Boffl commited on
Commit
bb7fdc3
·
verified ·
1 Parent(s): 4ae87ff

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": NaN,
14
+ "learning_rate": 4.11764705882353e-06,
15
+ "loss": 2.4846,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.02360578341693715,
20
+ "grad_norm": 1.4208085536956787,
21
+ "learning_rate": 9.411764705882354e-06,
22
+ "loss": 2.1584,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.03540867512540572,
27
+ "grad_norm": 0.5537272095680237,
28
+ "learning_rate": 1.5294117647058826e-05,
29
+ "loss": 1.6811,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0472115668338743,
34
+ "grad_norm": 0.7016017436981201,
35
+ "learning_rate": 2.1176470588235296e-05,
36
+ "loss": 1.4406,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.05901445854234287,
41
+ "grad_norm": 1.1232593059539795,
42
+ "learning_rate": 2.7058823529411766e-05,
43
+ "loss": 1.3102,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.07081735025081144,
48
+ "grad_norm": 2.9730782508850098,
49
+ "learning_rate": 3.294117647058824e-05,
50
+ "loss": 1.2155,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.08262024195928003,
55
+ "grad_norm": 0.692528247833252,
56
+ "learning_rate": 3.882352941176471e-05,
57
+ "loss": 1.1449,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.0944231336677486,
62
+ "grad_norm": 1.3414469957351685,
63
+ "learning_rate": 4.470588235294118e-05,
64
+ "loss": 1.1908,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.10622602537621717,
69
+ "grad_norm": 0.6828320622444153,
70
+ "learning_rate": 4.999978752922572e-05,
71
+ "loss": 1.1663,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.11802891708468574,
76
+ "grad_norm": NaN,
77
+ "learning_rate": 4.998640308387074e-05,
78
+ "loss": 1.1033,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.1298318087931543,
83
+ "grad_norm": 9.297845840454102,
84
+ "learning_rate": 4.993119095936937e-05,
85
+ "loss": 1.1636,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.14163470050162288,
90
+ "grad_norm": 0.8314323425292969,
91
+ "learning_rate": 4.983360758155341e-05,
92
+ "loss": 1.1268,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.15343759221009148,
97
+ "grad_norm": 0.6411977410316467,
98
+ "learning_rate": 4.9693818796090927e-05,
99
+ "loss": 1.1321,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.16524048391856005,
104
+ "grad_norm": 0.5500069856643677,
105
+ "learning_rate": 4.951206217791564e-05,
106
+ "loss": 1.0142,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.17704337562702863,
111
+ "grad_norm": 0.6950828433036804,
112
+ "learning_rate": 4.9288646627461645e-05,
113
+ "loss": 1.1114,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.1888462673354972,
118
+ "grad_norm": 0.6412365436553955,
119
+ "learning_rate": 4.902395184567859e-05,
120
+ "loss": 1.0839,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.20064915904396577,
125
+ "grad_norm": 0.6320505738258362,
126
+ "learning_rate": 4.871842768871928e-05,
127
+ "loss": 1.0705,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.21245205075243434,
132
+ "grad_norm": 0.7705304622650146,
133
+ "learning_rate": 4.837259340339665e-05,
134
+ "loss": 1.0312,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.2242549424609029,
139
+ "grad_norm": 0.6497272849082947,
140
+ "learning_rate": 4.7987036744709326e-05,
141
+ "loss": 1.0162,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.23605783416937148,
146
+ "grad_norm": 2.37109112739563,
147
+ "learning_rate": 4.756241297693566e-05,
148
+ "loss": 1.0297,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.24786072587784008,
153
+ "grad_norm": 0.523530125617981,
154
+ "learning_rate": 4.7099443759993837e-05,
155
+ "loss": 1.0039,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.2596636175863086,
160
+ "grad_norm": 0.8198627233505249,
161
+ "learning_rate": 4.659891592296071e-05,
162
+ "loss": 0.9934,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.2714665092947772,
167
+ "grad_norm": 0.7993373870849609,
168
+ "learning_rate": 4.606168012683394e-05,
169
+ "loss": 1.0378,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.28326940100324577,
174
+ "grad_norm": 0.7412521243095398,
175
+ "learning_rate": 4.548864941880988e-05,
176
+ "loss": 1.007,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.29507229271171437,
181
+ "grad_norm": 0.715391993522644,
182
+ "learning_rate": 4.488079768053447e-05,
183
+ "loss": 0.987,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.30687518442018297,
188
+ "grad_norm": 1.2131056785583496,
189
+ "learning_rate": 4.423915797296425e-05,
190
+ "loss": 0.9728,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.3186780761286515,
195
+ "grad_norm": 0.7467273473739624,
196
+ "learning_rate": 4.3564820780650496e-05,
197
+ "loss": 0.9608,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.3304809678371201,
202
+ "grad_norm": 0.8544695377349854,
203
+ "learning_rate": 4.285893215843037e-05,
204
+ "loss": 0.9591,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.34228385954558865,
209
+ "grad_norm": 0.7751792669296265,
210
+ "learning_rate": 4.2122691783674786e-05,
211
+ "loss": 0.9466,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.35408675125405725,
216
+ "grad_norm": 2.504579544067383,
217
+ "learning_rate": 4.1357350917403314e-05,
218
+ "loss": 0.9384,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.3658896429625258,
223
+ "grad_norm": 22.522701263427734,
224
+ "learning_rate": 4.056421027773126e-05,
225
+ "loss": 0.9517,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.3776925346709944,
230
+ "grad_norm": 0.9187076091766357,
231
+ "learning_rate": 3.974461782926299e-05,
232
+ "loss": 0.9449,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.389495426379463,
237
+ "grad_norm": 1.2791095972061157,
238
+ "learning_rate": 3.889996649218852e-05,
239
+ "loss": 0.9171,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.40129831808793154,
244
+ "grad_norm": 0.7749762535095215,
245
+ "learning_rate": 3.8031691774976904e-05,
246
+ "loss": 0.9611,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.41310120979640014,
251
+ "grad_norm": 0.917222797870636,
252
+ "learning_rate": 3.714126933468959e-05,
253
+ "loss": 0.9678,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.4249041015048687,
258
+ "grad_norm": 0.552499532699585,
259
+ "learning_rate": 3.623021246906018e-05,
260
+ "loss": 0.9134,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.4367069932133373,
265
+ "grad_norm": 0.5541794896125793,
266
+ "learning_rate": 3.530006954460274e-05,
267
+ "loss": 0.928,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.4485098849218058,
272
+ "grad_norm": 0.5857645869255066,
273
+ "learning_rate": 3.435242136511984e-05,
274
+ "loss": 0.8963,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.4603127766302744,
279
+ "grad_norm": 0.5237164497375488,
280
+ "learning_rate": 3.338887848508242e-05,
281
+ "loss": 0.8931,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.47211566833874297,
286
+ "grad_norm": 0.49927598237991333,
287
+ "learning_rate": 3.241107847244769e-05,
288
+ "loss": 0.9113,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.48391856004721157,
293
+ "grad_norm": 1.1223820447921753,
294
+ "learning_rate": 3.14206831255667e-05,
295
+ "loss": 0.9172,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.49572145175568016,
300
+ "grad_norm": 0.7306515574455261,
301
+ "learning_rate": 3.041937564891183e-05,
302
+ "loss": 0.903,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.5075243434641488,
307
+ "grad_norm": 1.0228462219238281,
308
+ "learning_rate": 2.940885779242387e-05,
309
+ "loss": 0.8676,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.5193272351726173,
314
+ "grad_norm": 0.5814535021781921,
315
+ "learning_rate": 2.8390846959340638e-05,
316
+ "loss": 0.8709,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.5311301268810859,
321
+ "grad_norm": 0.7466275095939636,
322
+ "learning_rate": 2.736707328742234e-05,
323
+ "loss": 0.8659,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.5429330185895545,
328
+ "grad_norm": 0.7288652062416077,
329
+ "learning_rate": 2.633927670853425e-05,
330
+ "loss": 0.8683,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.554735910298023,
335
+ "grad_norm": 0.5865510106086731,
336
+ "learning_rate": 2.5309203991584073e-05,
337
+ "loss": 0.871,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.5665388020064915,
342
+ "grad_norm": 0.5332498550415039,
343
+ "learning_rate": 2.4278605773839548e-05,
344
+ "loss": 0.8574,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.5783416937149601,
349
+ "grad_norm": 0.634554922580719,
350
+ "learning_rate": 2.3249233585671636e-05,
351
+ "loss": 0.9529,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.5901445854234287,
356
+ "grad_norm": 0.655619740486145,
357
+ "learning_rate": 2.2222836873779888e-05,
358
+ "loss": 0.8546,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.6019474771318973,
363
+ "grad_norm": 0.5780109167098999,
364
+ "learning_rate": 2.1201160027959077e-05,
365
+ "loss": 0.8452,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.6137503688403659,
370
+ "grad_norm": 0.49844804406166077,
371
+ "learning_rate": 2.0185939416460133e-05,
372
+ "loss": 0.876,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.6255532605488344,
377
+ "grad_norm": 0.430317223072052,
378
+ "learning_rate": 1.917890043498397e-05,
379
+ "loss": 0.8406,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.637356152257303,
384
+ "grad_norm": 0.4516479969024658,
385
+ "learning_rate": 1.8181754574323446e-05,
386
+ "loss": 0.8226,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.6491590439657716,
391
+ "grad_norm": 0.5004287362098694,
392
+ "learning_rate": 1.7196196511637084e-05,
393
+ "loss": 0.9068,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.6609619356742402,
398
+ "grad_norm": 0.6133776307106018,
399
+ "learning_rate": 1.6223901230298062e-05,
400
+ "loss": 0.8361,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.6727648273827088,
405
+ "grad_norm": 1.207897663116455,
406
+ "learning_rate": 1.5266521173213306e-05,
407
+ "loss": 0.8515,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.6845677190911773,
412
+ "grad_norm": 0.5756068825721741,
413
+ "learning_rate": 1.432568343445077e-05,
414
+ "loss": 0.8553,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.6963706107996459,
419
+ "grad_norm": 0.5454249382019043,
420
+ "learning_rate": 1.340298699394777e-05,
421
+ "loss": 0.8731,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.7081735025081145,
426
+ "grad_norm": 0.527680516242981,
427
+ "learning_rate": 1.2500000000000006e-05,
428
+ "loss": 0.8545,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.7199763942165831,
433
+ "grad_norm": 0.6664750576019287,
434
+ "learning_rate": 1.1618257104149898e-05,
435
+ "loss": 0.8259,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.7317792859250516,
440
+ "grad_norm": 0.7168521881103516,
441
+ "learning_rate": 1.0759256853003578e-05,
442
+ "loss": 0.856,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.7435821776335202,
447
+ "grad_norm": 0.4886401891708374,
448
+ "learning_rate": 9.92445914140912e-06,
449
+ "loss": 0.8448,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.7553850693419888,
454
+ "grad_norm": 0.541182279586792,
455
+ "learning_rate": 9.115282731324696e-06,
456
+ "loss": 0.8142,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.7671879610504574,
461
+ "grad_norm": 0.5412532091140747,
462
+ "learning_rate": 8.333102840593015e-06,
463
+ "loss": 0.8607,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.778990852758926,
468
+ "grad_norm": 0.603594183921814,
469
+ "learning_rate": 7.579248805720396e-06,
470
+ "loss": 0.8283,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.7907937444673945,
475
+ "grad_norm": 0.7654862403869629,
476
+ "learning_rate": 6.855001822632278e-06,
477
+ "loss": 0.8514,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.8025966361758631,
482
+ "grad_norm": 0.5184491872787476,
483
+ "learning_rate": 6.161592769245114e-06,
484
+ "loss": 0.8125,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.8143995278843317,
489
+ "grad_norm": 0.5151306986808777,
490
+ "learning_rate": 5.500200113555071e-06,
491
+ "loss": 0.8122,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.8262024195928003,
496
+ "grad_norm": 0.5323730111122131,
497
+ "learning_rate": 4.871947910798818e-06,
498
+ "loss": 0.7771,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.8380053113012688,
503
+ "grad_norm": 0.6055124402046204,
504
+ "learning_rate": 4.277903893090407e-06,
505
+ "loss": 0.8132,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.8498082030097374,
510
+ "grad_norm": 0.5266196727752686,
511
+ "learning_rate": 3.7190776547807447e-06,
512
+ "loss": 0.8095,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.861611094718206,
517
+ "grad_norm": 0.5904248356819153,
518
+ "learning_rate": 3.1964189366239377e-06,
519
+ "loss": 0.8285,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.8734139864266746,
524
+ "grad_norm": 0.6103527545928955,
525
+ "learning_rate": 2.7108160116663893e-06,
526
+ "loss": 0.8297,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.8852168781351432,
531
+ "grad_norm": 0.5870690941810608,
532
+ "learning_rate": 2.2630941756020512e-06,
533
+ "loss": 0.8621,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.8970197698436116,
538
+ "grad_norm": 0.49599605798721313,
539
+ "learning_rate": 1.8540143441593854e-06,
540
+ "loss": 0.8191,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.9088226615520802,
545
+ "grad_norm": 0.5189609527587891,
546
+ "learning_rate": 1.4842717599039047e-06,
547
+ "loss": 0.8048,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.9206255532605488,
552
+ "grad_norm": 0.485893577337265,
553
+ "learning_rate": 1.1544948106540775e-06,
554
+ "loss": 0.782,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.9324284449690174,
559
+ "grad_norm": 0.5677834749221802,
560
+ "learning_rate": 8.652439615187163e-07,
561
+ "loss": 0.8249,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.9442313366774859,
566
+ "grad_norm": 0.5319679379463196,
567
+ "learning_rate": 6.170108023709348e-07,
568
+ "loss": 0.817,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.9560342283859545,
573
+ "grad_norm": 0.5445159673690796,
574
+ "learning_rate": 4.1021721237745337e-07,
575
+ "loss": 0.8029,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.9678371200944231,
580
+ "grad_norm": 0.618567943572998,
581
+ "learning_rate": 2.452146430032165e-07,
582
+ "loss": 0.8493,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.9796400118028917,
587
+ "grad_norm": 0.5149559378623962,
588
+ "learning_rate": 1.2228352070983719e-07,
589
+ "loss": 0.8134,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.9914429035113603,
594
+ "grad_norm": 0.4901800751686096,
595
+ "learning_rate": 4.1632770363012056e-08,
596
+ "loss": 0.8336,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.9997049277072882,
601
+ "step": 847,
602
+ "total_flos": 1.1591373314404123e+19,
603
+ "train_loss": 0.973909290228149,
604
+ "train_runtime": 71632.8605,
605
+ "train_samples_per_second": 0.378,
606
+ "train_steps_per_second": 0.012
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": 1.1591373314404123e+19,
627
+ "train_batch_size": 8,
628
+ "trial_name": null,
629
+ "trial_params": null
630
+ }