anton-l HF staff commited on
Commit
9cbabe0
1 Parent(s): 7a14425

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.7944972826086957,
4
+ "eval_loss": 0.9835737347602844,
5
+ "eval_runtime": 167.4825,
6
+ "eval_samples_per_second": 35.156,
7
+ "eval_steps_per_second": 8.789,
8
+ "train_loss": 1.0006333545797823,
9
+ "train_runtime": 3643.6893,
10
+ "train_samples_per_second": 60.911,
11
+ "train_steps_per_second": 0.475
12
+ }
emissions.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
2
+ 2021-10-01T12:33:47,2f022d5a-f047-41b6-a149-809aae8bf977,codecarbon,3643.7068734169006,0.2999506914741666,0.5296674756739654,USA,USA,Iowa,Y,gcp,us-central1
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.7944972826086957,
4
+ "eval_loss": 0.9835737347602844,
5
+ "eval_runtime": 167.4825,
6
+ "eval_samples_per_second": 35.156,
7
+ "eval_steps_per_second": 8.789
8
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a2e050a6cea498195ebc8abd9177a62e4af8e6c0fe2bc5e4e1fb483b547bcbe
3
  size 378405907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394f9e8f7dba622f701d6396f2487226404829bcb112eff009a0d8667caf3eeb
3
  size 378405907
runs/Oct01_11-32-47_anton-gpu-v100/events.out.tfevents.1633087983.anton-gpu-v100.97311.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c28743504dd1d4f3782f9df80ada007451065925efec49d79dd835fbfacad70
3
- size 36891
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7effca265c8428073e67119dc8d2f4215c47b7292e112e51e55f10ba34c5e48c
3
+ size 37245
runs/Oct01_11-32-47_anton-gpu-v100/events.out.tfevents.1633091796.anton-gpu-v100.97311.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999f23063f5df1185fa26c797947c441311ccb57058853c9fde07779bf843e94
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 1.0006333545797823,
4
+ "train_runtime": 3643.6893,
5
+ "train_samples_per_second": 60.911,
6
+ "train_steps_per_second": 0.475
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,1153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9835737347602844,
3
+ "best_model_checkpoint": "wav2vec2-base-lang-id/checkpoint-1557",
4
+ "epoch": 9.997118155619596,
5
+ "global_step": 1730,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 1.7341040462427742e-05,
13
+ "loss": 3.8045,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.12,
18
+ "learning_rate": 3.4682080924855485e-05,
19
+ "loss": 3.795,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.17,
24
+ "learning_rate": 5.2023121387283234e-05,
25
+ "loss": 3.7695,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.23,
30
+ "learning_rate": 6.936416184971097e-05,
31
+ "loss": 3.748,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.29,
36
+ "learning_rate": 8.670520231213873e-05,
37
+ "loss": 3.7078,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.35,
42
+ "learning_rate": 0.00010404624277456647,
43
+ "loss": 3.7034,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.4,
48
+ "learning_rate": 0.00012138728323699421,
49
+ "loss": 3.6422,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.46,
54
+ "learning_rate": 0.00013872832369942194,
55
+ "loss": 3.5837,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.52,
60
+ "learning_rate": 0.00015606936416184968,
61
+ "loss": 3.4935,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.58,
66
+ "learning_rate": 0.00017341040462427745,
67
+ "loss": 3.4542,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.63,
72
+ "learning_rate": 0.0001907514450867052,
73
+ "loss": 3.3921,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.69,
78
+ "learning_rate": 0.00020809248554913294,
79
+ "loss": 3.3001,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.75,
84
+ "learning_rate": 0.00022543352601156065,
85
+ "loss": 3.272,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.81,
90
+ "learning_rate": 0.00024277456647398842,
91
+ "loss": 3.1537,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.86,
96
+ "learning_rate": 0.00026011560693641616,
97
+ "loss": 3.1013,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.92,
102
+ "learning_rate": 0.0002774566473988439,
103
+ "loss": 2.9714,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.98,
108
+ "learning_rate": 0.00029479768786127165,
109
+ "loss": 2.9568,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 1.0,
114
+ "eval_accuracy": 0.11463994565217392,
115
+ "eval_loss": 3.2865560054779053,
116
+ "eval_runtime": 166.1472,
117
+ "eval_samples_per_second": 35.438,
118
+ "eval_steps_per_second": 8.86,
119
+ "step": 173
120
+ },
121
+ {
122
+ "epoch": 1.04,
123
+ "learning_rate": 0.00029865125240847784,
124
+ "loss": 3.2585,
125
+ "step": 180
126
+ },
127
+ {
128
+ "epoch": 1.1,
129
+ "learning_rate": 0.0002967244701348747,
130
+ "loss": 2.9694,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 1.16,
135
+ "learning_rate": 0.00029479768786127165,
136
+ "loss": 2.7459,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 1.21,
141
+ "learning_rate": 0.0002928709055876686,
142
+ "loss": 2.6486,
143
+ "step": 210
144
+ },
145
+ {
146
+ "epoch": 1.27,
147
+ "learning_rate": 0.0002909441233140655,
148
+ "loss": 2.6249,
149
+ "step": 220
150
+ },
151
+ {
152
+ "epoch": 1.33,
153
+ "learning_rate": 0.0002890173410404624,
154
+ "loss": 2.5935,
155
+ "step": 230
156
+ },
157
+ {
158
+ "epoch": 1.39,
159
+ "learning_rate": 0.0002870905587668593,
160
+ "loss": 2.422,
161
+ "step": 240
162
+ },
163
+ {
164
+ "epoch": 1.44,
165
+ "learning_rate": 0.0002851637764932562,
166
+ "loss": 2.4574,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 1.5,
171
+ "learning_rate": 0.0002832369942196532,
172
+ "loss": 2.427,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 1.56,
177
+ "learning_rate": 0.00028131021194605007,
178
+ "loss": 2.3682,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 1.62,
183
+ "learning_rate": 0.000279383429672447,
184
+ "loss": 2.2995,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 1.67,
189
+ "learning_rate": 0.0002774566473988439,
190
+ "loss": 2.1737,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.73,
195
+ "learning_rate": 0.0002755298651252408,
196
+ "loss": 2.1063,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.79,
201
+ "learning_rate": 0.00027360308285163774,
202
+ "loss": 2.0759,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.85,
207
+ "learning_rate": 0.0002716763005780347,
208
+ "loss": 1.9768,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.9,
213
+ "learning_rate": 0.00026974951830443155,
214
+ "loss": 2.0376,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.96,
219
+ "learning_rate": 0.0002678227360308285,
220
+ "loss": 1.9243,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 2.0,
225
+ "eval_accuracy": 0.38400135869565216,
226
+ "eval_loss": 2.124117612838745,
227
+ "eval_runtime": 166.2747,
228
+ "eval_samples_per_second": 35.411,
229
+ "eval_steps_per_second": 8.853,
230
+ "step": 346
231
+ },
232
+ {
233
+ "epoch": 2.02,
234
+ "learning_rate": 0.0002658959537572254,
235
+ "loss": 1.8395,
236
+ "step": 350
237
+ },
238
+ {
239
+ "epoch": 2.08,
240
+ "learning_rate": 0.00026396917148362235,
241
+ "loss": 1.7052,
242
+ "step": 360
243
+ },
244
+ {
245
+ "epoch": 2.14,
246
+ "learning_rate": 0.00026204238921001923,
247
+ "loss": 1.6084,
248
+ "step": 370
249
+ },
250
+ {
251
+ "epoch": 2.2,
252
+ "learning_rate": 0.00026011560693641616,
253
+ "loss": 1.5298,
254
+ "step": 380
255
+ },
256
+ {
257
+ "epoch": 2.25,
258
+ "learning_rate": 0.0002581888246628131,
259
+ "loss": 1.5755,
260
+ "step": 390
261
+ },
262
+ {
263
+ "epoch": 2.31,
264
+ "learning_rate": 0.00025626204238921,
265
+ "loss": 1.4869,
266
+ "step": 400
267
+ },
268
+ {
269
+ "epoch": 2.37,
270
+ "learning_rate": 0.0002543352601156069,
271
+ "loss": 1.5374,
272
+ "step": 410
273
+ },
274
+ {
275
+ "epoch": 2.43,
276
+ "learning_rate": 0.00025240847784200384,
277
+ "loss": 1.448,
278
+ "step": 420
279
+ },
280
+ {
281
+ "epoch": 2.48,
282
+ "learning_rate": 0.00025048169556840077,
283
+ "loss": 1.4246,
284
+ "step": 430
285
+ },
286
+ {
287
+ "epoch": 2.54,
288
+ "learning_rate": 0.00024855491329479765,
289
+ "loss": 1.4545,
290
+ "step": 440
291
+ },
292
+ {
293
+ "epoch": 2.6,
294
+ "learning_rate": 0.0002466281310211946,
295
+ "loss": 1.4417,
296
+ "step": 450
297
+ },
298
+ {
299
+ "epoch": 2.66,
300
+ "learning_rate": 0.00024470134874759146,
301
+ "loss": 1.3385,
302
+ "step": 460
303
+ },
304
+ {
305
+ "epoch": 2.71,
306
+ "learning_rate": 0.00024277456647398842,
307
+ "loss": 1.4229,
308
+ "step": 470
309
+ },
310
+ {
311
+ "epoch": 2.77,
312
+ "learning_rate": 0.00024084778420038535,
313
+ "loss": 1.4225,
314
+ "step": 480
315
+ },
316
+ {
317
+ "epoch": 2.83,
318
+ "learning_rate": 0.00023892100192678226,
319
+ "loss": 1.4259,
320
+ "step": 490
321
+ },
322
+ {
323
+ "epoch": 2.89,
324
+ "learning_rate": 0.00023699421965317916,
325
+ "loss": 1.3656,
326
+ "step": 500
327
+ },
328
+ {
329
+ "epoch": 2.95,
330
+ "learning_rate": 0.00023506743737957607,
331
+ "loss": 1.2923,
332
+ "step": 510
333
+ },
334
+ {
335
+ "epoch": 3.0,
336
+ "eval_accuracy": 0.5489130434782609,
337
+ "eval_loss": 1.5498348474502563,
338
+ "eval_runtime": 166.2498,
339
+ "eval_samples_per_second": 35.417,
340
+ "eval_steps_per_second": 8.854,
341
+ "step": 519
342
+ },
343
+ {
344
+ "epoch": 3.01,
345
+ "learning_rate": 0.00023314065510597303,
346
+ "loss": 1.3854,
347
+ "step": 520
348
+ },
349
+ {
350
+ "epoch": 3.06,
351
+ "learning_rate": 0.00023121387283236994,
352
+ "loss": 1.1289,
353
+ "step": 530
354
+ },
355
+ {
356
+ "epoch": 3.12,
357
+ "learning_rate": 0.00022928709055876684,
358
+ "loss": 0.921,
359
+ "step": 540
360
+ },
361
+ {
362
+ "epoch": 3.18,
363
+ "learning_rate": 0.00022736030828516375,
364
+ "loss": 1.004,
365
+ "step": 550
366
+ },
367
+ {
368
+ "epoch": 3.24,
369
+ "learning_rate": 0.00022543352601156065,
370
+ "loss": 1.0642,
371
+ "step": 560
372
+ },
373
+ {
374
+ "epoch": 3.29,
375
+ "learning_rate": 0.0002235067437379576,
376
+ "loss": 1.0275,
377
+ "step": 570
378
+ },
379
+ {
380
+ "epoch": 3.35,
381
+ "learning_rate": 0.00022157996146435452,
382
+ "loss": 0.9369,
383
+ "step": 580
384
+ },
385
+ {
386
+ "epoch": 3.41,
387
+ "learning_rate": 0.00021965317919075142,
388
+ "loss": 0.9486,
389
+ "step": 590
390
+ },
391
+ {
392
+ "epoch": 3.47,
393
+ "learning_rate": 0.00021772639691714833,
394
+ "loss": 1.0021,
395
+ "step": 600
396
+ },
397
+ {
398
+ "epoch": 3.52,
399
+ "learning_rate": 0.00021579961464354526,
400
+ "loss": 0.8916,
401
+ "step": 610
402
+ },
403
+ {
404
+ "epoch": 3.58,
405
+ "learning_rate": 0.0002138728323699422,
406
+ "loss": 0.9455,
407
+ "step": 620
408
+ },
409
+ {
410
+ "epoch": 3.64,
411
+ "learning_rate": 0.0002119460500963391,
412
+ "loss": 0.9796,
413
+ "step": 630
414
+ },
415
+ {
416
+ "epoch": 3.7,
417
+ "learning_rate": 0.000210019267822736,
418
+ "loss": 0.8681,
419
+ "step": 640
420
+ },
421
+ {
422
+ "epoch": 3.76,
423
+ "learning_rate": 0.00020809248554913294,
424
+ "loss": 0.948,
425
+ "step": 650
426
+ },
427
+ {
428
+ "epoch": 3.81,
429
+ "learning_rate": 0.00020616570327552984,
430
+ "loss": 0.9276,
431
+ "step": 660
432
+ },
433
+ {
434
+ "epoch": 3.87,
435
+ "learning_rate": 0.00020423892100192677,
436
+ "loss": 0.847,
437
+ "step": 670
438
+ },
439
+ {
440
+ "epoch": 3.93,
441
+ "learning_rate": 0.00020231213872832368,
442
+ "loss": 0.9261,
443
+ "step": 680
444
+ },
445
+ {
446
+ "epoch": 3.99,
447
+ "learning_rate": 0.0002003853564547206,
448
+ "loss": 0.8659,
449
+ "step": 690
450
+ },
451
+ {
452
+ "epoch": 4.0,
453
+ "eval_accuracy": 0.6126019021739131,
454
+ "eval_loss": 1.4952939748764038,
455
+ "eval_runtime": 165.9075,
456
+ "eval_samples_per_second": 35.49,
457
+ "eval_steps_per_second": 8.872,
458
+ "step": 692
459
+ },
460
+ {
461
+ "epoch": 4.05,
462
+ "learning_rate": 0.00019845857418111752,
463
+ "loss": 0.6758,
464
+ "step": 700
465
+ },
466
+ {
467
+ "epoch": 4.1,
468
+ "learning_rate": 0.00019653179190751442,
469
+ "loss": 0.5885,
470
+ "step": 710
471
+ },
472
+ {
473
+ "epoch": 4.16,
474
+ "learning_rate": 0.00019460500963391133,
475
+ "loss": 0.6432,
476
+ "step": 720
477
+ },
478
+ {
479
+ "epoch": 4.22,
480
+ "learning_rate": 0.0001926782273603083,
481
+ "loss": 0.6774,
482
+ "step": 730
483
+ },
484
+ {
485
+ "epoch": 4.28,
486
+ "learning_rate": 0.0001907514450867052,
487
+ "loss": 0.7333,
488
+ "step": 740
489
+ },
490
+ {
491
+ "epoch": 4.33,
492
+ "learning_rate": 0.0001888246628131021,
493
+ "loss": 0.6775,
494
+ "step": 750
495
+ },
496
+ {
497
+ "epoch": 4.39,
498
+ "learning_rate": 0.000186897880539499,
499
+ "loss": 0.6461,
500
+ "step": 760
501
+ },
502
+ {
503
+ "epoch": 4.45,
504
+ "learning_rate": 0.0001849710982658959,
505
+ "loss": 0.6192,
506
+ "step": 770
507
+ },
508
+ {
509
+ "epoch": 4.51,
510
+ "learning_rate": 0.00018304431599229287,
511
+ "loss": 0.569,
512
+ "step": 780
513
+ },
514
+ {
515
+ "epoch": 4.56,
516
+ "learning_rate": 0.00018131021194605008,
517
+ "loss": 0.6447,
518
+ "step": 790
519
+ },
520
+ {
521
+ "epoch": 4.62,
522
+ "learning_rate": 0.00017938342967244698,
523
+ "loss": 0.556,
524
+ "step": 800
525
+ },
526
+ {
527
+ "epoch": 4.68,
528
+ "learning_rate": 0.0001774566473988439,
529
+ "loss": 0.6883,
530
+ "step": 810
531
+ },
532
+ {
533
+ "epoch": 4.74,
534
+ "learning_rate": 0.00017552986512524085,
535
+ "loss": 0.6146,
536
+ "step": 820
537
+ },
538
+ {
539
+ "epoch": 4.8,
540
+ "learning_rate": 0.00017360308285163775,
541
+ "loss": 0.6318,
542
+ "step": 830
543
+ },
544
+ {
545
+ "epoch": 4.85,
546
+ "learning_rate": 0.00017167630057803466,
547
+ "loss": 0.5785,
548
+ "step": 840
549
+ },
550
+ {
551
+ "epoch": 4.91,
552
+ "learning_rate": 0.00016974951830443156,
553
+ "loss": 0.6383,
554
+ "step": 850
555
+ },
556
+ {
557
+ "epoch": 4.97,
558
+ "learning_rate": 0.0001678227360308285,
559
+ "loss": 0.5539,
560
+ "step": 860
561
+ },
562
+ {
563
+ "epoch": 5.0,
564
+ "eval_accuracy": 0.6925951086956522,
565
+ "eval_loss": 1.2430508136749268,
566
+ "eval_runtime": 166.7541,
567
+ "eval_samples_per_second": 35.309,
568
+ "eval_steps_per_second": 8.827,
569
+ "step": 865
570
+ },
571
+ {
572
+ "epoch": 5.03,
573
+ "learning_rate": 0.00016589595375722543,
574
+ "loss": 0.5354,
575
+ "step": 870
576
+ },
577
+ {
578
+ "epoch": 5.09,
579
+ "learning_rate": 0.00016396917148362233,
580
+ "loss": 0.4011,
581
+ "step": 880
582
+ },
583
+ {
584
+ "epoch": 5.14,
585
+ "learning_rate": 0.00016204238921001924,
586
+ "loss": 0.4009,
587
+ "step": 890
588
+ },
589
+ {
590
+ "epoch": 5.2,
591
+ "learning_rate": 0.00016011560693641617,
592
+ "loss": 0.459,
593
+ "step": 900
594
+ },
595
+ {
596
+ "epoch": 5.26,
597
+ "learning_rate": 0.00015818882466281308,
598
+ "loss": 0.3829,
599
+ "step": 910
600
+ },
601
+ {
602
+ "epoch": 5.32,
603
+ "learning_rate": 0.00015626204238921,
604
+ "loss": 0.428,
605
+ "step": 920
606
+ },
607
+ {
608
+ "epoch": 5.37,
609
+ "learning_rate": 0.00015433526011560692,
610
+ "loss": 0.4654,
611
+ "step": 930
612
+ },
613
+ {
614
+ "epoch": 5.43,
615
+ "learning_rate": 0.00015240847784200385,
616
+ "loss": 0.4531,
617
+ "step": 940
618
+ },
619
+ {
620
+ "epoch": 5.49,
621
+ "learning_rate": 0.00015067437379576106,
622
+ "loss": 0.4221,
623
+ "step": 950
624
+ },
625
+ {
626
+ "epoch": 5.55,
627
+ "learning_rate": 0.000148747591522158,
628
+ "loss": 0.3927,
629
+ "step": 960
630
+ },
631
+ {
632
+ "epoch": 5.61,
633
+ "learning_rate": 0.0001468208092485549,
634
+ "loss": 0.4451,
635
+ "step": 970
636
+ },
637
+ {
638
+ "epoch": 5.66,
639
+ "learning_rate": 0.00014489402697495183,
640
+ "loss": 0.4363,
641
+ "step": 980
642
+ },
643
+ {
644
+ "epoch": 5.72,
645
+ "learning_rate": 0.00014296724470134873,
646
+ "loss": 0.4583,
647
+ "step": 990
648
+ },
649
+ {
650
+ "epoch": 5.78,
651
+ "learning_rate": 0.00014104046242774566,
652
+ "loss": 0.3788,
653
+ "step": 1000
654
+ },
655
+ {
656
+ "epoch": 5.84,
657
+ "learning_rate": 0.00013911368015414257,
658
+ "loss": 0.4333,
659
+ "step": 1010
660
+ },
661
+ {
662
+ "epoch": 5.89,
663
+ "learning_rate": 0.0001371868978805395,
664
+ "loss": 0.3448,
665
+ "step": 1020
666
+ },
667
+ {
668
+ "epoch": 5.95,
669
+ "learning_rate": 0.0001352601156069364,
670
+ "loss": 0.4101,
671
+ "step": 1030
672
+ },
673
+ {
674
+ "epoch": 6.0,
675
+ "eval_accuracy": 0.7231657608695652,
676
+ "eval_loss": 1.1443275213241577,
677
+ "eval_runtime": 167.1514,
678
+ "eval_samples_per_second": 35.226,
679
+ "eval_steps_per_second": 8.806,
680
+ "step": 1038
681
+ },
682
+ {
683
+ "epoch": 6.01,
684
+ "learning_rate": 0.0001333333333333333,
685
+ "loss": 0.4535,
686
+ "step": 1040
687
+ },
688
+ {
689
+ "epoch": 6.07,
690
+ "learning_rate": 0.00013140655105973025,
691
+ "loss": 0.3461,
692
+ "step": 1050
693
+ },
694
+ {
695
+ "epoch": 6.13,
696
+ "learning_rate": 0.00012947976878612715,
697
+ "loss": 0.2761,
698
+ "step": 1060
699
+ },
700
+ {
701
+ "epoch": 6.18,
702
+ "learning_rate": 0.00012755298651252408,
703
+ "loss": 0.2911,
704
+ "step": 1070
705
+ },
706
+ {
707
+ "epoch": 6.24,
708
+ "learning_rate": 0.000125626204238921,
709
+ "loss": 0.2985,
710
+ "step": 1080
711
+ },
712
+ {
713
+ "epoch": 6.3,
714
+ "learning_rate": 0.0001236994219653179,
715
+ "loss": 0.2858,
716
+ "step": 1090
717
+ },
718
+ {
719
+ "epoch": 6.36,
720
+ "learning_rate": 0.00012177263969171483,
721
+ "loss": 0.3162,
722
+ "step": 1100
723
+ },
724
+ {
725
+ "epoch": 6.41,
726
+ "learning_rate": 0.00011984585741811175,
727
+ "loss": 0.3326,
728
+ "step": 1110
729
+ },
730
+ {
731
+ "epoch": 6.47,
732
+ "learning_rate": 0.00011791907514450866,
733
+ "loss": 0.3024,
734
+ "step": 1120
735
+ },
736
+ {
737
+ "epoch": 6.53,
738
+ "learning_rate": 0.00011599229287090558,
739
+ "loss": 0.2981,
740
+ "step": 1130
741
+ },
742
+ {
743
+ "epoch": 6.59,
744
+ "learning_rate": 0.00011406551059730249,
745
+ "loss": 0.3112,
746
+ "step": 1140
747
+ },
748
+ {
749
+ "epoch": 6.65,
750
+ "learning_rate": 0.00011213872832369942,
751
+ "loss": 0.2206,
752
+ "step": 1150
753
+ },
754
+ {
755
+ "epoch": 6.7,
756
+ "learning_rate": 0.00011021194605009633,
757
+ "loss": 0.3052,
758
+ "step": 1160
759
+ },
760
+ {
761
+ "epoch": 6.76,
762
+ "learning_rate": 0.00010828516377649323,
763
+ "loss": 0.2799,
764
+ "step": 1170
765
+ },
766
+ {
767
+ "epoch": 6.82,
768
+ "learning_rate": 0.00010635838150289017,
769
+ "loss": 0.2793,
770
+ "step": 1180
771
+ },
772
+ {
773
+ "epoch": 6.88,
774
+ "learning_rate": 0.00010443159922928707,
775
+ "loss": 0.2992,
776
+ "step": 1190
777
+ },
778
+ {
779
+ "epoch": 6.93,
780
+ "learning_rate": 0.000102504816955684,
781
+ "loss": 0.3151,
782
+ "step": 1200
783
+ },
784
+ {
785
+ "epoch": 6.99,
786
+ "learning_rate": 0.00010057803468208092,
787
+ "loss": 0.2945,
788
+ "step": 1210
789
+ },
790
+ {
791
+ "epoch": 7.0,
792
+ "eval_accuracy": 0.7544157608695652,
793
+ "eval_loss": 1.0869863033294678,
794
+ "eval_runtime": 167.4711,
795
+ "eval_samples_per_second": 35.158,
796
+ "eval_steps_per_second": 8.79,
797
+ "step": 1211
798
+ },
799
+ {
800
+ "epoch": 7.05,
801
+ "learning_rate": 9.865125240847783e-05,
802
+ "loss": 0.2053,
803
+ "step": 1220
804
+ },
805
+ {
806
+ "epoch": 7.11,
807
+ "learning_rate": 9.672447013487476e-05,
808
+ "loss": 0.1619,
809
+ "step": 1230
810
+ },
811
+ {
812
+ "epoch": 7.17,
813
+ "learning_rate": 9.479768786127167e-05,
814
+ "loss": 0.2176,
815
+ "step": 1240
816
+ },
817
+ {
818
+ "epoch": 7.22,
819
+ "learning_rate": 9.28709055876686e-05,
820
+ "loss": 0.1907,
821
+ "step": 1250
822
+ },
823
+ {
824
+ "epoch": 7.28,
825
+ "learning_rate": 9.09441233140655e-05,
826
+ "loss": 0.1517,
827
+ "step": 1260
828
+ },
829
+ {
830
+ "epoch": 7.34,
831
+ "learning_rate": 8.901734104046241e-05,
832
+ "loss": 0.1932,
833
+ "step": 1270
834
+ },
835
+ {
836
+ "epoch": 7.4,
837
+ "learning_rate": 8.709055876685934e-05,
838
+ "loss": 0.2175,
839
+ "step": 1280
840
+ },
841
+ {
842
+ "epoch": 7.46,
843
+ "learning_rate": 8.516377649325625e-05,
844
+ "loss": 0.1794,
845
+ "step": 1290
846
+ },
847
+ {
848
+ "epoch": 7.51,
849
+ "learning_rate": 8.323699421965317e-05,
850
+ "loss": 0.1934,
851
+ "step": 1300
852
+ },
853
+ {
854
+ "epoch": 7.57,
855
+ "learning_rate": 8.131021194605009e-05,
856
+ "loss": 0.2138,
857
+ "step": 1310
858
+ },
859
+ {
860
+ "epoch": 7.63,
861
+ "learning_rate": 7.9383429672447e-05,
862
+ "loss": 0.1451,
863
+ "step": 1320
864
+ },
865
+ {
866
+ "epoch": 7.69,
867
+ "learning_rate": 7.745664739884392e-05,
868
+ "loss": 0.1691,
869
+ "step": 1330
870
+ },
871
+ {
872
+ "epoch": 7.74,
873
+ "learning_rate": 7.552986512524084e-05,
874
+ "loss": 0.1672,
875
+ "step": 1340
876
+ },
877
+ {
878
+ "epoch": 7.8,
879
+ "learning_rate": 7.360308285163776e-05,
880
+ "loss": 0.2004,
881
+ "step": 1350
882
+ },
883
+ {
884
+ "epoch": 7.86,
885
+ "learning_rate": 7.167630057803468e-05,
886
+ "loss": 0.1925,
887
+ "step": 1360
888
+ },
889
+ {
890
+ "epoch": 7.92,
891
+ "learning_rate": 6.974951830443159e-05,
892
+ "loss": 0.1649,
893
+ "step": 1370
894
+ },
895
+ {
896
+ "epoch": 7.97,
897
+ "learning_rate": 6.78227360308285e-05,
898
+ "loss": 0.1552,
899
+ "step": 1380
900
+ },
901
+ {
902
+ "epoch": 8.0,
903
+ "eval_accuracy": 0.7661345108695652,
904
+ "eval_loss": 1.1080151796340942,
905
+ "eval_runtime": 167.1864,
906
+ "eval_samples_per_second": 35.218,
907
+ "eval_steps_per_second": 8.805,
908
+ "step": 1384
909
+ },
910
+ {
911
+ "epoch": 8.03,
912
+ "learning_rate": 6.589595375722542e-05,
913
+ "loss": 0.1643,
914
+ "step": 1390
915
+ },
916
+ {
917
+ "epoch": 8.09,
918
+ "learning_rate": 6.396917148362234e-05,
919
+ "loss": 0.08,
920
+ "step": 1400
921
+ },
922
+ {
923
+ "epoch": 8.15,
924
+ "learning_rate": 6.204238921001926e-05,
925
+ "loss": 0.1022,
926
+ "step": 1410
927
+ },
928
+ {
929
+ "epoch": 8.21,
930
+ "learning_rate": 6.0115606936416174e-05,
931
+ "loss": 0.1466,
932
+ "step": 1420
933
+ },
934
+ {
935
+ "epoch": 8.27,
936
+ "learning_rate": 5.81888246628131e-05,
937
+ "loss": 0.1262,
938
+ "step": 1430
939
+ },
940
+ {
941
+ "epoch": 8.32,
942
+ "learning_rate": 5.626204238921002e-05,
943
+ "loss": 0.0895,
944
+ "step": 1440
945
+ },
946
+ {
947
+ "epoch": 8.38,
948
+ "learning_rate": 5.433526011560694e-05,
949
+ "loss": 0.1155,
950
+ "step": 1450
951
+ },
952
+ {
953
+ "epoch": 8.44,
954
+ "learning_rate": 5.2408477842003843e-05,
955
+ "loss": 0.1205,
956
+ "step": 1460
957
+ },
958
+ {
959
+ "epoch": 8.5,
960
+ "learning_rate": 5.048169556840076e-05,
961
+ "loss": 0.1196,
962
+ "step": 1470
963
+ },
964
+ {
965
+ "epoch": 8.55,
966
+ "learning_rate": 4.855491329479768e-05,
967
+ "loss": 0.1488,
968
+ "step": 1480
969
+ },
970
+ {
971
+ "epoch": 8.61,
972
+ "learning_rate": 4.66281310211946e-05,
973
+ "loss": 0.1263,
974
+ "step": 1490
975
+ },
976
+ {
977
+ "epoch": 8.67,
978
+ "learning_rate": 4.470134874759151e-05,
979
+ "loss": 0.1289,
980
+ "step": 1500
981
+ },
982
+ {
983
+ "epoch": 8.73,
984
+ "learning_rate": 4.277456647398843e-05,
985
+ "loss": 0.1628,
986
+ "step": 1510
987
+ },
988
+ {
989
+ "epoch": 8.78,
990
+ "learning_rate": 4.084778420038535e-05,
991
+ "loss": 0.1665,
992
+ "step": 1520
993
+ },
994
+ {
995
+ "epoch": 8.84,
996
+ "learning_rate": 3.892100192678227e-05,
997
+ "loss": 0.1234,
998
+ "step": 1530
999
+ },
1000
+ {
1001
+ "epoch": 8.9,
1002
+ "learning_rate": 3.699421965317919e-05,
1003
+ "loss": 0.1146,
1004
+ "step": 1540
1005
+ },
1006
+ {
1007
+ "epoch": 8.96,
1008
+ "learning_rate": 3.506743737957611e-05,
1009
+ "loss": 0.0968,
1010
+ "step": 1550
1011
+ },
1012
+ {
1013
+ "epoch": 9.0,
1014
+ "eval_accuracy": 0.7944972826086957,
1015
+ "eval_loss": 0.9835737347602844,
1016
+ "eval_runtime": 167.3463,
1017
+ "eval_samples_per_second": 35.185,
1018
+ "eval_steps_per_second": 8.796,
1019
+ "step": 1557
1020
+ },
1021
+ {
1022
+ "epoch": 9.02,
1023
+ "learning_rate": 3.314065510597302e-05,
1024
+ "loss": 0.1091,
1025
+ "step": 1560
1026
+ },
1027
+ {
1028
+ "epoch": 9.07,
1029
+ "learning_rate": 3.121387283236994e-05,
1030
+ "loss": 0.1036,
1031
+ "step": 1570
1032
+ },
1033
+ {
1034
+ "epoch": 9.13,
1035
+ "learning_rate": 2.9287090558766855e-05,
1036
+ "loss": 0.1183,
1037
+ "step": 1580
1038
+ },
1039
+ {
1040
+ "epoch": 9.19,
1041
+ "learning_rate": 2.7360308285163774e-05,
1042
+ "loss": 0.0903,
1043
+ "step": 1590
1044
+ },
1045
+ {
1046
+ "epoch": 9.25,
1047
+ "learning_rate": 2.543352601156069e-05,
1048
+ "loss": 0.0808,
1049
+ "step": 1600
1050
+ },
1051
+ {
1052
+ "epoch": 9.31,
1053
+ "learning_rate": 2.350674373795761e-05,
1054
+ "loss": 0.0749,
1055
+ "step": 1610
1056
+ },
1057
+ {
1058
+ "epoch": 9.36,
1059
+ "learning_rate": 2.1579961464354524e-05,
1060
+ "loss": 0.0523,
1061
+ "step": 1620
1062
+ },
1063
+ {
1064
+ "epoch": 9.42,
1065
+ "learning_rate": 1.9653179190751443e-05,
1066
+ "loss": 0.1112,
1067
+ "step": 1630
1068
+ },
1069
+ {
1070
+ "epoch": 9.48,
1071
+ "learning_rate": 1.7726396917148362e-05,
1072
+ "loss": 0.0949,
1073
+ "step": 1640
1074
+ },
1075
+ {
1076
+ "epoch": 9.54,
1077
+ "learning_rate": 1.5799614643545278e-05,
1078
+ "loss": 0.0858,
1079
+ "step": 1650
1080
+ },
1081
+ {
1082
+ "epoch": 9.59,
1083
+ "learning_rate": 1.3872832369942195e-05,
1084
+ "loss": 0.0603,
1085
+ "step": 1660
1086
+ },
1087
+ {
1088
+ "epoch": 9.65,
1089
+ "learning_rate": 1.1946050096339112e-05,
1090
+ "loss": 0.0718,
1091
+ "step": 1670
1092
+ },
1093
+ {
1094
+ "epoch": 9.71,
1095
+ "learning_rate": 1.0019267822736031e-05,
1096
+ "loss": 0.069,
1097
+ "step": 1680
1098
+ },
1099
+ {
1100
+ "epoch": 9.77,
1101
+ "learning_rate": 8.092485549132947e-06,
1102
+ "loss": 0.0748,
1103
+ "step": 1690
1104
+ },
1105
+ {
1106
+ "epoch": 9.82,
1107
+ "learning_rate": 6.165703275529864e-06,
1108
+ "loss": 0.0831,
1109
+ "step": 1700
1110
+ },
1111
+ {
1112
+ "epoch": 9.88,
1113
+ "learning_rate": 4.2389210019267816e-06,
1114
+ "loss": 0.0635,
1115
+ "step": 1710
1116
+ },
1117
+ {
1118
+ "epoch": 9.94,
1119
+ "learning_rate": 2.3121387283236993e-06,
1120
+ "loss": 0.0675,
1121
+ "step": 1720
1122
+ },
1123
+ {
1124
+ "epoch": 10.0,
1125
+ "learning_rate": 3.853564547206165e-07,
1126
+ "loss": 0.0623,
1127
+ "step": 1730
1128
+ },
1129
+ {
1130
+ "epoch": 10.0,
1131
+ "eval_accuracy": 0.7992527173913043,
1132
+ "eval_loss": 1.0252065658569336,
1133
+ "eval_runtime": 167.8251,
1134
+ "eval_samples_per_second": 35.084,
1135
+ "eval_steps_per_second": 8.771,
1136
+ "step": 1730
1137
+ },
1138
+ {
1139
+ "epoch": 10.0,
1140
+ "step": 1730,
1141
+ "total_flos": 1.8408056270747849e+19,
1142
+ "train_loss": 1.0006333545797823,
1143
+ "train_runtime": 3643.6893,
1144
+ "train_samples_per_second": 60.911,
1145
+ "train_steps_per_second": 0.475
1146
+ }
1147
+ ],
1148
+ "max_steps": 1730,
1149
+ "num_train_epochs": 10,
1150
+ "total_flos": 1.8408056270747849e+19,
1151
+ "trial_name": null,
1152
+ "trial_params": null
1153
+ }