Boffl commited on
Commit
f8ffd7a
1 Parent(s): a0553be

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +630 -0
trainer_state.json ADDED
@@ -0,0 +1,630 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9997049277072882,
5
+ "eval_steps": 500,
6
+ "global_step": 847,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.011802891708468575,
13
+ "grad_norm": 0.6382197141647339,
14
+ "learning_rate": 5.294117647058824e-06,
15
+ "loss": 1.7524,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.02360578341693715,
20
+ "grad_norm": 0.5001206994056702,
21
+ "learning_rate": 1.1176470588235295e-05,
22
+ "loss": 1.3315,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.03540867512540572,
27
+ "grad_norm": 0.41650518774986267,
28
+ "learning_rate": 1.7058823529411767e-05,
29
+ "loss": 1.1148,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0472115668338743,
34
+ "grad_norm": 0.42574718594551086,
35
+ "learning_rate": 2.235294117647059e-05,
36
+ "loss": 1.0196,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.05901445854234287,
41
+ "grad_norm": 0.3408316373825073,
42
+ "learning_rate": 2.823529411764706e-05,
43
+ "loss": 0.94,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.07081735025081144,
48
+ "grad_norm": 0.39876773953437805,
49
+ "learning_rate": 3.411764705882353e-05,
50
+ "loss": 0.8918,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.08262024195928003,
55
+ "grad_norm": 0.32425975799560547,
56
+ "learning_rate": 4e-05,
57
+ "loss": 0.8412,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.0944231336677486,
62
+ "grad_norm": 0.40873634815216064,
63
+ "learning_rate": 4.588235294117647e-05,
64
+ "loss": 0.887,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.10622602537621717,
69
+ "grad_norm": 0.4909669756889343,
70
+ "learning_rate": 4.9998087784700426e-05,
71
+ "loss": 0.8888,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.11802891708468574,
76
+ "grad_norm": 0.3897865414619446,
77
+ "learning_rate": 4.996410098317137e-05,
78
+ "loss": 0.8555,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.1298318087931543,
83
+ "grad_norm": 0.3305865228176117,
84
+ "learning_rate": 4.989723448187131e-05,
85
+ "loss": 0.8424,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.14163470050162288,
90
+ "grad_norm": 0.3554224669933319,
91
+ "learning_rate": 4.9845268462432916e-05,
92
+ "loss": 0.8445,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.15343759221009148,
97
+ "grad_norm": 0.46097129583358765,
98
+ "learning_rate": 4.970969070763177e-05,
99
+ "loss": 0.8377,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.16524048391856005,
104
+ "grad_norm": 0.3145534098148346,
105
+ "learning_rate": 4.953211814536217e-05,
106
+ "loss": 0.759,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.17704337562702863,
111
+ "grad_norm": 0.42392656207084656,
112
+ "learning_rate": 4.931285256513868e-05,
113
+ "loss": 0.8121,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.1888462673354972,
118
+ "grad_norm": 0.4339812994003296,
119
+ "learning_rate": 4.905226661492095e-05,
120
+ "loss": 0.7896,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.20064915904396577,
125
+ "grad_norm": 0.44723227620124817,
126
+ "learning_rate": 4.8750803167788136e-05,
127
+ "loss": 0.8057,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.21245205075243434,
132
+ "grad_norm": 0.46169158816337585,
133
+ "learning_rate": 4.840897456926373e-05,
134
+ "loss": 0.7724,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.2242549424609029,
139
+ "grad_norm": 0.41829928755760193,
140
+ "learning_rate": 4.8027361766570117e-05,
141
+ "loss": 0.7458,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.23605783416937148,
146
+ "grad_norm": 0.4120149612426758,
147
+ "learning_rate": 4.760661332129254e-05,
148
+ "loss": 0.7686,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.24786072587784008,
153
+ "grad_norm": 0.3918631970882416,
154
+ "learning_rate": 4.7147444307130686e-05,
155
+ "loss": 0.769,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.2596636175863086,
160
+ "grad_norm": 0.4276711642742157,
161
+ "learning_rate": 4.665063509461097e-05,
162
+ "loss": 0.7574,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.2714665092947772,
167
+ "grad_norm": 0.42904192209243774,
168
+ "learning_rate": 4.6117030024825114e-05,
169
+ "loss": 0.7826,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.28326940100324577,
174
+ "grad_norm": 0.5145927667617798,
175
+ "learning_rate": 4.554753597444896e-05,
176
+ "loss": 0.7954,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.29507229271171437,
181
+ "grad_norm": 0.3549771010875702,
182
+ "learning_rate": 4.494312081448029e-05,
183
+ "loss": 0.7527,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.30687518442018297,
188
+ "grad_norm": 0.4441188871860504,
189
+ "learning_rate": 4.4304811765315105e-05,
190
+ "loss": 0.7321,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3186780761286515,
195
+ "grad_norm": 0.3967060148715973,
196
+ "learning_rate": 4.3633693650957976e-05,
197
+ "loss": 0.7047,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.3304809678371201,
202
+ "grad_norm": 0.44348135590553284,
203
+ "learning_rate": 4.293090705533342e-05,
204
+ "loss": 0.7431,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.34228385954558865,
209
+ "grad_norm": 0.9141893982887268,
210
+ "learning_rate": 4.219764638383177e-05,
211
+ "loss": 0.7177,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.35408675125405725,
216
+ "grad_norm": 0.45525214076042175,
217
+ "learning_rate": 4.1435157833383955e-05,
218
+ "loss": 0.7128,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.3658896429625258,
223
+ "grad_norm": 0.537662148475647,
224
+ "learning_rate": 4.06447372745151e-05,
225
+ "loss": 0.7162,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.3776925346709944,
230
+ "grad_norm": 0.4020293653011322,
231
+ "learning_rate": 3.982772804897649e-05,
232
+ "loss": 0.7212,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.389495426379463,
237
+ "grad_norm": 0.6390876173973083,
238
+ "learning_rate": 3.898551868669883e-05,
239
+ "loss": 0.716,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.40129831808793154,
244
+ "grad_norm": 0.47102075815200806,
245
+ "learning_rate": 3.811954054594702e-05,
246
+ "loss": 0.733,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.41310120979640014,
251
+ "grad_norm": 0.5660268664360046,
252
+ "learning_rate": 3.723126538068686e-05,
253
+ "loss": 0.764,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.4249041015048687,
258
+ "grad_norm": 0.595162570476532,
259
+ "learning_rate": 3.632220283929822e-05,
260
+ "loss": 0.7302,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.4367069932133373,
265
+ "grad_norm": 0.5331649780273438,
266
+ "learning_rate": 3.5393897898885606e-05,
267
+ "loss": 0.7127,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.4485098849218058,
272
+ "grad_norm": 0.4248451590538025,
273
+ "learning_rate": 3.444792823954651e-05,
274
+ "loss": 0.6933,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.4603127766302744,
279
+ "grad_norm": 0.5570621490478516,
280
+ "learning_rate": 3.348590156306017e-05,
281
+ "loss": 0.7012,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.47211566833874297,
286
+ "grad_norm": 0.41210871934890747,
287
+ "learning_rate": 3.25094528605536e-05,
288
+ "loss": 0.7006,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.48391856004721157,
293
+ "grad_norm": 0.5020595788955688,
294
+ "learning_rate": 3.152024163378867e-05,
295
+ "loss": 0.7159,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.49572145175568016,
300
+ "grad_norm": 0.5407310724258423,
301
+ "learning_rate": 3.051994907479265e-05,
302
+ "loss": 0.7002,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5075243434641488,
307
+ "grad_norm": 0.422695130109787,
308
+ "learning_rate": 2.9510275208625522e-05,
309
+ "loss": 0.6721,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.5193272351726173,
314
+ "grad_norm": 0.4953523576259613,
315
+ "learning_rate": 2.849293600414002e-05,
316
+ "loss": 0.6612,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.5311301268810859,
321
+ "grad_norm": 0.44490641355514526,
322
+ "learning_rate": 2.7469660457644857e-05,
323
+ "loss": 0.6786,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.5429330185895545,
328
+ "grad_norm": 0.3714945912361145,
329
+ "learning_rate": 2.644218765442728e-05,
330
+ "loss": 0.6731,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.554735910298023,
335
+ "grad_norm": 0.44450584053993225,
336
+ "learning_rate": 2.541226381312924e-05,
337
+ "loss": 0.6876,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.5665388020064915,
342
+ "grad_norm": 0.4537455439567566,
343
+ "learning_rate": 2.4381639318000126e-05,
344
+ "loss": 0.6757,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.5783416937149601,
349
+ "grad_norm": 0.4810272753238678,
350
+ "learning_rate": 2.3352065744070072e-05,
351
+ "loss": 0.7128,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.5901445854234287,
356
+ "grad_norm": 0.49226102232933044,
357
+ "learning_rate": 2.2325292880299335e-05,
358
+ "loss": 0.6928,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6019474771318973,
363
+ "grad_norm": 0.46990668773651123,
364
+ "learning_rate": 2.1303065755763277e-05,
365
+ "loss": 0.6482,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.6137503688403659,
370
+ "grad_norm": 0.43036311864852905,
371
+ "learning_rate": 2.0287121673926828e-05,
372
+ "loss": 0.6759,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.6255532605488344,
377
+ "grad_norm": 0.373436838388443,
378
+ "learning_rate": 1.92791872600489e-05,
379
+ "loss": 0.674,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.637356152257303,
384
+ "grad_norm": 0.4169735312461853,
385
+ "learning_rate": 1.8280975526734657e-05,
386
+ "loss": 0.6636,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.6491590439657716,
391
+ "grad_norm": 0.3966214060783386,
392
+ "learning_rate": 1.7294182962622846e-05,
393
+ "loss": 0.658,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.6609619356742402,
398
+ "grad_norm": 0.45455384254455566,
399
+ "learning_rate": 1.632048664915622e-05,
400
+ "loss": 0.6563,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.6727648273827088,
405
+ "grad_norm": 0.513671875,
406
+ "learning_rate": 1.536154141033482e-05,
407
+ "loss": 0.6481,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.6845677190911773,
412
+ "grad_norm": 0.4144147038459778,
413
+ "learning_rate": 1.4418977000296552e-05,
414
+ "loss": 0.681,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.6963706107996459,
419
+ "grad_norm": 0.4277999997138977,
420
+ "learning_rate": 1.3494395333504622e-05,
421
+ "loss": 0.655,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.7081735025081145,
426
+ "grad_norm": 0.4542660415172577,
427
+ "learning_rate": 1.2589367762249347e-05,
428
+ "loss": 0.6557,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.7199763942165831,
433
+ "grad_norm": 0.518882155418396,
434
+ "learning_rate": 1.1705432406091085e-05,
435
+ "loss": 0.6504,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.7317792859250516,
440
+ "grad_norm": 0.3764165937900543,
441
+ "learning_rate": 1.0844091537783316e-05,
442
+ "loss": 0.6509,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.7435821776335202,
447
+ "grad_norm": 0.40605178475379944,
448
+ "learning_rate": 1.0006809030118181e-05,
449
+ "loss": 0.6619,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.7553850693419888,
454
+ "grad_norm": 0.42034676671028137,
455
+ "learning_rate": 9.195007868033933e-06,
456
+ "loss": 0.6083,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.7671879610504574,
461
+ "grad_norm": 0.4199008345603943,
462
+ "learning_rate": 8.410067730212439e-06,
463
+ "loss": 0.6464,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.778990852758926,
468
+ "grad_norm": 0.4271228611469269,
469
+ "learning_rate": 7.653322644276779e-06,
470
+ "loss": 0.6342,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.7907937444673945,
475
+ "grad_norm": 0.49036702513694763,
476
+ "learning_rate": 6.926058719574207e-06,
477
+ "loss": 0.6492,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.8025966361758631,
482
+ "grad_norm": 0.4103890061378479,
483
+ "learning_rate": 6.229511961397455e-06,
484
+ "loss": 0.6294,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.8143995278843317,
489
+ "grad_norm": 0.38033077120780945,
490
+ "learning_rate": 5.564866170359351e-06,
491
+ "loss": 0.638,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.8262024195928003,
496
+ "grad_norm": 0.3652307987213135,
497
+ "learning_rate": 4.933250930490715e-06,
498
+ "loss": 0.6096,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.8380053113012688,
503
+ "grad_norm": 0.5351826548576355,
504
+ "learning_rate": 4.335739689480778e-06,
505
+ "loss": 0.6285,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.8498082030097374,
510
+ "grad_norm": 0.427626371383667,
511
+ "learning_rate": 3.773347934323035e-06,
512
+ "loss": 0.6257,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.861611094718206,
517
+ "grad_norm": 0.46427205204963684,
518
+ "learning_rate": 3.2470314654667487e-06,
519
+ "loss": 0.6142,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.8734139864266746,
524
+ "grad_norm": 0.5393053293228149,
525
+ "learning_rate": 2.7576847724075123e-06,
526
+ "loss": 0.6485,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.8852168781351432,
531
+ "grad_norm": 0.4637604057788849,
532
+ "learning_rate": 2.3061395134774038e-06,
533
+ "loss": 0.6407,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.8970197698436116,
538
+ "grad_norm": 0.40724095702171326,
539
+ "learning_rate": 1.8931631024185327e-06,
540
+ "loss": 0.6535,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.9088226615520802,
545
+ "grad_norm": 0.4840000569820404,
546
+ "learning_rate": 1.5194574041419802e-06,
547
+ "loss": 0.642,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.9206255532605488,
552
+ "grad_norm": 0.41105934977531433,
553
+ "learning_rate": 1.185657541888857e-06,
554
+ "loss": 0.617,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.9324284449690174,
559
+ "grad_norm": 0.557059645652771,
560
+ "learning_rate": 8.923308178206552e-07,
561
+ "loss": 0.6415,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.9442313366774859,
566
+ "grad_norm": 0.38617223501205444,
567
+ "learning_rate": 6.39975748873431e-07,
568
+ "loss": 0.6388,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.9560342283859545,
573
+ "grad_norm": 0.4779140055179596,
574
+ "learning_rate": 4.2902121951440834e-07,
575
+ "loss": 0.6366,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.9678371200944231,
580
+ "grad_norm": 0.4569835662841797,
581
+ "learning_rate": 2.5982575284084486e-07,
582
+ "loss": 0.6735,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.9796400118028917,
587
+ "grad_norm": 0.4118465185165405,
588
+ "learning_rate": 1.3267690126008425e-07,
589
+ "loss": 0.6238,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.9914429035113603,
594
+ "grad_norm": 0.4550204873085022,
595
+ "learning_rate": 4.779075778620079e-08,
596
+ "loss": 0.6613,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.9997049277072882,
601
+ "step": 847,
602
+ "total_flos": 5.491458012295987e+18,
603
+ "train_loss": 0.7367874357185229,
604
+ "train_runtime": 38132.292,
605
+ "train_samples_per_second": 0.711,
606
+ "train_steps_per_second": 0.022
607
+ }
608
+ ],
609
+ "logging_steps": 10,
610
+ "max_steps": 847,
611
+ "num_input_tokens_seen": 0,
612
+ "num_train_epochs": 1,
613
+ "save_steps": 100,
614
+ "stateful_callbacks": {
615
+ "TrainerControl": {
616
+ "args": {
617
+ "should_epoch_stop": false,
618
+ "should_evaluate": false,
619
+ "should_log": false,
620
+ "should_save": true,
621
+ "should_training_stop": true
622
+ },
623
+ "attributes": {}
624
+ }
625
+ },
626
+ "total_flos": 5.491458012295987e+18,
627
+ "train_batch_size": 8,
628
+ "trial_name": null,
629
+ "trial_params": null
630
+ }