JEdward7777 commited on
Commit
7fb93c7
1 Parent(s): adcc6fe

End of training

Browse files
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 39.86,
3
  "eval_accuracy": 1.0,
4
- "eval_loss": 0.026065116748213768,
5
- "eval_runtime": 3.2422,
6
- "eval_samples_per_second": 14.805,
7
- "eval_steps_per_second": 0.617,
8
- "total_flos": 4.264272913587241e+17,
9
- "train_loss": 0.1722367246945699,
10
- "train_runtime": 1999.9903,
11
- "train_samples_per_second": 8.6,
12
- "train_steps_per_second": 0.06
13
  }
 
1
  {
2
  "epoch": 39.86,
3
  "eval_accuracy": 1.0,
4
+ "eval_loss": 0.04471803084015846,
5
+ "eval_runtime": 3.4855,
6
+ "eval_samples_per_second": 14.058,
7
+ "eval_steps_per_second": 0.574,
8
+ "total_flos": 4.283662751949128e+17,
9
+ "train_loss": 0.5828357299168905,
10
+ "train_runtime": 1853.5405,
11
+ "train_samples_per_second": 9.323,
12
+ "train_steps_per_second": 0.065
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 39.86,
3
  "eval_accuracy": 1.0,
4
- "eval_loss": 0.026065116748213768,
5
- "eval_runtime": 3.2422,
6
- "eval_samples_per_second": 14.805,
7
- "eval_steps_per_second": 0.617
8
  }
 
1
  {
2
  "epoch": 39.86,
3
  "eval_accuracy": 1.0,
4
+ "eval_loss": 0.04471803084015846,
5
+ "eval_runtime": 3.4855,
6
+ "eval_samples_per_second": 14.058,
7
+ "eval_steps_per_second": 0.574
8
  }
runs/Oct24_13-49-06_8582a94b2abd/events.out.tfevents.1666621505.8582a94b2abd.75.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07926b9e10cd0c815963fb82432b5a6754568f45a6dde40b66527c0deffbeddc
3
+ size 357
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 39.86,
3
- "total_flos": 4.264272913587241e+17,
4
- "train_loss": 0.1722367246945699,
5
- "train_runtime": 1999.9903,
6
- "train_samples_per_second": 8.6,
7
- "train_steps_per_second": 0.06
8
  }
 
1
  {
2
  "epoch": 39.86,
3
+ "total_flos": 4.283662751949128e+17,
4
+ "train_loss": 0.5828357299168905,
5
+ "train_runtime": 1853.5405,
6
+ "train_samples_per_second": 9.323,
7
+ "train_steps_per_second": 0.065
8
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "best_metric": 1.0,
3
- "best_model_checkpoint": "delivery_truck_classification/checkpoint-3",
4
  "epoch": 39.857142857142854,
5
  "global_step": 120,
6
  "is_hyper_param_search": false,
@@ -9,413 +9,413 @@
9
  "log_history": [
10
  {
11
  "epoch": 0.86,
12
- "eval_accuracy": 1.0,
13
- "eval_loss": 0.026065116748213768,
14
- "eval_runtime": 3.4495,
15
- "eval_samples_per_second": 13.915,
16
- "eval_steps_per_second": 0.58,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 1.86,
21
- "eval_accuracy": 1.0,
22
- "eval_loss": 0.024647483602166176,
23
- "eval_runtime": 3.9431,
24
- "eval_samples_per_second": 12.173,
25
- "eval_steps_per_second": 0.507,
26
  "step": 6
27
  },
28
  {
29
  "epoch": 2.86,
30
- "eval_accuracy": 0.9791666666666666,
31
- "eval_loss": 0.035011451691389084,
32
- "eval_runtime": 3.4736,
33
- "eval_samples_per_second": 13.818,
34
- "eval_steps_per_second": 0.576,
35
  "step": 9
36
  },
37
  {
38
  "epoch": 3.86,
39
- "eval_accuracy": 1.0,
40
- "eval_loss": 0.029779432341456413,
41
- "eval_runtime": 3.1788,
42
- "eval_samples_per_second": 15.1,
43
- "eval_steps_per_second": 0.629,
44
  "step": 12
45
  },
46
  {
47
  "epoch": 4.86,
48
- "eval_accuracy": 0.9791666666666666,
49
- "eval_loss": 0.036166682839393616,
50
- "eval_runtime": 3.497,
51
- "eval_samples_per_second": 13.726,
52
- "eval_steps_per_second": 0.572,
53
  "step": 15
54
  },
55
  {
56
  "epoch": 5.86,
57
- "eval_accuracy": 0.9791666666666666,
58
- "eval_loss": 0.05407286807894707,
59
- "eval_runtime": 3.4858,
60
- "eval_samples_per_second": 13.77,
61
- "eval_steps_per_second": 0.574,
62
  "step": 18
63
  },
64
  {
65
  "epoch": 6.57,
66
  "learning_rate": 4.62962962962963e-05,
67
- "loss": 0.2214,
68
  "step": 20
69
  },
70
  {
71
  "epoch": 6.86,
72
- "eval_accuracy": 0.9791666666666666,
73
- "eval_loss": 0.03632530942559242,
74
- "eval_runtime": 3.1393,
75
- "eval_samples_per_second": 15.29,
76
- "eval_steps_per_second": 0.637,
77
  "step": 21
78
  },
79
  {
80
  "epoch": 7.86,
81
- "eval_accuracy": 1.0,
82
- "eval_loss": 0.02213350497186184,
83
- "eval_runtime": 3.7451,
84
- "eval_samples_per_second": 12.817,
85
- "eval_steps_per_second": 0.534,
86
  "step": 24
87
  },
88
  {
89
  "epoch": 8.86,
90
- "eval_accuracy": 0.9791666666666666,
91
- "eval_loss": 0.03659434616565704,
92
- "eval_runtime": 3.4556,
93
- "eval_samples_per_second": 13.89,
94
- "eval_steps_per_second": 0.579,
95
  "step": 27
96
  },
97
  {
98
  "epoch": 9.86,
99
- "eval_accuracy": 0.9791666666666666,
100
- "eval_loss": 0.05018351972103119,
101
- "eval_runtime": 3.2792,
102
- "eval_samples_per_second": 14.638,
103
- "eval_steps_per_second": 0.61,
104
  "step": 30
105
  },
106
  {
107
  "epoch": 10.86,
108
- "eval_accuracy": 0.9791666666666666,
109
- "eval_loss": 0.03546701744198799,
110
- "eval_runtime": 3.4963,
111
- "eval_samples_per_second": 13.729,
112
- "eval_steps_per_second": 0.572,
113
  "step": 33
114
  },
115
  {
116
  "epoch": 11.86,
117
- "eval_accuracy": 1.0,
118
- "eval_loss": 0.021759234368801117,
119
- "eval_runtime": 3.5458,
120
- "eval_samples_per_second": 13.537,
121
- "eval_steps_per_second": 0.564,
122
  "step": 36
123
  },
124
  {
125
  "epoch": 12.86,
126
- "eval_accuracy": 1.0,
127
- "eval_loss": 0.014033220708370209,
128
- "eval_runtime": 3.2728,
129
- "eval_samples_per_second": 14.666,
130
- "eval_steps_per_second": 0.611,
131
  "step": 39
132
  },
133
  {
134
  "epoch": 13.29,
135
  "learning_rate": 3.7037037037037037e-05,
136
- "loss": 0.183,
137
  "step": 40
138
  },
139
  {
140
  "epoch": 13.86,
141
- "eval_accuracy": 1.0,
142
- "eval_loss": 0.017221327871084213,
143
- "eval_runtime": 3.4953,
144
- "eval_samples_per_second": 13.733,
145
- "eval_steps_per_second": 0.572,
146
  "step": 42
147
  },
148
  {
149
  "epoch": 14.86,
150
- "eval_accuracy": 0.9791666666666666,
151
- "eval_loss": 0.03003031760454178,
152
- "eval_runtime": 3.4946,
153
- "eval_samples_per_second": 13.735,
154
- "eval_steps_per_second": 0.572,
155
  "step": 45
156
  },
157
  {
158
  "epoch": 15.86,
159
- "eval_accuracy": 0.9791666666666666,
160
- "eval_loss": 0.058922749012708664,
161
- "eval_runtime": 3.184,
162
- "eval_samples_per_second": 15.075,
163
- "eval_steps_per_second": 0.628,
164
  "step": 48
165
  },
166
  {
167
  "epoch": 16.86,
168
- "eval_accuracy": 0.9791666666666666,
169
- "eval_loss": 0.06934068351984024,
170
- "eval_runtime": 3.4776,
171
- "eval_samples_per_second": 13.803,
172
- "eval_steps_per_second": 0.575,
173
  "step": 51
174
  },
175
  {
176
  "epoch": 17.86,
177
- "eval_accuracy": 0.9791666666666666,
178
- "eval_loss": 0.04955345392227173,
179
- "eval_runtime": 3.6895,
180
- "eval_samples_per_second": 13.01,
181
- "eval_steps_per_second": 0.542,
182
  "step": 54
183
  },
184
  {
185
  "epoch": 18.86,
186
- "eval_accuracy": 0.9791666666666666,
187
- "eval_loss": 0.03155900537967682,
188
- "eval_runtime": 3.1541,
189
- "eval_samples_per_second": 15.218,
190
- "eval_steps_per_second": 0.634,
191
  "step": 57
192
  },
193
  {
194
  "epoch": 19.86,
195
  "learning_rate": 2.777777777777778e-05,
196
- "loss": 0.1706,
197
  "step": 60
198
  },
199
  {
200
  "epoch": 19.86,
201
- "eval_accuracy": 0.9791666666666666,
202
- "eval_loss": 0.03406331315636635,
203
- "eval_runtime": 4.5532,
204
- "eval_samples_per_second": 10.542,
205
- "eval_steps_per_second": 0.439,
206
  "step": 60
207
  },
208
  {
209
  "epoch": 20.86,
210
- "eval_accuracy": 0.9791666666666666,
211
- "eval_loss": 0.03481491655111313,
212
- "eval_runtime": 3.4718,
213
- "eval_samples_per_second": 13.826,
214
- "eval_steps_per_second": 0.576,
215
  "step": 63
216
  },
217
  {
218
  "epoch": 21.86,
219
- "eval_accuracy": 0.9791666666666666,
220
- "eval_loss": 0.03439461812376976,
221
- "eval_runtime": 3.2108,
222
- "eval_samples_per_second": 14.949,
223
- "eval_steps_per_second": 0.623,
224
  "step": 66
225
  },
226
  {
227
  "epoch": 22.86,
228
- "eval_accuracy": 0.9791666666666666,
229
- "eval_loss": 0.04687784984707832,
230
- "eval_runtime": 3.5128,
231
- "eval_samples_per_second": 13.664,
232
- "eval_steps_per_second": 0.569,
233
  "step": 69
234
  },
235
  {
236
  "epoch": 23.86,
237
- "eval_accuracy": 0.9791666666666666,
238
- "eval_loss": 0.05970446392893791,
239
- "eval_runtime": 3.7464,
240
- "eval_samples_per_second": 12.812,
241
- "eval_steps_per_second": 0.534,
242
  "step": 72
243
  },
244
  {
245
  "epoch": 24.86,
246
- "eval_accuracy": 0.9791666666666666,
247
- "eval_loss": 0.05298614129424095,
248
- "eval_runtime": 3.1637,
249
- "eval_samples_per_second": 15.172,
250
- "eval_steps_per_second": 0.632,
251
  "step": 75
252
  },
253
  {
254
  "epoch": 25.86,
255
- "eval_accuracy": 0.9791666666666666,
256
- "eval_loss": 0.040230389684438705,
257
- "eval_runtime": 3.5114,
258
- "eval_samples_per_second": 13.67,
259
- "eval_steps_per_second": 0.57,
260
  "step": 78
261
  },
262
  {
263
  "epoch": 26.57,
264
  "learning_rate": 1.8518518518518518e-05,
265
- "loss": 0.1644,
266
  "step": 80
267
  },
268
  {
269
  "epoch": 26.86,
270
- "eval_accuracy": 0.9791666666666666,
271
- "eval_loss": 0.03619036078453064,
272
- "eval_runtime": 3.7338,
273
- "eval_samples_per_second": 12.856,
274
- "eval_steps_per_second": 0.536,
275
  "step": 81
276
  },
277
  {
278
  "epoch": 27.86,
279
- "eval_accuracy": 0.9791666666666666,
280
- "eval_loss": 0.038440290838479996,
281
- "eval_runtime": 3.2337,
282
- "eval_samples_per_second": 14.844,
283
- "eval_steps_per_second": 0.618,
284
  "step": 84
285
  },
286
  {
287
  "epoch": 28.86,
288
- "eval_accuracy": 0.9791666666666666,
289
- "eval_loss": 0.03096356801688671,
290
- "eval_runtime": 3.4785,
291
- "eval_samples_per_second": 13.799,
292
- "eval_steps_per_second": 0.575,
293
  "step": 87
294
  },
295
  {
296
  "epoch": 29.86,
297
- "eval_accuracy": 0.9791666666666666,
298
- "eval_loss": 0.02927880547940731,
299
- "eval_runtime": 3.5018,
300
- "eval_samples_per_second": 13.707,
301
- "eval_steps_per_second": 0.571,
302
  "step": 90
303
  },
304
  {
305
  "epoch": 30.86,
306
- "eval_accuracy": 0.9791666666666666,
307
- "eval_loss": 0.03753955289721489,
308
- "eval_runtime": 3.2739,
309
- "eval_samples_per_second": 14.662,
310
- "eval_steps_per_second": 0.611,
311
  "step": 93
312
  },
313
  {
314
  "epoch": 31.86,
315
- "eval_accuracy": 0.9791666666666666,
316
- "eval_loss": 0.04604535177350044,
317
- "eval_runtime": 3.9083,
318
- "eval_samples_per_second": 12.282,
319
- "eval_steps_per_second": 0.512,
320
  "step": 96
321
  },
322
  {
323
  "epoch": 32.86,
324
- "eval_accuracy": 0.9791666666666666,
325
- "eval_loss": 0.05220605805516243,
326
- "eval_runtime": 3.4983,
327
- "eval_samples_per_second": 13.721,
328
- "eval_steps_per_second": 0.572,
329
  "step": 99
330
  },
331
  {
332
  "epoch": 33.29,
333
  "learning_rate": 9.259259259259259e-06,
334
- "loss": 0.1539,
335
  "step": 100
336
  },
337
  {
338
  "epoch": 33.86,
339
- "eval_accuracy": 0.9791666666666666,
340
- "eval_loss": 0.05513928830623627,
341
- "eval_runtime": 3.1674,
342
- "eval_samples_per_second": 15.154,
343
- "eval_steps_per_second": 0.631,
344
  "step": 102
345
  },
346
  {
347
  "epoch": 34.86,
348
- "eval_accuracy": 0.9791666666666666,
349
- "eval_loss": 0.05517812445759773,
350
- "eval_runtime": 3.4831,
351
- "eval_samples_per_second": 13.781,
352
- "eval_steps_per_second": 0.574,
353
  "step": 105
354
  },
355
  {
356
  "epoch": 35.86,
357
- "eval_accuracy": 0.9791666666666666,
358
- "eval_loss": 0.054359838366508484,
359
- "eval_runtime": 3.6987,
360
- "eval_samples_per_second": 12.977,
361
- "eval_steps_per_second": 0.541,
362
  "step": 108
363
  },
364
  {
365
  "epoch": 36.86,
366
- "eval_accuracy": 0.9791666666666666,
367
- "eval_loss": 0.05520467087626457,
368
- "eval_runtime": 3.1659,
369
- "eval_samples_per_second": 15.162,
370
- "eval_steps_per_second": 0.632,
371
  "step": 111
372
  },
373
  {
374
  "epoch": 37.86,
375
- "eval_accuracy": 0.9791666666666666,
376
- "eval_loss": 0.054130103439092636,
377
- "eval_runtime": 3.4868,
378
- "eval_samples_per_second": 13.766,
379
- "eval_steps_per_second": 0.574,
380
  "step": 114
381
  },
382
  {
383
  "epoch": 38.86,
384
- "eval_accuracy": 0.9791666666666666,
385
- "eval_loss": 0.0525875948369503,
386
- "eval_runtime": 3.4473,
387
- "eval_samples_per_second": 13.924,
388
- "eval_steps_per_second": 0.58,
389
  "step": 117
390
  },
391
  {
392
  "epoch": 39.86,
393
  "learning_rate": 0.0,
394
- "loss": 0.1401,
395
  "step": 120
396
  },
397
  {
398
  "epoch": 39.86,
399
- "eval_accuracy": 0.9791666666666666,
400
- "eval_loss": 0.05150062218308449,
401
- "eval_runtime": 3.1357,
402
- "eval_samples_per_second": 15.308,
403
- "eval_steps_per_second": 0.638,
404
  "step": 120
405
  },
406
  {
407
  "epoch": 39.86,
408
  "step": 120,
409
- "total_flos": 4.264272913587241e+17,
410
- "train_loss": 0.1722367246945699,
411
- "train_runtime": 1999.9903,
412
- "train_samples_per_second": 8.6,
413
- "train_steps_per_second": 0.06
414
  }
415
  ],
416
  "max_steps": 120,
417
  "num_train_epochs": 40,
418
- "total_flos": 4.264272913587241e+17,
419
  "trial_name": null,
420
  "trial_params": null
421
  }
 
1
  {
2
  "best_metric": 1.0,
3
+ "best_model_checkpoint": "delivery_truck_classification/checkpoint-93",
4
  "epoch": 39.857142857142854,
5
  "global_step": 120,
6
  "is_hyper_param_search": false,
 
9
  "log_history": [
10
  {
11
  "epoch": 0.86,
12
+ "eval_accuracy": 0.22448979591836735,
13
+ "eval_loss": 1.7165862321853638,
14
+ "eval_runtime": 3.3593,
15
+ "eval_samples_per_second": 14.586,
16
+ "eval_steps_per_second": 0.595,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 1.86,
21
+ "eval_accuracy": 0.40816326530612246,
22
+ "eval_loss": 1.5815682411193848,
23
+ "eval_runtime": 3.8537,
24
+ "eval_samples_per_second": 12.715,
25
+ "eval_steps_per_second": 0.519,
26
  "step": 6
27
  },
28
  {
29
  "epoch": 2.86,
30
+ "eval_accuracy": 0.5510204081632653,
31
+ "eval_loss": 1.4084097146987915,
32
+ "eval_runtime": 3.6101,
33
+ "eval_samples_per_second": 13.573,
34
+ "eval_steps_per_second": 0.554,
35
  "step": 9
36
  },
37
  {
38
  "epoch": 3.86,
39
+ "eval_accuracy": 0.6326530612244898,
40
+ "eval_loss": 1.1761205196380615,
41
+ "eval_runtime": 3.605,
42
+ "eval_samples_per_second": 13.592,
43
+ "eval_steps_per_second": 0.555,
44
  "step": 12
45
  },
46
  {
47
  "epoch": 4.86,
48
+ "eval_accuracy": 0.7346938775510204,
49
+ "eval_loss": 0.924461841583252,
50
+ "eval_runtime": 3.397,
51
+ "eval_samples_per_second": 14.424,
52
+ "eval_steps_per_second": 0.589,
53
  "step": 15
54
  },
55
  {
56
  "epoch": 5.86,
57
+ "eval_accuracy": 0.7959183673469388,
58
+ "eval_loss": 0.6986315250396729,
59
+ "eval_runtime": 3.6429,
60
+ "eval_samples_per_second": 13.451,
61
+ "eval_steps_per_second": 0.549,
62
  "step": 18
63
  },
64
  {
65
  "epoch": 6.57,
66
  "learning_rate": 4.62962962962963e-05,
67
+ "loss": 1.608,
68
  "step": 20
69
  },
70
  {
71
  "epoch": 6.86,
72
+ "eval_accuracy": 0.8367346938775511,
73
+ "eval_loss": 0.5158075094223022,
74
+ "eval_runtime": 3.6761,
75
+ "eval_samples_per_second": 13.329,
76
+ "eval_steps_per_second": 0.544,
77
  "step": 21
78
  },
79
  {
80
  "epoch": 7.86,
81
+ "eval_accuracy": 0.8775510204081632,
82
+ "eval_loss": 0.37532907724380493,
83
+ "eval_runtime": 3.6821,
84
+ "eval_samples_per_second": 13.308,
85
+ "eval_steps_per_second": 0.543,
86
  "step": 24
87
  },
88
  {
89
  "epoch": 8.86,
90
+ "eval_accuracy": 0.8979591836734694,
91
+ "eval_loss": 0.30922260880470276,
92
+ "eval_runtime": 3.4322,
93
+ "eval_samples_per_second": 14.276,
94
+ "eval_steps_per_second": 0.583,
95
  "step": 27
96
  },
97
  {
98
  "epoch": 9.86,
99
+ "eval_accuracy": 0.9387755102040817,
100
+ "eval_loss": 0.2584000825881958,
101
+ "eval_runtime": 3.7632,
102
+ "eval_samples_per_second": 13.021,
103
+ "eval_steps_per_second": 0.531,
104
  "step": 30
105
  },
106
  {
107
  "epoch": 10.86,
108
+ "eval_accuracy": 0.9183673469387755,
109
+ "eval_loss": 0.2158631533384323,
110
+ "eval_runtime": 3.7248,
111
+ "eval_samples_per_second": 13.155,
112
+ "eval_steps_per_second": 0.537,
113
  "step": 33
114
  },
115
  {
116
  "epoch": 11.86,
117
+ "eval_accuracy": 0.9591836734693877,
118
+ "eval_loss": 0.19079165160655975,
119
+ "eval_runtime": 3.4555,
120
+ "eval_samples_per_second": 14.18,
121
+ "eval_steps_per_second": 0.579,
122
  "step": 36
123
  },
124
  {
125
  "epoch": 12.86,
126
+ "eval_accuracy": 0.9591836734693877,
127
+ "eval_loss": 0.1801912933588028,
128
+ "eval_runtime": 3.6849,
129
+ "eval_samples_per_second": 13.298,
130
+ "eval_steps_per_second": 0.543,
131
  "step": 39
132
  },
133
  {
134
  "epoch": 13.29,
135
  "learning_rate": 3.7037037037037037e-05,
136
+ "loss": 0.6473,
137
  "step": 40
138
  },
139
  {
140
  "epoch": 13.86,
141
+ "eval_accuracy": 0.9591836734693877,
142
+ "eval_loss": 0.16818924248218536,
143
+ "eval_runtime": 3.6554,
144
+ "eval_samples_per_second": 13.405,
145
+ "eval_steps_per_second": 0.547,
146
  "step": 42
147
  },
148
  {
149
  "epoch": 14.86,
150
+ "eval_accuracy": 0.9591836734693877,
151
+ "eval_loss": 0.15600401163101196,
152
+ "eval_runtime": 3.4217,
153
+ "eval_samples_per_second": 14.32,
154
+ "eval_steps_per_second": 0.585,
155
  "step": 45
156
  },
157
  {
158
  "epoch": 15.86,
159
+ "eval_accuracy": 0.9591836734693877,
160
+ "eval_loss": 0.13216617703437805,
161
+ "eval_runtime": 3.736,
162
+ "eval_samples_per_second": 13.116,
163
+ "eval_steps_per_second": 0.535,
164
  "step": 48
165
  },
166
  {
167
  "epoch": 16.86,
168
+ "eval_accuracy": 0.9591836734693877,
169
+ "eval_loss": 0.11014676839113235,
170
+ "eval_runtime": 3.6145,
171
+ "eval_samples_per_second": 13.557,
172
+ "eval_steps_per_second": 0.553,
173
  "step": 51
174
  },
175
  {
176
  "epoch": 17.86,
177
+ "eval_accuracy": 0.9591836734693877,
178
+ "eval_loss": 0.0938219353556633,
179
+ "eval_runtime": 3.6148,
180
+ "eval_samples_per_second": 13.555,
181
+ "eval_steps_per_second": 0.553,
182
  "step": 54
183
  },
184
  {
185
  "epoch": 18.86,
186
+ "eval_accuracy": 0.9795918367346939,
187
+ "eval_loss": 0.08886948227882385,
188
+ "eval_runtime": 3.3763,
189
+ "eval_samples_per_second": 14.513,
190
+ "eval_steps_per_second": 0.592,
191
  "step": 57
192
  },
193
  {
194
  "epoch": 19.86,
195
  "learning_rate": 2.777777777777778e-05,
196
+ "loss": 0.3855,
197
  "step": 60
198
  },
199
  {
200
  "epoch": 19.86,
201
+ "eval_accuracy": 0.9795918367346939,
202
+ "eval_loss": 0.10251900553703308,
203
+ "eval_runtime": 3.6959,
204
+ "eval_samples_per_second": 13.258,
205
+ "eval_steps_per_second": 0.541,
206
  "step": 60
207
  },
208
  {
209
  "epoch": 20.86,
210
+ "eval_accuracy": 0.9795918367346939,
211
+ "eval_loss": 0.09841162711381912,
212
+ "eval_runtime": 3.6698,
213
+ "eval_samples_per_second": 13.352,
214
+ "eval_steps_per_second": 0.545,
215
  "step": 63
216
  },
217
  {
218
  "epoch": 21.86,
219
+ "eval_accuracy": 0.9591836734693877,
220
+ "eval_loss": 0.08669053018093109,
221
+ "eval_runtime": 3.4251,
222
+ "eval_samples_per_second": 14.306,
223
+ "eval_steps_per_second": 0.584,
224
  "step": 66
225
  },
226
  {
227
  "epoch": 22.86,
228
+ "eval_accuracy": 0.9591836734693877,
229
+ "eval_loss": 0.08126597851514816,
230
+ "eval_runtime": 3.4044,
231
+ "eval_samples_per_second": 14.393,
232
+ "eval_steps_per_second": 0.587,
233
  "step": 69
234
  },
235
  {
236
  "epoch": 23.86,
237
+ "eval_accuracy": 0.9591836734693877,
238
+ "eval_loss": 0.07681093364953995,
239
+ "eval_runtime": 3.6377,
240
+ "eval_samples_per_second": 13.47,
241
+ "eval_steps_per_second": 0.55,
242
  "step": 72
243
  },
244
  {
245
  "epoch": 24.86,
246
+ "eval_accuracy": 0.9795918367346939,
247
+ "eval_loss": 0.07339165359735489,
248
+ "eval_runtime": 3.6437,
249
+ "eval_samples_per_second": 13.448,
250
+ "eval_steps_per_second": 0.549,
251
  "step": 75
252
  },
253
  {
254
  "epoch": 25.86,
255
+ "eval_accuracy": 0.9795918367346939,
256
+ "eval_loss": 0.0697600468993187,
257
+ "eval_runtime": 3.6092,
258
+ "eval_samples_per_second": 13.577,
259
+ "eval_steps_per_second": 0.554,
260
  "step": 78
261
  },
262
  {
263
  "epoch": 26.57,
264
  "learning_rate": 1.8518518518518518e-05,
265
+ "loss": 0.306,
266
  "step": 80
267
  },
268
  {
269
  "epoch": 26.86,
270
+ "eval_accuracy": 0.9591836734693877,
271
+ "eval_loss": 0.061838988214731216,
272
+ "eval_runtime": 3.3297,
273
+ "eval_samples_per_second": 14.716,
274
+ "eval_steps_per_second": 0.601,
275
  "step": 81
276
  },
277
  {
278
  "epoch": 27.86,
279
+ "eval_accuracy": 0.9795918367346939,
280
+ "eval_loss": 0.05467281490564346,
281
+ "eval_runtime": 3.6132,
282
+ "eval_samples_per_second": 13.562,
283
+ "eval_steps_per_second": 0.554,
284
  "step": 84
285
  },
286
  {
287
  "epoch": 28.86,
288
+ "eval_accuracy": 0.9591836734693877,
289
+ "eval_loss": 0.053797200322151184,
290
+ "eval_runtime": 3.6286,
291
+ "eval_samples_per_second": 13.504,
292
+ "eval_steps_per_second": 0.551,
293
  "step": 87
294
  },
295
  {
296
  "epoch": 29.86,
297
+ "eval_accuracy": 0.9795918367346939,
298
+ "eval_loss": 0.048745423555374146,
299
+ "eval_runtime": 3.5673,
300
+ "eval_samples_per_second": 13.736,
301
+ "eval_steps_per_second": 0.561,
302
  "step": 90
303
  },
304
  {
305
  "epoch": 30.86,
306
+ "eval_accuracy": 1.0,
307
+ "eval_loss": 0.04471803084015846,
308
+ "eval_runtime": 3.3732,
309
+ "eval_samples_per_second": 14.526,
310
+ "eval_steps_per_second": 0.593,
311
  "step": 93
312
  },
313
  {
314
  "epoch": 31.86,
315
+ "eval_accuracy": 1.0,
316
+ "eval_loss": 0.04248499870300293,
317
+ "eval_runtime": 3.634,
318
+ "eval_samples_per_second": 13.484,
319
+ "eval_steps_per_second": 0.55,
320
  "step": 96
321
  },
322
  {
323
  "epoch": 32.86,
324
+ "eval_accuracy": 1.0,
325
+ "eval_loss": 0.04510816931724548,
326
+ "eval_runtime": 3.5707,
327
+ "eval_samples_per_second": 13.723,
328
+ "eval_steps_per_second": 0.56,
329
  "step": 99
330
  },
331
  {
332
  "epoch": 33.29,
333
  "learning_rate": 9.259259259259259e-06,
334
+ "loss": 0.2966,
335
  "step": 100
336
  },
337
  {
338
  "epoch": 33.86,
339
+ "eval_accuracy": 1.0,
340
+ "eval_loss": 0.04972054436802864,
341
+ "eval_runtime": 3.5902,
342
+ "eval_samples_per_second": 13.648,
343
+ "eval_steps_per_second": 0.557,
344
  "step": 102
345
  },
346
  {
347
  "epoch": 34.86,
348
+ "eval_accuracy": 1.0,
349
+ "eval_loss": 0.05577036738395691,
350
+ "eval_runtime": 3.3881,
351
+ "eval_samples_per_second": 14.462,
352
+ "eval_steps_per_second": 0.59,
353
  "step": 105
354
  },
355
  {
356
  "epoch": 35.86,
357
+ "eval_accuracy": 0.9795918367346939,
358
+ "eval_loss": 0.05818271264433861,
359
+ "eval_runtime": 3.6322,
360
+ "eval_samples_per_second": 13.491,
361
+ "eval_steps_per_second": 0.551,
362
  "step": 108
363
  },
364
  {
365
  "epoch": 36.86,
366
+ "eval_accuracy": 0.9591836734693877,
367
+ "eval_loss": 0.061642248183488846,
368
+ "eval_runtime": 3.5883,
369
+ "eval_samples_per_second": 13.655,
370
+ "eval_steps_per_second": 0.557,
371
  "step": 111
372
  },
373
  {
374
  "epoch": 37.86,
375
+ "eval_accuracy": 0.9591836734693877,
376
+ "eval_loss": 0.06565477699041367,
377
+ "eval_runtime": 3.6509,
378
+ "eval_samples_per_second": 13.421,
379
+ "eval_steps_per_second": 0.548,
380
  "step": 114
381
  },
382
  {
383
  "epoch": 38.86,
384
+ "eval_accuracy": 0.9591836734693877,
385
+ "eval_loss": 0.067948117852211,
386
+ "eval_runtime": 3.3455,
387
+ "eval_samples_per_second": 14.647,
388
+ "eval_steps_per_second": 0.598,
389
  "step": 117
390
  },
391
  {
392
  "epoch": 39.86,
393
  "learning_rate": 0.0,
394
+ "loss": 0.2535,
395
  "step": 120
396
  },
397
  {
398
  "epoch": 39.86,
399
+ "eval_accuracy": 0.9591836734693877,
400
+ "eval_loss": 0.06835878640413284,
401
+ "eval_runtime": 3.6892,
402
+ "eval_samples_per_second": 13.282,
403
+ "eval_steps_per_second": 0.542,
404
  "step": 120
405
  },
406
  {
407
  "epoch": 39.86,
408
  "step": 120,
409
+ "total_flos": 4.283662751949128e+17,
410
+ "train_loss": 0.5828357299168905,
411
+ "train_runtime": 1853.5405,
412
+ "train_samples_per_second": 9.323,
413
+ "train_steps_per_second": 0.065
414
  }
415
  ],
416
  "max_steps": 120,
417
  "num_train_epochs": 40,
418
+ "total_flos": 4.283662751949128e+17,
419
  "trial_name": null,
420
  "trial_params": null
421
  }