rooftopcoder commited on
Commit
04bee0f
1 Parent(s): b1194e3

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.09259259259259259,
4
+ "eval_f1": 0.05973409306742639,
5
+ "eval_loss": 0.7936302423477173,
6
+ "eval_runtime": 2.005,
7
+ "eval_samples": 54,
8
+ "eval_samples_per_second": 26.933,
9
+ "eval_steps_per_second": 1.995,
10
+ "predict_accuracy": 0.08267568583239383,
11
+ "predict_f1": 0.045617221543158844,
12
+ "predict_loss": 0.8681505918502808,
13
+ "predict_runtime": 259.1585,
14
+ "predict_samples": 7983,
15
+ "predict_samples_per_second": 30.804,
16
+ "predict_steps_per_second": 1.925,
17
+ "train_loss": 0.960862031856172,
18
+ "train_runtime": 14382.9455,
19
+ "train_samples": 108647,
20
+ "train_samples_per_second": 22.662,
21
+ "train_steps_per_second": 2.833
22
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.09259259259259259,
4
+ "eval_f1": 0.05973409306742639,
5
+ "eval_loss": 0.7936302423477173,
6
+ "eval_runtime": 2.005,
7
+ "eval_samples": 54,
8
+ "eval_samples_per_second": 26.933,
9
+ "eval_steps_per_second": 1.995
10
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "decoder_start_token_id": 2,
5
  "early_stopping": true,
 
1
  {
 
2
  "bos_token_id": 0,
3
  "decoder_start_token_id": 2,
4
  "early_stopping": true,
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_accuracy": 0.08267568583239383,
3
+ "predict_f1": 0.045617221543158844,
4
+ "predict_loss": 0.8681505918502808,
5
+ "predict_runtime": 259.1585,
6
+ "predict_samples": 7983,
7
+ "predict_samples_per_second": 30.804,
8
+ "predict_steps_per_second": 1.925
9
+ }
runs/May10_19-00-03_1a6e58a818b7/events.out.tfevents.1683759629.1a6e58a818b7.3774.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09616c6f3f88757a68b85bf157507057115e7aaa52dc2c78ac8634b890f3850
3
+ size 416
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.960862031856172,
4
+ "train_runtime": 14382.9455,
5
+ "train_samples": 108647,
6
+ "train_samples_per_second": 22.662,
7
+ "train_steps_per_second": 2.833
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,511 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 40743,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 4.754122497055359e-05,
13
+ "loss": 1.7036,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 4.50873576756969e-05,
19
+ "loss": 1.41,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.11,
24
+ "learning_rate": 4.2633490380840206e-05,
25
+ "loss": 1.3415,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.15,
30
+ "learning_rate": 4.0179623085983514e-05,
31
+ "loss": 1.3378,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.18,
36
+ "learning_rate": 3.7725755791126815e-05,
37
+ "loss": 1.2834,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.22,
42
+ "learning_rate": 3.527188849627012e-05,
43
+ "loss": 1.2521,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.26,
48
+ "learning_rate": 3.281802120141343e-05,
49
+ "loss": 1.2503,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.29,
54
+ "learning_rate": 3.0364153906556735e-05,
55
+ "loss": 1.2091,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.33,
60
+ "learning_rate": 2.7910286611700043e-05,
61
+ "loss": 1.1859,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.37,
66
+ "learning_rate": 2.5456419316843344e-05,
67
+ "loss": 1.1315,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.4,
72
+ "learning_rate": 2.3002552021986652e-05,
73
+ "loss": 1.1428,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.44,
78
+ "learning_rate": 2.0548684727129957e-05,
79
+ "loss": 1.131,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.48,
84
+ "learning_rate": 1.8094817432273264e-05,
85
+ "loss": 1.1061,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.52,
90
+ "learning_rate": 1.564095013741657e-05,
91
+ "loss": 1.0928,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.55,
96
+ "learning_rate": 1.3187082842559875e-05,
97
+ "loss": 1.0874,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.59,
102
+ "learning_rate": 1.0733215547703181e-05,
103
+ "loss": 1.0383,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.63,
108
+ "learning_rate": 8.279348252846486e-06,
109
+ "loss": 1.053,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.66,
114
+ "learning_rate": 5.8254809579897925e-06,
115
+ "loss": 1.0296,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.7,
120
+ "learning_rate": 3.3716136631330974e-06,
121
+ "loss": 1.0306,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.74,
126
+ "learning_rate": 9.177463682764037e-07,
127
+ "loss": 1.0046,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.77,
132
+ "learning_rate": 0.0,
133
+ "loss": 1.0091,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.81,
138
+ "learning_rate": 0.0,
139
+ "loss": 1.0358,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.85,
144
+ "learning_rate": 0.0,
145
+ "loss": 1.0118,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.88,
150
+ "learning_rate": 0.0,
151
+ "loss": 0.9876,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.92,
156
+ "learning_rate": 0.0,
157
+ "loss": 1.0315,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.96,
162
+ "learning_rate": 0.0,
163
+ "loss": 1.0118,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.99,
168
+ "learning_rate": 0.0,
169
+ "loss": 1.0024,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 1.03,
174
+ "learning_rate": 0.0,
175
+ "loss": 0.8988,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.07,
180
+ "learning_rate": 0.0,
181
+ "loss": 0.8442,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.1,
186
+ "learning_rate": 0.0,
187
+ "loss": 0.8775,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 1.14,
192
+ "learning_rate": 0.0,
193
+ "loss": 0.8822,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 1.18,
198
+ "learning_rate": 0.0,
199
+ "loss": 0.8732,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.21,
204
+ "learning_rate": 0.0,
205
+ "loss": 0.8775,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.25,
210
+ "learning_rate": 0.0,
211
+ "loss": 0.8662,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.29,
216
+ "learning_rate": 0.0,
217
+ "loss": 0.8707,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.33,
222
+ "learning_rate": 0.0,
223
+ "loss": 0.8568,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.36,
228
+ "learning_rate": 0.0,
229
+ "loss": 0.8737,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.4,
234
+ "learning_rate": 0.0,
235
+ "loss": 0.8579,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.44,
240
+ "learning_rate": 0.0,
241
+ "loss": 0.883,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.47,
246
+ "learning_rate": 0.0,
247
+ "loss": 0.8582,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.51,
252
+ "learning_rate": 0.0,
253
+ "loss": 0.8591,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 1.55,
258
+ "learning_rate": 0.0,
259
+ "loss": 0.8582,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 1.58,
264
+ "learning_rate": 0.0,
265
+ "loss": 0.8864,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 1.62,
270
+ "learning_rate": 0.0,
271
+ "loss": 0.8819,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 1.66,
276
+ "learning_rate": 0.0,
277
+ "loss": 0.8462,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.69,
282
+ "learning_rate": 0.0,
283
+ "loss": 0.8641,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.73,
288
+ "learning_rate": 0.0,
289
+ "loss": 0.8762,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 1.77,
294
+ "learning_rate": 0.0,
295
+ "loss": 0.8787,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 1.8,
300
+ "learning_rate": 0.0,
301
+ "loss": 0.8632,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.84,
306
+ "learning_rate": 0.0,
307
+ "loss": 0.8648,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 1.88,
312
+ "learning_rate": 0.0,
313
+ "loss": 0.8755,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 1.91,
318
+ "learning_rate": 0.0,
319
+ "loss": 0.8521,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 1.95,
324
+ "learning_rate": 0.0,
325
+ "loss": 0.8941,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 1.99,
330
+ "learning_rate": 0.0,
331
+ "loss": 0.8518,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 2.02,
336
+ "learning_rate": 0.0,
337
+ "loss": 0.8689,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 2.06,
342
+ "learning_rate": 0.0,
343
+ "loss": 0.8546,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 2.1,
348
+ "learning_rate": 0.0,
349
+ "loss": 0.8404,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 2.14,
354
+ "learning_rate": 0.0,
355
+ "loss": 0.8472,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 2.17,
360
+ "learning_rate": 0.0,
361
+ "loss": 0.8793,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 2.21,
366
+ "learning_rate": 0.0,
367
+ "loss": 0.8845,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 2.25,
372
+ "learning_rate": 0.0,
373
+ "loss": 0.8487,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 2.28,
378
+ "learning_rate": 0.0,
379
+ "loss": 0.8641,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 2.32,
384
+ "learning_rate": 0.0,
385
+ "loss": 0.886,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 2.36,
390
+ "learning_rate": 0.0,
391
+ "loss": 0.8828,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 2.39,
396
+ "learning_rate": 0.0,
397
+ "loss": 0.8637,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 2.43,
402
+ "learning_rate": 0.0,
403
+ "loss": 0.8748,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 2.47,
408
+ "learning_rate": 0.0,
409
+ "loss": 0.879,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 2.5,
414
+ "learning_rate": 0.0,
415
+ "loss": 0.9094,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 2.54,
420
+ "learning_rate": 0.0,
421
+ "loss": 0.8687,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 2.58,
426
+ "learning_rate": 0.0,
427
+ "loss": 0.8475,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 2.61,
432
+ "learning_rate": 0.0,
433
+ "loss": 0.8596,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 2.65,
438
+ "learning_rate": 0.0,
439
+ "loss": 0.8806,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 2.69,
444
+ "learning_rate": 0.0,
445
+ "loss": 0.8705,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 2.72,
450
+ "learning_rate": 0.0,
451
+ "loss": 0.865,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 2.76,
456
+ "learning_rate": 0.0,
457
+ "loss": 0.8704,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 2.8,
462
+ "learning_rate": 0.0,
463
+ "loss": 0.8679,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 2.83,
468
+ "learning_rate": 0.0,
469
+ "loss": 0.8774,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 2.87,
474
+ "learning_rate": 0.0,
475
+ "loss": 0.8955,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 2.91,
480
+ "learning_rate": 0.0,
481
+ "loss": 0.8778,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 2.95,
486
+ "learning_rate": 0.0,
487
+ "loss": 0.8495,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 2.98,
492
+ "learning_rate": 0.0,
493
+ "loss": 0.8836,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 3.0,
498
+ "step": 40743,
499
+ "total_flos": 9.6652398495744e+16,
500
+ "train_loss": 0.960862031856172,
501
+ "train_runtime": 14382.9455,
502
+ "train_samples_per_second": 22.662,
503
+ "train_steps_per_second": 2.833
504
+ }
505
+ ],
506
+ "max_steps": 40743,
507
+ "num_train_epochs": 3,
508
+ "total_flos": 9.6652398495744e+16,
509
+ "trial_name": null,
510
+ "trial_params": null
511
+ }