Colder203 commited on
Commit
9d30c4e
·
verified ·
1 Parent(s): 99793fd

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +593 -0
trainer_state.json ADDED
@@ -0,0 +1,593 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.4708236471176765,
5
+ "eval_steps": 500,
6
+ "global_step": 8000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005885295588970956,
13
+ "grad_norm": 29.875,
14
+ "learning_rate": 3.9215686274509805e-05,
15
+ "loss": 1.0686,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.011770591177941912,
20
+ "grad_norm": 11.375,
21
+ "learning_rate": 7.843137254901961e-05,
22
+ "loss": 0.6153,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.01765588676691287,
27
+ "grad_norm": 20.25,
28
+ "learning_rate": 0.00011764705882352942,
29
+ "loss": 0.5969,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.023541182355883823,
34
+ "grad_norm": 4.5,
35
+ "learning_rate": 0.00015686274509803922,
36
+ "loss": 0.5478,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.02942647794485478,
41
+ "grad_norm": 7.40625,
42
+ "learning_rate": 0.000196078431372549,
43
+ "loss": 0.5599,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.03531177353382574,
48
+ "grad_norm": 2.71875,
49
+ "learning_rate": 0.00019998528443307886,
50
+ "loss": 0.565,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.04119706912279669,
55
+ "grad_norm": 30.875,
56
+ "learning_rate": 0.00019993442136695625,
57
+ "loss": 0.5501,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.047082364711767646,
62
+ "grad_norm": 3.328125,
63
+ "learning_rate": 0.00019984724760441856,
64
+ "loss": 0.5355,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.05296766030073861,
69
+ "grad_norm": 6.03125,
70
+ "learning_rate": 0.00019972379481963764,
71
+ "loss": 0.5344,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.05885295588970956,
76
+ "grad_norm": 29.75,
77
+ "learning_rate": 0.00019956410786859524,
78
+ "loss": 0.5016,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.06473825147868052,
83
+ "grad_norm": 14.0625,
84
+ "learning_rate": 0.00019936824477278514,
85
+ "loss": 0.5091,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.07062354706765148,
90
+ "grad_norm": 24.75,
91
+ "learning_rate": 0.00019913627669813103,
92
+ "loss": 0.5005,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.07650884265662243,
97
+ "grad_norm": 3.203125,
98
+ "learning_rate": 0.00019886828792912894,
99
+ "loss": 0.4961,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.08239413824559338,
104
+ "grad_norm": 1.875,
105
+ "learning_rate": 0.0001985643758382227,
106
+ "loss": 0.4755,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.08827943383456434,
111
+ "grad_norm": 7.46875,
112
+ "learning_rate": 0.00019822465085042422,
113
+ "loss": 0.4889,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.09416472942353529,
118
+ "grad_norm": 3.859375,
119
+ "learning_rate": 0.0001978492364031911,
120
+ "loss": 0.5024,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.10005002501250625,
125
+ "grad_norm": 14.4375,
126
+ "learning_rate": 0.00019743826890157614,
127
+ "loss": 0.4681,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.10593532060147721,
132
+ "grad_norm": 10.375,
133
+ "learning_rate": 0.0001969918976686652,
134
+ "loss": 0.488,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.11182061619044817,
139
+ "grad_norm": 9.5625,
140
+ "learning_rate": 0.00019651028489132147,
141
+ "loss": 0.4859,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.11770591177941912,
146
+ "grad_norm": 15.125,
147
+ "learning_rate": 0.0001959936055612557,
148
+ "loss": 0.5028,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.12359120736839008,
153
+ "grad_norm": 12.5625,
154
+ "learning_rate": 0.0001954420474114435,
155
+ "loss": 0.4937,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.12947650295736104,
160
+ "grad_norm": 3.890625,
161
+ "learning_rate": 0.00019485581084791376,
162
+ "loss": 0.4801,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.13536179854633199,
167
+ "grad_norm": 19.125,
168
+ "learning_rate": 0.0001942351088769319,
169
+ "loss": 0.4853,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.14124709413530295,
174
+ "grad_norm": 11.8125,
175
+ "learning_rate": 0.0001935801670276052,
176
+ "loss": 0.4739,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.1471323897242739,
181
+ "grad_norm": 35.5,
182
+ "learning_rate": 0.00019289122326993777,
183
+ "loss": 0.4868,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.15301768531324486,
188
+ "grad_norm": 20.875,
189
+ "learning_rate": 0.00019216852792836516,
190
+ "loss": 0.4925,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.1589029809022158,
195
+ "grad_norm": 12.5625,
196
+ "learning_rate": 0.00019141234359080055,
197
+ "loss": 0.4808,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.16478827649118677,
202
+ "grad_norm": 8.6875,
203
+ "learning_rate": 0.00019062294501322416,
204
+ "loss": 0.4757,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.17067357208015774,
209
+ "grad_norm": 20.625,
210
+ "learning_rate": 0.0001898006190198525,
211
+ "loss": 0.4805,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.17655886766912868,
216
+ "grad_norm": 10.25,
217
+ "learning_rate": 0.0001889456643989218,
218
+ "loss": 0.4832,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.18244416325809965,
223
+ "grad_norm": 20.25,
224
+ "learning_rate": 0.00018805839179412485,
225
+ "loss": 0.4559,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.18832945884707059,
230
+ "grad_norm": 8.5625,
231
+ "learning_rate": 0.00018713912359174,
232
+ "loss": 0.497,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.19421475443604155,
237
+ "grad_norm": 6.40625,
238
+ "learning_rate": 0.00018618819380349382,
239
+ "loss": 0.4776,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.2001000500250125,
244
+ "grad_norm": 12.8125,
245
+ "learning_rate": 0.00018520594794519941,
246
+ "loss": 0.4915,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.20598534561398346,
251
+ "grad_norm": 1.84375,
252
+ "learning_rate": 0.00018419274291121485,
253
+ "loss": 0.4498,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.21187064120295443,
258
+ "grad_norm": 3.8125,
259
+ "learning_rate": 0.00018314894684476736,
260
+ "loss": 0.4625,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.21775593679192537,
265
+ "grad_norm": 19.125,
266
+ "learning_rate": 0.00018207493900419027,
267
+ "loss": 0.4625,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.22364123238089634,
272
+ "grad_norm": 11.5,
273
+ "learning_rate": 0.00018097110962512128,
274
+ "loss": 0.4655,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.22952652796986728,
279
+ "grad_norm": 6.3125,
280
+ "learning_rate": 0.00017983785977871209,
281
+ "loss": 0.4488,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.23541182355883825,
286
+ "grad_norm": 9.875,
287
+ "learning_rate": 0.00017867560122590125,
288
+ "loss": 0.4441,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.24129711914780919,
293
+ "grad_norm": 12.875,
294
+ "learning_rate": 0.00017748475626780277,
295
+ "loss": 0.4732,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.24718241473678015,
300
+ "grad_norm": 4.21875,
301
+ "learning_rate": 0.0001762657575922649,
302
+ "loss": 0.4544,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.2530677103257511,
307
+ "grad_norm": 3.125,
308
+ "learning_rate": 0.0001750190481166552,
309
+ "loss": 0.4779,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.2589530059147221,
314
+ "grad_norm": 2.1875,
315
+ "learning_rate": 0.00017374508082692848,
316
+ "loss": 0.4661,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.26483830150369303,
321
+ "grad_norm": 26.25,
322
+ "learning_rate": 0.0001724443186130367,
323
+ "loss": 0.4916,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.27072359709266397,
328
+ "grad_norm": 8.125,
329
+ "learning_rate": 0.00017111723410073991,
330
+ "loss": 0.449,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.2766088926816349,
335
+ "grad_norm": 8.625,
336
+ "learning_rate": 0.00016976430947988007,
337
+ "loss": 0.45,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.2824941882706059,
342
+ "grad_norm": 3.59375,
343
+ "learning_rate": 0.00016838603632917954,
344
+ "loss": 0.4593,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.28837948385957685,
349
+ "grad_norm": 6.40625,
350
+ "learning_rate": 0.0001669829154376285,
351
+ "loss": 0.4847,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.2942647794485478,
356
+ "grad_norm": 13.125,
357
+ "learning_rate": 0.00016555545662252536,
358
+ "loss": 0.4576,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.3001500750375188,
363
+ "grad_norm": 14.3125,
364
+ "learning_rate": 0.00016410417854423735,
365
+ "loss": 0.4457,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.3060353706264897,
370
+ "grad_norm": 29.0,
371
+ "learning_rate": 0.00016262960851774752,
372
+ "loss": 0.4972,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.31192066621546066,
377
+ "grad_norm": 20.75,
378
+ "learning_rate": 0.00016113228232105757,
379
+ "loss": 0.4715,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.3178059618044316,
384
+ "grad_norm": 22.5,
385
+ "learning_rate": 0.0001596127440005152,
386
+ "loss": 0.4696,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.3236912573934026,
391
+ "grad_norm": 8.1875,
392
+ "learning_rate": 0.00015807154567313775,
393
+ "loss": 0.4629,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.32957655298237354,
398
+ "grad_norm": 4.375,
399
+ "learning_rate": 0.0001565092473260029,
400
+ "loss": 0.475,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.3354618485713445,
405
+ "grad_norm": 13.5,
406
+ "learning_rate": 0.00015492641661278005,
407
+ "loss": 0.4511,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.3413471441603155,
412
+ "grad_norm": 3.5625,
413
+ "learning_rate": 0.0001533236286474762,
414
+ "loss": 0.4743,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.3472324397492864,
419
+ "grad_norm": 11.8125,
420
+ "learning_rate": 0.0001517014657954708,
421
+ "loss": 0.4418,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.35311773533825735,
426
+ "grad_norm": 26.125,
427
+ "learning_rate": 0.00015006051746191626,
428
+ "loss": 0.45,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.3590030309272283,
433
+ "grad_norm": 15.375,
434
+ "learning_rate": 0.00014840137987758028,
435
+ "loss": 0.4463,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.3648883265161993,
440
+ "grad_norm": 5.90625,
441
+ "learning_rate": 0.00014672465588220837,
442
+ "loss": 0.4559,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.37077362210517023,
447
+ "grad_norm": 12.9375,
448
+ "learning_rate": 0.0001450309547054846,
449
+ "loss": 0.4398,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.37665891769414117,
454
+ "grad_norm": 21.875,
455
+ "learning_rate": 0.00014332089174567126,
456
+ "loss": 0.4454,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.38254421328311217,
461
+ "grad_norm": 16.875,
462
+ "learning_rate": 0.00014159508834600657,
463
+ "loss": 0.4443,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.3884295088720831,
468
+ "grad_norm": 34.25,
469
+ "learning_rate": 0.00013985417156894267,
470
+ "loss": 0.4762,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 0.39431480446105405,
475
+ "grad_norm": 4.5625,
476
+ "learning_rate": 0.0001380987739683055,
477
+ "loss": 0.4795,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 0.400200100050025,
482
+ "grad_norm": 15.75,
483
+ "learning_rate": 0.00013632953335945927,
484
+ "loss": 0.4603,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 0.406085395638996,
489
+ "grad_norm": 5.40625,
490
+ "learning_rate": 0.00013454709258755942,
491
+ "loss": 0.4674,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 0.4119706912279669,
496
+ "grad_norm": 30.125,
497
+ "learning_rate": 0.00013275209929397775,
498
+ "loss": 0.4595,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 0.41785598681693786,
503
+ "grad_norm": 16.875,
504
+ "learning_rate": 0.0001309452056809851,
505
+ "loss": 0.4398,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 0.42374128240590886,
510
+ "grad_norm": 5.6875,
511
+ "learning_rate": 0.00012912706827477671,
512
+ "loss": 0.4693,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 0.4296265779948798,
517
+ "grad_norm": 17.125,
518
+ "learning_rate": 0.00012729834768692667,
519
+ "loss": 0.4564,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 0.43551187358385074,
524
+ "grad_norm": 9.75,
525
+ "learning_rate": 0.00012545970837435756,
526
+ "loss": 0.4732,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 0.4413971691728217,
531
+ "grad_norm": 6.3125,
532
+ "learning_rate": 0.00012361181839791357,
533
+ "loss": 0.4647,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 0.4472824647617927,
538
+ "grad_norm": 19.0,
539
+ "learning_rate": 0.00012175534917962352,
540
+ "loss": 0.4697,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 0.4531677603507636,
545
+ "grad_norm": 19.375,
546
+ "learning_rate": 0.00011989097525874294,
547
+ "loss": 0.4814,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 0.45905305593973456,
552
+ "grad_norm": 2.015625,
553
+ "learning_rate": 0.00011801937404666336,
554
+ "loss": 0.4688,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 0.46493835152870555,
559
+ "grad_norm": 9.625,
560
+ "learning_rate": 0.00011614122558077828,
561
+ "loss": 0.4665,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 0.4708236471176765,
566
+ "grad_norm": 21.875,
567
+ "learning_rate": 0.00011425721227739465,
568
+ "loss": 0.472,
569
+ "step": 8000
570
+ }
571
+ ],
572
+ "logging_steps": 100,
573
+ "max_steps": 16991,
574
+ "num_input_tokens_seen": 0,
575
+ "num_train_epochs": 1,
576
+ "save_steps": 4000,
577
+ "stateful_callbacks": {
578
+ "TrainerControl": {
579
+ "args": {
580
+ "should_epoch_stop": false,
581
+ "should_evaluate": false,
582
+ "should_log": false,
583
+ "should_save": true,
584
+ "should_training_stop": false
585
+ },
586
+ "attributes": {}
587
+ }
588
+ },
589
+ "total_flos": 1.253476198349144e+18,
590
+ "train_batch_size": 8,
591
+ "trial_name": null,
592
+ "trial_params": null
593
+ }