TinyPixel commited on
Commit
0cb0ff2
1 Parent(s): 70e50be

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 sha256:642f477bb24d61218babd0670664f3a4df918b5d8bb35c0f50583a34a92be0b7
3
  size 242266152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8fcbf20a23a54843f4f02f9ee58f4c759f2629d56922d1bfcda1deeed89204
3
  size 242266152
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:639e62b4dffb7f663a3bddbc13c477870e8d84e0071e56ab04cc450206838a09
3
  size 484650042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9a42b84599d237dd2eeb15587074c3e8008db0e0422582ba91d642b057d623
3
  size 484650042
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:324b380e4b844f229ef1eb78c684dbffa81653737123018b945caa09ff6d0595
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2bc52f59e8c6bff4bf14e7f294210c35627b5e5f0f51cb11a975faa9e7492b2
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:824a429c5f95423b97fd2ff7dc1e1dffcd96691286babb37392f00bfcecaeb1b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ea39dd85d8fdd7963ae8fca104a21064c32ab31d9951bd542c75f5d686bcc7
3
  size 1064
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.9990680335507922,
5
  "eval_steps": 500,
6
- "global_step": 67,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -205,6 +205,408 @@
205
  "learning_rate": 0.0002,
206
  "loss": 1.3281,
207
  "step": 66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
208
  }
209
  ],
210
  "logging_steps": 2,
@@ -212,7 +614,7 @@
212
  "num_input_tokens_seen": 0,
213
  "num_train_epochs": 3,
214
  "save_steps": 500,
215
- "total_flos": 4514943194996736.0,
216
  "train_batch_size": 1,
217
  "trial_name": null,
218
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.9972041006523766,
5
  "eval_steps": 500,
6
+ "global_step": 201,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
205
  "learning_rate": 0.0002,
206
  "loss": 1.3281,
207
  "step": 66
208
+ },
209
+ {
210
+ "epoch": 1.01,
211
+ "learning_rate": 0.0002,
212
+ "loss": 1.5778,
213
+ "step": 68
214
+ },
215
+ {
216
+ "epoch": 1.04,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.7498,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 1.07,
223
+ "learning_rate": 0.0002,
224
+ "loss": 1.4881,
225
+ "step": 72
226
+ },
227
+ {
228
+ "epoch": 1.1,
229
+ "learning_rate": 0.0002,
230
+ "loss": 1.3024,
231
+ "step": 74
232
+ },
233
+ {
234
+ "epoch": 1.13,
235
+ "learning_rate": 0.0002,
236
+ "loss": 1.213,
237
+ "step": 76
238
+ },
239
+ {
240
+ "epoch": 1.16,
241
+ "learning_rate": 0.0002,
242
+ "loss": 1.1186,
243
+ "step": 78
244
+ },
245
+ {
246
+ "epoch": 1.19,
247
+ "learning_rate": 0.0002,
248
+ "loss": 1.2948,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 1.22,
253
+ "learning_rate": 0.0002,
254
+ "loss": 1.4703,
255
+ "step": 82
256
+ },
257
+ {
258
+ "epoch": 1.25,
259
+ "learning_rate": 0.0002,
260
+ "loss": 1.4854,
261
+ "step": 84
262
+ },
263
+ {
264
+ "epoch": 1.28,
265
+ "learning_rate": 0.0002,
266
+ "loss": 1.8885,
267
+ "step": 86
268
+ },
269
+ {
270
+ "epoch": 1.31,
271
+ "learning_rate": 0.0002,
272
+ "loss": 1.4097,
273
+ "step": 88
274
+ },
275
+ {
276
+ "epoch": 1.34,
277
+ "learning_rate": 0.0002,
278
+ "loss": 1.3966,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 1.37,
283
+ "learning_rate": 0.0002,
284
+ "loss": 1.1886,
285
+ "step": 92
286
+ },
287
+ {
288
+ "epoch": 1.4,
289
+ "learning_rate": 0.0002,
290
+ "loss": 0.8788,
291
+ "step": 94
292
+ },
293
+ {
294
+ "epoch": 1.43,
295
+ "learning_rate": 0.0002,
296
+ "loss": 1.2402,
297
+ "step": 96
298
+ },
299
+ {
300
+ "epoch": 1.46,
301
+ "learning_rate": 0.0002,
302
+ "loss": 1.3957,
303
+ "step": 98
304
+ },
305
+ {
306
+ "epoch": 1.49,
307
+ "learning_rate": 0.0002,
308
+ "loss": 1.7168,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 1.52,
313
+ "learning_rate": 0.0002,
314
+ "loss": 2.1251,
315
+ "step": 102
316
+ },
317
+ {
318
+ "epoch": 1.55,
319
+ "learning_rate": 0.0002,
320
+ "loss": 1.414,
321
+ "step": 104
322
+ },
323
+ {
324
+ "epoch": 1.58,
325
+ "learning_rate": 0.0002,
326
+ "loss": 1.3645,
327
+ "step": 106
328
+ },
329
+ {
330
+ "epoch": 1.61,
331
+ "learning_rate": 0.0002,
332
+ "loss": 1.2092,
333
+ "step": 108
334
+ },
335
+ {
336
+ "epoch": 1.64,
337
+ "learning_rate": 0.0002,
338
+ "loss": 1.2043,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 1.67,
343
+ "learning_rate": 0.0002,
344
+ "loss": 1.1517,
345
+ "step": 112
346
+ },
347
+ {
348
+ "epoch": 1.7,
349
+ "learning_rate": 0.0002,
350
+ "loss": 1.3399,
351
+ "step": 114
352
+ },
353
+ {
354
+ "epoch": 1.73,
355
+ "learning_rate": 0.0002,
356
+ "loss": 1.6851,
357
+ "step": 116
358
+ },
359
+ {
360
+ "epoch": 1.76,
361
+ "learning_rate": 0.0002,
362
+ "loss": 1.8936,
363
+ "step": 118
364
+ },
365
+ {
366
+ "epoch": 1.79,
367
+ "learning_rate": 0.0002,
368
+ "loss": 1.3716,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 1.82,
373
+ "learning_rate": 0.0002,
374
+ "loss": 1.294,
375
+ "step": 122
376
+ },
377
+ {
378
+ "epoch": 1.85,
379
+ "learning_rate": 0.0002,
380
+ "loss": 1.3861,
381
+ "step": 124
382
+ },
383
+ {
384
+ "epoch": 1.88,
385
+ "learning_rate": 0.0002,
386
+ "loss": 1.0778,
387
+ "step": 126
388
+ },
389
+ {
390
+ "epoch": 1.91,
391
+ "learning_rate": 0.0002,
392
+ "loss": 1.1379,
393
+ "step": 128
394
+ },
395
+ {
396
+ "epoch": 1.94,
397
+ "learning_rate": 0.0002,
398
+ "loss": 1.3452,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 1.97,
403
+ "learning_rate": 0.0002,
404
+ "loss": 1.278,
405
+ "step": 132
406
+ },
407
+ {
408
+ "epoch": 2.0,
409
+ "learning_rate": 0.0002,
410
+ "loss": 1.3397,
411
+ "step": 134
412
+ },
413
+ {
414
+ "epoch": 2.03,
415
+ "learning_rate": 0.0002,
416
+ "loss": 2.2703,
417
+ "step": 136
418
+ },
419
+ {
420
+ "epoch": 2.06,
421
+ "learning_rate": 0.0002,
422
+ "loss": 1.6646,
423
+ "step": 138
424
+ },
425
+ {
426
+ "epoch": 2.09,
427
+ "learning_rate": 0.0002,
428
+ "loss": 1.2176,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 2.12,
433
+ "learning_rate": 0.0002,
434
+ "loss": 1.1505,
435
+ "step": 142
436
+ },
437
+ {
438
+ "epoch": 2.15,
439
+ "learning_rate": 0.0002,
440
+ "loss": 1.0954,
441
+ "step": 144
442
+ },
443
+ {
444
+ "epoch": 2.18,
445
+ "learning_rate": 0.0002,
446
+ "loss": 0.8709,
447
+ "step": 146
448
+ },
449
+ {
450
+ "epoch": 2.21,
451
+ "learning_rate": 0.0002,
452
+ "loss": 0.9939,
453
+ "step": 148
454
+ },
455
+ {
456
+ "epoch": 2.24,
457
+ "learning_rate": 0.0002,
458
+ "loss": 0.8664,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 2.27,
463
+ "learning_rate": 0.0002,
464
+ "loss": 2.2894,
465
+ "step": 152
466
+ },
467
+ {
468
+ "epoch": 2.3,
469
+ "learning_rate": 0.0002,
470
+ "loss": 1.344,
471
+ "step": 154
472
+ },
473
+ {
474
+ "epoch": 2.33,
475
+ "learning_rate": 0.0002,
476
+ "loss": 1.3445,
477
+ "step": 156
478
+ },
479
+ {
480
+ "epoch": 2.36,
481
+ "learning_rate": 0.0002,
482
+ "loss": 1.3249,
483
+ "step": 158
484
+ },
485
+ {
486
+ "epoch": 2.39,
487
+ "learning_rate": 0.0002,
488
+ "loss": 1.0913,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 2.42,
493
+ "learning_rate": 0.0002,
494
+ "loss": 1.0874,
495
+ "step": 162
496
+ },
497
+ {
498
+ "epoch": 2.45,
499
+ "learning_rate": 0.0002,
500
+ "loss": 1.0708,
501
+ "step": 164
502
+ },
503
+ {
504
+ "epoch": 2.48,
505
+ "learning_rate": 0.0002,
506
+ "loss": 0.9724,
507
+ "step": 166
508
+ },
509
+ {
510
+ "epoch": 2.51,
511
+ "learning_rate": 0.0002,
512
+ "loss": 2.274,
513
+ "step": 168
514
+ },
515
+ {
516
+ "epoch": 2.53,
517
+ "learning_rate": 0.0002,
518
+ "loss": 1.577,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 2.56,
523
+ "learning_rate": 0.0002,
524
+ "loss": 1.3309,
525
+ "step": 172
526
+ },
527
+ {
528
+ "epoch": 2.59,
529
+ "learning_rate": 0.0002,
530
+ "loss": 1.2529,
531
+ "step": 174
532
+ },
533
+ {
534
+ "epoch": 2.62,
535
+ "learning_rate": 0.0002,
536
+ "loss": 1.0096,
537
+ "step": 176
538
+ },
539
+ {
540
+ "epoch": 2.65,
541
+ "learning_rate": 0.0002,
542
+ "loss": 0.8955,
543
+ "step": 178
544
+ },
545
+ {
546
+ "epoch": 2.68,
547
+ "learning_rate": 0.0002,
548
+ "loss": 1.1604,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 2.71,
553
+ "learning_rate": 0.0002,
554
+ "loss": 0.9809,
555
+ "step": 182
556
+ },
557
+ {
558
+ "epoch": 2.74,
559
+ "learning_rate": 0.0002,
560
+ "loss": 2.0555,
561
+ "step": 184
562
+ },
563
+ {
564
+ "epoch": 2.77,
565
+ "learning_rate": 0.0002,
566
+ "loss": 1.3211,
567
+ "step": 186
568
+ },
569
+ {
570
+ "epoch": 2.8,
571
+ "learning_rate": 0.0002,
572
+ "loss": 1.2553,
573
+ "step": 188
574
+ },
575
+ {
576
+ "epoch": 2.83,
577
+ "learning_rate": 0.0002,
578
+ "loss": 1.3017,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 2.86,
583
+ "learning_rate": 0.0002,
584
+ "loss": 1.0527,
585
+ "step": 192
586
+ },
587
+ {
588
+ "epoch": 2.89,
589
+ "learning_rate": 0.0002,
590
+ "loss": 1.0405,
591
+ "step": 194
592
+ },
593
+ {
594
+ "epoch": 2.92,
595
+ "learning_rate": 0.0002,
596
+ "loss": 1.0728,
597
+ "step": 196
598
+ },
599
+ {
600
+ "epoch": 2.95,
601
+ "learning_rate": 0.0002,
602
+ "loss": 0.9397,
603
+ "step": 198
604
+ },
605
+ {
606
+ "epoch": 2.98,
607
+ "learning_rate": 0.0002,
608
+ "loss": 1.0564,
609
+ "step": 200
610
  }
611
  ],
612
  "logging_steps": 2,
 
614
  "num_input_tokens_seen": 0,
615
  "num_train_epochs": 3,
616
  "save_steps": 500,
617
+ "total_flos": 1.3543695925420032e+16,
618
  "train_batch_size": 1,
619
  "trial_name": null,
620
  "trial_params": null