amyeroberts HF staff commited on
Commit
3440cc3
1 Parent(s): 05510b7

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9849624060150376,
4
+ "eval_loss": 0.0629788488149643,
5
+ "eval_runtime": 9.1129,
6
+ "eval_samples_per_second": 14.595,
7
+ "eval_steps_per_second": 1.865,
8
+ "train_loss": 0.23407576583898984,
9
+ "train_runtime": 956.3524,
10
+ "train_samples_per_second": 5.406,
11
+ "train_steps_per_second": 0.68
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9849624060150376,
4
+ "eval_loss": 0.0629788488149643,
5
+ "eval_runtime": 9.1129,
6
+ "eval_samples_per_second": 14.595,
7
+ "eval_steps_per_second": 1.865
8
+ }
runs/Jan30_16-00-50_Amys-MacBook-Pro-2.local/events.out.tfevents.1675097027.Amys-MacBook-Pro-2.local.76511.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5603e1de6979c086fc92fcc5290654fa838b01800a0c49b3606efb5c842e66
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.23407576583898984,
4
+ "train_runtime": 956.3524,
5
+ "train_samples_per_second": 5.406,
6
+ "train_steps_per_second": 0.68
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,460 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0629788488149643,
3
+ "best_model_checkpoint": "./beans_outputs/checkpoint-650",
4
+ "epoch": 5.0,
5
+ "global_step": 650,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 1.9692307692307696e-05,
13
+ "loss": 1.0376,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.15,
18
+ "learning_rate": 1.9384615384615386e-05,
19
+ "loss": 0.9321,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.23,
24
+ "learning_rate": 1.907692307692308e-05,
25
+ "loss": 0.8443,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.31,
30
+ "learning_rate": 1.876923076923077e-05,
31
+ "loss": 0.6961,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.38,
36
+ "learning_rate": 1.8461538461538465e-05,
37
+ "loss": 0.6817,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.46,
42
+ "learning_rate": 1.8153846153846155e-05,
43
+ "loss": 0.6014,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.54,
48
+ "learning_rate": 1.784615384615385e-05,
49
+ "loss": 0.5399,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.62,
54
+ "learning_rate": 1.753846153846154e-05,
55
+ "loss": 0.4494,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.69,
60
+ "learning_rate": 1.7230769230769234e-05,
61
+ "loss": 0.4639,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.77,
66
+ "learning_rate": 1.6923076923076924e-05,
67
+ "loss": 0.3812,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.85,
72
+ "learning_rate": 1.6615384615384618e-05,
73
+ "loss": 0.2879,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.92,
78
+ "learning_rate": 1.630769230769231e-05,
79
+ "loss": 0.2905,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "learning_rate": 1.6000000000000003e-05,
85
+ "loss": 0.3038,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 1.0,
90
+ "eval_accuracy": 0.9624060150375939,
91
+ "eval_loss": 0.23956194519996643,
92
+ "eval_runtime": 9.1028,
93
+ "eval_samples_per_second": 14.611,
94
+ "eval_steps_per_second": 1.868,
95
+ "step": 130
96
+ },
97
+ {
98
+ "epoch": 1.08,
99
+ "learning_rate": 1.5692307692307693e-05,
100
+ "loss": 0.1833,
101
+ "step": 140
102
+ },
103
+ {
104
+ "epoch": 1.15,
105
+ "learning_rate": 1.5384615384615387e-05,
106
+ "loss": 0.2351,
107
+ "step": 150
108
+ },
109
+ {
110
+ "epoch": 1.23,
111
+ "learning_rate": 1.5076923076923078e-05,
112
+ "loss": 0.2677,
113
+ "step": 160
114
+ },
115
+ {
116
+ "epoch": 1.31,
117
+ "learning_rate": 1.4769230769230772e-05,
118
+ "loss": 0.1575,
119
+ "step": 170
120
+ },
121
+ {
122
+ "epoch": 1.38,
123
+ "learning_rate": 1.4461538461538462e-05,
124
+ "loss": 0.2751,
125
+ "step": 180
126
+ },
127
+ {
128
+ "epoch": 1.46,
129
+ "learning_rate": 1.4153846153846156e-05,
130
+ "loss": 0.189,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 1.54,
135
+ "learning_rate": 1.3846153846153847e-05,
136
+ "loss": 0.1909,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 1.62,
141
+ "learning_rate": 1.353846153846154e-05,
142
+ "loss": 0.2285,
143
+ "step": 210
144
+ },
145
+ {
146
+ "epoch": 1.69,
147
+ "learning_rate": 1.3230769230769231e-05,
148
+ "loss": 0.2254,
149
+ "step": 220
150
+ },
151
+ {
152
+ "epoch": 1.77,
153
+ "learning_rate": 1.2923076923076925e-05,
154
+ "loss": 0.1991,
155
+ "step": 230
156
+ },
157
+ {
158
+ "epoch": 1.85,
159
+ "learning_rate": 1.2615384615384616e-05,
160
+ "loss": 0.1753,
161
+ "step": 240
162
+ },
163
+ {
164
+ "epoch": 1.92,
165
+ "learning_rate": 1.230769230769231e-05,
166
+ "loss": 0.0943,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 2.0,
171
+ "learning_rate": 1.2e-05,
172
+ "loss": 0.1609,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 2.0,
177
+ "eval_accuracy": 0.9774436090225563,
178
+ "eval_loss": 0.11299962550401688,
179
+ "eval_runtime": 8.6644,
180
+ "eval_samples_per_second": 15.35,
181
+ "eval_steps_per_second": 1.962,
182
+ "step": 260
183
+ },
184
+ {
185
+ "epoch": 2.08,
186
+ "learning_rate": 1.1692307692307694e-05,
187
+ "loss": 0.1253,
188
+ "step": 270
189
+ },
190
+ {
191
+ "epoch": 2.15,
192
+ "learning_rate": 1.1384615384615385e-05,
193
+ "loss": 0.1537,
194
+ "step": 280
195
+ },
196
+ {
197
+ "epoch": 2.23,
198
+ "learning_rate": 1.1076923076923079e-05,
199
+ "loss": 0.0875,
200
+ "step": 290
201
+ },
202
+ {
203
+ "epoch": 2.31,
204
+ "learning_rate": 1.076923076923077e-05,
205
+ "loss": 0.1023,
206
+ "step": 300
207
+ },
208
+ {
209
+ "epoch": 2.38,
210
+ "learning_rate": 1.0461538461538463e-05,
211
+ "loss": 0.1109,
212
+ "step": 310
213
+ },
214
+ {
215
+ "epoch": 2.46,
216
+ "learning_rate": 1.0153846153846154e-05,
217
+ "loss": 0.2311,
218
+ "step": 320
219
+ },
220
+ {
221
+ "epoch": 2.54,
222
+ "learning_rate": 9.846153846153848e-06,
223
+ "loss": 0.1223,
224
+ "step": 330
225
+ },
226
+ {
227
+ "epoch": 2.62,
228
+ "learning_rate": 9.53846153846154e-06,
229
+ "loss": 0.243,
230
+ "step": 340
231
+ },
232
+ {
233
+ "epoch": 2.69,
234
+ "learning_rate": 9.230769230769232e-06,
235
+ "loss": 0.244,
236
+ "step": 350
237
+ },
238
+ {
239
+ "epoch": 2.77,
240
+ "learning_rate": 8.923076923076925e-06,
241
+ "loss": 0.1226,
242
+ "step": 360
243
+ },
244
+ {
245
+ "epoch": 2.85,
246
+ "learning_rate": 8.615384615384617e-06,
247
+ "loss": 0.1115,
248
+ "step": 370
249
+ },
250
+ {
251
+ "epoch": 2.92,
252
+ "learning_rate": 8.307692307692309e-06,
253
+ "loss": 0.0942,
254
+ "step": 380
255
+ },
256
+ {
257
+ "epoch": 3.0,
258
+ "learning_rate": 8.000000000000001e-06,
259
+ "loss": 0.2313,
260
+ "step": 390
261
+ },
262
+ {
263
+ "epoch": 3.0,
264
+ "eval_accuracy": 0.9849624060150376,
265
+ "eval_loss": 0.08092895895242691,
266
+ "eval_runtime": 9.1773,
267
+ "eval_samples_per_second": 14.492,
268
+ "eval_steps_per_second": 1.852,
269
+ "step": 390
270
+ },
271
+ {
272
+ "epoch": 3.08,
273
+ "learning_rate": 7.692307692307694e-06,
274
+ "loss": 0.1309,
275
+ "step": 400
276
+ },
277
+ {
278
+ "epoch": 3.15,
279
+ "learning_rate": 7.384615384615386e-06,
280
+ "loss": 0.1914,
281
+ "step": 410
282
+ },
283
+ {
284
+ "epoch": 3.23,
285
+ "learning_rate": 7.076923076923078e-06,
286
+ "loss": 0.181,
287
+ "step": 420
288
+ },
289
+ {
290
+ "epoch": 3.31,
291
+ "learning_rate": 6.76923076923077e-06,
292
+ "loss": 0.1004,
293
+ "step": 430
294
+ },
295
+ {
296
+ "epoch": 3.38,
297
+ "learning_rate": 6.461538461538463e-06,
298
+ "loss": 0.1426,
299
+ "step": 440
300
+ },
301
+ {
302
+ "epoch": 3.46,
303
+ "learning_rate": 6.153846153846155e-06,
304
+ "loss": 0.1059,
305
+ "step": 450
306
+ },
307
+ {
308
+ "epoch": 3.54,
309
+ "learning_rate": 5.846153846153847e-06,
310
+ "loss": 0.1353,
311
+ "step": 460
312
+ },
313
+ {
314
+ "epoch": 3.62,
315
+ "learning_rate": 5.538461538461539e-06,
316
+ "loss": 0.1861,
317
+ "step": 470
318
+ },
319
+ {
320
+ "epoch": 3.69,
321
+ "learning_rate": 5.230769230769232e-06,
322
+ "loss": 0.1331,
323
+ "step": 480
324
+ },
325
+ {
326
+ "epoch": 3.77,
327
+ "learning_rate": 4.923076923076924e-06,
328
+ "loss": 0.0799,
329
+ "step": 490
330
+ },
331
+ {
332
+ "epoch": 3.85,
333
+ "learning_rate": 4.615384615384616e-06,
334
+ "loss": 0.1271,
335
+ "step": 500
336
+ },
337
+ {
338
+ "epoch": 3.92,
339
+ "learning_rate": 4.307692307692308e-06,
340
+ "loss": 0.1483,
341
+ "step": 510
342
+ },
343
+ {
344
+ "epoch": 4.0,
345
+ "learning_rate": 4.000000000000001e-06,
346
+ "loss": 0.1436,
347
+ "step": 520
348
+ },
349
+ {
350
+ "epoch": 4.0,
351
+ "eval_accuracy": 0.9849624060150376,
352
+ "eval_loss": 0.07378804683685303,
353
+ "eval_runtime": 9.6033,
354
+ "eval_samples_per_second": 13.849,
355
+ "eval_steps_per_second": 1.77,
356
+ "step": 520
357
+ },
358
+ {
359
+ "epoch": 4.08,
360
+ "learning_rate": 3.692307692307693e-06,
361
+ "loss": 0.0915,
362
+ "step": 530
363
+ },
364
+ {
365
+ "epoch": 4.15,
366
+ "learning_rate": 3.384615384615385e-06,
367
+ "loss": 0.0917,
368
+ "step": 540
369
+ },
370
+ {
371
+ "epoch": 4.23,
372
+ "learning_rate": 3.0769230769230774e-06,
373
+ "loss": 0.0608,
374
+ "step": 550
375
+ },
376
+ {
377
+ "epoch": 4.31,
378
+ "learning_rate": 2.7692307692307697e-06,
379
+ "loss": 0.0646,
380
+ "step": 560
381
+ },
382
+ {
383
+ "epoch": 4.38,
384
+ "learning_rate": 2.461538461538462e-06,
385
+ "loss": 0.1057,
386
+ "step": 570
387
+ },
388
+ {
389
+ "epoch": 4.46,
390
+ "learning_rate": 2.153846153846154e-06,
391
+ "loss": 0.0616,
392
+ "step": 580
393
+ },
394
+ {
395
+ "epoch": 4.54,
396
+ "learning_rate": 1.8461538461538465e-06,
397
+ "loss": 0.0472,
398
+ "step": 590
399
+ },
400
+ {
401
+ "epoch": 4.62,
402
+ "learning_rate": 1.5384615384615387e-06,
403
+ "loss": 0.2017,
404
+ "step": 600
405
+ },
406
+ {
407
+ "epoch": 4.69,
408
+ "learning_rate": 1.230769230769231e-06,
409
+ "loss": 0.1336,
410
+ "step": 610
411
+ },
412
+ {
413
+ "epoch": 4.77,
414
+ "learning_rate": 9.230769230769232e-07,
415
+ "loss": 0.1378,
416
+ "step": 620
417
+ },
418
+ {
419
+ "epoch": 4.85,
420
+ "learning_rate": 6.153846153846155e-07,
421
+ "loss": 0.1161,
422
+ "step": 630
423
+ },
424
+ {
425
+ "epoch": 4.92,
426
+ "learning_rate": 3.0769230769230774e-07,
427
+ "loss": 0.1167,
428
+ "step": 640
429
+ },
430
+ {
431
+ "epoch": 5.0,
432
+ "learning_rate": 0.0,
433
+ "loss": 0.1086,
434
+ "step": 650
435
+ },
436
+ {
437
+ "epoch": 5.0,
438
+ "eval_accuracy": 0.9849624060150376,
439
+ "eval_loss": 0.0629788488149643,
440
+ "eval_runtime": 9.6544,
441
+ "eval_samples_per_second": 13.776,
442
+ "eval_steps_per_second": 1.761,
443
+ "step": 650
444
+ },
445
+ {
446
+ "epoch": 5.0,
447
+ "step": 650,
448
+ "total_flos": 4.006371770595533e+17,
449
+ "train_loss": 0.23407576583898984,
450
+ "train_runtime": 956.3524,
451
+ "train_samples_per_second": 5.406,
452
+ "train_steps_per_second": 0.68
453
+ }
454
+ ],
455
+ "max_steps": 650,
456
+ "num_train_epochs": 5,
457
+ "total_flos": 4.006371770595533e+17,
458
+ "trial_name": null,
459
+ "trial_params": null
460
+ }