jinghan23 commited on
Commit
193ed96
·
verified ·
1 Parent(s): b63ac42

Upload to Hugging Face - trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +1010 -0
trainer_state.json ADDED
@@ -0,0 +1,1010 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9942299156679982,
5
+ "eval_steps": 500,
6
+ "global_step": 140,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.5339343547821045,
14
+ "learning_rate": 1e-05,
15
+ "loss": 0.4406,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.4306606948375702,
21
+ "learning_rate": 1e-05,
22
+ "loss": 0.4472,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "grad_norm": 0.48949554562568665,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.4724,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03,
34
+ "grad_norm": 0.7450588941574097,
35
+ "learning_rate": 1e-05,
36
+ "loss": 0.4314,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.04,
41
+ "grad_norm": 0.39597198367118835,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.4576,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "grad_norm": 0.4372778832912445,
49
+ "learning_rate": 1e-05,
50
+ "loss": 0.4573,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "grad_norm": 0.5514771938323975,
56
+ "learning_rate": 1e-05,
57
+ "loss": 0.4342,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.06,
62
+ "grad_norm": 0.6987231969833374,
63
+ "learning_rate": 1e-05,
64
+ "loss": 0.4239,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "grad_norm": 0.5473514795303345,
70
+ "learning_rate": 1e-05,
71
+ "loss": 0.4599,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.07,
76
+ "grad_norm": 0.5179272890090942,
77
+ "learning_rate": 1e-05,
78
+ "loss": 0.4462,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.08,
83
+ "grad_norm": 0.5821484923362732,
84
+ "learning_rate": 1e-05,
85
+ "loss": 0.435,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.09,
90
+ "grad_norm": 0.5863294005393982,
91
+ "learning_rate": 1e-05,
92
+ "loss": 0.4272,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "grad_norm": 0.4016607403755188,
98
+ "learning_rate": 1e-05,
99
+ "loss": 0.4491,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.1,
104
+ "grad_norm": 0.4974324703216553,
105
+ "learning_rate": 1e-05,
106
+ "loss": 0.4542,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.11,
111
+ "grad_norm": 0.5260458588600159,
112
+ "learning_rate": 1e-05,
113
+ "loss": 0.4387,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.11,
118
+ "grad_norm": 0.7002240419387817,
119
+ "learning_rate": 1e-05,
120
+ "loss": 0.4274,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.12,
125
+ "grad_norm": 0.3600125014781952,
126
+ "learning_rate": 1e-05,
127
+ "loss": 0.4564,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.13,
132
+ "grad_norm": 0.4479730725288391,
133
+ "learning_rate": 1e-05,
134
+ "loss": 0.4284,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "grad_norm": 0.539320170879364,
140
+ "learning_rate": 1e-05,
141
+ "loss": 0.44,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.14,
146
+ "grad_norm": 0.8680666089057922,
147
+ "learning_rate": 1e-05,
148
+ "loss": 0.4301,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.15,
153
+ "grad_norm": 0.41423720121383667,
154
+ "learning_rate": 1e-05,
155
+ "loss": 0.4466,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.16,
160
+ "grad_norm": 0.441376268863678,
161
+ "learning_rate": 1e-05,
162
+ "loss": 0.4447,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.16,
167
+ "grad_norm": 0.5229262709617615,
168
+ "learning_rate": 1e-05,
169
+ "loss": 0.4344,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.17,
174
+ "grad_norm": 0.7713359594345093,
175
+ "learning_rate": 1e-05,
176
+ "loss": 0.4375,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.18,
181
+ "grad_norm": 0.4245271384716034,
182
+ "learning_rate": 1e-05,
183
+ "loss": 0.4618,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.18,
188
+ "grad_norm": 0.4831457734107971,
189
+ "learning_rate": 1e-05,
190
+ "loss": 0.4403,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.19,
195
+ "grad_norm": 0.58194899559021,
196
+ "learning_rate": 1e-05,
197
+ "loss": 0.4229,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.2,
202
+ "grad_norm": 0.7558773159980774,
203
+ "learning_rate": 1e-05,
204
+ "loss": 0.3974,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.21,
209
+ "grad_norm": 0.39629215002059937,
210
+ "learning_rate": 1e-05,
211
+ "loss": 0.4616,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.21,
216
+ "grad_norm": 0.49573493003845215,
217
+ "learning_rate": 1e-05,
218
+ "loss": 0.4417,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.22,
223
+ "grad_norm": 0.5668038129806519,
224
+ "learning_rate": 1e-05,
225
+ "loss": 0.43,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.23,
230
+ "grad_norm": 0.7516561150550842,
231
+ "learning_rate": 1e-05,
232
+ "loss": 0.414,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.23,
237
+ "grad_norm": 1.1010799407958984,
238
+ "learning_rate": 1e-05,
239
+ "loss": 892.876,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.24,
244
+ "grad_norm": 0.4981920123100281,
245
+ "learning_rate": 1e-05,
246
+ "loss": 0.4428,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.25,
251
+ "grad_norm": 0.6654168963432312,
252
+ "learning_rate": 1e-05,
253
+ "loss": 0.4234,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.26,
258
+ "grad_norm": 0.9636304378509521,
259
+ "learning_rate": 1e-05,
260
+ "loss": 0.4185,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.26,
265
+ "grad_norm": 0.39848971366882324,
266
+ "learning_rate": 1e-05,
267
+ "loss": 0.4517,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.27,
272
+ "grad_norm": 0.5225277543067932,
273
+ "learning_rate": 1e-05,
274
+ "loss": 0.4459,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.28,
279
+ "grad_norm": 0.5011440515518188,
280
+ "learning_rate": 1e-05,
281
+ "loss": 0.4403,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.28,
286
+ "grad_norm": 0.9465950727462769,
287
+ "learning_rate": 1e-05,
288
+ "loss": 0.4103,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.29,
293
+ "grad_norm": 0.43049702048301697,
294
+ "learning_rate": 1e-05,
295
+ "loss": 0.4553,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.3,
300
+ "grad_norm": 0.48856088519096375,
301
+ "learning_rate": 1e-05,
302
+ "loss": 0.449,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.31,
307
+ "grad_norm": 0.6367886066436768,
308
+ "learning_rate": 1e-05,
309
+ "loss": 0.4405,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.31,
314
+ "grad_norm": 0.6144514679908752,
315
+ "learning_rate": 1e-05,
316
+ "loss": 0.4364,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.32,
321
+ "grad_norm": 0.4697144031524658,
322
+ "learning_rate": 1e-05,
323
+ "loss": 0.451,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.33,
328
+ "grad_norm": 0.5866898894309998,
329
+ "learning_rate": 1e-05,
330
+ "loss": 0.4387,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.33,
335
+ "grad_norm": 0.5469757914543152,
336
+ "learning_rate": 1e-05,
337
+ "loss": 0.4464,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.34,
342
+ "grad_norm": 0.5702504515647888,
343
+ "learning_rate": 1e-05,
344
+ "loss": 0.4237,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.35,
349
+ "grad_norm": 0.4027068614959717,
350
+ "learning_rate": 1e-05,
351
+ "loss": 0.4608,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.36,
356
+ "grad_norm": 0.4725416302680969,
357
+ "learning_rate": 1e-05,
358
+ "loss": 0.4564,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.36,
363
+ "grad_norm": 0.5751639008522034,
364
+ "learning_rate": 1e-05,
365
+ "loss": 0.4406,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.37,
370
+ "grad_norm": 1.0833802223205566,
371
+ "learning_rate": 1e-05,
372
+ "loss": 0.4157,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.38,
377
+ "grad_norm": 0.44081103801727295,
378
+ "learning_rate": 1e-05,
379
+ "loss": 0.4618,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.38,
384
+ "grad_norm": 0.46274518966674805,
385
+ "learning_rate": 1e-05,
386
+ "loss": 0.4391,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.39,
391
+ "grad_norm": 0.48259931802749634,
392
+ "learning_rate": 1e-05,
393
+ "loss": 0.4456,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.4,
398
+ "grad_norm": 0.7039265632629395,
399
+ "learning_rate": 1e-05,
400
+ "loss": 0.4201,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.4,
405
+ "grad_norm": 0.4099649488925934,
406
+ "learning_rate": 1e-05,
407
+ "loss": 0.4373,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.41,
412
+ "grad_norm": 0.47295379638671875,
413
+ "learning_rate": 1e-05,
414
+ "loss": 0.4475,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.42,
419
+ "grad_norm": 0.5771341919898987,
420
+ "learning_rate": 1e-05,
421
+ "loss": 0.4205,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.43,
426
+ "grad_norm": 0.7415468692779541,
427
+ "learning_rate": 1e-05,
428
+ "loss": 0.4287,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.43,
433
+ "grad_norm": 0.5697640776634216,
434
+ "learning_rate": 1e-05,
435
+ "loss": 0.4351,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.44,
440
+ "grad_norm": 0.494108110666275,
441
+ "learning_rate": 1e-05,
442
+ "loss": 0.4356,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.45,
447
+ "grad_norm": 0.7063843011856079,
448
+ "learning_rate": 1e-05,
449
+ "loss": 0.4101,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.45,
454
+ "grad_norm": 0.9190882444381714,
455
+ "learning_rate": 1e-05,
456
+ "loss": 0.4008,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.46,
461
+ "grad_norm": 0.6143580675125122,
462
+ "learning_rate": 1e-05,
463
+ "loss": 1077.2749,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.47,
468
+ "grad_norm": 0.6259483098983765,
469
+ "learning_rate": 1e-05,
470
+ "loss": 0.4455,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.48,
475
+ "grad_norm": 0.6354689002037048,
476
+ "learning_rate": 1e-05,
477
+ "loss": 0.4249,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.48,
482
+ "grad_norm": 0.8926694393157959,
483
+ "learning_rate": 1e-05,
484
+ "loss": 0.428,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.49,
489
+ "grad_norm": 0.37563061714172363,
490
+ "learning_rate": 1e-05,
491
+ "loss": 0.4522,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.5,
496
+ "grad_norm": 0.4575391113758087,
497
+ "learning_rate": 1e-05,
498
+ "loss": 0.4601,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.5,
503
+ "grad_norm": 0.5881872177124023,
504
+ "learning_rate": 1e-05,
505
+ "loss": 0.4284,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.51,
510
+ "grad_norm": 1.1317410469055176,
511
+ "learning_rate": 1e-05,
512
+ "loss": 0.4023,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.52,
517
+ "grad_norm": 0.5603578090667725,
518
+ "learning_rate": 1e-05,
519
+ "loss": 0.4573,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.53,
524
+ "grad_norm": 0.6214807629585266,
525
+ "learning_rate": 1e-05,
526
+ "loss": 0.4535,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.53,
531
+ "grad_norm": 0.6941476464271545,
532
+ "learning_rate": 1e-05,
533
+ "loss": 0.4351,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.54,
538
+ "grad_norm": 0.8727200031280518,
539
+ "learning_rate": 1e-05,
540
+ "loss": 0.4248,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.55,
545
+ "grad_norm": 0.6732370853424072,
546
+ "learning_rate": 1e-05,
547
+ "loss": 0.45,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.55,
552
+ "grad_norm": 0.7978621125221252,
553
+ "learning_rate": 1e-05,
554
+ "loss": 0.4417,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.56,
559
+ "grad_norm": 0.7042059898376465,
560
+ "learning_rate": 1e-05,
561
+ "loss": 0.3983,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.57,
566
+ "grad_norm": 1.2186613082885742,
567
+ "learning_rate": 1e-05,
568
+ "loss": 0.3991,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.58,
573
+ "grad_norm": 0.5385881066322327,
574
+ "learning_rate": 1e-05,
575
+ "loss": 0.4516,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.58,
580
+ "grad_norm": 0.6898678541183472,
581
+ "learning_rate": 1e-05,
582
+ "loss": 0.4246,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.59,
587
+ "grad_norm": 0.8373177647590637,
588
+ "learning_rate": 1e-05,
589
+ "loss": 0.4199,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.6,
594
+ "grad_norm": 0.8186657428741455,
595
+ "learning_rate": 1e-05,
596
+ "loss": 0.4425,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.6,
601
+ "grad_norm": 0.8698004484176636,
602
+ "learning_rate": 1e-05,
603
+ "loss": 0.4432,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.61,
608
+ "grad_norm": 1.0647398233413696,
609
+ "learning_rate": 1e-05,
610
+ "loss": 0.4308,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.62,
615
+ "grad_norm": 0.8065099120140076,
616
+ "learning_rate": 1e-05,
617
+ "loss": 0.4369,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.62,
622
+ "grad_norm": 1.0753732919692993,
623
+ "learning_rate": 1e-05,
624
+ "loss": 0.4055,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.63,
629
+ "grad_norm": 0.4561431407928467,
630
+ "learning_rate": 1e-05,
631
+ "loss": 0.4482,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.64,
636
+ "grad_norm": 0.5589205026626587,
637
+ "learning_rate": 1e-05,
638
+ "loss": 0.4517,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.65,
643
+ "grad_norm": 0.7920203804969788,
644
+ "learning_rate": 1e-05,
645
+ "loss": 0.4107,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.65,
650
+ "grad_norm": 1.1868764162063599,
651
+ "learning_rate": 1e-05,
652
+ "loss": 0.406,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.66,
657
+ "grad_norm": 0.5007905960083008,
658
+ "learning_rate": 1e-05,
659
+ "loss": 0.4582,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.67,
664
+ "grad_norm": 0.588740348815918,
665
+ "learning_rate": 1e-05,
666
+ "loss": 0.4285,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.67,
671
+ "grad_norm": 0.7123900651931763,
672
+ "learning_rate": 1e-05,
673
+ "loss": 0.445,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.68,
678
+ "grad_norm": 0.7591605186462402,
679
+ "learning_rate": 1e-05,
680
+ "loss": 0.4111,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.69,
685
+ "grad_norm": 0.6483467817306519,
686
+ "learning_rate": 1e-05,
687
+ "loss": 0.4353,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.7,
692
+ "grad_norm": 0.6339621543884277,
693
+ "learning_rate": 1e-05,
694
+ "loss": 0.4167,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.7,
699
+ "grad_norm": 0.9539307951927185,
700
+ "learning_rate": 1e-05,
701
+ "loss": 0.4129,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.71,
706
+ "grad_norm": 0.9566183090209961,
707
+ "learning_rate": 1e-05,
708
+ "loss": 0.4122,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.72,
713
+ "grad_norm": 0.45071572065353394,
714
+ "learning_rate": 1e-05,
715
+ "loss": 0.4367,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.72,
720
+ "grad_norm": 0.6243826746940613,
721
+ "learning_rate": 1e-05,
722
+ "loss": 0.4517,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.73,
727
+ "grad_norm": 1.0642685890197754,
728
+ "learning_rate": 1e-05,
729
+ "loss": 0.418,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.74,
734
+ "grad_norm": 0.8378849029541016,
735
+ "learning_rate": 1e-05,
736
+ "loss": 0.3948,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.75,
741
+ "grad_norm": 0.5254150629043579,
742
+ "learning_rate": 1e-05,
743
+ "loss": 0.4566,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.75,
748
+ "grad_norm": 0.677213728427887,
749
+ "learning_rate": 1e-05,
750
+ "loss": 0.4484,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.76,
755
+ "grad_norm": 1.118269920349121,
756
+ "learning_rate": 1e-05,
757
+ "loss": 0.4523,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.77,
762
+ "grad_norm": 1.260345458984375,
763
+ "learning_rate": 1e-05,
764
+ "loss": 0.408,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.77,
769
+ "grad_norm": 0.7494204044342041,
770
+ "learning_rate": 1e-05,
771
+ "loss": 0.4275,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.78,
776
+ "grad_norm": 0.6795545220375061,
777
+ "learning_rate": 1e-05,
778
+ "loss": 0.4505,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.79,
783
+ "grad_norm": 0.8415333032608032,
784
+ "learning_rate": 1e-05,
785
+ "loss": 0.442,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.8,
790
+ "grad_norm": 1.064477562904358,
791
+ "learning_rate": 1e-05,
792
+ "loss": 0.4019,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.8,
797
+ "grad_norm": 0.6557851433753967,
798
+ "learning_rate": 1e-05,
799
+ "loss": 0.4534,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.81,
804
+ "grad_norm": 0.7865703701972961,
805
+ "learning_rate": 1e-05,
806
+ "loss": 0.4339,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.82,
811
+ "grad_norm": 0.7419100403785706,
812
+ "learning_rate": 1e-05,
813
+ "loss": 0.4364,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.82,
818
+ "grad_norm": 1.0382827520370483,
819
+ "learning_rate": 1e-05,
820
+ "loss": 0.4028,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.83,
825
+ "grad_norm": 0.9644023776054382,
826
+ "learning_rate": 1e-05,
827
+ "loss": 0.4383,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.84,
832
+ "grad_norm": 0.859690248966217,
833
+ "learning_rate": 1e-05,
834
+ "loss": 0.4327,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.85,
839
+ "grad_norm": 0.8699947595596313,
840
+ "learning_rate": 1e-05,
841
+ "loss": 0.4275,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.85,
846
+ "grad_norm": 1.2335870265960693,
847
+ "learning_rate": 1e-05,
848
+ "loss": 0.3891,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.86,
853
+ "grad_norm": 0.506551206111908,
854
+ "learning_rate": 1e-05,
855
+ "loss": 0.4568,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.87,
860
+ "grad_norm": 2.2713043689727783,
861
+ "learning_rate": 1e-05,
862
+ "loss": 0.4419,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.87,
867
+ "grad_norm": 0.6728506684303284,
868
+ "learning_rate": 1e-05,
869
+ "loss": 0.4447,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.88,
874
+ "grad_norm": 0.8511173725128174,
875
+ "learning_rate": 1e-05,
876
+ "loss": 0.3946,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.89,
881
+ "grad_norm": 0.5495295524597168,
882
+ "learning_rate": 1e-05,
883
+ "loss": 1092.1152,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.89,
888
+ "grad_norm": 0.9345693588256836,
889
+ "learning_rate": 1e-05,
890
+ "loss": 0.4477,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.9,
895
+ "grad_norm": 0.6886237263679504,
896
+ "learning_rate": 1e-05,
897
+ "loss": 0.4283,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.91,
902
+ "grad_norm": 0.6619666814804077,
903
+ "learning_rate": 1e-05,
904
+ "loss": 0.4212,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.92,
909
+ "grad_norm": 0.534345805644989,
910
+ "learning_rate": 1e-05,
911
+ "loss": 0.4368,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.92,
916
+ "grad_norm": 0.7200596332550049,
917
+ "learning_rate": 1e-05,
918
+ "loss": 0.4117,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.93,
923
+ "grad_norm": 0.6517333388328552,
924
+ "learning_rate": 1e-05,
925
+ "loss": 0.4215,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.94,
930
+ "grad_norm": 0.6811349391937256,
931
+ "learning_rate": 1e-05,
932
+ "loss": 0.4057,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.94,
937
+ "grad_norm": 0.4850296974182129,
938
+ "learning_rate": 1e-05,
939
+ "loss": 0.4407,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.95,
944
+ "grad_norm": 0.5540636777877808,
945
+ "learning_rate": 1e-05,
946
+ "loss": 0.4077,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.96,
951
+ "grad_norm": 0.4562750458717346,
952
+ "learning_rate": 1e-05,
953
+ "loss": 0.4208,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.97,
958
+ "grad_norm": 0.8182024359703064,
959
+ "learning_rate": 1e-05,
960
+ "loss": 0.4151,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.97,
965
+ "grad_norm": 0.39840784668922424,
966
+ "learning_rate": 1e-05,
967
+ "loss": 0.4633,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.98,
972
+ "grad_norm": 0.5493362545967102,
973
+ "learning_rate": 1e-05,
974
+ "loss": 0.4378,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.99,
979
+ "grad_norm": 0.6024540066719055,
980
+ "learning_rate": 1e-05,
981
+ "loss": 0.4087,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.99,
986
+ "grad_norm": 0.6966805458068848,
987
+ "learning_rate": 1e-05,
988
+ "loss": 0.4299,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.99,
993
+ "step": 140,
994
+ "total_flos": 190411138334720.0,
995
+ "train_loss": 22.297974420232432,
996
+ "train_runtime": 30487.3439,
997
+ "train_samples_per_second": 0.074,
998
+ "train_steps_per_second": 0.005
999
+ }
1000
+ ],
1001
+ "logging_steps": 1.0,
1002
+ "max_steps": 140,
1003
+ "num_input_tokens_seen": 0,
1004
+ "num_train_epochs": 1,
1005
+ "save_steps": 30,
1006
+ "total_flos": 190411138334720.0,
1007
+ "train_batch_size": 1,
1008
+ "trial_name": null,
1009
+ "trial_params": null
1010
+ }