anton-l HF staff commited on
Commit
7bd12b1
1 Parent(s): d8fd7a2

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.2797214673913043,
4
+ "eval_loss": 2.7213878631591797,
5
+ "eval_runtime": 53.5552,
6
+ "eval_samples_per_second": 109.943,
7
+ "eval_steps_per_second": 27.486,
8
+ "train_loss": 2.723648586162942,
9
+ "train_runtime": 2280.0763,
10
+ "train_samples_per_second": 97.339,
11
+ "train_steps_per_second": 0.759
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
+ 2021-10-27T21:28:12,d3882e9a-e7e5-4a5e-bcdf-9a433e67b1ee,codecarbon,2280.1669363975525,0.16935276866480697,0.29905133085786156,USA,USA,Iowa,Y,gcp,us-central1
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.2797214673913043,
4
+ "eval_loss": 2.7213878631591797,
5
+ "eval_runtime": 53.5552,
6
+ "eval_samples_per_second": 109.943,
7
+ "eval_steps_per_second": 27.486
8
+ }
runs/Oct27_20-49-53_anton-gpu-v100/events.out.tfevents.1635367812.anton-gpu-v100.151816.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7356099b4833a3b1dbcf2137864c599509197bba643eab4be4c38d58900f839b
3
- size 36319
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dcc6ce0ace4004fa8163a6f6bc41365f5fa20124e2c651f3057858dcec730a9
3
+ size 36673
runs/Oct27_20-49-53_anton-gpu-v100/events.out.tfevents.1635370146.anton-gpu-v100.151816.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ab3b4906aec4a749e326646511ae00683e861a70ce28674276b99e2f8f0219
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 2.723648586162942,
4
+ "train_runtime": 2280.0763,
5
+ "train_samples_per_second": 97.339,
6
+ "train_steps_per_second": 0.759
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,1153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.7213878631591797,
3
+ "best_model_checkpoint": "distilhubert-ft-common-language/checkpoint-1730",
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": 1.7341040462427746e-06,
13
+ "loss": 3.8053,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.12,
18
+ "learning_rate": 3.468208092485549e-06,
19
+ "loss": 3.8023,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.17,
24
+ "learning_rate": 5.202312138728324e-06,
25
+ "loss": 3.7997,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.23,
30
+ "learning_rate": 6.936416184971098e-06,
31
+ "loss": 3.7984,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.29,
36
+ "learning_rate": 8.670520231213873e-06,
37
+ "loss": 3.7896,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.35,
42
+ "learning_rate": 1.0404624277456647e-05,
43
+ "loss": 3.7927,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.4,
48
+ "learning_rate": 1.2138728323699422e-05,
49
+ "loss": 3.7864,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.46,
54
+ "learning_rate": 1.3872832369942197e-05,
55
+ "loss": 3.777,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.52,
60
+ "learning_rate": 1.560693641618497e-05,
61
+ "loss": 3.7708,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.58,
66
+ "learning_rate": 1.7341040462427746e-05,
67
+ "loss": 3.7625,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.63,
72
+ "learning_rate": 1.9075144508670522e-05,
73
+ "loss": 3.756,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.69,
78
+ "learning_rate": 2.0809248554913295e-05,
79
+ "loss": 3.75,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.75,
84
+ "learning_rate": 2.2543352601156068e-05,
85
+ "loss": 3.747,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.81,
90
+ "learning_rate": 2.4277456647398844e-05,
91
+ "loss": 3.7278,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.86,
96
+ "learning_rate": 2.601156069364162e-05,
97
+ "loss": 3.7176,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.92,
102
+ "learning_rate": 2.7745664739884393e-05,
103
+ "loss": 3.6797,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.98,
108
+ "learning_rate": 2.9479768786127166e-05,
109
+ "loss": 3.6543,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 1.0,
114
+ "eval_accuracy": 0.04908288043478261,
115
+ "eval_loss": 3.7611067295074463,
116
+ "eval_runtime": 52.1768,
117
+ "eval_samples_per_second": 112.847,
118
+ "eval_steps_per_second": 28.212,
119
+ "step": 173
120
+ },
121
+ {
122
+ "epoch": 1.04,
123
+ "learning_rate": 2.9865125240847786e-05,
124
+ "loss": 3.8088,
125
+ "step": 180
126
+ },
127
+ {
128
+ "epoch": 1.1,
129
+ "learning_rate": 2.9672447013487474e-05,
130
+ "loss": 3.6031,
131
+ "step": 190
132
+ },
133
+ {
134
+ "epoch": 1.16,
135
+ "learning_rate": 2.9479768786127166e-05,
136
+ "loss": 3.5492,
137
+ "step": 200
138
+ },
139
+ {
140
+ "epoch": 1.21,
141
+ "learning_rate": 2.928709055876686e-05,
142
+ "loss": 3.5422,
143
+ "step": 210
144
+ },
145
+ {
146
+ "epoch": 1.27,
147
+ "learning_rate": 2.9094412331406553e-05,
148
+ "loss": 3.5229,
149
+ "step": 220
150
+ },
151
+ {
152
+ "epoch": 1.33,
153
+ "learning_rate": 2.8901734104046242e-05,
154
+ "loss": 3.4998,
155
+ "step": 230
156
+ },
157
+ {
158
+ "epoch": 1.39,
159
+ "learning_rate": 2.8709055876685934e-05,
160
+ "loss": 3.4431,
161
+ "step": 240
162
+ },
163
+ {
164
+ "epoch": 1.44,
165
+ "learning_rate": 2.8516377649325626e-05,
166
+ "loss": 3.4477,
167
+ "step": 250
168
+ },
169
+ {
170
+ "epoch": 1.5,
171
+ "learning_rate": 2.832369942196532e-05,
172
+ "loss": 3.435,
173
+ "step": 260
174
+ },
175
+ {
176
+ "epoch": 1.56,
177
+ "learning_rate": 2.813102119460501e-05,
178
+ "loss": 3.4089,
179
+ "step": 270
180
+ },
181
+ {
182
+ "epoch": 1.62,
183
+ "learning_rate": 2.79383429672447e-05,
184
+ "loss": 3.3528,
185
+ "step": 280
186
+ },
187
+ {
188
+ "epoch": 1.67,
189
+ "learning_rate": 2.7745664739884393e-05,
190
+ "loss": 3.3388,
191
+ "step": 290
192
+ },
193
+ {
194
+ "epoch": 1.73,
195
+ "learning_rate": 2.7552986512524085e-05,
196
+ "loss": 3.3147,
197
+ "step": 300
198
+ },
199
+ {
200
+ "epoch": 1.79,
201
+ "learning_rate": 2.7360308285163777e-05,
202
+ "loss": 3.3178,
203
+ "step": 310
204
+ },
205
+ {
206
+ "epoch": 1.85,
207
+ "learning_rate": 2.716763005780347e-05,
208
+ "loss": 3.2654,
209
+ "step": 320
210
+ },
211
+ {
212
+ "epoch": 1.9,
213
+ "learning_rate": 2.697495183044316e-05,
214
+ "loss": 3.2578,
215
+ "step": 330
216
+ },
217
+ {
218
+ "epoch": 1.96,
219
+ "learning_rate": 2.6782273603082853e-05,
220
+ "loss": 3.2221,
221
+ "step": 340
222
+ },
223
+ {
224
+ "epoch": 2.0,
225
+ "eval_accuracy": 0.13519021739130435,
226
+ "eval_loss": 3.4867842197418213,
227
+ "eval_runtime": 52.2245,
228
+ "eval_samples_per_second": 112.744,
229
+ "eval_steps_per_second": 28.186,
230
+ "step": 346
231
+ },
232
+ {
233
+ "epoch": 2.02,
234
+ "learning_rate": 2.658959537572254e-05,
235
+ "loss": 3.3213,
236
+ "step": 350
237
+ },
238
+ {
239
+ "epoch": 2.08,
240
+ "learning_rate": 2.6396917148362237e-05,
241
+ "loss": 3.2115,
242
+ "step": 360
243
+ },
244
+ {
245
+ "epoch": 2.14,
246
+ "learning_rate": 2.620423892100193e-05,
247
+ "loss": 3.1688,
248
+ "step": 370
249
+ },
250
+ {
251
+ "epoch": 2.2,
252
+ "learning_rate": 2.601156069364162e-05,
253
+ "loss": 3.1121,
254
+ "step": 380
255
+ },
256
+ {
257
+ "epoch": 2.25,
258
+ "learning_rate": 2.581888246628131e-05,
259
+ "loss": 3.1319,
260
+ "step": 390
261
+ },
262
+ {
263
+ "epoch": 2.31,
264
+ "learning_rate": 2.5626204238921e-05,
265
+ "loss": 3.0432,
266
+ "step": 400
267
+ },
268
+ {
269
+ "epoch": 2.37,
270
+ "learning_rate": 2.5433526011560693e-05,
271
+ "loss": 3.0898,
272
+ "step": 410
273
+ },
274
+ {
275
+ "epoch": 2.43,
276
+ "learning_rate": 2.5240847784200388e-05,
277
+ "loss": 3.0542,
278
+ "step": 420
279
+ },
280
+ {
281
+ "epoch": 2.48,
282
+ "learning_rate": 2.5048169556840077e-05,
283
+ "loss": 3.0457,
284
+ "step": 430
285
+ },
286
+ {
287
+ "epoch": 2.54,
288
+ "learning_rate": 2.485549132947977e-05,
289
+ "loss": 3.0342,
290
+ "step": 440
291
+ },
292
+ {
293
+ "epoch": 2.6,
294
+ "learning_rate": 2.466281310211946e-05,
295
+ "loss": 3.0365,
296
+ "step": 450
297
+ },
298
+ {
299
+ "epoch": 2.66,
300
+ "learning_rate": 2.4470134874759152e-05,
301
+ "loss": 3.0378,
302
+ "step": 460
303
+ },
304
+ {
305
+ "epoch": 2.71,
306
+ "learning_rate": 2.4277456647398844e-05,
307
+ "loss": 3.0531,
308
+ "step": 470
309
+ },
310
+ {
311
+ "epoch": 2.77,
312
+ "learning_rate": 2.4084778420038536e-05,
313
+ "loss": 3.0055,
314
+ "step": 480
315
+ },
316
+ {
317
+ "epoch": 2.83,
318
+ "learning_rate": 2.3892100192678228e-05,
319
+ "loss": 2.9554,
320
+ "step": 490
321
+ },
322
+ {
323
+ "epoch": 2.89,
324
+ "learning_rate": 2.369942196531792e-05,
325
+ "loss": 2.9419,
326
+ "step": 500
327
+ },
328
+ {
329
+ "epoch": 2.95,
330
+ "learning_rate": 2.350674373795761e-05,
331
+ "loss": 2.9332,
332
+ "step": 510
333
+ },
334
+ {
335
+ "epoch": 3.0,
336
+ "eval_accuracy": 0.18614130434782608,
337
+ "eval_loss": 3.2731645107269287,
338
+ "eval_runtime": 52.3596,
339
+ "eval_samples_per_second": 112.453,
340
+ "eval_steps_per_second": 28.113,
341
+ "step": 519
342
+ },
343
+ {
344
+ "epoch": 3.01,
345
+ "learning_rate": 2.3314065510597304e-05,
346
+ "loss": 3.1159,
347
+ "step": 520
348
+ },
349
+ {
350
+ "epoch": 3.06,
351
+ "learning_rate": 2.3121387283236996e-05,
352
+ "loss": 2.9039,
353
+ "step": 530
354
+ },
355
+ {
356
+ "epoch": 3.12,
357
+ "learning_rate": 2.2928709055876687e-05,
358
+ "loss": 2.8746,
359
+ "step": 540
360
+ },
361
+ {
362
+ "epoch": 3.18,
363
+ "learning_rate": 2.2736030828516376e-05,
364
+ "loss": 2.8507,
365
+ "step": 550
366
+ },
367
+ {
368
+ "epoch": 3.24,
369
+ "learning_rate": 2.2543352601156068e-05,
370
+ "loss": 2.8744,
371
+ "step": 560
372
+ },
373
+ {
374
+ "epoch": 3.29,
375
+ "learning_rate": 2.2350674373795763e-05,
376
+ "loss": 2.8733,
377
+ "step": 570
378
+ },
379
+ {
380
+ "epoch": 3.35,
381
+ "learning_rate": 2.2157996146435455e-05,
382
+ "loss": 2.8357,
383
+ "step": 580
384
+ },
385
+ {
386
+ "epoch": 3.41,
387
+ "learning_rate": 2.1965317919075144e-05,
388
+ "loss": 2.8052,
389
+ "step": 590
390
+ },
391
+ {
392
+ "epoch": 3.47,
393
+ "learning_rate": 2.1772639691714835e-05,
394
+ "loss": 2.8315,
395
+ "step": 600
396
+ },
397
+ {
398
+ "epoch": 3.52,
399
+ "learning_rate": 2.1579961464354527e-05,
400
+ "loss": 2.7872,
401
+ "step": 610
402
+ },
403
+ {
404
+ "epoch": 3.58,
405
+ "learning_rate": 2.1387283236994223e-05,
406
+ "loss": 2.8001,
407
+ "step": 620
408
+ },
409
+ {
410
+ "epoch": 3.64,
411
+ "learning_rate": 2.119460500963391e-05,
412
+ "loss": 2.8338,
413
+ "step": 630
414
+ },
415
+ {
416
+ "epoch": 3.7,
417
+ "learning_rate": 2.1001926782273603e-05,
418
+ "loss": 2.7424,
419
+ "step": 640
420
+ },
421
+ {
422
+ "epoch": 3.76,
423
+ "learning_rate": 2.0809248554913295e-05,
424
+ "loss": 2.7635,
425
+ "step": 650
426
+ },
427
+ {
428
+ "epoch": 3.81,
429
+ "learning_rate": 2.0616570327552987e-05,
430
+ "loss": 2.7298,
431
+ "step": 660
432
+ },
433
+ {
434
+ "epoch": 3.87,
435
+ "learning_rate": 2.042389210019268e-05,
436
+ "loss": 2.7291,
437
+ "step": 670
438
+ },
439
+ {
440
+ "epoch": 3.93,
441
+ "learning_rate": 2.023121387283237e-05,
442
+ "loss": 2.7619,
443
+ "step": 680
444
+ },
445
+ {
446
+ "epoch": 3.99,
447
+ "learning_rate": 2.0038535645472063e-05,
448
+ "loss": 2.7299,
449
+ "step": 690
450
+ },
451
+ {
452
+ "epoch": 4.0,
453
+ "eval_accuracy": 0.21722146739130435,
454
+ "eval_loss": 3.0944418907165527,
455
+ "eval_runtime": 52.2448,
456
+ "eval_samples_per_second": 112.7,
457
+ "eval_steps_per_second": 28.175,
458
+ "step": 692
459
+ },
460
+ {
461
+ "epoch": 4.05,
462
+ "learning_rate": 1.9845857418111754e-05,
463
+ "loss": 2.7785,
464
+ "step": 700
465
+ },
466
+ {
467
+ "epoch": 4.1,
468
+ "learning_rate": 1.9653179190751443e-05,
469
+ "loss": 2.6889,
470
+ "step": 710
471
+ },
472
+ {
473
+ "epoch": 4.16,
474
+ "learning_rate": 1.9460500963391135e-05,
475
+ "loss": 2.6733,
476
+ "step": 720
477
+ },
478
+ {
479
+ "epoch": 4.22,
480
+ "learning_rate": 1.926782273603083e-05,
481
+ "loss": 2.6498,
482
+ "step": 730
483
+ },
484
+ {
485
+ "epoch": 4.28,
486
+ "learning_rate": 1.9075144508670522e-05,
487
+ "loss": 2.6287,
488
+ "step": 740
489
+ },
490
+ {
491
+ "epoch": 4.33,
492
+ "learning_rate": 1.888246628131021e-05,
493
+ "loss": 2.6984,
494
+ "step": 750
495
+ },
496
+ {
497
+ "epoch": 4.39,
498
+ "learning_rate": 1.8689788053949903e-05,
499
+ "loss": 2.6441,
500
+ "step": 760
501
+ },
502
+ {
503
+ "epoch": 4.45,
504
+ "learning_rate": 1.8497109826589594e-05,
505
+ "loss": 2.5994,
506
+ "step": 770
507
+ },
508
+ {
509
+ "epoch": 4.51,
510
+ "learning_rate": 1.830443159922929e-05,
511
+ "loss": 2.5836,
512
+ "step": 780
513
+ },
514
+ {
515
+ "epoch": 4.56,
516
+ "learning_rate": 1.8111753371868978e-05,
517
+ "loss": 2.6276,
518
+ "step": 790
519
+ },
520
+ {
521
+ "epoch": 4.62,
522
+ "learning_rate": 1.791907514450867e-05,
523
+ "loss": 2.5829,
524
+ "step": 800
525
+ },
526
+ {
527
+ "epoch": 4.68,
528
+ "learning_rate": 1.7726396917148362e-05,
529
+ "loss": 2.5749,
530
+ "step": 810
531
+ },
532
+ {
533
+ "epoch": 4.74,
534
+ "learning_rate": 1.7533718689788054e-05,
535
+ "loss": 2.5888,
536
+ "step": 820
537
+ },
538
+ {
539
+ "epoch": 4.8,
540
+ "learning_rate": 1.7341040462427746e-05,
541
+ "loss": 2.6274,
542
+ "step": 830
543
+ },
544
+ {
545
+ "epoch": 4.85,
546
+ "learning_rate": 1.7148362235067438e-05,
547
+ "loss": 2.5904,
548
+ "step": 840
549
+ },
550
+ {
551
+ "epoch": 4.91,
552
+ "learning_rate": 1.695568400770713e-05,
553
+ "loss": 2.591,
554
+ "step": 850
555
+ },
556
+ {
557
+ "epoch": 4.97,
558
+ "learning_rate": 1.676300578034682e-05,
559
+ "loss": 2.5638,
560
+ "step": 860
561
+ },
562
+ {
563
+ "epoch": 5.0,
564
+ "eval_accuracy": 0.23997961956521738,
565
+ "eval_loss": 2.9790401458740234,
566
+ "eval_runtime": 53.2919,
567
+ "eval_samples_per_second": 110.486,
568
+ "eval_steps_per_second": 27.621,
569
+ "step": 865
570
+ },
571
+ {
572
+ "epoch": 5.03,
573
+ "learning_rate": 1.657032755298651e-05,
574
+ "loss": 2.6508,
575
+ "step": 870
576
+ },
577
+ {
578
+ "epoch": 5.09,
579
+ "learning_rate": 1.6377649325626205e-05,
580
+ "loss": 2.4978,
581
+ "step": 880
582
+ },
583
+ {
584
+ "epoch": 5.14,
585
+ "learning_rate": 1.6184971098265897e-05,
586
+ "loss": 2.5373,
587
+ "step": 890
588
+ },
589
+ {
590
+ "epoch": 5.2,
591
+ "learning_rate": 1.599229287090559e-05,
592
+ "loss": 2.4849,
593
+ "step": 900
594
+ },
595
+ {
596
+ "epoch": 5.26,
597
+ "learning_rate": 1.5799614643545278e-05,
598
+ "loss": 2.4536,
599
+ "step": 910
600
+ },
601
+ {
602
+ "epoch": 5.32,
603
+ "learning_rate": 1.560693641618497e-05,
604
+ "loss": 2.5074,
605
+ "step": 920
606
+ },
607
+ {
608
+ "epoch": 5.37,
609
+ "learning_rate": 1.5414258188824665e-05,
610
+ "loss": 2.5256,
611
+ "step": 930
612
+ },
613
+ {
614
+ "epoch": 5.43,
615
+ "learning_rate": 1.5221579961464355e-05,
616
+ "loss": 2.5123,
617
+ "step": 940
618
+ },
619
+ {
620
+ "epoch": 5.49,
621
+ "learning_rate": 1.5028901734104047e-05,
622
+ "loss": 2.4545,
623
+ "step": 950
624
+ },
625
+ {
626
+ "epoch": 5.55,
627
+ "learning_rate": 1.4836223506743737e-05,
628
+ "loss": 2.4744,
629
+ "step": 960
630
+ },
631
+ {
632
+ "epoch": 5.61,
633
+ "learning_rate": 1.464354527938343e-05,
634
+ "loss": 2.5031,
635
+ "step": 970
636
+ },
637
+ {
638
+ "epoch": 5.66,
639
+ "learning_rate": 1.4450867052023121e-05,
640
+ "loss": 2.4676,
641
+ "step": 980
642
+ },
643
+ {
644
+ "epoch": 5.72,
645
+ "learning_rate": 1.4258188824662813e-05,
646
+ "loss": 2.4683,
647
+ "step": 990
648
+ },
649
+ {
650
+ "epoch": 5.78,
651
+ "learning_rate": 1.4065510597302505e-05,
652
+ "loss": 2.4079,
653
+ "step": 1000
654
+ },
655
+ {
656
+ "epoch": 5.84,
657
+ "learning_rate": 1.3872832369942197e-05,
658
+ "loss": 2.5185,
659
+ "step": 1010
660
+ },
661
+ {
662
+ "epoch": 5.89,
663
+ "learning_rate": 1.3680154142581889e-05,
664
+ "loss": 2.3855,
665
+ "step": 1020
666
+ },
667
+ {
668
+ "epoch": 5.95,
669
+ "learning_rate": 1.348747591522158e-05,
670
+ "loss": 2.3871,
671
+ "step": 1030
672
+ },
673
+ {
674
+ "epoch": 6.0,
675
+ "eval_accuracy": 0.25900135869565216,
676
+ "eval_loss": 2.8667969703674316,
677
+ "eval_runtime": 52.4176,
678
+ "eval_samples_per_second": 112.329,
679
+ "eval_steps_per_second": 28.082,
680
+ "step": 1038
681
+ },
682
+ {
683
+ "epoch": 6.01,
684
+ "learning_rate": 1.329479768786127e-05,
685
+ "loss": 2.5741,
686
+ "step": 1040
687
+ },
688
+ {
689
+ "epoch": 6.07,
690
+ "learning_rate": 1.3102119460500964e-05,
691
+ "loss": 2.4171,
692
+ "step": 1050
693
+ },
694
+ {
695
+ "epoch": 6.13,
696
+ "learning_rate": 1.2909441233140654e-05,
697
+ "loss": 2.3616,
698
+ "step": 1060
699
+ },
700
+ {
701
+ "epoch": 6.18,
702
+ "learning_rate": 1.2716763005780346e-05,
703
+ "loss": 2.3999,
704
+ "step": 1070
705
+ },
706
+ {
707
+ "epoch": 6.24,
708
+ "learning_rate": 1.2524084778420038e-05,
709
+ "loss": 2.397,
710
+ "step": 1080
711
+ },
712
+ {
713
+ "epoch": 6.3,
714
+ "learning_rate": 1.233140655105973e-05,
715
+ "loss": 2.3259,
716
+ "step": 1090
717
+ },
718
+ {
719
+ "epoch": 6.36,
720
+ "learning_rate": 1.2138728323699422e-05,
721
+ "loss": 2.3675,
722
+ "step": 1100
723
+ },
724
+ {
725
+ "epoch": 6.41,
726
+ "learning_rate": 1.1946050096339114e-05,
727
+ "loss": 2.4148,
728
+ "step": 1110
729
+ },
730
+ {
731
+ "epoch": 6.47,
732
+ "learning_rate": 1.1753371868978804e-05,
733
+ "loss": 2.3335,
734
+ "step": 1120
735
+ },
736
+ {
737
+ "epoch": 6.53,
738
+ "learning_rate": 1.1560693641618498e-05,
739
+ "loss": 2.3388,
740
+ "step": 1130
741
+ },
742
+ {
743
+ "epoch": 6.59,
744
+ "learning_rate": 1.1368015414258188e-05,
745
+ "loss": 2.3687,
746
+ "step": 1140
747
+ },
748
+ {
749
+ "epoch": 6.65,
750
+ "learning_rate": 1.1175337186897882e-05,
751
+ "loss": 2.3935,
752
+ "step": 1150
753
+ },
754
+ {
755
+ "epoch": 6.7,
756
+ "learning_rate": 1.0982658959537572e-05,
757
+ "loss": 2.3787,
758
+ "step": 1160
759
+ },
760
+ {
761
+ "epoch": 6.76,
762
+ "learning_rate": 1.0789980732177264e-05,
763
+ "loss": 2.3359,
764
+ "step": 1170
765
+ },
766
+ {
767
+ "epoch": 6.82,
768
+ "learning_rate": 1.0597302504816956e-05,
769
+ "loss": 2.3163,
770
+ "step": 1180
771
+ },
772
+ {
773
+ "epoch": 6.88,
774
+ "learning_rate": 1.0404624277456647e-05,
775
+ "loss": 2.2941,
776
+ "step": 1190
777
+ },
778
+ {
779
+ "epoch": 6.93,
780
+ "learning_rate": 1.021194605009634e-05,
781
+ "loss": 2.3482,
782
+ "step": 1200
783
+ },
784
+ {
785
+ "epoch": 6.99,
786
+ "learning_rate": 1.0019267822736031e-05,
787
+ "loss": 2.3384,
788
+ "step": 1210
789
+ },
790
+ {
791
+ "epoch": 7.0,
792
+ "eval_accuracy": 0.26528532608695654,
793
+ "eval_loss": 2.797226905822754,
794
+ "eval_runtime": 52.6478,
795
+ "eval_samples_per_second": 111.838,
796
+ "eval_steps_per_second": 27.959,
797
+ "step": 1211
798
+ },
799
+ {
800
+ "epoch": 7.05,
801
+ "learning_rate": 9.826589595375721e-06,
802
+ "loss": 2.4462,
803
+ "step": 1220
804
+ },
805
+ {
806
+ "epoch": 7.11,
807
+ "learning_rate": 9.633911368015415e-06,
808
+ "loss": 2.3397,
809
+ "step": 1230
810
+ },
811
+ {
812
+ "epoch": 7.17,
813
+ "learning_rate": 9.441233140655105e-06,
814
+ "loss": 2.3068,
815
+ "step": 1240
816
+ },
817
+ {
818
+ "epoch": 7.22,
819
+ "learning_rate": 9.248554913294797e-06,
820
+ "loss": 2.2785,
821
+ "step": 1250
822
+ },
823
+ {
824
+ "epoch": 7.28,
825
+ "learning_rate": 9.055876685934489e-06,
826
+ "loss": 2.2983,
827
+ "step": 1260
828
+ },
829
+ {
830
+ "epoch": 7.34,
831
+ "learning_rate": 8.863198458574181e-06,
832
+ "loss": 2.2559,
833
+ "step": 1270
834
+ },
835
+ {
836
+ "epoch": 7.4,
837
+ "learning_rate": 8.670520231213873e-06,
838
+ "loss": 2.3161,
839
+ "step": 1280
840
+ },
841
+ {
842
+ "epoch": 7.46,
843
+ "learning_rate": 8.477842003853565e-06,
844
+ "loss": 2.2974,
845
+ "step": 1290
846
+ },
847
+ {
848
+ "epoch": 7.51,
849
+ "learning_rate": 8.285163776493255e-06,
850
+ "loss": 2.2194,
851
+ "step": 1300
852
+ },
853
+ {
854
+ "epoch": 7.57,
855
+ "learning_rate": 8.092485549132949e-06,
856
+ "loss": 2.2578,
857
+ "step": 1310
858
+ },
859
+ {
860
+ "epoch": 7.63,
861
+ "learning_rate": 7.899807321772639e-06,
862
+ "loss": 2.2955,
863
+ "step": 1320
864
+ },
865
+ {
866
+ "epoch": 7.69,
867
+ "learning_rate": 7.707129094412332e-06,
868
+ "loss": 2.2507,
869
+ "step": 1330
870
+ },
871
+ {
872
+ "epoch": 7.74,
873
+ "learning_rate": 7.5144508670520235e-06,
874
+ "loss": 2.2126,
875
+ "step": 1340
876
+ },
877
+ {
878
+ "epoch": 7.8,
879
+ "learning_rate": 7.321772639691715e-06,
880
+ "loss": 2.2839,
881
+ "step": 1350
882
+ },
883
+ {
884
+ "epoch": 7.86,
885
+ "learning_rate": 7.129094412331406e-06,
886
+ "loss": 2.2479,
887
+ "step": 1360
888
+ },
889
+ {
890
+ "epoch": 7.92,
891
+ "learning_rate": 6.936416184971098e-06,
892
+ "loss": 2.3274,
893
+ "step": 1370
894
+ },
895
+ {
896
+ "epoch": 7.97,
897
+ "learning_rate": 6.74373795761079e-06,
898
+ "loss": 2.2648,
899
+ "step": 1380
900
+ },
901
+ {
902
+ "epoch": 8.0,
903
+ "eval_accuracy": 0.26953125,
904
+ "eval_loss": 2.7625250816345215,
905
+ "eval_runtime": 52.8682,
906
+ "eval_samples_per_second": 111.371,
907
+ "eval_steps_per_second": 27.843,
908
+ "step": 1384
909
+ },
910
+ {
911
+ "epoch": 8.03,
912
+ "learning_rate": 6.551059730250482e-06,
913
+ "loss": 2.3574,
914
+ "step": 1390
915
+ },
916
+ {
917
+ "epoch": 8.09,
918
+ "learning_rate": 6.358381502890173e-06,
919
+ "loss": 2.2461,
920
+ "step": 1400
921
+ },
922
+ {
923
+ "epoch": 8.15,
924
+ "learning_rate": 6.165703275529865e-06,
925
+ "loss": 2.2491,
926
+ "step": 1410
927
+ },
928
+ {
929
+ "epoch": 8.21,
930
+ "learning_rate": 5.973025048169557e-06,
931
+ "loss": 2.248,
932
+ "step": 1420
933
+ },
934
+ {
935
+ "epoch": 8.27,
936
+ "learning_rate": 5.780346820809249e-06,
937
+ "loss": 2.1882,
938
+ "step": 1430
939
+ },
940
+ {
941
+ "epoch": 8.32,
942
+ "learning_rate": 5.587668593448941e-06,
943
+ "loss": 2.2115,
944
+ "step": 1440
945
+ },
946
+ {
947
+ "epoch": 8.38,
948
+ "learning_rate": 5.394990366088632e-06,
949
+ "loss": 2.1844,
950
+ "step": 1450
951
+ },
952
+ {
953
+ "epoch": 8.44,
954
+ "learning_rate": 5.202312138728324e-06,
955
+ "loss": 2.2053,
956
+ "step": 1460
957
+ },
958
+ {
959
+ "epoch": 8.5,
960
+ "learning_rate": 5.009633911368016e-06,
961
+ "loss": 2.2574,
962
+ "step": 1470
963
+ },
964
+ {
965
+ "epoch": 8.55,
966
+ "learning_rate": 4.8169556840077075e-06,
967
+ "loss": 2.206,
968
+ "step": 1480
969
+ },
970
+ {
971
+ "epoch": 8.61,
972
+ "learning_rate": 4.624277456647399e-06,
973
+ "loss": 2.1392,
974
+ "step": 1490
975
+ },
976
+ {
977
+ "epoch": 8.67,
978
+ "learning_rate": 4.4315992292870905e-06,
979
+ "loss": 2.216,
980
+ "step": 1500
981
+ },
982
+ {
983
+ "epoch": 8.73,
984
+ "learning_rate": 4.238921001926782e-06,
985
+ "loss": 2.237,
986
+ "step": 1510
987
+ },
988
+ {
989
+ "epoch": 8.78,
990
+ "learning_rate": 4.046242774566474e-06,
991
+ "loss": 2.2508,
992
+ "step": 1520
993
+ },
994
+ {
995
+ "epoch": 8.84,
996
+ "learning_rate": 3.853564547206166e-06,
997
+ "loss": 2.2308,
998
+ "step": 1530
999
+ },
1000
+ {
1001
+ "epoch": 8.9,
1002
+ "learning_rate": 3.6608863198458577e-06,
1003
+ "loss": 2.2232,
1004
+ "step": 1540
1005
+ },
1006
+ {
1007
+ "epoch": 8.96,
1008
+ "learning_rate": 3.468208092485549e-06,
1009
+ "loss": 2.2162,
1010
+ "step": 1550
1011
+ },
1012
+ {
1013
+ "epoch": 9.0,
1014
+ "eval_accuracy": 0.2781929347826087,
1015
+ "eval_loss": 2.74048113822937,
1016
+ "eval_runtime": 52.3324,
1017
+ "eval_samples_per_second": 112.512,
1018
+ "eval_steps_per_second": 28.128,
1019
+ "step": 1557
1020
+ },
1021
+ {
1022
+ "epoch": 9.02,
1023
+ "learning_rate": 3.275529865125241e-06,
1024
+ "loss": 2.3302,
1025
+ "step": 1560
1026
+ },
1027
+ {
1028
+ "epoch": 9.07,
1029
+ "learning_rate": 3.0828516377649325e-06,
1030
+ "loss": 2.1352,
1031
+ "step": 1570
1032
+ },
1033
+ {
1034
+ "epoch": 9.13,
1035
+ "learning_rate": 2.8901734104046244e-06,
1036
+ "loss": 2.1507,
1037
+ "step": 1580
1038
+ },
1039
+ {
1040
+ "epoch": 9.19,
1041
+ "learning_rate": 2.697495183044316e-06,
1042
+ "loss": 2.196,
1043
+ "step": 1590
1044
+ },
1045
+ {
1046
+ "epoch": 9.25,
1047
+ "learning_rate": 2.504816955684008e-06,
1048
+ "loss": 2.1476,
1049
+ "step": 1600
1050
+ },
1051
+ {
1052
+ "epoch": 9.31,
1053
+ "learning_rate": 2.3121387283236993e-06,
1054
+ "loss": 2.2158,
1055
+ "step": 1610
1056
+ },
1057
+ {
1058
+ "epoch": 9.36,
1059
+ "learning_rate": 2.119460500963391e-06,
1060
+ "loss": 2.2092,
1061
+ "step": 1620
1062
+ },
1063
+ {
1064
+ "epoch": 9.42,
1065
+ "learning_rate": 1.926782273603083e-06,
1066
+ "loss": 2.1339,
1067
+ "step": 1630
1068
+ },
1069
+ {
1070
+ "epoch": 9.48,
1071
+ "learning_rate": 1.7341040462427746e-06,
1072
+ "loss": 2.21,
1073
+ "step": 1640
1074
+ },
1075
+ {
1076
+ "epoch": 9.54,
1077
+ "learning_rate": 1.5414258188824663e-06,
1078
+ "loss": 2.1851,
1079
+ "step": 1650
1080
+ },
1081
+ {
1082
+ "epoch": 9.59,
1083
+ "learning_rate": 1.348747591522158e-06,
1084
+ "loss": 2.2059,
1085
+ "step": 1660
1086
+ },
1087
+ {
1088
+ "epoch": 9.65,
1089
+ "learning_rate": 1.1560693641618497e-06,
1090
+ "loss": 2.1826,
1091
+ "step": 1670
1092
+ },
1093
+ {
1094
+ "epoch": 9.71,
1095
+ "learning_rate": 9.633911368015416e-07,
1096
+ "loss": 2.2376,
1097
+ "step": 1680
1098
+ },
1099
+ {
1100
+ "epoch": 9.77,
1101
+ "learning_rate": 7.707129094412331e-07,
1102
+ "loss": 2.2424,
1103
+ "step": 1690
1104
+ },
1105
+ {
1106
+ "epoch": 9.82,
1107
+ "learning_rate": 5.780346820809248e-07,
1108
+ "loss": 2.1717,
1109
+ "step": 1700
1110
+ },
1111
+ {
1112
+ "epoch": 9.88,
1113
+ "learning_rate": 3.8535645472061657e-07,
1114
+ "loss": 2.1962,
1115
+ "step": 1710
1116
+ },
1117
+ {
1118
+ "epoch": 9.94,
1119
+ "learning_rate": 1.9267822736030828e-07,
1120
+ "loss": 2.1859,
1121
+ "step": 1720
1122
+ },
1123
+ {
1124
+ "epoch": 10.0,
1125
+ "learning_rate": 0.0,
1126
+ "loss": 2.1915,
1127
+ "step": 1730
1128
+ },
1129
+ {
1130
+ "epoch": 10.0,
1131
+ "eval_accuracy": 0.2797214673913043,
1132
+ "eval_loss": 2.7213878631591797,
1133
+ "eval_runtime": 52.7577,
1134
+ "eval_samples_per_second": 111.605,
1135
+ "eval_steps_per_second": 27.901,
1136
+ "step": 1730
1137
+ },
1138
+ {
1139
+ "epoch": 10.0,
1140
+ "step": 1730,
1141
+ "total_flos": 4.612789080268588e+18,
1142
+ "train_loss": 2.723648586162942,
1143
+ "train_runtime": 2280.0763,
1144
+ "train_samples_per_second": 97.339,
1145
+ "train_steps_per_second": 0.759
1146
+ }
1147
+ ],
1148
+ "max_steps": 1730,
1149
+ "num_train_epochs": 10,
1150
+ "total_flos": 4.612789080268588e+18,
1151
+ "trial_name": null,
1152
+ "trial_params": null
1153
+ }