elissoncardoso1 commited on
Commit
eb77ff0
·
verified ·
1 Parent(s): 9d33eda

Upload checkpoint-1000\trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-1000//trainer_state.json +750 -0
checkpoint-1000//trainer_state.json ADDED
@@ -0,0 +1,750 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1000,
3
+ "best_metric": 1.4522794485092163,
4
+ "best_model_checkpoint": "./finetuned_model\\checkpoint-1000",
5
+ "epoch": 1.555858310626703,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.015570260801868432,
14
+ "grad_norm": 0.20217418670654297,
15
+ "learning_rate": 1.8e-05,
16
+ "loss": 2.2788,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.031140521603736863,
21
+ "grad_norm": 0.21721592545509338,
22
+ "learning_rate": 3.8e-05,
23
+ "loss": 2.2974,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.04671078240560529,
28
+ "grad_norm": 0.18691149353981018,
29
+ "learning_rate": 5.8e-05,
30
+ "loss": 2.2254,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.06228104320747373,
35
+ "grad_norm": 0.2627484202384949,
36
+ "learning_rate": 7.800000000000001e-05,
37
+ "loss": 2.1722,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.07785130400934216,
42
+ "grad_norm": 0.4096653461456299,
43
+ "learning_rate": 9.8e-05,
44
+ "loss": 2.0316,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.09342156481121058,
49
+ "grad_norm": 2.0437684059143066,
50
+ "learning_rate": 0.000118,
51
+ "loss": 1.8762,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.10899182561307902,
56
+ "grad_norm": 0.2537792921066284,
57
+ "learning_rate": 0.000138,
58
+ "loss": 1.8509,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.12456208641494745,
63
+ "grad_norm": 0.25586166977882385,
64
+ "learning_rate": 0.00015800000000000002,
65
+ "loss": 1.7,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1401323472168159,
70
+ "grad_norm": 0.2822591960430145,
71
+ "learning_rate": 0.00017800000000000002,
72
+ "loss": 1.7905,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.15570260801868432,
77
+ "grad_norm": 0.2682412564754486,
78
+ "learning_rate": 0.00019800000000000002,
79
+ "loss": 1.7157,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.17127286882055273,
84
+ "grad_norm": 0.30413559079170227,
85
+ "learning_rate": 0.00019901585565882995,
86
+ "loss": 1.6886,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.18684312962242117,
91
+ "grad_norm": 0.30645519495010376,
92
+ "learning_rate": 0.00019792236194641883,
93
+ "loss": 1.6956,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.2024133904242896,
98
+ "grad_norm": 0.3002190589904785,
99
+ "learning_rate": 0.00019682886823400766,
100
+ "loss": 1.6521,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.21798365122615804,
105
+ "grad_norm": 0.29828041791915894,
106
+ "learning_rate": 0.0001957353745215965,
107
+ "loss": 1.6584,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.23355391202802647,
112
+ "grad_norm": 0.301546573638916,
113
+ "learning_rate": 0.00019464188080918536,
114
+ "loss": 1.6613,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.2491241728298949,
119
+ "grad_norm": 0.347465842962265,
120
+ "learning_rate": 0.00019354838709677422,
121
+ "loss": 1.6284,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.2646944336317633,
126
+ "grad_norm": 0.31749042868614197,
127
+ "learning_rate": 0.00019245489338436304,
128
+ "loss": 1.5873,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.2802646944336318,
133
+ "grad_norm": 0.32523462176322937,
134
+ "learning_rate": 0.0001913613996719519,
135
+ "loss": 1.5703,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.2958349552355002,
140
+ "grad_norm": 0.3478928804397583,
141
+ "learning_rate": 0.00019026790595954074,
142
+ "loss": 1.6148,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.31140521603736865,
147
+ "grad_norm": 0.3863014578819275,
148
+ "learning_rate": 0.0001891744122471296,
149
+ "loss": 1.6695,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.32697547683923706,
154
+ "grad_norm": 0.31040167808532715,
155
+ "learning_rate": 0.00018808091853471842,
156
+ "loss": 1.636,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.34254573764110546,
161
+ "grad_norm": 0.34434080123901367,
162
+ "learning_rate": 0.0001869874248223073,
163
+ "loss": 1.6309,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.3581159984429739,
168
+ "grad_norm": 0.35271912813186646,
169
+ "learning_rate": 0.00018589393110989613,
170
+ "loss": 1.5183,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.37368625924484233,
175
+ "grad_norm": 0.3652435839176178,
176
+ "learning_rate": 0.00018480043739748498,
177
+ "loss": 1.5748,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.3892565200467108,
182
+ "grad_norm": 0.3423960208892822,
183
+ "learning_rate": 0.00018370694368507383,
184
+ "loss": 1.6099,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.4048267808485792,
189
+ "grad_norm": 0.3742424249649048,
190
+ "learning_rate": 0.00018261344997266268,
191
+ "loss": 1.6456,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.42039704165044767,
196
+ "grad_norm": 0.36541569232940674,
197
+ "learning_rate": 0.0001815199562602515,
198
+ "loss": 1.5256,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.4359673024523161,
203
+ "grad_norm": 0.32436609268188477,
204
+ "learning_rate": 0.00018042646254784036,
205
+ "loss": 1.6154,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.4515375632541845,
210
+ "grad_norm": 0.3482036888599396,
211
+ "learning_rate": 0.0001793329688354292,
212
+ "loss": 1.5598,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.46710782405605294,
217
+ "grad_norm": 0.32296016812324524,
218
+ "learning_rate": 0.00017823947512301804,
219
+ "loss": 1.557,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.48267808485792135,
224
+ "grad_norm": 0.3758240044116974,
225
+ "learning_rate": 0.0001771459814106069,
226
+ "loss": 1.5237,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.4982483456597898,
231
+ "grad_norm": 0.3592066466808319,
232
+ "learning_rate": 0.00017605248769819574,
233
+ "loss": 1.5331,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.5138186064616582,
238
+ "grad_norm": 0.3503170907497406,
239
+ "learning_rate": 0.0001749589939857846,
240
+ "loss": 1.5598,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.5293888672635266,
245
+ "grad_norm": 0.3589423894882202,
246
+ "learning_rate": 0.00017386550027337342,
247
+ "loss": 1.5694,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.5449591280653951,
252
+ "grad_norm": 0.4173847436904907,
253
+ "learning_rate": 0.0001727720065609623,
254
+ "loss": 1.6035,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.5605293888672636,
259
+ "grad_norm": 0.3429367244243622,
260
+ "learning_rate": 0.00017167851284855112,
261
+ "loss": 1.5636,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.576099649669132,
266
+ "grad_norm": 0.3459906280040741,
267
+ "learning_rate": 0.00017058501913613997,
268
+ "loss": 1.4638,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.5916699104710004,
273
+ "grad_norm": 0.36562731862068176,
274
+ "learning_rate": 0.00016949152542372882,
275
+ "loss": 1.5236,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.6072401712728688,
280
+ "grad_norm": 0.4281690716743469,
281
+ "learning_rate": 0.00016839803171131768,
282
+ "loss": 1.5328,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.6228104320747373,
287
+ "grad_norm": 0.3289957642555237,
288
+ "learning_rate": 0.0001673045379989065,
289
+ "loss": 1.5511,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.6383806928766057,
294
+ "grad_norm": 0.34759992361068726,
295
+ "learning_rate": 0.00016621104428649535,
296
+ "loss": 1.5047,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.6539509536784741,
301
+ "grad_norm": 0.36279717087745667,
302
+ "learning_rate": 0.0001651175505740842,
303
+ "loss": 1.5314,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.6695212144803425,
308
+ "grad_norm": 0.3549306094646454,
309
+ "learning_rate": 0.00016402405686167306,
310
+ "loss": 1.5158,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.6850914752822109,
315
+ "grad_norm": 0.37329429388046265,
316
+ "learning_rate": 0.00016293056314926188,
317
+ "loss": 1.4927,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.7006617360840794,
322
+ "grad_norm": 0.3531767427921295,
323
+ "learning_rate": 0.00016183706943685076,
324
+ "loss": 1.5568,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.7162319968859479,
329
+ "grad_norm": 0.3837789297103882,
330
+ "learning_rate": 0.0001607435757244396,
331
+ "loss": 1.5042,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.7318022576878163,
336
+ "grad_norm": 0.3604554533958435,
337
+ "learning_rate": 0.00015965008201202844,
338
+ "loss": 1.5362,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.7473725184896847,
343
+ "grad_norm": 0.4049264192581177,
344
+ "learning_rate": 0.0001585565882996173,
345
+ "loss": 1.5754,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.7629427792915532,
350
+ "grad_norm": 0.3917747139930725,
351
+ "learning_rate": 0.00015746309458720614,
352
+ "loss": 1.5257,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.7785130400934216,
357
+ "grad_norm": 0.37551721930503845,
358
+ "learning_rate": 0.00015636960087479497,
359
+ "loss": 1.5712,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.7785130400934216,
364
+ "eval_loss": 1.5167639255523682,
365
+ "eval_runtime": 260.2191,
366
+ "eval_samples_per_second": 9.872,
367
+ "eval_steps_per_second": 1.237,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 0.79408330089529,
372
+ "grad_norm": 0.4406639635562897,
373
+ "learning_rate": 0.00015527610716238382,
374
+ "loss": 1.5319,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 0.8096535616971584,
379
+ "grad_norm": 0.37547779083251953,
380
+ "learning_rate": 0.00015418261344997267,
381
+ "loss": 1.535,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 0.8252238224990268,
386
+ "grad_norm": 0.3571765422821045,
387
+ "learning_rate": 0.00015308911973756152,
388
+ "loss": 1.4872,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 0.8407940833008953,
393
+ "grad_norm": 0.36505362391471863,
394
+ "learning_rate": 0.00015199562602515035,
395
+ "loss": 1.5346,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 0.8563643441027637,
400
+ "grad_norm": 0.34871625900268555,
401
+ "learning_rate": 0.00015090213231273923,
402
+ "loss": 1.5243,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 0.8719346049046321,
407
+ "grad_norm": 0.374802827835083,
408
+ "learning_rate": 0.00014980863860032805,
409
+ "loss": 1.5031,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 0.8875048657065006,
414
+ "grad_norm": 0.41518205404281616,
415
+ "learning_rate": 0.00014871514488791688,
416
+ "loss": 1.5265,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 0.903075126508369,
421
+ "grad_norm": 0.3830599784851074,
422
+ "learning_rate": 0.00014762165117550576,
423
+ "loss": 1.5212,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 0.9186453873102375,
428
+ "grad_norm": 0.37755969166755676,
429
+ "learning_rate": 0.00014652815746309458,
430
+ "loss": 1.49,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 0.9342156481121059,
435
+ "grad_norm": 0.3936685621738434,
436
+ "learning_rate": 0.00014543466375068343,
437
+ "loss": 1.5361,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 0.9497859089139743,
442
+ "grad_norm": 0.35126620531082153,
443
+ "learning_rate": 0.0001443411700382723,
444
+ "loss": 1.5182,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 0.9653561697158427,
449
+ "grad_norm": 0.4049900770187378,
450
+ "learning_rate": 0.00014324767632586114,
451
+ "loss": 1.5134,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 0.9809264305177112,
456
+ "grad_norm": 0.39619603753089905,
457
+ "learning_rate": 0.00014215418261344996,
458
+ "loss": 1.4918,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 0.9964966913195796,
463
+ "grad_norm": 0.38389134407043457,
464
+ "learning_rate": 0.00014106068890103882,
465
+ "loss": 1.5066,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 1.0108991825613078,
470
+ "grad_norm": 0.3816758096218109,
471
+ "learning_rate": 0.00013996719518862767,
472
+ "loss": 1.4342,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 1.0264694433631762,
477
+ "grad_norm": 0.3684230446815491,
478
+ "learning_rate": 0.00013887370147621652,
479
+ "loss": 1.509,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 1.0420397041650449,
484
+ "grad_norm": 0.4102369248867035,
485
+ "learning_rate": 0.00013778020776380534,
486
+ "loss": 1.4011,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 1.0576099649669133,
491
+ "grad_norm": 0.40174803137779236,
492
+ "learning_rate": 0.00013668671405139422,
493
+ "loss": 1.4155,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 1.0731802257687817,
498
+ "grad_norm": 0.4212823510169983,
499
+ "learning_rate": 0.00013559322033898305,
500
+ "loss": 1.4078,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 1.08875048657065,
505
+ "grad_norm": 0.41347914934158325,
506
+ "learning_rate": 0.0001344997266265719,
507
+ "loss": 1.4245,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 1.1043207473725185,
512
+ "grad_norm": 0.3938431441783905,
513
+ "learning_rate": 0.00013340623291416075,
514
+ "loss": 1.3777,
515
+ "step": 710
516
+ },
517
+ {
518
+ "epoch": 1.119891008174387,
519
+ "grad_norm": 0.4172612130641937,
520
+ "learning_rate": 0.0001323127392017496,
521
+ "loss": 1.4435,
522
+ "step": 720
523
+ },
524
+ {
525
+ "epoch": 1.1354612689762553,
526
+ "grad_norm": 0.4305002987384796,
527
+ "learning_rate": 0.00013121924548933843,
528
+ "loss": 1.479,
529
+ "step": 730
530
+ },
531
+ {
532
+ "epoch": 1.1510315297781237,
533
+ "grad_norm": 0.4031375050544739,
534
+ "learning_rate": 0.0001301257517769273,
535
+ "loss": 1.4107,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 1.1666017905799921,
540
+ "grad_norm": 0.4102884829044342,
541
+ "learning_rate": 0.00012903225806451613,
542
+ "loss": 1.5123,
543
+ "step": 750
544
+ },
545
+ {
546
+ "epoch": 1.1821720513818605,
547
+ "grad_norm": 0.44275203347206116,
548
+ "learning_rate": 0.00012793876435210499,
549
+ "loss": 1.426,
550
+ "step": 760
551
+ },
552
+ {
553
+ "epoch": 1.1977423121837292,
554
+ "grad_norm": 0.4467061758041382,
555
+ "learning_rate": 0.00012684527063969384,
556
+ "loss": 1.4495,
557
+ "step": 770
558
+ },
559
+ {
560
+ "epoch": 1.2133125729855976,
561
+ "grad_norm": 0.40034279227256775,
562
+ "learning_rate": 0.0001257517769272827,
563
+ "loss": 1.4541,
564
+ "step": 780
565
+ },
566
+ {
567
+ "epoch": 1.228882833787466,
568
+ "grad_norm": 0.42505356669425964,
569
+ "learning_rate": 0.00012465828321487152,
570
+ "loss": 1.4767,
571
+ "step": 790
572
+ },
573
+ {
574
+ "epoch": 1.2444530945893344,
575
+ "grad_norm": 0.3754604458808899,
576
+ "learning_rate": 0.00012356478950246037,
577
+ "loss": 1.4144,
578
+ "step": 800
579
+ },
580
+ {
581
+ "epoch": 1.2600233553912028,
582
+ "grad_norm": 0.3871001601219177,
583
+ "learning_rate": 0.00012247129579004922,
584
+ "loss": 1.4618,
585
+ "step": 810
586
+ },
587
+ {
588
+ "epoch": 1.2755936161930712,
589
+ "grad_norm": 0.416062593460083,
590
+ "learning_rate": 0.00012137780207763807,
591
+ "loss": 1.4258,
592
+ "step": 820
593
+ },
594
+ {
595
+ "epoch": 1.2911638769949396,
596
+ "grad_norm": 0.3869543969631195,
597
+ "learning_rate": 0.00012028430836522691,
598
+ "loss": 1.379,
599
+ "step": 830
600
+ },
601
+ {
602
+ "epoch": 1.306734137796808,
603
+ "grad_norm": 0.4507176876068115,
604
+ "learning_rate": 0.00011919081465281574,
605
+ "loss": 1.4011,
606
+ "step": 840
607
+ },
608
+ {
609
+ "epoch": 1.3223043985986767,
610
+ "grad_norm": 0.4298593997955322,
611
+ "learning_rate": 0.0001180973209404046,
612
+ "loss": 1.3897,
613
+ "step": 850
614
+ },
615
+ {
616
+ "epoch": 1.337874659400545,
617
+ "grad_norm": 0.4016563296318054,
618
+ "learning_rate": 0.00011700382722799344,
619
+ "loss": 1.4004,
620
+ "step": 860
621
+ },
622
+ {
623
+ "epoch": 1.3534449202024135,
624
+ "grad_norm": 0.45489302277565,
625
+ "learning_rate": 0.00011591033351558229,
626
+ "loss": 1.3974,
627
+ "step": 870
628
+ },
629
+ {
630
+ "epoch": 1.3690151810042819,
631
+ "grad_norm": 0.4141370356082916,
632
+ "learning_rate": 0.00011481683980317113,
633
+ "loss": 1.4417,
634
+ "step": 880
635
+ },
636
+ {
637
+ "epoch": 1.3845854418061503,
638
+ "grad_norm": 0.4654589295387268,
639
+ "learning_rate": 0.00011372334609075998,
640
+ "loss": 1.479,
641
+ "step": 890
642
+ },
643
+ {
644
+ "epoch": 1.4001557026080187,
645
+ "grad_norm": 0.4696764051914215,
646
+ "learning_rate": 0.00011262985237834882,
647
+ "loss": 1.4009,
648
+ "step": 900
649
+ },
650
+ {
651
+ "epoch": 1.415725963409887,
652
+ "grad_norm": 0.4807955324649811,
653
+ "learning_rate": 0.00011153635866593767,
654
+ "loss": 1.3897,
655
+ "step": 910
656
+ },
657
+ {
658
+ "epoch": 1.4312962242117555,
659
+ "grad_norm": 0.5069774985313416,
660
+ "learning_rate": 0.00011044286495352651,
661
+ "loss": 1.431,
662
+ "step": 920
663
+ },
664
+ {
665
+ "epoch": 1.446866485013624,
666
+ "grad_norm": 0.43647122383117676,
667
+ "learning_rate": 0.00010934937124111538,
668
+ "loss": 1.4042,
669
+ "step": 930
670
+ },
671
+ {
672
+ "epoch": 1.4624367458154923,
673
+ "grad_norm": 0.43918347358703613,
674
+ "learning_rate": 0.0001082558775287042,
675
+ "loss": 1.4403,
676
+ "step": 940
677
+ },
678
+ {
679
+ "epoch": 1.4780070066173607,
680
+ "grad_norm": 0.39581167697906494,
681
+ "learning_rate": 0.00010716238381629307,
682
+ "loss": 1.4027,
683
+ "step": 950
684
+ },
685
+ {
686
+ "epoch": 1.4935772674192291,
687
+ "grad_norm": 0.42234891653060913,
688
+ "learning_rate": 0.0001060688901038819,
689
+ "loss": 1.4291,
690
+ "step": 960
691
+ },
692
+ {
693
+ "epoch": 1.5091475282210975,
694
+ "grad_norm": 0.40230894088745117,
695
+ "learning_rate": 0.00010497539639147076,
696
+ "loss": 1.3847,
697
+ "step": 970
698
+ },
699
+ {
700
+ "epoch": 1.5247177890229662,
701
+ "grad_norm": 0.41914451122283936,
702
+ "learning_rate": 0.0001038819026790596,
703
+ "loss": 1.364,
704
+ "step": 980
705
+ },
706
+ {
707
+ "epoch": 1.5402880498248346,
708
+ "grad_norm": 0.4406910240650177,
709
+ "learning_rate": 0.00010278840896664845,
710
+ "loss": 1.4437,
711
+ "step": 990
712
+ },
713
+ {
714
+ "epoch": 1.555858310626703,
715
+ "grad_norm": 0.4232882857322693,
716
+ "learning_rate": 0.00010169491525423729,
717
+ "loss": 1.4319,
718
+ "step": 1000
719
+ },
720
+ {
721
+ "epoch": 1.555858310626703,
722
+ "eval_loss": 1.4522794485092163,
723
+ "eval_runtime": 260.6355,
724
+ "eval_samples_per_second": 9.857,
725
+ "eval_steps_per_second": 1.235,
726
+ "step": 1000
727
+ }
728
+ ],
729
+ "logging_steps": 10,
730
+ "max_steps": 1929,
731
+ "num_input_tokens_seen": 0,
732
+ "num_train_epochs": 3,
733
+ "save_steps": 500,
734
+ "stateful_callbacks": {
735
+ "TrainerControl": {
736
+ "args": {
737
+ "should_epoch_stop": false,
738
+ "should_evaluate": false,
739
+ "should_log": false,
740
+ "should_save": true,
741
+ "should_training_stop": false
742
+ },
743
+ "attributes": {}
744
+ }
745
+ },
746
+ "total_flos": 7.998377278046208e+16,
747
+ "train_batch_size": 4,
748
+ "trial_name": null,
749
+ "trial_params": null
750
+ }