PLB commited on
Commit
62551ce
·
verified ·
1 Parent(s): 87a56c6

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +435 -0
trainer_state.json ADDED
@@ -0,0 +1,435 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 560,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.17857142857142858,
14
+ "grad_norm": 2.5338213443756104,
15
+ "learning_rate": 3.2142857142857144e-05,
16
+ "loss": 0.9093,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.35714285714285715,
21
+ "grad_norm": 1.8161640167236328,
22
+ "learning_rate": 6.785714285714286e-05,
23
+ "loss": 0.2903,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.5357142857142857,
28
+ "grad_norm": 1.7190877199172974,
29
+ "learning_rate": 9.999912820328665e-05,
30
+ "loss": 0.2339,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.7142857142857143,
35
+ "grad_norm": 1.3515009880065918,
36
+ "learning_rate": 9.989454937810925e-05,
37
+ "loss": 0.1691,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.8928571428571429,
42
+ "grad_norm": 1.1145479679107666,
43
+ "learning_rate": 9.961602898685226e-05,
44
+ "loss": 0.1126,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.0714285714285714,
49
+ "grad_norm": 0.8124198913574219,
50
+ "learning_rate": 9.916453800277115e-05,
51
+ "loss": 0.0773,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 1.25,
56
+ "grad_norm": 1.0860916376113892,
57
+ "learning_rate": 9.854165040638723e-05,
58
+ "loss": 0.0683,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.4285714285714286,
63
+ "grad_norm": 0.7404114603996277,
64
+ "learning_rate": 9.774953769830246e-05,
65
+ "loss": 0.052,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.6071428571428572,
70
+ "grad_norm": 0.6764904260635376,
71
+ "learning_rate": 9.679096132894921e-05,
72
+ "loss": 0.0518,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 1.7857142857142856,
77
+ "grad_norm": 0.7629515528678894,
78
+ "learning_rate": 9.56692630716669e-05,
79
+ "loss": 0.0462,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 1.9642857142857144,
84
+ "grad_norm": 0.5626688003540039,
85
+ "learning_rate": 9.438835337266603e-05,
86
+ "loss": 0.0407,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 2.142857142857143,
91
+ "grad_norm": 1.1673179864883423,
92
+ "learning_rate": 9.295269771849427e-05,
93
+ "loss": 0.0382,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 2.3214285714285716,
98
+ "grad_norm": 1.1967400312423706,
99
+ "learning_rate": 9.136730106852995e-05,
100
+ "loss": 0.0401,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 2.5,
105
+ "grad_norm": 0.8308486342430115,
106
+ "learning_rate": 8.963769040677413e-05,
107
+ "loss": 0.0396,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 2.678571428571429,
112
+ "grad_norm": 0.9734421372413635,
113
+ "learning_rate": 8.776989547376889e-05,
114
+ "loss": 0.035,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 2.857142857142857,
119
+ "grad_norm": 0.9629505276679993,
120
+ "learning_rate": 8.577042774581396e-05,
121
+ "loss": 0.0381,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 3.0357142857142856,
126
+ "grad_norm": 0.38612839579582214,
127
+ "learning_rate": 8.364625773476409e-05,
128
+ "loss": 0.0306,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 3.2142857142857144,
133
+ "grad_norm": 0.5558330416679382,
134
+ "learning_rate": 8.140479068754396e-05,
135
+ "loss": 0.0283,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 3.392857142857143,
140
+ "grad_norm": 0.6917959451675415,
141
+ "learning_rate": 7.905384077009693e-05,
142
+ "loss": 0.0321,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 3.571428571428571,
147
+ "grad_norm": 0.5424484610557556,
148
+ "learning_rate": 7.660160382576683e-05,
149
+ "loss": 0.0283,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 3.75,
154
+ "grad_norm": 0.611579179763794,
155
+ "learning_rate": 7.405662880308238e-05,
156
+ "loss": 0.0326,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 3.928571428571429,
161
+ "grad_norm": 0.8048507571220398,
162
+ "learning_rate": 7.14277879525518e-05,
163
+ "loss": 0.0315,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 4.107142857142857,
168
+ "grad_norm": 0.7426259517669678,
169
+ "learning_rate": 6.872424589636763e-05,
170
+ "loss": 0.0275,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 4.285714285714286,
175
+ "grad_norm": 0.75429767370224,
176
+ "learning_rate": 6.595542767884983e-05,
177
+ "loss": 0.0249,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 4.464285714285714,
182
+ "grad_norm": 0.7748964428901672,
183
+ "learning_rate": 6.313098590900977e-05,
184
+ "loss": 0.0312,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 4.642857142857143,
189
+ "grad_norm": 0.5361077189445496,
190
+ "learning_rate": 6.026076710978171e-05,
191
+ "loss": 0.0259,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 4.821428571428571,
196
+ "grad_norm": 0.6900258660316467,
197
+ "learning_rate": 5.735477739123484e-05,
198
+ "loss": 0.0225,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 5.0,
203
+ "grad_norm": 0.7184466123580933,
204
+ "learning_rate": 5.442314756743511e-05,
205
+ "loss": 0.0212,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 5.178571428571429,
210
+ "grad_norm": 0.6176795363426208,
211
+ "learning_rate": 5.147609783856619e-05,
212
+ "loss": 0.0226,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 5.357142857142857,
217
+ "grad_norm": 0.7196623682975769,
218
+ "learning_rate": 4.8523902161433824e-05,
219
+ "loss": 0.0211,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 5.535714285714286,
224
+ "grad_norm": 0.5302695035934448,
225
+ "learning_rate": 4.5576852432564896e-05,
226
+ "loss": 0.0216,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 5.714285714285714,
231
+ "grad_norm": 0.41389530897140503,
232
+ "learning_rate": 4.264522260876517e-05,
233
+ "loss": 0.0235,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 5.892857142857143,
238
+ "grad_norm": 0.42803147435188293,
239
+ "learning_rate": 3.973923289021829e-05,
240
+ "loss": 0.019,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 6.071428571428571,
245
+ "grad_norm": 0.5015178322792053,
246
+ "learning_rate": 3.686901409099023e-05,
247
+ "loss": 0.022,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 6.25,
252
+ "grad_norm": 0.5396034717559814,
253
+ "learning_rate": 3.404457232115017e-05,
254
+ "loss": 0.0216,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 6.428571428571429,
259
+ "grad_norm": 0.5539416074752808,
260
+ "learning_rate": 3.1275754103632384e-05,
261
+ "loss": 0.0231,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 6.607142857142857,
266
+ "grad_norm": 0.4802437722682953,
267
+ "learning_rate": 2.8572212047448194e-05,
268
+ "loss": 0.0212,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 6.785714285714286,
273
+ "grad_norm": 0.29384422302246094,
274
+ "learning_rate": 2.594337119691763e-05,
275
+ "loss": 0.0193,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 6.964285714285714,
280
+ "grad_norm": 0.4893832504749298,
281
+ "learning_rate": 2.3398396174233178e-05,
282
+ "loss": 0.0214,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 7.142857142857143,
287
+ "grad_norm": 0.2931596338748932,
288
+ "learning_rate": 2.094615922990309e-05,
289
+ "loss": 0.0195,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 7.321428571428571,
294
+ "grad_norm": 0.6393173933029175,
295
+ "learning_rate": 1.8595209312456054e-05,
296
+ "loss": 0.0189,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 7.5,
301
+ "grad_norm": 0.52290278673172,
302
+ "learning_rate": 1.6353742265235923e-05,
303
+ "loss": 0.0156,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 7.678571428571429,
308
+ "grad_norm": 0.3446985185146332,
309
+ "learning_rate": 1.4229572254186046e-05,
310
+ "loss": 0.0175,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 7.857142857142857,
315
+ "grad_norm": 0.2511596083641052,
316
+ "learning_rate": 1.2230104526231107e-05,
317
+ "loss": 0.0187,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 8.035714285714286,
322
+ "grad_norm": 0.4132586121559143,
323
+ "learning_rate": 1.0362309593225878e-05,
324
+ "loss": 0.0197,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 8.214285714285714,
329
+ "grad_norm": 0.4198119044303894,
330
+ "learning_rate": 8.632698931470063e-06,
331
+ "loss": 0.0195,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 8.392857142857142,
336
+ "grad_norm": 0.2853988707065582,
337
+ "learning_rate": 7.047302281505736e-06,
338
+ "loss": 0.0184,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 8.571428571428571,
343
+ "grad_norm": 0.27527064085006714,
344
+ "learning_rate": 5.611646627333977e-06,
345
+ "loss": 0.0164,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 8.75,
350
+ "grad_norm": 0.27603819966316223,
351
+ "learning_rate": 4.330736928333107e-06,
352
+ "loss": 0.0147,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 8.928571428571429,
357
+ "grad_norm": 0.24762211740016937,
358
+ "learning_rate": 3.20903867105079e-06,
359
+ "loss": 0.0168,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 9.107142857142858,
364
+ "grad_norm": 0.23618640005588531,
365
+ "learning_rate": 2.2504623016975535e-06,
366
+ "loss": 0.0172,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 9.285714285714286,
371
+ "grad_norm": 0.27931779623031616,
372
+ "learning_rate": 1.4583495936127679e-06,
373
+ "loss": 0.0175,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 9.464285714285714,
378
+ "grad_norm": 0.18601159751415253,
379
+ "learning_rate": 8.354619972288702e-07,
380
+ "loss": 0.0178,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 9.642857142857142,
385
+ "grad_norm": 0.24232065677642822,
386
+ "learning_rate": 3.839710131477492e-07,
387
+ "loss": 0.02,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 9.821428571428571,
392
+ "grad_norm": 0.20322400331497192,
393
+ "learning_rate": 1.0545062189075139e-07,
394
+ "loss": 0.0158,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 10.0,
399
+ "grad_norm": 0.40607011318206787,
400
+ "learning_rate": 8.717967133586858e-10,
401
+ "loss": 0.0173,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 10.0,
406
+ "step": 560,
407
+ "total_flos": 0.0,
408
+ "train_loss": 0.055652551033667154,
409
+ "train_runtime": 1195.1625,
410
+ "train_samples_per_second": 49.734,
411
+ "train_steps_per_second": 0.469
412
+ }
413
+ ],
414
+ "logging_steps": 10,
415
+ "max_steps": 560,
416
+ "num_input_tokens_seen": 0,
417
+ "num_train_epochs": 10,
418
+ "save_steps": 3000,
419
+ "stateful_callbacks": {
420
+ "TrainerControl": {
421
+ "args": {
422
+ "should_epoch_stop": false,
423
+ "should_evaluate": false,
424
+ "should_log": false,
425
+ "should_save": true,
426
+ "should_training_stop": true
427
+ },
428
+ "attributes": {}
429
+ }
430
+ },
431
+ "total_flos": 0.0,
432
+ "train_batch_size": 107,
433
+ "trial_name": null,
434
+ "trial_params": null
435
+ }