Inserloft commited on
Commit
f47d27d
·
verified ·
1 Parent(s): b977ee3

Delete trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -502
trainer_state.json DELETED
@@ -1,502 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.05097381220398021,
6
- "eval_steps": 500,
7
- "global_step": 3000,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.0008495635367330034,
14
- "grad_norm": 2.2921929359436035,
15
- "learning_rate": 7.35e-06,
16
- "loss": 10.29970947265625,
17
- "step": 50
18
- },
19
- {
20
- "epoch": 0.0016991270734660069,
21
- "grad_norm": 1.5014020204544067,
22
- "learning_rate": 1.485e-05,
23
- "loss": 9.447623291015624,
24
- "step": 100
25
- },
26
- {
27
- "epoch": 0.0025486906101990104,
28
- "grad_norm": 1.1717920303344727,
29
- "learning_rate": 2.2349999999999998e-05,
30
- "loss": 8.584126586914062,
31
- "step": 150
32
- },
33
- {
34
- "epoch": 0.0033982541469320137,
35
- "grad_norm": 0.9378017783164978,
36
- "learning_rate": 2.985e-05,
37
- "loss": 8.290836791992188,
38
- "step": 200
39
- },
40
- {
41
- "epoch": 0.004247817683665017,
42
- "grad_norm": 0.9766564965248108,
43
- "learning_rate": 3.735e-05,
44
- "loss": 8.238416137695312,
45
- "step": 250
46
- },
47
- {
48
- "epoch": 0.005097381220398021,
49
- "grad_norm": 0.8814884424209595,
50
- "learning_rate": 4.484999999999999e-05,
51
- "loss": 8.232381591796875,
52
- "step": 300
53
- },
54
- {
55
- "epoch": 0.005946944757131024,
56
- "grad_norm": 0.8784363865852356,
57
- "learning_rate": 5.234999999999999e-05,
58
- "loss": 8.220962524414062,
59
- "step": 350
60
- },
61
- {
62
- "epoch": 0.0067965082938640274,
63
- "grad_norm": 0.8463743329048157,
64
- "learning_rate": 5.985e-05,
65
- "loss": 8.23321533203125,
66
- "step": 400
67
- },
68
- {
69
- "epoch": 0.007646071830597031,
70
- "grad_norm": 1.164692759513855,
71
- "learning_rate": 6.735e-05,
72
- "loss": 8.241315307617187,
73
- "step": 450
74
- },
75
- {
76
- "epoch": 0.008495635367330034,
77
- "grad_norm": 0.9384698867797852,
78
- "learning_rate": 7.484999999999999e-05,
79
- "loss": 8.23368408203125,
80
- "step": 500
81
- },
82
- {
83
- "epoch": 0.008495635367330034,
84
- "eval_loss": 8.224983215332031,
85
- "eval_runtime": 214.2145,
86
- "eval_samples_per_second": 179.428,
87
- "eval_steps_per_second": 22.431,
88
- "step": 500
89
- },
90
- {
91
- "epoch": 0.009345198904063037,
92
- "grad_norm": 0.8738101720809937,
93
- "learning_rate": 8.235e-05,
94
- "loss": 8.240723876953124,
95
- "step": 550
96
- },
97
- {
98
- "epoch": 0.010194762440796042,
99
- "grad_norm": 0.8343268632888794,
100
- "learning_rate": 8.984999999999999e-05,
101
- "loss": 8.231287841796876,
102
- "step": 600
103
- },
104
- {
105
- "epoch": 0.011044325977529044,
106
- "grad_norm": 0.8430389761924744,
107
- "learning_rate": 9.735e-05,
108
- "loss": 8.23207763671875,
109
- "step": 650
110
- },
111
- {
112
- "epoch": 0.011893889514262047,
113
- "grad_norm": 0.9249081015586853,
114
- "learning_rate": 0.00010484999999999999,
115
- "loss": 8.226725463867188,
116
- "step": 700
117
- },
118
- {
119
- "epoch": 0.012743453050995052,
120
- "grad_norm": 0.8848555088043213,
121
- "learning_rate": 0.00011235,
122
- "loss": 8.223170166015626,
123
- "step": 750
124
- },
125
- {
126
- "epoch": 0.013593016587728055,
127
- "grad_norm": 1.1157618761062622,
128
- "learning_rate": 0.00011985,
129
- "loss": 8.216035766601562,
130
- "step": 800
131
- },
132
- {
133
- "epoch": 0.014442580124461058,
134
- "grad_norm": 0.9552467465400696,
135
- "learning_rate": 0.00012734999999999998,
136
- "loss": 8.214351196289062,
137
- "step": 850
138
- },
139
- {
140
- "epoch": 0.015292143661194062,
141
- "grad_norm": 0.9281343221664429,
142
- "learning_rate": 0.00013485,
143
- "loss": 8.214883422851562,
144
- "step": 900
145
- },
146
- {
147
- "epoch": 0.016141707197927065,
148
- "grad_norm": 0.9026381969451904,
149
- "learning_rate": 0.00014235,
150
- "loss": 8.202714233398437,
151
- "step": 950
152
- },
153
- {
154
- "epoch": 0.016991270734660068,
155
- "grad_norm": 1.047902226448059,
156
- "learning_rate": 0.00014984999999999998,
157
- "loss": 8.200950927734375,
158
- "step": 1000
159
- },
160
- {
161
- "epoch": 0.016991270734660068,
162
- "eval_loss": 8.193246841430664,
163
- "eval_runtime": 213.0642,
164
- "eval_samples_per_second": 180.396,
165
- "eval_steps_per_second": 22.552,
166
- "step": 1000
167
- },
168
- {
169
- "epoch": 0.01784083427139307,
170
- "grad_norm": 0.7946310639381409,
171
- "learning_rate": 0.00015734999999999998,
172
- "loss": 8.194002685546875,
173
- "step": 1050
174
- },
175
- {
176
- "epoch": 0.018690397808126074,
177
- "grad_norm": 0.7916894555091858,
178
- "learning_rate": 0.00016485,
179
- "loss": 8.197877197265624,
180
- "step": 1100
181
- },
182
- {
183
- "epoch": 0.01953996134485908,
184
- "grad_norm": 0.8219326734542847,
185
- "learning_rate": 0.00017235,
186
- "loss": 8.19470947265625,
187
- "step": 1150
188
- },
189
- {
190
- "epoch": 0.020389524881592083,
191
- "grad_norm": 0.8771915435791016,
192
- "learning_rate": 0.00017984999999999998,
193
- "loss": 8.182391357421874,
194
- "step": 1200
195
- },
196
- {
197
- "epoch": 0.021239088418325086,
198
- "grad_norm": 0.887346088886261,
199
- "learning_rate": 0.00018735,
200
- "loss": 8.177872314453126,
201
- "step": 1250
202
- },
203
- {
204
- "epoch": 0.02208865195505809,
205
- "grad_norm": 0.7836199998855591,
206
- "learning_rate": 0.00019484999999999997,
207
- "loss": 8.194529418945313,
208
- "step": 1300
209
- },
210
- {
211
- "epoch": 0.022938215491791092,
212
- "grad_norm": 0.7709180116653442,
213
- "learning_rate": 0.00020234999999999999,
214
- "loss": 8.176567993164063,
215
- "step": 1350
216
- },
217
- {
218
- "epoch": 0.023787779028524095,
219
- "grad_norm": 0.8244626522064209,
220
- "learning_rate": 0.00020984999999999998,
221
- "loss": 8.180636596679687,
222
- "step": 1400
223
- },
224
- {
225
- "epoch": 0.024637342565257098,
226
- "grad_norm": 0.7698231935501099,
227
- "learning_rate": 0.00021735,
228
- "loss": 8.173869018554688,
229
- "step": 1450
230
- },
231
- {
232
- "epoch": 0.025486906101990104,
233
- "grad_norm": 0.7591619491577148,
234
- "learning_rate": 0.00022485,
235
- "loss": 8.163311157226563,
236
- "step": 1500
237
- },
238
- {
239
- "epoch": 0.025486906101990104,
240
- "eval_loss": 8.166845321655273,
241
- "eval_runtime": 216.2866,
242
- "eval_samples_per_second": 177.709,
243
- "eval_steps_per_second": 22.216,
244
- "step": 1500
245
- },
246
- {
247
- "epoch": 0.026336469638723107,
248
- "grad_norm": 0.726202130317688,
249
- "learning_rate": 0.00023234999999999998,
250
- "loss": 8.167291870117188,
251
- "step": 1550
252
- },
253
- {
254
- "epoch": 0.02718603317545611,
255
- "grad_norm": 0.8223204612731934,
256
- "learning_rate": 0.00023984999999999998,
257
- "loss": 8.162225341796875,
258
- "step": 1600
259
- },
260
- {
261
- "epoch": 0.028035596712189113,
262
- "grad_norm": 0.6965987682342529,
263
- "learning_rate": 0.00024734999999999997,
264
- "loss": 8.143677368164063,
265
- "step": 1650
266
- },
267
- {
268
- "epoch": 0.028885160248922116,
269
- "grad_norm": 0.6973395347595215,
270
- "learning_rate": 0.00025485,
271
- "loss": 8.155018310546875,
272
- "step": 1700
273
- },
274
- {
275
- "epoch": 0.02973472378565512,
276
- "grad_norm": 0.7717684507369995,
277
- "learning_rate": 0.00026235,
278
- "loss": 8.157542724609375,
279
- "step": 1750
280
- },
281
- {
282
- "epoch": 0.030584287322388125,
283
- "grad_norm": 0.723139226436615,
284
- "learning_rate": 0.00026984999999999997,
285
- "loss": 8.1351708984375,
286
- "step": 1800
287
- },
288
- {
289
- "epoch": 0.03143385085912113,
290
- "grad_norm": 0.7955517768859863,
291
- "learning_rate": 0.00027735,
292
- "loss": 8.134263916015625,
293
- "step": 1850
294
- },
295
- {
296
- "epoch": 0.03228341439585413,
297
- "grad_norm": 0.8079131841659546,
298
- "learning_rate": 0.00028484999999999996,
299
- "loss": 8.131721801757813,
300
- "step": 1900
301
- },
302
- {
303
- "epoch": 0.033132977932587133,
304
- "grad_norm": 0.925956666469574,
305
- "learning_rate": 0.00029235,
306
- "loss": 8.121426391601563,
307
- "step": 1950
308
- },
309
- {
310
- "epoch": 0.033982541469320136,
311
- "grad_norm": 0.7581774592399597,
312
- "learning_rate": 0.00029985,
313
- "loss": 8.129930419921875,
314
- "step": 2000
315
- },
316
- {
317
- "epoch": 0.033982541469320136,
318
- "eval_loss": 8.113646507263184,
319
- "eval_runtime": 215.3894,
320
- "eval_samples_per_second": 178.449,
321
- "eval_steps_per_second": 22.308,
322
- "step": 2000
323
- },
324
- {
325
- "epoch": 0.03483210500605314,
326
- "grad_norm": 0.6788080334663391,
327
- "learning_rate": 0.0002999999416751376,
328
- "loss": 8.118410034179687,
329
- "step": 2050
330
- },
331
- {
332
- "epoch": 0.03568166854278614,
333
- "grad_norm": 0.649872899055481,
334
- "learning_rate": 0.000299999761915093,
335
- "loss": 8.122174682617187,
336
- "step": 2100
337
- },
338
- {
339
- "epoch": 0.036531232079519145,
340
- "grad_norm": 0.7973966598510742,
341
- "learning_rate": 0.00029999946069571965,
342
- "loss": 8.119035034179687,
343
- "step": 2150
344
- },
345
- {
346
- "epoch": 0.03738079561625215,
347
- "grad_norm": 0.7167413234710693,
348
- "learning_rate": 0.0002999990380172616,
349
- "loss": 8.09365234375,
350
- "step": 2200
351
- },
352
- {
353
- "epoch": 0.03823035915298515,
354
- "grad_norm": 0.7007924318313599,
355
- "learning_rate": 0.0002999984938800611,
356
- "loss": 8.109237060546874,
357
- "step": 2250
358
- },
359
- {
360
- "epoch": 0.03907992268971816,
361
- "grad_norm": 0.703641951084137,
362
- "learning_rate": 0.00029999782828455865,
363
- "loss": 8.102305297851563,
364
- "step": 2300
365
- },
366
- {
367
- "epoch": 0.039929486226451164,
368
- "grad_norm": 0.996090292930603,
369
- "learning_rate": 0.00029999704123129326,
370
- "loss": 8.100062866210937,
371
- "step": 2350
372
- },
373
- {
374
- "epoch": 0.040779049763184166,
375
- "grad_norm": 0.6838179230690002,
376
- "learning_rate": 0.00029999613272090227,
377
- "loss": 8.115880737304687,
378
- "step": 2400
379
- },
380
- {
381
- "epoch": 0.04162861329991717,
382
- "grad_norm": 0.6444393992424011,
383
- "learning_rate": 0.0002999951027541213,
384
- "loss": 8.1059130859375,
385
- "step": 2450
386
- },
387
- {
388
- "epoch": 0.04247817683665017,
389
- "grad_norm": 0.7024487853050232,
390
- "learning_rate": 0.0002999939513317843,
391
- "loss": 8.09420166015625,
392
- "step": 2500
393
- },
394
- {
395
- "epoch": 0.04247817683665017,
396
- "eval_loss": 8.074261665344238,
397
- "eval_runtime": 218.8102,
398
- "eval_samples_per_second": 175.659,
399
- "eval_steps_per_second": 21.96,
400
- "step": 2500
401
- },
402
- {
403
- "epoch": 0.043327740373383175,
404
- "grad_norm": 0.6988140344619751,
405
- "learning_rate": 0.0002999926784548237,
406
- "loss": 8.071203002929687,
407
- "step": 2550
408
- },
409
- {
410
- "epoch": 0.04417730391011618,
411
- "grad_norm": 0.6819867491722107,
412
- "learning_rate": 0.0002999912841242701,
413
- "loss": 8.073958129882813,
414
- "step": 2600
415
- },
416
- {
417
- "epoch": 0.04502686744684918,
418
- "grad_norm": 0.6717061400413513,
419
- "learning_rate": 0.00029998976834125256,
420
- "loss": 8.078544311523437,
421
- "step": 2650
422
- },
423
- {
424
- "epoch": 0.045876430983582184,
425
- "grad_norm": 0.6351542472839355,
426
- "learning_rate": 0.0002999881311069985,
427
- "loss": 8.07291259765625,
428
- "step": 2700
429
- },
430
- {
431
- "epoch": 0.04672599452031519,
432
- "grad_norm": 0.6544303894042969,
433
- "learning_rate": 0.0002999863724228336,
434
- "loss": 8.054371337890625,
435
- "step": 2750
436
- },
437
- {
438
- "epoch": 0.04757555805704819,
439
- "grad_norm": 0.6814166903495789,
440
- "learning_rate": 0.0002999844922901819,
441
- "loss": 8.073319702148437,
442
- "step": 2800
443
- },
444
- {
445
- "epoch": 0.04842512159378119,
446
- "grad_norm": 0.6586683988571167,
447
- "learning_rate": 0.0002999824907105659,
448
- "loss": 8.044788818359375,
449
- "step": 2850
450
- },
451
- {
452
- "epoch": 0.049274685130514195,
453
- "grad_norm": 0.6417912244796753,
454
- "learning_rate": 0.0002999803676856062,
455
- "loss": 8.045443725585937,
456
- "step": 2900
457
- },
458
- {
459
- "epoch": 0.050124248667247205,
460
- "grad_norm": 0.5847958922386169,
461
- "learning_rate": 0.00029997812321702193,
462
- "loss": 8.032376708984375,
463
- "step": 2950
464
- },
465
- {
466
- "epoch": 0.05097381220398021,
467
- "grad_norm": 0.6639038324356079,
468
- "learning_rate": 0.0002999757573066305,
469
- "loss": 8.031983642578124,
470
- "step": 3000
471
- },
472
- {
473
- "epoch": 0.05097381220398021,
474
- "eval_loss": 8.033109664916992,
475
- "eval_runtime": 215.8555,
476
- "eval_samples_per_second": 178.064,
477
- "eval_steps_per_second": 22.26,
478
- "step": 3000
479
- }
480
- ],
481
- "logging_steps": 50,
482
- "max_steps": 176562,
483
- "num_input_tokens_seen": 0,
484
- "num_train_epochs": 3,
485
- "save_steps": 1000,
486
- "stateful_callbacks": {
487
- "TrainerControl": {
488
- "args": {
489
- "should_epoch_stop": false,
490
- "should_evaluate": false,
491
- "should_log": false,
492
- "should_save": true,
493
- "should_training_stop": false
494
- },
495
- "attributes": {}
496
- }
497
- },
498
- "total_flos": 7.466630670906163e+16,
499
- "train_batch_size": 8,
500
- "trial_name": null,
501
- "trial_params": null
502
- }