ybkim95-ai commited on
Commit
3fef2ff
·
verified ·
1 Parent(s): 8867b85

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +497 -0
trainer_state.json ADDED
@@ -0,0 +1,497 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.936936936936937,
5
+ "eval_steps": 500,
6
+ "global_step": 65,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07207207207207207,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 0.0,
15
+ "loss": 110.9883,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.14414414414414414,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 0.0,
22
+ "loss": 110.4609,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.21621621621621623,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 0.0,
29
+ "loss": 111.4512,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.2882882882882883,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 0.0,
36
+ "loss": 111.1406,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.36036036036036034,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 0.0,
43
+ "loss": 110.6152,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.43243243243243246,
48
+ "grad_norm": 0.0,
49
+ "learning_rate": 0.0,
50
+ "loss": 111.1738,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.5045045045045045,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 0.0,
57
+ "loss": 110.5547,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5765765765765766,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 0.0,
64
+ "loss": 110.459,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.6486486486486487,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 0.0,
71
+ "loss": 111.123,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.7207207207207207,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 0.0,
78
+ "loss": 111.6152,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.7927927927927928,
83
+ "grad_norm": 0.0,
84
+ "learning_rate": 0.0,
85
+ "loss": 110.6719,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.8648648648648649,
90
+ "grad_norm": 0.0,
91
+ "learning_rate": 0.0,
92
+ "loss": 110.877,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.9369369369369369,
97
+ "grad_norm": 0.0,
98
+ "learning_rate": 0.0,
99
+ "loss": 111.459,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.072072072072072,
104
+ "grad_norm": 0.0,
105
+ "learning_rate": 0.0,
106
+ "loss": 124.793,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.1441441441441442,
111
+ "grad_norm": 0.0,
112
+ "learning_rate": 0.0,
113
+ "loss": 111.0137,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.2162162162162162,
118
+ "grad_norm": 0.0,
119
+ "learning_rate": 0.0,
120
+ "loss": 110.7871,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.2882882882882882,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 0.0,
127
+ "loss": 110.6484,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.3603603603603602,
132
+ "grad_norm": 0.0,
133
+ "learning_rate": 0.0,
134
+ "loss": 110.6309,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.4324324324324325,
139
+ "grad_norm": 121.69364311021961,
140
+ "learning_rate": 0.0001,
141
+ "loss": 111.0137,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.5045045045045045,
146
+ "grad_norm": 121.82811999006017,
147
+ "learning_rate": 9.993977281025862e-05,
148
+ "loss": 102.374,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 1.5765765765765765,
153
+ "grad_norm": 43.762035174980724,
154
+ "learning_rate": 9.975923633360985e-05,
155
+ "loss": 37.7349,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 1.6486486486486487,
160
+ "grad_norm": 43.762035174980724,
161
+ "learning_rate": 9.975923633360985e-05,
162
+ "loss": 23.8311,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 1.7207207207207207,
167
+ "grad_norm": 43.762035174980724,
168
+ "learning_rate": 9.975923633360985e-05,
169
+ "loss": 23.6587,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 1.7927927927927927,
174
+ "grad_norm": 67.60606900572056,
175
+ "learning_rate": 9.945882549823906e-05,
176
+ "loss": 23.4604,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.864864864864865,
181
+ "grad_norm": 47.84182107476679,
182
+ "learning_rate": 9.903926402016153e-05,
183
+ "loss": 22.4585,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.936936936936937,
188
+ "grad_norm": 97.3110950444501,
189
+ "learning_rate": 9.850156265972721e-05,
190
+ "loss": 15.5953,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 2.0720720720720722,
195
+ "grad_norm": 13.359584588085475,
196
+ "learning_rate": 9.784701678661045e-05,
197
+ "loss": 5.8495,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.144144144144144,
202
+ "grad_norm": 15.499340904743185,
203
+ "learning_rate": 9.707720325915104e-05,
204
+ "loss": 3.2645,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.2162162162162162,
209
+ "grad_norm": 5.2516204512990035,
210
+ "learning_rate": 9.619397662556435e-05,
211
+ "loss": 0.7318,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.2882882882882885,
216
+ "grad_norm": 6.351586523632304,
217
+ "learning_rate": 9.519946465617218e-05,
218
+ "loss": 0.8066,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.3603603603603602,
223
+ "grad_norm": 4.296773347519179,
224
+ "learning_rate": 9.409606321741775e-05,
225
+ "loss": 0.389,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 2.4324324324324325,
230
+ "grad_norm": 3.7567276687430526,
231
+ "learning_rate": 9.288643050001361e-05,
232
+ "loss": 0.238,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 2.5045045045045047,
237
+ "grad_norm": 0.8841967237890292,
238
+ "learning_rate": 9.157348061512727e-05,
239
+ "loss": 0.1217,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 2.5765765765765765,
244
+ "grad_norm": 2.065381666847204,
245
+ "learning_rate": 9.016037657403224e-05,
246
+ "loss": 0.7948,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 2.6486486486486487,
251
+ "grad_norm": 36.57744419486038,
252
+ "learning_rate": 8.865052266813685e-05,
253
+ "loss": 1.8392,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 2.7207207207207205,
258
+ "grad_norm": 6.098258360827327,
259
+ "learning_rate": 8.704755626774796e-05,
260
+ "loss": 0.4845,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 2.7927927927927927,
265
+ "grad_norm": 4.902366899534486,
266
+ "learning_rate": 8.535533905932738e-05,
267
+ "loss": 0.2728,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 2.864864864864865,
272
+ "grad_norm": 3.3005947444072987,
273
+ "learning_rate": 8.357794774235092e-05,
274
+ "loss": 0.2294,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 2.936936936936937,
279
+ "grad_norm": 0.5713662641479601,
280
+ "learning_rate": 8.171966420818228e-05,
281
+ "loss": 0.0271,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 3.0720720720720722,
286
+ "grad_norm": 0.3093144415337581,
287
+ "learning_rate": 7.978496522462167e-05,
288
+ "loss": 0.0544,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 3.144144144144144,
293
+ "grad_norm": 6.086269384303536,
294
+ "learning_rate": 7.777851165098012e-05,
295
+ "loss": 0.0918,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 3.2162162162162162,
300
+ "grad_norm": 0.8619135383139304,
301
+ "learning_rate": 7.570513720966108e-05,
302
+ "loss": 0.0149,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 3.2882882882882885,
307
+ "grad_norm": 0.170124990369711,
308
+ "learning_rate": 7.35698368412999e-05,
309
+ "loss": 0.0106,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 3.3603603603603602,
314
+ "grad_norm": 0.2984404823393874,
315
+ "learning_rate": 7.137775467151411e-05,
316
+ "loss": 0.1274,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 3.4324324324324325,
321
+ "grad_norm": 2.7538582006280317,
322
+ "learning_rate": 6.91341716182545e-05,
323
+ "loss": 1.8402,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 3.5045045045045047,
328
+ "grad_norm": 2.7538582006280317,
329
+ "learning_rate": 6.91341716182545e-05,
330
+ "loss": 4.0066,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 3.5765765765765765,
335
+ "grad_norm": 243.24225964046624,
336
+ "learning_rate": 6.6844492669611e-05,
337
+ "loss": 2.8196,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 3.6486486486486487,
342
+ "grad_norm": 4.988008998052072,
343
+ "learning_rate": 6.451423386272312e-05,
344
+ "loss": 0.377,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 3.7207207207207205,
349
+ "grad_norm": 0.2693118570806549,
350
+ "learning_rate": 6.21490089951632e-05,
351
+ "loss": 0.0247,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 3.7927927927927927,
356
+ "grad_norm": 0.05521830464606099,
357
+ "learning_rate": 5.9754516100806423e-05,
358
+ "loss": 0.0091,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 3.864864864864865,
363
+ "grad_norm": 0.6910149711748117,
364
+ "learning_rate": 5.733652372276809e-05,
365
+ "loss": 0.0199,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 3.936936936936937,
370
+ "grad_norm": 0.10849567725705088,
371
+ "learning_rate": 5.490085701647805e-05,
372
+ "loss": 0.0033,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 4.072072072072072,
377
+ "grad_norm": 0.10809313247991727,
378
+ "learning_rate": 5.245338371637091e-05,
379
+ "loss": 0.0146,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 4.1441441441441444,
384
+ "grad_norm": 0.05128671267400455,
385
+ "learning_rate": 5e-05,
386
+ "loss": 0.0023,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 4.216216216216216,
391
+ "grad_norm": 0.04446616393871321,
392
+ "learning_rate": 4.7546616283629105e-05,
393
+ "loss": 0.0706,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 4.288288288288288,
398
+ "grad_norm": 92.7258697131631,
399
+ "learning_rate": 4.509914298352197e-05,
400
+ "loss": 0.0734,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 4.36036036036036,
405
+ "grad_norm": 0.10509705390750478,
406
+ "learning_rate": 4.2663476277231915e-05,
407
+ "loss": 0.0052,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 4.4324324324324325,
412
+ "grad_norm": 0.05685107825836915,
413
+ "learning_rate": 4.0245483899193595e-05,
414
+ "loss": 0.0009,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 4.504504504504505,
419
+ "grad_norm": 0.0071402069274671244,
420
+ "learning_rate": 3.785099100483681e-05,
421
+ "loss": 0.0004,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 4.576576576576577,
426
+ "grad_norm": 0.007037629263124771,
427
+ "learning_rate": 3.5485766137276894e-05,
428
+ "loss": 0.0033,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 4.648648648648649,
433
+ "grad_norm": 0.07795566744834063,
434
+ "learning_rate": 3.3155507330389e-05,
435
+ "loss": 0.0067,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 4.7207207207207205,
440
+ "grad_norm": 0.21346197540898718,
441
+ "learning_rate": 3.086582838174551e-05,
442
+ "loss": 0.0008,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 4.792792792792793,
447
+ "grad_norm": 0.07957365304285995,
448
+ "learning_rate": 2.8622245328485907e-05,
449
+ "loss": 0.005,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 4.864864864864865,
454
+ "grad_norm": 0.0022461733078342535,
455
+ "learning_rate": 2.6430163158700115e-05,
456
+ "loss": 0.0076,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 4.936936936936937,
461
+ "grad_norm": 0.06343292790647254,
462
+ "learning_rate": 2.4294862790338917e-05,
463
+ "loss": 0.0001,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 4.936936936936937,
468
+ "step": 65,
469
+ "total_flos": 3.90161235112362e+17,
470
+ "train_loss": 36.849671179973164,
471
+ "train_runtime": 1387.5254,
472
+ "train_samples_per_second": 3.175,
473
+ "train_steps_per_second": 0.047
474
+ }
475
+ ],
476
+ "logging_steps": 1.0,
477
+ "max_steps": 65,
478
+ "num_input_tokens_seen": 0,
479
+ "num_train_epochs": 5,
480
+ "save_steps": 500,
481
+ "stateful_callbacks": {
482
+ "TrainerControl": {
483
+ "args": {
484
+ "should_epoch_stop": false,
485
+ "should_evaluate": false,
486
+ "should_log": false,
487
+ "should_save": true,
488
+ "should_training_stop": true
489
+ },
490
+ "attributes": {}
491
+ }
492
+ },
493
+ "total_flos": 3.90161235112362e+17,
494
+ "train_batch_size": 2,
495
+ "trial_name": null,
496
+ "trial_params": null
497
+ }