codestylist commited on
Commit
5fe89a5
1 Parent(s): 6c9a538

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +510 -0
trainer_state.json ADDED
@@ -0,0 +1,510 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3929971796106486,
5
+ "global_step": 40500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 0.0019942675013184747,
13
+ "loss": 0.2155,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 0.0019885350026369497,
19
+ "loss": 0.2135,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 0.001982802503955424,
25
+ "loss": 0.2123,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.07,
30
+ "learning_rate": 0.001977070005273899,
31
+ "loss": 0.2196,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 0.0019713375065923736,
37
+ "loss": 0.2223,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.1,
42
+ "learning_rate": 0.0019656050079108482,
43
+ "loss": 0.2209,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "learning_rate": 0.001959872509229323,
49
+ "loss": 0.2181,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.14,
54
+ "learning_rate": 0.0019541400105477975,
55
+ "loss": 0.2142,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.15,
60
+ "learning_rate": 0.0019484075118662723,
61
+ "loss": 0.2145,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.17,
66
+ "learning_rate": 0.001942675013184747,
67
+ "loss": 0.2261,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.19,
72
+ "learning_rate": 0.0019369425145032218,
73
+ "loss": 0.2171,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.21,
78
+ "learning_rate": 0.0019312100158216962,
79
+ "loss": 0.2158,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.22,
84
+ "learning_rate": 0.001925477517140171,
85
+ "loss": 0.2179,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "learning_rate": 0.001919745018458646,
91
+ "loss": 0.2137,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.26,
96
+ "learning_rate": 0.0019140125197771205,
97
+ "loss": 0.2148,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.28,
102
+ "learning_rate": 0.0019082800210955954,
103
+ "loss": 0.2114,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.29,
108
+ "learning_rate": 0.0019025475224140698,
109
+ "loss": 0.2138,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.31,
114
+ "learning_rate": 0.0018968150237325446,
115
+ "loss": 0.2159,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.33,
120
+ "learning_rate": 0.0018910825250510192,
121
+ "loss": 0.2185,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.34,
126
+ "learning_rate": 0.001885350026369494,
127
+ "loss": 0.2123,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.36,
132
+ "learning_rate": 0.0018796175276879685,
133
+ "loss": 0.2172,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.38,
138
+ "learning_rate": 0.0018738850290064433,
139
+ "loss": 0.2162,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.4,
144
+ "learning_rate": 0.001868152530324918,
145
+ "loss": 0.2103,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.41,
150
+ "learning_rate": 0.0018624200316433928,
151
+ "loss": 0.221,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.43,
156
+ "learning_rate": 0.0018566875329618674,
157
+ "loss": 0.2108,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.45,
162
+ "learning_rate": 0.001850955034280342,
163
+ "loss": 0.2217,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.46,
168
+ "learning_rate": 0.001845222535598817,
169
+ "loss": 0.2157,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.48,
174
+ "learning_rate": 0.0018394900369172915,
175
+ "loss": 0.2076,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.5,
180
+ "learning_rate": 0.0018337575382357664,
181
+ "loss": 0.2162,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.52,
186
+ "learning_rate": 0.001828025039554241,
187
+ "loss": 0.207,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.53,
192
+ "learning_rate": 0.0018222925408727156,
193
+ "loss": 0.2131,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.55,
198
+ "learning_rate": 0.0018165600421911903,
199
+ "loss": 0.2119,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.57,
204
+ "learning_rate": 0.001810827543509665,
205
+ "loss": 0.2205,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.58,
210
+ "learning_rate": 0.0018050950448281397,
211
+ "loss": 0.2134,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.6,
216
+ "learning_rate": 0.0017993625461466144,
217
+ "loss": 0.216,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.62,
222
+ "learning_rate": 0.001793630047465089,
223
+ "loss": 0.2132,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.64,
228
+ "learning_rate": 0.0017878975487835638,
229
+ "loss": 0.2125,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.65,
234
+ "learning_rate": 0.0017821650501020385,
235
+ "loss": 0.2138,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.67,
240
+ "learning_rate": 0.0017764325514205133,
241
+ "loss": 0.2111,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.69,
246
+ "learning_rate": 0.001770700052738988,
247
+ "loss": 0.209,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.71,
252
+ "learning_rate": 0.0017649675540574626,
253
+ "loss": 0.2086,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.72,
258
+ "learning_rate": 0.0017592350553759374,
259
+ "loss": 0.211,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.74,
264
+ "learning_rate": 0.001753502556694412,
265
+ "loss": 0.206,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.76,
270
+ "learning_rate": 0.0017477700580128869,
271
+ "loss": 0.2149,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.77,
276
+ "learning_rate": 0.0017420375593313613,
277
+ "loss": 0.2093,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 0.79,
282
+ "learning_rate": 0.0017363050606498361,
283
+ "loss": 0.2089,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 0.81,
288
+ "learning_rate": 0.0017305725619683107,
289
+ "loss": 0.2093,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 0.83,
294
+ "learning_rate": 0.0017248400632867856,
295
+ "loss": 0.2009,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 0.84,
300
+ "learning_rate": 0.00171910756460526,
301
+ "loss": 0.2058,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 0.86,
306
+ "learning_rate": 0.0017133750659237348,
307
+ "loss": 0.2143,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 0.88,
312
+ "learning_rate": 0.0017076425672422095,
313
+ "loss": 0.2071,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 0.89,
318
+ "learning_rate": 0.0017019100685606843,
319
+ "loss": 0.2098,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 0.91,
324
+ "learning_rate": 0.0016961775698791592,
325
+ "loss": 0.2064,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 0.93,
330
+ "learning_rate": 0.0016904450711976336,
331
+ "loss": 0.207,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 0.95,
336
+ "learning_rate": 0.0016847125725161084,
337
+ "loss": 0.2063,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 0.96,
342
+ "learning_rate": 0.001678980073834583,
343
+ "loss": 0.2109,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 0.98,
348
+ "learning_rate": 0.0016732475751530579,
349
+ "loss": 0.2038,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 1.0,
354
+ "learning_rate": 0.0016675150764715325,
355
+ "loss": 0.2082,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 1.0,
360
+ "eval_loss": 0.1924375593662262,
361
+ "eval_runtime": 1182.2501,
362
+ "eval_samples_per_second": 147.549,
363
+ "eval_steps_per_second": 6.148,
364
+ "step": 29074
365
+ },
366
+ {
367
+ "epoch": 1.01,
368
+ "learning_rate": 0.0016617825777900071,
369
+ "loss": 0.2098,
370
+ "step": 29500
371
+ },
372
+ {
373
+ "epoch": 1.03,
374
+ "learning_rate": 0.0016560500791084818,
375
+ "loss": 0.2011,
376
+ "step": 30000
377
+ },
378
+ {
379
+ "epoch": 1.05,
380
+ "learning_rate": 0.0016503175804269566,
381
+ "loss": 0.2008,
382
+ "step": 30500
383
+ },
384
+ {
385
+ "epoch": 1.07,
386
+ "learning_rate": 0.0016445850817454312,
387
+ "loss": 0.1995,
388
+ "step": 31000
389
+ },
390
+ {
391
+ "epoch": 1.08,
392
+ "learning_rate": 0.0016388525830639059,
393
+ "loss": 0.2022,
394
+ "step": 31500
395
+ },
396
+ {
397
+ "epoch": 1.1,
398
+ "learning_rate": 0.0016331200843823805,
399
+ "loss": 0.2006,
400
+ "step": 32000
401
+ },
402
+ {
403
+ "epoch": 1.12,
404
+ "learning_rate": 0.0016273875857008553,
405
+ "loss": 0.2007,
406
+ "step": 32500
407
+ },
408
+ {
409
+ "epoch": 1.14,
410
+ "learning_rate": 0.0016216550870193302,
411
+ "loss": 0.2041,
412
+ "step": 33000
413
+ },
414
+ {
415
+ "epoch": 1.15,
416
+ "learning_rate": 0.0016159225883378048,
417
+ "loss": 0.2069,
418
+ "step": 33500
419
+ },
420
+ {
421
+ "epoch": 1.17,
422
+ "learning_rate": 0.0016101900896562794,
423
+ "loss": 0.2029,
424
+ "step": 34000
425
+ },
426
+ {
427
+ "epoch": 1.19,
428
+ "learning_rate": 0.001604457590974754,
429
+ "loss": 0.2002,
430
+ "step": 34500
431
+ },
432
+ {
433
+ "epoch": 1.2,
434
+ "learning_rate": 0.0015987250922932289,
435
+ "loss": 0.2026,
436
+ "step": 35000
437
+ },
438
+ {
439
+ "epoch": 1.22,
440
+ "learning_rate": 0.0015929925936117035,
441
+ "loss": 0.1978,
442
+ "step": 35500
443
+ },
444
+ {
445
+ "epoch": 1.24,
446
+ "learning_rate": 0.0015872600949301781,
447
+ "loss": 0.2063,
448
+ "step": 36000
449
+ },
450
+ {
451
+ "epoch": 1.26,
452
+ "learning_rate": 0.0015815275962486528,
453
+ "loss": 0.1958,
454
+ "step": 36500
455
+ },
456
+ {
457
+ "epoch": 1.27,
458
+ "learning_rate": 0.0015757950975671276,
459
+ "loss": 0.2023,
460
+ "step": 37000
461
+ },
462
+ {
463
+ "epoch": 1.29,
464
+ "learning_rate": 0.0015700625988856022,
465
+ "loss": 0.2014,
466
+ "step": 37500
467
+ },
468
+ {
469
+ "epoch": 1.31,
470
+ "learning_rate": 0.001564330100204077,
471
+ "loss": 0.2116,
472
+ "step": 38000
473
+ },
474
+ {
475
+ "epoch": 1.32,
476
+ "learning_rate": 0.0015585976015225515,
477
+ "loss": 0.2047,
478
+ "step": 38500
479
+ },
480
+ {
481
+ "epoch": 1.34,
482
+ "learning_rate": 0.0015528651028410263,
483
+ "loss": 0.2048,
484
+ "step": 39000
485
+ },
486
+ {
487
+ "epoch": 1.36,
488
+ "learning_rate": 0.0015471326041595012,
489
+ "loss": 0.2003,
490
+ "step": 39500
491
+ },
492
+ {
493
+ "epoch": 1.38,
494
+ "learning_rate": 0.0015414001054779758,
495
+ "loss": 0.2046,
496
+ "step": 40000
497
+ },
498
+ {
499
+ "epoch": 1.39,
500
+ "learning_rate": 0.0015356676067964507,
501
+ "loss": 0.2001,
502
+ "step": 40500
503
+ }
504
+ ],
505
+ "max_steps": 174444,
506
+ "num_train_epochs": 6,
507
+ "total_flos": 1.3154952419475456e+17,
508
+ "trial_name": null,
509
+ "trial_params": null
510
+ }