253661235e-05,
38
- "loss": 2.4065,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.12,
43
  "learning_rate": 1.9994755690455154e-05,
44
- "loss": 2.3711,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.14,
49
  "learning_rate": 1.998543473718677e-05,
50
- "loss": 2.3178,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.16,
55
  "learning_rate": 1.9971458739130598e-05,
56
- "loss": 2.4023,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.18,
61
  "learning_rate": 1.995283421166614e-05,
62
- "loss": 2.1702,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.2,
67
  "learning_rate": 1.9929569837240567e-05,
68
- "loss": 2.0057,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.22,
73
  "learning_rate": 1.990167646132107e-05,
74
- "loss": 2.2092,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.24,
79
  "learning_rate": 1.9869167087338908e-05,
80
- "loss": 2.0733,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.26,
85
  "learning_rate": 1.983205687062742e-05,
86
- "loss": 2.2622,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.28,
91
  "learning_rate": 1.9790363111356838e-05,
92
- "loss": 2.3358,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.3,
97
  "learning_rate": 1.9744105246469264e-05,
98
- "loss": 2.2823,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.32,
103
  "learning_rate": 1.9693304840617456e-05,
104
- "loss": 2.3289,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.34,
109
  "learning_rate": 1.963798557611178e-05,
110
- "loss": 2.235,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.36,
115
  "learning_rate": 1.957817324187987e-05,
116
- "loss": 2.1541,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.38,
121
  "learning_rate": 1.9513895721444286e-05,
122
- "loss": 2.2524,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.4,
127
  "learning_rate": 1.9445182979923657e-05,
128
- "loss": 2.3427,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.42,
133
  "learning_rate": 1.937206705006344e-05,
134
- "loss": 2.136,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.44,
139
  "learning_rate": 1.9294582017302797e-05,
140
- "loss": 2.152,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.46,
145
  "learning_rate": 1.921276400388451e-05,
146
- "loss": 2.1322,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.48,
151
  "learning_rate": 1.9126651152015404e-05,
152
- "loss": 2.2564,
153
  "step": 48
154
  },
155
  {
156
  "epoch": 0.5,
157
  "learning_rate": 1.9036283606085057e-05,
158
- "loss": 2.2246,
159
  "step": 50
160
  },
161
  {
162
  "epoch": 0.52,
163
  "learning_rate": 1.8941703493951163e-05,
164
- "loss": 2.1903,
165
  "step": 52
166
  },
167
  {
168
  "epoch": 0.54,
169
  "learning_rate": 1.8842954907300236e-05,
170
- "loss": 2.1431,
171
  "step": 54
172
  },
173
  {
174
  "epoch": 0.56,
175
  "learning_rate": 1.874008388109276e-05,
176
- "loss": 2.2975,
177
  "step": 56
178
  },
179
  {
180
  "epoch": 0.58,
181
  "learning_rate": 1.863313837210247e-05,
182
- "loss": 2.1324,
183
  "step": 58
184
  },
185
  {
186
  "epoch": 0.6,
187
  "learning_rate": 1.8522168236559693e-05,
188
- "loss": 2.1113,
189
  "step": 60
190
  },
191
  {
192
  "epoch": 0.62,
193
  "learning_rate": 1.840722520690921e-05,
194
- "loss": 2.3031,
195
  "step": 62
196
  },
197
  {
198
  "epoch": 0.64,
199
  "learning_rate": 1.8288362867693414e-05,
200
- "loss": 2.135,
201
  "step": 64
202
  },
203
  {
204
  "epoch": 0.66,
205
  "learning_rate": 1.816563663057211e-05,
206
- "loss": 2.0996,
207
  "step": 66
208
  },
209
  {
210
  "epoch": 0.68,
211
  "learning_rate": 1.8039103708490503e-05,
212
- "loss": 2.2049,
213
  "step": 68
214
  },
215
  {
216
  "epoch": 0.7,
217
  "learning_rate": 1.790882308900746e-05,
218
- "loss": 2.1811,
219
  "step": 70
220
  },
221
  {
222
  "epoch": 0.72,
223
  "learning_rate": 1.7774855506796497e-05,
224
- "loss": 2.1447,
225
  "step": 72
226
  },
227
  {
228
  "epoch": 0.74,
229
  "learning_rate": 1.7637263415332272e-05,
230
- "loss": 2.1883,
231
  "step": 74
232
  },
233
  {
234
  "epoch": 0.76,
235
  "learning_rate": 1.749611095777581e-05,
236
- "loss": 2.143,
237
  "step": 76
238
  },
239
  {
240
  "epoch": 0.78,
241
  "learning_rate": 1.7351463937072008e-05,
242
- "loss": 2.3966,
243
  "step": 78
244
  },
245
  {
246
  "epoch": 0.8,
247
  "learning_rate": 1.7203389785273402e-05,
248
- "loss": 2.1011,
249
  "step": 80
250
  },
251
  {
252
  "epoch": 0.82,
253
  "learning_rate": 1.705195753210446e-05,
254
- "loss": 2.1543,
255
  "step": 82
256
  },
257
  {
258
  "epoch": 0.84,
259
  "learning_rate": 1.6897237772781046e-05,
260
- "loss": 2.3031,
261
  "step": 84
262
  },
263
  {
264
  "epoch": 0.86,
265
  "learning_rate": 1.673930263510011e-05,
266
- "loss": 2.1147,
267
  "step": 86
268
  },
269
  {
270
  "epoch": 0.88,
271
  "learning_rate": 1.6578225745814907e-05,
272
- "loss": 2.2728,
273
  "step": 88
274
  },
275
  {
276
  "epoch": 0.89,
277
  "learning_rate": 1.6414082196311402e-05,
278
- "loss": 2.1936,
279
  "step": 90
280
  },
281
  {
282
  "epoch": 0.91,
283
  "learning_rate": 1.6246948507601915e-05,
284
- "loss": 1.9656,
285
  "step": 92
286
  },
287
  {
288
  "epoch": 0.93,
289
  "learning_rate": 1.607690259465229e-05,
290
- "loss": 2.1498,
291
  "step": 94
292
  },
293
  {
294
  "epoch": 0.95,
295
  "learning_rate": 1.5904023730059227e-05,
296
- "loss": 2.153,
297
  "step": 96
298
  },
299
  {
300
  "epoch": 0.97,
301
  "learning_rate": 1.57283925070947e-05,
302
- "loss": 2.2002,
303
  "step": 98
304
  },
305
  {
306
  "epoch": 0.99,
307
  "learning_rate": 1.55500908021347e-05,
308
- "loss": 1.9758,
309
  "step": 100
310
  },
311
  {
312
  "epoch": 1.01,
313
  "learning_rate": 1.536920173648984e-05,
314
- "loss": 2.1241,
315
  "step": 102
316
  },
317
  {
318
  "epoch": 1.03,
319
  "learning_rate": 1.5185809637655548e-05,
320
- "loss": 2.131,
321
  "step": 104
322
  },
323
  {
324
  "epoch": 1.05,
325
  "learning_rate": 1.5000000000000002e-05,
326
- "loss": 2.2022,
327
  "step": 106
328
  },
329
  {
330
  "epoch": 1.07,
331
  "learning_rate": 1.4811859444908053e-05,
332
- "loss": 2.2409,
333
  "step": 108
334
  },
335
  {
336
  "epoch": 1.09,
337
  "learning_rate": 1.4621475680399771e-05,
338
- "loss": 2.2267,
339
  "step": 110
340
  },
341
  {
342
  "epoch": 1.11,
343
  "learning_rate": 1.4428937460242417e-05,
344
- "loss": 2.1693,
345
  "step": 112
346
  },
347
  {
348
  "epoch": 1.13,
349
  "learning_rate": 1.4234334542574906e-05,
350
- "loss": 2.0854,
351
  "step": 114
352
  },
353
  {
354
  "epoch": 1.15,
355
  "learning_rate": 1.4037757648064019e-05,
356
- "loss": 2.1075,
357
  "step": 116
358
  },
359
  {
360
  "epoch": 1.17,
361
  "learning_rate": 1.3839298417611964e-05,
362
- "loss": 2.0815,
363
  "step": 118
364
  },
365
  {
366
  "epoch": 1.19,
367
  "learning_rate": 1.3639049369634878e-05,
368
- "loss": 2.0867,
369
  "step": 120
370
  },
371
  {
372
  "epoch": 1.21,
373
  "learning_rate": 1.3437103856932266e-05,
374
- "loss": 2.1021,
375
  "step": 122
376
  },
377
  {
378
  "epoch": 1.23,
379
  "learning_rate": 1.3233556023167487e-05,
380
- "loss": 2.0964,
381
  "step": 124
382
  },
383
  {
384
  "epoch": 1.25,
385
  "learning_rate": 1.3028500758979507e-05,
386
- "loss": 2.1726,
387
  "step": 126
388
  },
389
  {
390
  "epoch": 1.27,
391
  "learning_rate": 1.2822033657746478e-05,
392
- "loss": 2.1817,
393
  "step": 128
394
  },
395
  {
396
  "epoch": 1.29,
397
  "learning_rate": 1.2614250971021658e-05,
398
- "loss": 2.092,
399
  "step": 130
400
  },
401
  {
402
  "epoch": 1.31,
403
  "learning_rate": 1.2405249563662539e-05,
404
- "loss": 2.1974,
405
  "step": 132
406
  },
407
  {
408
  "epoch": 1.33,
409
  "learning_rate": 1.2195126868674052e-05,
410
- "loss": 2.2407,
411
  "step": 134
412
  },
413
  {
414
  "epoch": 1.35,
415
  "learning_rate": 1.1983980841786899e-05,
416
- "loss": 2.0893,
417
  "step": 136
418
  },
419
  {
420
  "epoch": 1.37,
421
  "learning_rate": 1.177190991579223e-05,
422
- "loss": 2.1196,
423
  "step": 138
424
  },
425
  {
426
  "epoch": 1.39,
427
  "learning_rate": 1.1559012954653865e-05,
428
- "loss": 2.3453,
429
  "step": 140
430
  },
431
  {
432
  "epoch": 1.41,
433
  "learning_rate": 1.1345389207419588e-05,
434
- "loss": 2.1678,
435
  "step": 142
436
  },
437
  {
438
  "epoch": 1.43,
439
  "learning_rate": 1.1131138261952845e-05,
440
- "loss": 2.1813,
441
  "step": 144
442
  },
443
  {
444
  "epoch": 1.45,
445
  "learning_rate": 1.0916359998506549e-05,
446
- "loss": 1.9234,
447
  "step": 146
448
  },
449
  {
450
  "epoch": 1.47,
451
  "learning_rate": 1.070115454316054e-05,
452
- "loss": 2.0101,
453
  "step": 148
454
  },
455
  {
456
  "epoch": 1.49,
457
  "learning_rate": 1.0485622221144485e-05,
458
- "loss": 2.1219,
459
  "step": 150
460
  },
461
  {
462
  "epoch": 1.51,
463
  "learning_rate": 1.0269863510067872e-05,
464
- "loss": 2.005,
465
  "step": 152
466
  },
467
  {
468
  "epoch": 1.53,
469
  "learning_rate": 1.0053978993079046e-05,
470
- "loss": 2.2665,
471
  "step": 154
472
  },
473
  {
474
  "epoch": 1.55,
475
  "learning_rate": 9.838069311974986e-06,
476
- "loss": 2.1162,
477
  "step": 156
478
  },
479
  {
480
  "epoch": 1.57,
481
  "learning_rate": 9.622235120283769e-06,
482
- "loss": 2.1579,
483
  "step": 158
484
  },
485
  {
486
  "epoch": 1.59,
487
  "learning_rate": 9.406577036341548e-06,
488
- "loss": 2.2042,
489
  "step": 160
490
  },
491
  {
492
  "epoch": 1.61,
493
  "learning_rate": 9.19119559638596e-06,
494
- "loss": 2.2177,
495
  "step": 162
496
  },
497
  {
498
  "epoch": 1.63,
499
  "learning_rate": 8.976191207687775e-06,
500
- "loss": 2.0318,
501
  "step": 164
502
  },
503
  {
504
  "epoch": 1.65,
505
  "learning_rate": 8.7616641017427e-06,
506
- "loss": 2.1748,
507
  "step": 166
508
  },
509
  {
510
  "epoch": 1.67,
511
  "learning_rate": 8.5477142875451e-06,
512
- "loss": 1.9726,
513
  "step": 168
514
  },
515
  {
516
  "epoch": 1.69,
517
  "learning_rate": 8.334441504965456e-06,
518
- "loss": 1.924,
519
  "step": 170
520
  },
521
  {
522
  "epoch": 1.71,
523
  "learning_rate": 8.1219451782533e-06,
524
- "loss": 2.0598,
525
  "step": 172
526
  },
527
  {
528
  "epoch": 1.73,
529
  "learning_rate": 7.91032436968725e-06,
530
- "loss": 2.1213,
531
  "step": 174
532
  },
533
  {
534
  "epoch": 1.75,
535
  "learning_rate": 7.699677733393827e-06,
536
- "loss": 2.2904,
537
  "step": 176
538
  },
539
  {
540
  "epoch": 1.77,
541
  "learning_rate": 7.490103469356513e-06,
542
- "loss": 2.2139,
543
  "step": 178
544
  },
545
  {
546
  "epoch": 1.79,
547
  "learning_rate": 7.2816992776365714e-06,
548
- "loss": 2.1279,
549
  "step": 180
550
  },
551
  {
552
  "epoch": 1.81,
553
  "learning_rate": 7.0745623128268605e-06,
554
- "loss": 2.2162,
555
  "step": 182
556
  },
557
  {
558
  "epoch": 1.83,
559
  "learning_rate": 6.868789138759977e-06,
560
- "loss": 2.1864,
561
  "step": 184
562
  },
563
  {
564
  "epoch": 1.85,
565
  "learning_rate": 6.664475683491797e-06,
566
- "loss": 2.1537,
567
  "step": 186
568
  },
569
  {
570
  "epoch": 1.87,
571
  "learning_rate": 6.461717194581394e-06,
572
- "loss": 2.171,
573
  "step": 188
574
  },
575
  {
576
  "epoch": 1.89,
577
  "learning_rate": 6.260608194688207e-06,
578
- "loss": 2.1803,
579
  "step": 190
580
  },
581
  {
582
  "epoch": 1.91,
583
  "learning_rate": 6.061242437507131e-06,
584
- "loss": 2.0529,
585
  "step": 192
586
  },
587
  {
588
  "epoch": 1.93,
589
  "learning_rate": 5.863712864062089e-06,
590
- "loss": 2.0671,
591
  "step": 194
592
  },
593
  {
594
  "epoch": 1.95,
595
  "learning_rate": 5.6681115593784705e-06,
596
- "loss": 2.15,
597
  "step": 196
598
  },
599
  {
600
  "epoch": 1.97,
601
  "learning_rate": 5.4745297095546125e-06,
602
- "loss": 2.168,
603
  "step": 198
604
  },
605
  {
606
  "epoch": 1.99,
607
  "learning_rate": 5.2830575592523415e-06,
608
- "loss": 1.8829,
609
  "step": 200
610
  },
611
  {
612
  "epoch": 2.01,
613
  "learning_rate": 5.093784369626397e-06,
614
- "loss": 1.8625,
615
  "step": 202
616
  },
617
  {
618
  "epoch": 2.03,
619
  "learning_rate": 4.9067983767123736e-06,
620
- "loss": 2.2729,
621
  "step": 204
622
  },
623
  {
624
  "epoch": 2.05,
625
  "learning_rate": 4.722186750292511e-06,
626
- "loss": 2.1912,
627
  "step": 206
628
  },
629
  {
630
  "epoch": 2.07,
631
  "learning_rate": 4.54003555325862e-06,
632
- "loss": 2.115,
633
  "step": 208
634
  },
635
  {
636
  "epoch": 2.09,
637
  "learning_rate": 4.360429701490935e-06,
638
- "loss": 2.1249,
639
  "step": 210
640
  },
641
  {
642
  "epoch": 2.11,
643
  "learning_rate": 4.183452924271776e-06,
644
- "loss": 2.1941,
645
  "step": 212
646
  },
647
  {
648
  "epoch": 2.13,
649
  "learning_rate": 4.009187725252309e-06,
650
- "loss": 2.1044,
651
  "step": 214
652
  },
653
  {
654
  "epoch": 2.15,
655
  "learning_rate": 3.837715343990727e-06,
656
- "loss": 2.1149,
657
  "step": 216
658
  },
659
  {
660
  "epoch": 2.17,
661
  "learning_rate": 3.669115718079702e-06,
662
- "loss": 1.9624,
663
  "step": 218
664
  },
665
  {
666
  "epoch": 2.19,
667
  "learning_rate": 3.5034674458807893e-06,
668
- "loss": 2.1396,
669
  "step": 220
670
  },
671
  {
672
  "epoch": 2.21,
673
  "learning_rate": 3.3408477498831917e-06,
674
- "loss": 1.9964,
675
  "step": 222
676
  },
677
  {
678
  "epoch": 2.23,
679
  "learning_rate": 3.1813324407038826e-06,
680
- "loss": 1.9679,
681
  "step": 224
682
  },
683
  {
684
  "epoch": 2.25,
685
  "learning_rate": 3.024995881745972e-06,
686
- "loss": 2.0472,
687
  "step": 226
688
  },
689
  {
690
  "epoch": 2.27,
691
  "learning_rate": 2.8719109545317102e-06,
692
- "loss": 2.1399,
693
  "step": 228
694
  },
695
  {
696
  "epoch": 2.29,
697
  "learning_rate": 2.722149024726307e-06,
698
- "loss": 2.1447,
699
  "step": 230
700
  },
701
  {
702
  "epoch": 2.31,
703
  "learning_rate": 2.5757799088684654e-06,
704
- "loss": 2.176,
705
  "step": 232
706
  },
707
  {
708
  "epoch": 2.33,
709
  "learning_rate": 2.432871841823047e-06,
710
- "loss": 2.2318,
711
  "step": 234
712
  },
713
  {
714
  "epoch": 2.35,
715
  "learning_rate": 2.293491444971109e-06,
716
- "loss": 2.1988,
717
  "step": 236
718
  },
719
  {
720
  "epoch": 2.37,
721
  "learning_rate": 2.157703695152109e-06,
722
- "loss": 2.1636,
723
  "step": 238
724
  },
725
  {
726
  "epoch": 2.39,
727
  "learning_rate": 2.025571894372794e-06,
728
- "loss": 2.1685,
729
  "step": 240
730
  },
731
  {
732
  "epoch": 2.41,
733
  "learning_rate": 1.897157640296825e-06,
734
- "loss": 2.0524,
735
  "step": 242
736
  },
737
  {
738
  "epoch": 2.43,
739
  "learning_rate": 1.7725207975289883e-06,
740
- "loss": 2.1376,
741
  "step": 244
742
  },
743
  {
744
  "epoch": 2.45,
745
  "learning_rate": 1.6517194697072903e-06,
746
- "loss": 1.9918,
747
  "step": 246
748
  },
749
  {
750
  "epoch": 2.47,
751
  "learning_rate": 1.534809972415998e-06,
752
- "loss": 2.0566,
753
  "step": 248
754
  },
755
  {
756
  "epoch": 2.49,
757
  "learning_rate": 1.4218468069322576e-06,
758
- "loss": 2.1923,
759
  "step": 250
760
  },
761
  {
762
  "epoch": 2.51,
763
  "learning_rate": 1.3128826348184886e-06,
764
- "loss": 1.906,
765
  "step": 252
766
  },
767
  {
768
  "epoch": 2.53,
769
  "learning_rate": 1.207968253372438e-06,
770
- "loss": 2.1381,
771
  "step": 254
772
  },
773
  {
774
  "epoch": 2.55,
775
  "learning_rate": 1.1071525719463094e-06,
776
- "loss": 2.2416,
777
  "step": 256
778
  },
779
  {
780
  "epoch": 2.57,
781
  "learning_rate": 1.010482589146048e-06,
782
- "loss": 2.1186,
783
  "step": 258
784
  },
785
  {
786
  "epoch": 2.59,
787
  "learning_rate": 9.180033709213454e-07,
788
- "loss": 2.1209,
789
  "step": 260
790
  },
791
  {
792
  "epoch": 2.61,
793
  "learning_rate": 8.297580295566576e-07,
794
- "loss": 2.0745,
795
  "step": 262
796
  },
797
  {
798
  "epoch": 2.63,
799
  "learning_rate": 7.457877035729588e-07,
800
- "loss": 2.1211,
801
  "step": 264
802
  },
803
  {
804
  "epoch": 2.65,
805
  "learning_rate": 6.661315385496426e-07,
806
- "loss": 2.1062,
807
  "step": 266
808
  },
809
  {
810
  "epoch": 2.67,
811
  "learning_rate": 5.908266688755049e-07,
812
- "loss": 2.1468,
813
  "step": 268
814
  },
815
  {
816
  "epoch": 2.68,
817
  "learning_rate": 5.199082004372958e-07,
818
- "loss": 2.0994,
819
  "step": 270
820
  },
821
  {
822
  "epoch": 2.7,
823
  "learning_rate": 4.534091942539476e-07,
824
- "loss": 2.0678,
825
  "step": 272
826
  },
827
  {
828
  "epoch": 2.72,
829
  "learning_rate": 3.913606510640644e-07,
830
- "loss": 2.1135,
831
  "step": 274
832
  },
833
  {
834
  "epoch": 2.74,
835
  "learning_rate": 3.3379149687388866e-07,
836
- "loss": 2.2148,
837
  "step": 276
838
  },
839
  {
840
  "epoch": 2.76,
841
  "learning_rate": 2.807285694724804e-07,
842
- "loss": 2.173,
843
  "step": 278
844
  },
845
  {
846
  "epoch": 2.78,
847
  "learning_rate": 2.3219660592038285e-07,
848
- "loss": 2.0792,
849
  "step": 280
850
  },
851
  {
852
  "epoch": 2.8,
853
  "learning_rate": 1.8821823101760949e-07,
854
- "loss": 2.0483,
855
  "step": 282
856
  },
857
  {
858
  "epoch": 2.82,
859
  "learning_rate": 1.4881394675633543e-07,
860
- "loss": 2.1416,
861
  "step": 284
862
  },
863
  {
864
  "epoch": 2.84,
865
  "learning_rate": 1.1400212276321377e-07,
866
- "loss": 2.2714,
867
  "step": 286
868
  },
869
  {
870
  "epoch": 2.86,
871
  "learning_rate": 8.379898773574924e-08,
872
- "loss": 2.0962,
873
  "step": 288
874
  },
875
  {
876
  "epoch": 2.88,
877
  "learning_rate": 5.821862187675775e-08,
878
- "loss": 2.1808,
879
  "step": 290
880
  },
881
  {
882
  "epoch": 2.9,
883
  "learning_rate": 3.727295033040035e-08,
884
- "loss": 2.1085,
885
  "step": 292
886
  },
887
  {
888
  "epoch": 2.92,
889
  "learning_rate": 2.0971737622883515e-08,
890
- "loss": 1.9238,
891
  "step": 294
892
  },
893
  {
894
  "epoch": 2.94,
895
  "learning_rate": 9.322583110392692e-09,
896
- "loss": 2.1334,
897
  "step": 296
898
  },
899
  {
900
  "epoch": 2.96,
901
  "learning_rate": 2.330917436402791e-09,
902
- "loss": 2.0183,
903
  "step": 298
904
  },
905
  {
906
  "epoch": 2.98,
907
  "learning_rate": 0.0,
908
- "loss": 1.9954,
909
  "step": 300
910
  }
911
  ],
@@ -914,7 +914,7 @@
914
  "num_input_tokens_seen": 0,
915
  "num_train_epochs": 3,
916
  "save_steps": 500,
917
- "total_flos": 4.176251079524352e+16,
918
  "train_batch_size": 1,
919
  "trial_name": null,
920
  "trial_params": null
 
11
  {
12
  "epoch": 0.02,
13
  "learning_rate": 4.444444444444444e-06,
14
+ "loss": 2.3493,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.04,
19
  "learning_rate": 8.888888888888888e-06,
20
+ "loss": 2.2393,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.06,
25
  "learning_rate": 1.3333333333333333e-05,
26
+ "loss": 2.2582,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.08,
31
  "learning_rate": 1.7777777777777777e-05,
32
+ "loss": 2.2492,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.1,
37
  "learning_rate": 1.9999417253661235e-05,
38
+ "loss": 2.3767,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.12,
43
  "learning_rate": 1.9994755690455154e-05,
44
+ "loss": 2.346,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.14,
49
  "learning_rate": 1.998543473718677e-05,
50
+ "loss": 2.3169,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.16,
55
  "learning_rate": 1.9971458739130598e-05,
56
+ "loss": 2.3683,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.18,
61
  "learning_rate": 1.995283421166614e-05,
62
+ "loss": 2.1442,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.2,
67
  "learning_rate": 1.9929569837240567e-05,
68
+ "loss": 1.9793,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.22,
73
  "learning_rate": 1.990167646132107e-05,
74
+ "loss": 2.1757,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.24,
79
  "learning_rate": 1.9869167087338908e-05,
80
+ "loss": 2.0477,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.26,
85
  "learning_rate": 1.983205687062742e-05,
86
+ "loss": 2.2111,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.28,
91
  "learning_rate": 1.9790363111356838e-05,
92
+ "loss": 2.3174,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.3,
97
  "learning_rate": 1.9744105246469264e-05,
98
+ "loss": 2.2621,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.32,
103
  "learning_rate": 1.9693304840617456e-05,
104
+ "loss": 2.3094,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.34,
109
  "learning_rate": 1.963798557611178e-05,
110
+ "loss": 2.2201,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.36,
115
  "learning_rate": 1.957817324187987e-05,
116
+ "loss": 2.1306,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.38,
121
  "learning_rate": 1.9513895721444286e-05,
122
+ "loss": 2.2803,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.4,
127
  "learning_rate": 1.9445182979923657e-05,
128
+ "loss": 2.2775,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.42,
133
  "learning_rate": 1.937206705006344e-05,
134
+ "loss": 2.1384,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.44,
139
  "learning_rate": 1.9294582017302797e-05,
140
+ "loss": 2.1593,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.46,
145
  "learning_rate": 1.921276400388451e-05,
146
+ "loss": 2.0969,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.48,
151
  "learning_rate": 1.9126651152015404e-05,
152
+ "loss": 2.2361,
153
  "step": 48
154
  },
155
  {
156
  "epoch": 0.5,
157
  "learning_rate": 1.9036283606085057e-05,
158
+ "loss": 2.1953,
159
  "step": 50
160
  },
161
  {
162
  "epoch": 0.52,
163
  "learning_rate": 1.8941703493951163e-05,
164
+ "loss": 2.1927,
165
  "step": 52
166
  },
167
  {
168
  "epoch": 0.54,
169
  "learning_rate": 1.8842954907300236e-05,
170
+ "loss": 2.1323,
171
  "step": 54
172
  },
173
  {
174
  "epoch": 0.56,
175
  "learning_rate": 1.874008388109276e-05,
176
+ "loss": 2.2825,
177
  "step": 56
178
  },
179
  {
180
  "epoch": 0.58,
181
  "learning_rate": 1.863313837210247e-05,
182
+ "loss": 2.1155,
183
  "step": 58
184
  },
185
  {
186
  "epoch": 0.6,
187
  "learning_rate": 1.8522168236559693e-05,
188
+ "loss": 2.1101,
189
  "step": 60
190
  },
191
  {
192
  "epoch": 0.62,
193
  "learning_rate": 1.840722520690921e-05,
194
+ "loss": 2.2914,
195
  "step": 62
196
  },
197
  {
198
  "epoch": 0.64,
199
  "learning_rate": 1.8288362867693414e-05,
200
+ "loss": 2.1126,
201
  "step": 64
202
  },
203
  {
204
  "epoch": 0.66,
205
  "learning_rate": 1.816563663057211e-05,
206
+ "loss": 2.0641,
207
  "step": 66
208
  },
209
  {
210
  "epoch": 0.68,
211
  "learning_rate": 1.8039103708490503e-05,
212
+ "loss": 2.202,
213
  "step": 68
214
  },
215
  {
216
  "epoch": 0.7,
217
  "learning_rate": 1.790882308900746e-05,
218
+ "loss": 2.1626,
219
  "step": 70
220
  },
221
  {
222
  "epoch": 0.72,
223
  "learning_rate": 1.7774855506796497e-05,
224
+ "loss": 2.1288,
225
  "step": 72
226
  },
227
  {
228
  "epoch": 0.74,
229
  "learning_rate": 1.7637263415332272e-05,
230
+ "loss": 2.1682,
231
  "step": 74
232
  },
233
  {
234
  "epoch": 0.76,
235
  "learning_rate": 1.749611095777581e-05,
236
+ "loss": 2.1166,
237
  "step": 76
238
  },
239
  {
240
  "epoch": 0.78,
241
  "learning_rate": 1.7351463937072008e-05,
242
+ "loss": 2.3802,
243
  "step": 78
244
  },
245
  {
246
  "epoch": 0.8,
247
  "learning_rate": 1.7203389785273402e-05,
248
+ "loss": 2.0564,
249
  "step": 80
250
  },
251
  {
252
  "epoch": 0.82,
253
  "learning_rate": 1.705195753210446e-05,
254
+ "loss": 2.1812,
255
  "step": 82
256
  },
257
  {
258
  "epoch": 0.84,
259
  "learning_rate": 1.6897237772781046e-05,
260
+ "loss": 2.2436,
261
  "step": 84
262
  },
263
  {
264
  "epoch": 0.86,
265
  "learning_rate": 1.673930263510011e-05,
266
+ "loss": 2.1431,
267
  "step": 86
268
  },
269
  {
270
  "epoch": 0.88,
271
  "learning_rate": 1.6578225745814907e-05,
272
+ "loss": 2.2472,
273
  "step": 88
274
  },
275
  {
276
  "epoch": 0.89,
277
  "learning_rate": 1.6414082196311402e-05,
278
+ "loss": 2.1835,
279
  "step": 90
280
  },
281
  {
282
  "epoch": 0.91,
283
  "learning_rate": 1.6246948507601915e-05,
284
+ "loss": 1.949,
285
  "step": 92
286
  },
287
  {
288
  "epoch": 0.93,
289
  "learning_rate": 1.607690259465229e-05,
290
+ "loss": 2.1323,
291
  "step": 94
292
  },
293
  {
294
  "epoch": 0.95,
295
  "learning_rate": 1.5904023730059227e-05,
296
+ "loss": 2.1359,
297
  "step": 96
298
  },
299
  {
300
  "epoch": 0.97,
301
  "learning_rate": 1.57283925070947e-05,
302
+ "loss": 2.1792,
303
  "step": 98
304
  },
305
  {
306
  "epoch": 0.99,
307
  "learning_rate": 1.55500908021347e-05,
308
+ "loss": 1.9448,
309
  "step": 100
310
  },
311
  {
312
  "epoch": 1.01,
313
  "learning_rate": 1.536920173648984e-05,
314
+ "loss": 2.0926,
315
  "step": 102
316
  },
317
  {
318
  "epoch": 1.03,
319
  "learning_rate": 1.5185809637655548e-05,
320
+ "loss": 2.1539,
321
  "step": 104
322
  },
323
  {
324
  "epoch": 1.05,
325
  "learning_rate": 1.5000000000000002e-05,
326
+ "loss": 2.1697,
327
  "step": 106
328
  },
329
  {
330
  "epoch": 1.07,
331
  "learning_rate": 1.4811859444908053e-05,
332
+ "loss": 2.1884,
333
  "step": 108
334
  },
335
  {
336
  "epoch": 1.09,
337
  "learning_rate": 1.4621475680399771e-05,
338
+ "loss": 2.2353,
339
  "step": 110
340
  },
341
  {
342
  "epoch": 1.11,
343
  "learning_rate": 1.4428937460242417e-05,
344
+ "loss": 2.171,
345
  "step": 112
346
  },
347
  {
348
  "epoch": 1.13,
349
  "learning_rate": 1.4234334542574906e-05,
350
+ "loss": 2.0805,
351
  "step": 114
352
  },
353
  {
354
  "epoch": 1.15,
355
  "learning_rate": 1.4037757648064019e-05,
356
+ "loss": 2.0794,
357
  "step": 116
358
  },
359
  {
360
  "epoch": 1.17,
361
  "learning_rate": 1.3839298417611964e-05,
362
+ "loss": 2.1013,
363
  "step": 118
364
  },
365
  {
366
  "epoch": 1.19,
367
  "learning_rate": 1.3639049369634878e-05,
368
+ "loss": 2.0357,
369
  "step": 120
370
  },
371
  {
372
  "epoch": 1.21,
373
  "learning_rate": 1.3437103856932266e-05,
374
+ "loss": 2.0828,
375
  "step": 122
376
  },
377
  {
378
  "epoch": 1.23,
379
  "learning_rate": 1.3233556023167487e-05,
380
+ "loss": 2.0749,
381
  "step": 124
382
  },
383
  {
384
  "epoch": 1.25,
385
  "learning_rate": 1.3028500758979507e-05,
386
+ "loss": 2.1431,
387
  "step": 126
388
  },
389
  {
390
  "epoch": 1.27,
391
  "learning_rate": 1.2822033657746478e-05,
392
+ "loss": 2.1671,
393
  "step": 128
394
  },
395
  {
396
  "epoch": 1.29,
397
  "learning_rate": 1.2614250971021658e-05,
398
+ "loss": 2.0789,
399
  "step": 130
400
  },
401
  {
402
  "epoch": 1.31,
403
  "learning_rate": 1.2405249563662539e-05,
404
+ "loss": 2.1831,
405
  "step": 132
406
  },
407
  {
408
  "epoch": 1.33,
409
  "learning_rate": 1.2195126868674052e-05,
410
+ "loss": 2.2281,
411
  "step": 134
412
  },
413
  {
414
  "epoch": 1.35,
415
  "learning_rate": 1.1983980841786899e-05,
416
+ "loss": 2.0755,
417
  "step": 136
418
  },
419
  {
420
  "epoch": 1.37,
421
  "learning_rate": 1.177190991579223e-05,
422
+ "loss": 2.1071,
423
  "step": 138
424
  },
425
  {
426
  "epoch": 1.39,
427
  "learning_rate": 1.1559012954653865e-05,
428
+ "loss": 2.3303,
429
  "step": 140
430
  },
431
  {
432
  "epoch": 1.41,
433
  "learning_rate": 1.1345389207419588e-05,
434
+ "loss": 2.1512,
435
  "step": 142
436
  },
437
  {
438
  "epoch": 1.43,
439
  "learning_rate": 1.1131138261952845e-05,
440
+ "loss": 2.1662,
441
  "step": 144
442
  },
443
  {
444
  "epoch": 1.45,
445
  "learning_rate": 1.0916359998506549e-05,
446
+ "loss": 1.95,
447
  "step": 146
448
  },
449
  {
450
  "epoch": 1.47,
451
  "learning_rate": 1.070115454316054e-05,
452
+ "loss": 1.9442,
453
  "step": 148
454
  },
455
  {
456
  "epoch": 1.49,
457
  "learning_rate": 1.0485622221144485e-05,
458
+ "loss": 2.0977,
459
  "step": 150
460
  },
461
  {
462
  "epoch": 1.51,
463
  "learning_rate": 1.0269863510067872e-05,
464
+ "loss": 1.9636,
465
  "step": 152
466
  },
467
  {
468
  "epoch": 1.53,
469
  "learning_rate": 1.0053978993079046e-05,
470
+ "loss": 2.2701,
471
  "step": 154
472
  },
473
  {
474
  "epoch": 1.55,
475
  "learning_rate": 9.838069311974986e-06,
476
+ "loss": 2.1423,
477
  "step": 156
478
  },
479
  {
480
  "epoch": 1.57,
481
  "learning_rate": 9.622235120283769e-06,
482
+ "loss": 2.09,
483
  "step": 158
484
  },
485
  {
486
  "epoch": 1.59,
487
  "learning_rate": 9.406577036341548e-06,
488
+ "loss": 2.1742,
489
  "step": 160
490
  },
491
  {
492
  "epoch": 1.61,
493
  "learning_rate": 9.19119559638596e-06,
494
+ "loss": 2.2062,
495
  "step": 162
496
  },
497
  {
498
  "epoch": 1.63,
499
  "learning_rate": 8.976191207687775e-06,
500
+ "loss": 2.018,
501
  "step": 164
502
  },
503
  {
504
  "epoch": 1.65,
505
  "learning_rate": 8.7616641017427e-06,
506
+ "loss": 2.1516,
507
  "step": 166
508
  },
509
  {
510
  "epoch": 1.67,
511
  "learning_rate": 8.5477142875451e-06,
512
+ "loss": 1.9848,
513
  "step": 168
514
  },
515
  {
516
  "epoch": 1.69,
517
  "learning_rate": 8.334441504965456e-06,
518
+ "loss": 1.9065,
519
  "step": 170
520
  },
521
  {
522
  "epoch": 1.71,
523
  "learning_rate": 8.1219451782533e-06,
524
+ "loss": 2.0868,
525
  "step": 172
526
  },
527
  {
528
  "epoch": 1.73,
529
  "learning_rate": 7.91032436968725e-06,
530
+ "loss": 2.0552,
531
  "step": 174
532
  },
533
  {
534
  "epoch": 1.75,
535
  "learning_rate": 7.699677733393827e-06,
536
+ "loss": 2.2632,
537
  "step": 176
538
  },
539
  {
540
  "epoch": 1.77,
541
  "learning_rate": 7.490103469356513e-06,
542
+ "loss": 2.2019,
543
  "step": 178
544
  },
545
  {
546
  "epoch": 1.79,
547
  "learning_rate": 7.2816992776365714e-06,
548
+ "loss": 2.1141,
549
  "step": 180
550
  },
551
  {
552
  "epoch": 1.81,
553
  "learning_rate": 7.0745623128268605e-06,
554
+ "loss": 2.2028,
555
  "step": 182
556
  },
557
  {
558
  "epoch": 1.83,
559
  "learning_rate": 6.868789138759977e-06,
560
+ "loss": 2.1724,
561
  "step": 184
562
  },
563
  {
564
  "epoch": 1.85,
565
  "learning_rate": 6.664475683491797e-06,
566
+ "loss": 2.1409,
567
  "step": 186
568
  },
569
  {
570
  "epoch": 1.87,
571
  "learning_rate": 6.461717194581394e-06,
572
+ "loss": 2.1512,
573
  "step": 188
574
  },
575
  {
576
  "epoch": 1.89,
577
  "learning_rate": 6.260608194688207e-06,
578
+ "loss": 2.1712,
579
  "step": 190
580
  },
581
  {
582
  "epoch": 1.91,
583
  "learning_rate": 6.061242437507131e-06,
584
+ "loss": 2.0359,
585
  "step": 192
586
  },
587
  {
588
  "epoch": 1.93,
589
  "learning_rate": 5.863712864062089e-06,
590
+ "loss": 2.0491,
591
  "step": 194
592
  },
593
  {
594
  "epoch": 1.95,
595
  "learning_rate": 5.6681115593784705e-06,
596
+ "loss": 2.1313,
597
  "step": 196
598
  },
599
  {
600
  "epoch": 1.97,
601
  "learning_rate": 5.4745297095546125e-06,
602
+ "loss": 2.1493,
603
  "step": 198
604
  },
605
  {
606
  "epoch": 1.99,
607
  "learning_rate": 5.2830575592523415e-06,
608
+ "loss": 1.8546,
609
  "step": 200
610
  },
611
  {
612
  "epoch": 2.01,
613
  "learning_rate": 5.093784369626397e-06,
614
+ "loss": 1.8436,
615
  "step": 202
616
  },
617
  {
618
  "epoch": 2.03,
619
  "learning_rate": 4.9067983767123736e-06,
620
+ "loss": 2.2585,
621
  "step": 204
622
  },
623
  {
624
  "epoch": 2.05,
625
  "learning_rate": 4.722186750292511e-06,
626
+ "loss": 2.179,
627
  "step": 206
628
  },
629
  {
630
  "epoch": 2.07,
631
  "learning_rate": 4.54003555325862e-06,
632
+ "loss": 2.0755,
633
  "step": 208
634
  },
635
  {
636
  "epoch": 2.09,
637
  "learning_rate": 4.360429701490935e-06,
638
+ "loss": 2.1043,
639
  "step": 210
640
  },
641
  {
642
  "epoch": 2.11,
643
  "learning_rate": 4.183452924271776e-06,
644
+ "loss": 2.1665,
645
  "step": 212
646
  },
647
  {
648
  "epoch": 2.13,
649
  "learning_rate": 4.009187725252309e-06,
650
+ "loss": 2.1439,
651
  "step": 214
652
  },
653
  {
654
  "epoch": 2.15,
655
  "learning_rate": 3.837715343990727e-06,
656
+ "loss": 2.0962,
657
  "step": 216
658
  },
659
  {
660
  "epoch": 2.17,
661
  "learning_rate": 3.669115718079702e-06,
662
+ "loss": 1.9462,
663
  "step": 218
664
  },
665
  {
666
  "epoch": 2.19,
667
  "learning_rate": 3.5034674458807893e-06,
668
+ "loss": 2.1219,
669
  "step": 220
670
  },
671
  {
672
  "epoch": 2.21,
673
  "learning_rate": 3.3408477498831917e-06,
674
+ "loss": 1.9764,
675
  "step": 222
676
  },
677
  {
678
  "epoch": 2.23,
679
  "learning_rate": 3.1813324407038826e-06,
680
+ "loss": 1.9481,
681
  "step": 224
682
  },
683
  {
684
  "epoch": 2.25,
685
  "learning_rate": 3.024995881745972e-06,
686
+ "loss": 2.0247,
687
  "step": 226
688
  },
689
  {
690
  "epoch": 2.27,
691
  "learning_rate": 2.8719109545317102e-06,
692
+ "loss": 2.1188,
693
  "step": 228
694
  },
695
  {
696
  "epoch": 2.29,
697
  "learning_rate": 2.722149024726307e-06,
698
+ "loss": 2.1318,
699
  "step": 230
700
  },
701
  {
702
  "epoch": 2.31,
703
  "learning_rate": 2.5757799088684654e-06,
704
+ "loss": 2.1614,
705
  "step": 232
706
  },
707
  {
708
  "epoch": 2.33,
709
  "learning_rate": 2.432871841823047e-06,
710
+ "loss": 2.2558,
711
  "step": 234
712
  },
713
  {
714
  "epoch": 2.35,
715
  "learning_rate": 2.293491444971109e-06,
716
+ "loss": 2.1416,
717
  "step": 236
718
  },
719
  {
720
  "epoch": 2.37,
721
  "learning_rate": 2.157703695152109e-06,
722
+ "loss": 2.1837,
723
  "step": 238
724
  },
725
  {
726
  "epoch": 2.39,
727
  "learning_rate": 2.025571894372794e-06,
728
+ "loss": 2.1546,
729
  "step": 240
730
  },
731
  {
732
  "epoch": 2.41,
733
  "learning_rate": 1.897157640296825e-06,
734
+ "loss": 2.0068,
735
  "step": 242
736
  },
737
  {
738
  "epoch": 2.43,
739
  "learning_rate": 1.7725207975289883e-06,
740
+ "loss": 2.1211,
741
  "step": 244
742
  },
743
  {
744
  "epoch": 2.45,
745
  "learning_rate": 1.6517194697072903e-06,
746
+ "loss": 1.9734,
747
  "step": 246
748
  },
749
  {
750
  "epoch": 2.47,
751
  "learning_rate": 1.534809972415998e-06,
752
+ "loss": 2.0373,
753
  "step": 248
754
  },
755
  {
756
  "epoch": 2.49,
757
  "learning_rate": 1.4218468069322576e-06,
758
+ "loss": 2.1672,
759
  "step": 250
760
  },
761
  {
762
  "epoch": 2.51,
763
  "learning_rate": 1.3128826348184886e-06,
764
+ "loss": 1.8759,
765
  "step": 252
766
  },
767
  {
768
  "epoch": 2.53,
769
  "learning_rate": 1.207968253372438e-06,
770
+ "loss": 2.125,
771
  "step": 254
772
  },
773
  {
774
  "epoch": 2.55,
775
  "learning_rate": 1.1071525719463094e-06,
776
+ "loss": 2.2288,
777
  "step": 256
778
  },
779
  {
780
  "epoch": 2.57,
781
  "learning_rate": 1.010482589146048e-06,
782
+ "loss": 2.1027,
783
  "step": 258
784
  },
785
  {
786
  "epoch": 2.59,
787
  "learning_rate": 9.180033709213454e-07,
788
+ "loss": 2.1087,
789
  "step": 260
790
  },
791
  {
792
  "epoch": 2.61,
793
  "learning_rate": 8.297580295566576e-07,
794
+ "loss": 2.06,
795
  "step": 262
796
  },
797
  {
798
  "epoch": 2.63,
799
  "learning_rate": 7.457877035729588e-07,
800
+ "loss": 2.1075,
801
  "step": 264
802
  },
803
  {
804
  "epoch": 2.65,
805
  "learning_rate": 6.661315385496426e-07,
806
+ "loss": 2.0915,
807
  "step": 266
808
  },
809
  {
810
  "epoch": 2.67,
811
  "learning_rate": 5.908266688755049e-07,
812
+ "loss": 2.1329,
813
  "step": 268
814
  },
815
  {
816
  "epoch": 2.68,
817
  "learning_rate": 5.199082004372958e-07,
818
+ "loss": 2.1243,
819
  "step": 270
820
  },
821
  {
822
  "epoch": 2.7,
823
  "learning_rate": 4.534091942539476e-07,
824
+ "loss": 2.0102,
825
  "step": 272
826
  },
827
  {
828
  "epoch": 2.72,
829
  "learning_rate": 3.913606510640644e-07,
830
+ "loss": 2.0946,
831
  "step": 274
832
  },
833
  {
834
  "epoch": 2.74,
835
  "learning_rate": 3.3379149687388866e-07,
836
+ "loss": 2.1817,
837
  "step": 276
838
  },
839
  {
840
  "epoch": 2.76,
841
  "learning_rate": 2.807285694724804e-07,
842
+ "loss": 2.1439,
843
  "step": 278
844
  },
845
  {
846
  "epoch": 2.78,
847
  "learning_rate": 2.3219660592038285e-07,
848
+ "loss": 2.0749,
849
  "step": 280
850
  },
851
  {
852
  "epoch": 2.8,
853
  "learning_rate": 1.8821823101760949e-07,
854
+ "loss": 2.0326,
855
  "step": 282
856
  },
857
  {
858
  "epoch": 2.82,
859
  "learning_rate": 1.4881394675633543e-07,
860
+ "loss": 2.1358,
861
  "step": 284
862
  },
863
  {
864
  "epoch": 2.84,
865
  "learning_rate": 1.1400212276321377e-07,
866
+ "loss": 2.2447,
867
  "step": 286
868
  },
869
  {
870
  "epoch": 2.86,
871
  "learning_rate": 8.379898773574924e-08,
872
+ "loss": 2.0762,
873
  "step": 288
874
  },
875
  {
876
  "epoch": 2.88,
877
  "learning_rate": 5.821862187675775e-08,
878
+ "loss": 2.1836,
879
  "step": 290
880
  },
881
  {
882
  "epoch": 2.9,
883
  "learning_rate": 3.727295033040035e-08,
884
+ "loss": 2.0916,
885
  "step": 292
886
  },
887
  {
888
  "epoch": 2.92,
889
  "learning_rate": 2.0971737622883515e-08,
890
+ "loss": 1.9081,
891
  "step": 294
892
  },
893
  {
894
  "epoch": 2.94,
895
  "learning_rate": 9.322583110392692e-09,
896
+ "loss": 2.1174,
897
  "step": 296
898
  },
899
  {
900
  "epoch": 2.96,
901
  "learning_rate": 2.330917436402791e-09,
902
+ "loss": 1.9993,
903
  "step": 298
904
  },
905
  {
906
  "epoch": 2.98,
907
  "learning_rate": 0.0,
908
+ "loss": 1.9734,
909
  "step": 300
910
  }
911
  ],
 
914
  "num_input_tokens_seen": 0,
915
  "num_train_epochs": 3,
916
  "save_steps": 500,
917
+ "total_flos": 4.184372252435251e+16,
918
  "train_batch_size": 1,
919
  "trial_name": null,
920
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f13c39c2bc5a32dc6a6572fb0df440e3ea9dd3b799864078a856617868734c49
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8017515587dfdca91006080d6c855ee0e8a118b7dae062e24a3c2125ec8ead77
3
  size 4728