HBboy commited on
Commit
9637e59
·
verified ·
1 Parent(s): d41df73

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +462 -0
trainer_state.json ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 19.336166381835938,
14
+ "learning_rate": 4.999859193643945e-05,
15
+ "loss": 2.4671,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.1,
20
+ "grad_norm": 10.850088119506836,
21
+ "learning_rate": 4.9949326364020314e-05,
22
+ "loss": 2.4246,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.15,
27
+ "grad_norm": 10.342315673828125,
28
+ "learning_rate": 4.982981614472039e-05,
29
+ "loss": 2.5563,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.2,
34
+ "grad_norm": 11.594865798950195,
35
+ "learning_rate": 4.9640397758692715e-05,
36
+ "loss": 2.5333,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.25,
41
+ "grad_norm": 9.311284065246582,
42
+ "learning_rate": 4.938160451202521e-05,
43
+ "loss": 2.5209,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.3,
48
+ "grad_norm": 16.79537010192871,
49
+ "learning_rate": 4.9054165035221236e-05,
50
+ "loss": 2.8026,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.35,
55
+ "grad_norm": 10.748820304870605,
56
+ "learning_rate": 4.865900123174574e-05,
57
+ "loss": 2.8341,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.4,
62
+ "grad_norm": 11.450349807739258,
63
+ "learning_rate": 4.819722568241274e-05,
64
+ "loss": 2.7475,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.45,
69
+ "grad_norm": 9.321686744689941,
70
+ "learning_rate": 4.767013851292212e-05,
71
+ "loss": 2.7298,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.5,
76
+ "grad_norm": 9.671792984008789,
77
+ "learning_rate": 4.7079223733365237e-05,
78
+ "loss": 2.6166,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.55,
83
+ "grad_norm": 8.407944679260254,
84
+ "learning_rate": 4.642614506000523e-05,
85
+ "loss": 2.5359,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.6,
90
+ "grad_norm": 8.98971939086914,
91
+ "learning_rate": 4.571274123109606e-05,
92
+ "loss": 2.479,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.65,
97
+ "grad_norm": 8.909531593322754,
98
+ "learning_rate": 4.4941020829928245e-05,
99
+ "loss": 2.4882,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.7,
104
+ "grad_norm": 7.584418296813965,
105
+ "learning_rate": 4.4113156629677316e-05,
106
+ "loss": 2.3675,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.75,
111
+ "grad_norm": 8.56999683380127,
112
+ "learning_rate": 4.323147947597666e-05,
113
+ "loss": 2.4285,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.8,
118
+ "grad_norm": 9.06714153289795,
119
+ "learning_rate": 4.229847172443866e-05,
120
+ "loss": 2.5075,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.85,
125
+ "grad_norm": 7.845032691955566,
126
+ "learning_rate": 4.131676025160047e-05,
127
+ "loss": 2.4794,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.9,
132
+ "grad_norm": 7.793240070343018,
133
+ "learning_rate": 4.028910905897229e-05,
134
+ "loss": 2.5271,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.95,
139
+ "grad_norm": 7.8635029792785645,
140
+ "learning_rate": 3.9218411491011176e-05,
141
+ "loss": 2.4032,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 1.0,
146
+ "grad_norm": 8.155007362365723,
147
+ "learning_rate": 3.8107682088930794e-05,
148
+ "loss": 2.4891,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 1.05,
153
+ "grad_norm": 8.073945999145508,
154
+ "learning_rate": 3.6960048103282566e-05,
155
+ "loss": 1.412,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 1.1,
160
+ "grad_norm": 8.153766632080078,
161
+ "learning_rate": 3.577874068920446e-05,
162
+ "loss": 1.3875,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 1.15,
167
+ "grad_norm": 6.7796630859375,
168
+ "learning_rate": 3.456708580912725e-05,
169
+ "loss": 1.3676,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 1.2,
174
+ "grad_norm": 7.609086513519287,
175
+ "learning_rate": 3.332849486855144e-05,
176
+ "loss": 1.3438,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 1.25,
181
+ "grad_norm": 7.6227126121521,
182
+ "learning_rate": 3.2066455111259945e-05,
183
+ "loss": 1.3895,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 1.3,
188
+ "grad_norm": 7.66270637512207,
189
+ "learning_rate": 3.0784519801008546e-05,
190
+ "loss": 1.3399,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 1.35,
195
+ "grad_norm": 7.801215171813965,
196
+ "learning_rate": 2.9486298217337637e-05,
197
+ "loss": 1.3101,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 1.4,
202
+ "grad_norm": 7.925507545471191,
203
+ "learning_rate": 2.8175445493671972e-05,
204
+ "loss": 1.4303,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 1.45,
209
+ "grad_norm": 7.386769771575928,
210
+ "learning_rate": 2.6855652326319063e-05,
211
+ "loss": 1.3833,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 1.5,
216
+ "grad_norm": 7.175492763519287,
217
+ "learning_rate": 2.5530634583340592e-05,
218
+ "loss": 1.3684,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 1.55,
223
+ "grad_norm": 7.5672607421875,
224
+ "learning_rate": 2.4204122842552896e-05,
225
+ "loss": 1.4123,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 1.6,
230
+ "grad_norm": 7.482105731964111,
231
+ "learning_rate": 2.287985188811228e-05,
232
+ "loss": 1.3913,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 1.65,
237
+ "grad_norm": 7.868821144104004,
238
+ "learning_rate": 2.1561550195257378e-05,
239
+ "loss": 1.4338,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 1.7,
244
+ "grad_norm": 7.905065059661865,
245
+ "learning_rate": 2.025292943281429e-05,
246
+ "loss": 1.3506,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 1.75,
251
+ "grad_norm": 8.045072555541992,
252
+ "learning_rate": 1.895767401301994e-05,
253
+ "loss": 1.4525,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 1.8,
258
+ "grad_norm": 6.936304092407227,
259
+ "learning_rate": 1.7679430718086243e-05,
260
+ "loss": 1.3534,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 1.85,
265
+ "grad_norm": 7.464107990264893,
266
+ "learning_rate": 1.6421798432711345e-05,
267
+ "loss": 1.322,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 1.9,
272
+ "grad_norm": 7.77186393737793,
273
+ "learning_rate": 1.5188318011445906e-05,
274
+ "loss": 1.3326,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 1.95,
279
+ "grad_norm": 7.153684139251709,
280
+ "learning_rate": 1.3982462309442889e-05,
281
+ "loss": 1.3804,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 2.0,
286
+ "grad_norm": 6.911492824554443,
287
+ "learning_rate": 1.2807626404659142e-05,
288
+ "loss": 1.3938,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 2.05,
293
+ "grad_norm": 5.748324394226074,
294
+ "learning_rate": 1.1667118039038064e-05,
295
+ "loss": 0.732,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 2.1,
300
+ "grad_norm": 7.109584808349609,
301
+ "learning_rate": 1.0564148305586296e-05,
302
+ "loss": 0.6639,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 2.15,
307
+ "grad_norm": 7.395934104919434,
308
+ "learning_rate": 9.501822607564678e-06,
309
+ "loss": 0.5978,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 2.2,
314
+ "grad_norm": 8.013920783996582,
315
+ "learning_rate": 8.483131915247968e-06,
316
+ "loss": 0.6269,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 2.25,
321
+ "grad_norm": 6.068602561950684,
322
+ "learning_rate": 7.510944344869774e-06,
323
+ "loss": 0.6189,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 2.3,
328
+ "grad_norm": 5.850319862365723,
329
+ "learning_rate": 6.587997083462197e-06,
330
+ "loss": 0.6096,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 2.35,
335
+ "grad_norm": 5.7608642578125,
336
+ "learning_rate": 5.7168886823256355e-06,
337
+ "loss": 0.5799,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 2.4,
342
+ "grad_norm": 6.143069267272949,
343
+ "learning_rate": 4.900071740826489e-06,
344
+ "loss": 0.6156,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 2.45,
349
+ "grad_norm": 5.740133285522461,
350
+ "learning_rate": 4.139846001121514e-06,
351
+ "loss": 0.6387,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 2.5,
356
+ "grad_norm": 6.231141567230225,
357
+ "learning_rate": 3.438351873250492e-06,
358
+ "loss": 0.6032,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 2.55,
363
+ "grad_norm": 6.172192096710205,
364
+ "learning_rate": 2.797564408827319e-06,
365
+ "loss": 0.5976,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 2.6,
370
+ "grad_norm": 6.317423343658447,
371
+ "learning_rate": 2.219287740296605e-06,
372
+ "loss": 0.5687,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 2.65,
377
+ "grad_norm": 9.063169479370117,
378
+ "learning_rate": 1.7051500014118454e-06,
379
+ "loss": 0.5843,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 2.7,
384
+ "grad_norm": 6.360856056213379,
385
+ "learning_rate": 1.2565987432367033e-06,
386
+ "loss": 0.5979,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 2.75,
391
+ "grad_norm": 6.228647232055664,
392
+ "learning_rate": 8.748968585755274e-07,
393
+ "loss": 0.5601,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 2.8,
398
+ "grad_norm": 6.196378231048584,
399
+ "learning_rate": 5.611190263078464e-07,
400
+ "loss": 0.6004,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 2.85,
405
+ "grad_norm": 6.535120964050293,
406
+ "learning_rate": 3.1614868563778487e-07,
407
+ "loss": 0.6026,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 2.9,
412
+ "grad_norm": 6.039511203765869,
413
+ "learning_rate": 1.406755487774386e-07,
414
+ "loss": 0.6162,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 2.95,
419
+ "grad_norm": 6.509077548980713,
420
+ "learning_rate": 3.5193659067131455e-08,
421
+ "loss": 0.6627,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 3.0,
426
+ "grad_norm": 6.356975555419922,
427
+ "learning_rate": 0.0,
428
+ "loss": 0.5781,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 3.0,
433
+ "step": 300,
434
+ "total_flos": 2138970911670272.0,
435
+ "train_loss": 1.5124793648719788,
436
+ "train_runtime": 1380.9582,
437
+ "train_samples_per_second": 6.95,
438
+ "train_steps_per_second": 0.217
439
+ }
440
+ ],
441
+ "logging_steps": 5,
442
+ "max_steps": 300,
443
+ "num_input_tokens_seen": 0,
444
+ "num_train_epochs": 3,
445
+ "save_steps": 100,
446
+ "stateful_callbacks": {
447
+ "TrainerControl": {
448
+ "args": {
449
+ "should_epoch_stop": false,
450
+ "should_evaluate": false,
451
+ "should_log": false,
452
+ "should_save": true,
453
+ "should_training_stop": true
454
+ },
455
+ "attributes": {}
456
+ }
457
+ },
458
+ "total_flos": 2138970911670272.0,
459
+ "train_batch_size": 2,
460
+ "trial_name": null,
461
+ "trial_params": null
462
+ }