JEdward7777 commited on
Commit
86ef599
1 Parent(s): 12e944a

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": 0.04471803084015846,
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
  }
 
1
  {
2
+ "epoch": 39.8,
3
  "eval_accuracy": 1.0,
4
+ "eval_loss": 0.18712519109249115,
5
+ "eval_runtime": 3.4703,
6
+ "eval_samples_per_second": 14.696,
7
+ "eval_steps_per_second": 0.576,
8
+ "total_flos": 4.535730650653655e+17,
9
+ "train_loss": 0.6862462480862935,
10
+ "train_runtime": 1980.068,
11
+ "train_samples_per_second": 9.252,
12
+ "train_steps_per_second": 0.061
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
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
  }
 
1
  {
2
+ "epoch": 39.8,
3
  "eval_accuracy": 1.0,
4
+ "eval_loss": 0.18712519109249115,
5
+ "eval_runtime": 3.4703,
6
+ "eval_samples_per_second": 14.696,
7
+ "eval_steps_per_second": 0.576
8
  }
runs/Nov14_14-58-22_9bda67708a3a/events.out.tfevents.1668440211.9bda67708a3a.78.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65cbad3ab0c60afde627394f4a636ea1711a5a7854984e8083a800113cb060a
3
+ size 357
train_results.json CHANGED
@@ -1,8 +1,8 @@
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
  }
 
1
  {
2
+ "epoch": 39.8,
3
+ "total_flos": 4.535730650653655e+17,
4
+ "train_loss": 0.6862462480862935,
5
+ "train_runtime": 1980.068,
6
+ "train_samples_per_second": 9.252,
7
+ "train_steps_per_second": 0.061
8
  }
trainer_state.json CHANGED
@@ -1,421 +1,421 @@
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,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
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
  }
 
1
  {
2
  "best_metric": 1.0,
3
+ "best_model_checkpoint": "delivery_truck_classification/checkpoint-33",
4
+ "epoch": 39.8,
5
  "global_step": 120,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 0.8,
12
+ "eval_accuracy": 0.0392156862745098,
13
+ "eval_loss": 1.8911739587783813,
14
+ "eval_runtime": 3.471,
15
+ "eval_samples_per_second": 14.693,
16
+ "eval_steps_per_second": 0.576,
17
  "step": 3
18
  },
19
  {
20
+ "epoch": 1.8,
21
+ "eval_accuracy": 0.27450980392156865,
22
+ "eval_loss": 1.7519241571426392,
23
+ "eval_runtime": 3.9826,
24
+ "eval_samples_per_second": 12.806,
25
+ "eval_steps_per_second": 0.502,
26
  "step": 6
27
  },
28
  {
29
+ "epoch": 2.8,
30
+ "eval_accuracy": 0.47058823529411764,
31
+ "eval_loss": 1.5549100637435913,
32
+ "eval_runtime": 3.7484,
33
+ "eval_samples_per_second": 13.606,
34
+ "eval_steps_per_second": 0.534,
35
  "step": 9
36
  },
37
  {
38
+ "epoch": 3.8,
39
+ "eval_accuracy": 0.6666666666666666,
40
+ "eval_loss": 1.2850992679595947,
41
+ "eval_runtime": 3.3946,
42
+ "eval_samples_per_second": 15.024,
43
+ "eval_steps_per_second": 0.589,
44
  "step": 12
45
  },
46
  {
47
+ "epoch": 4.8,
48
+ "eval_accuracy": 0.7647058823529411,
49
+ "eval_loss": 0.9967808723449707,
50
+ "eval_runtime": 3.7653,
51
+ "eval_samples_per_second": 13.545,
52
+ "eval_steps_per_second": 0.531,
53
  "step": 15
54
  },
55
  {
56
+ "epoch": 5.8,
57
+ "eval_accuracy": 0.7843137254901961,
58
+ "eval_loss": 0.7825759649276733,
59
+ "eval_runtime": 3.7762,
60
+ "eval_samples_per_second": 13.506,
61
+ "eval_steps_per_second": 0.53,
62
  "step": 18
63
  },
64
  {
65
+ "epoch": 6.53,
66
  "learning_rate": 4.62962962962963e-05,
67
+ "loss": 1.787,
68
  "step": 20
69
  },
70
  {
71
+ "epoch": 6.8,
72
+ "eval_accuracy": 0.8823529411764706,
73
+ "eval_loss": 0.600950300693512,
74
+ "eval_runtime": 3.4707,
75
+ "eval_samples_per_second": 14.694,
76
+ "eval_steps_per_second": 0.576,
77
  "step": 21
78
  },
79
  {
80
+ "epoch": 7.8,
81
+ "eval_accuracy": 0.9019607843137255,
82
+ "eval_loss": 0.43014010787010193,
83
+ "eval_runtime": 3.7555,
84
+ "eval_samples_per_second": 13.58,
85
+ "eval_steps_per_second": 0.533,
86
  "step": 24
87
  },
88
  {
89
+ "epoch": 8.8,
90
+ "eval_accuracy": 0.8823529411764706,
91
+ "eval_loss": 0.3232599198818207,
92
+ "eval_runtime": 3.738,
93
+ "eval_samples_per_second": 13.644,
94
+ "eval_steps_per_second": 0.535,
95
  "step": 27
96
  },
97
  {
98
+ "epoch": 9.8,
99
+ "eval_accuracy": 0.9411764705882353,
100
+ "eval_loss": 0.2302764505147934,
101
+ "eval_runtime": 3.4208,
102
+ "eval_samples_per_second": 14.909,
103
+ "eval_steps_per_second": 0.585,
104
  "step": 30
105
  },
106
  {
107
+ "epoch": 10.8,
108
+ "eval_accuracy": 1.0,
109
+ "eval_loss": 0.18712519109249115,
110
+ "eval_runtime": 3.7332,
111
+ "eval_samples_per_second": 13.661,
112
+ "eval_steps_per_second": 0.536,
113
  "step": 33
114
  },
115
  {
116
+ "epoch": 11.8,
117
+ "eval_accuracy": 0.9607843137254902,
118
+ "eval_loss": 0.16001677513122559,
119
+ "eval_runtime": 3.7595,
120
+ "eval_samples_per_second": 13.566,
121
+ "eval_steps_per_second": 0.532,
122
  "step": 36
123
  },
124
  {
125
+ "epoch": 12.8,
126
+ "eval_accuracy": 0.9803921568627451,
127
+ "eval_loss": 0.13339409232139587,
128
+ "eval_runtime": 3.4512,
129
+ "eval_samples_per_second": 14.778,
130
+ "eval_steps_per_second": 0.58,
131
  "step": 39
132
  },
133
  {
134
+ "epoch": 13.27,
135
  "learning_rate": 3.7037037037037037e-05,
136
+ "loss": 0.7554,
137
  "step": 40
138
  },
139
  {
140
+ "epoch": 13.8,
141
+ "eval_accuracy": 1.0,
142
+ "eval_loss": 0.10250363498926163,
143
+ "eval_runtime": 3.7508,
144
+ "eval_samples_per_second": 13.597,
145
+ "eval_steps_per_second": 0.533,
146
  "step": 42
147
  },
148
  {
149
+ "epoch": 14.8,
150
+ "eval_accuracy": 1.0,
151
+ "eval_loss": 0.09086543321609497,
152
+ "eval_runtime": 3.7591,
153
+ "eval_samples_per_second": 13.567,
154
+ "eval_steps_per_second": 0.532,
155
  "step": 45
156
  },
157
  {
158
+ "epoch": 15.8,
159
+ "eval_accuracy": 1.0,
160
+ "eval_loss": 0.07331494987010956,
161
+ "eval_runtime": 3.4513,
162
+ "eval_samples_per_second": 14.777,
163
+ "eval_steps_per_second": 0.579,
164
  "step": 48
165
  },
166
  {
167
+ "epoch": 16.8,
168
+ "eval_accuracy": 1.0,
169
+ "eval_loss": 0.062474265694618225,
170
+ "eval_runtime": 3.8017,
171
+ "eval_samples_per_second": 13.415,
172
+ "eval_steps_per_second": 0.526,
173
  "step": 51
174
  },
175
  {
176
+ "epoch": 17.8,
177
+ "eval_accuracy": 1.0,
178
+ "eval_loss": 0.060241490602493286,
179
+ "eval_runtime": 3.8432,
180
+ "eval_samples_per_second": 13.27,
181
+ "eval_steps_per_second": 0.52,
182
  "step": 54
183
  },
184
  {
185
+ "epoch": 18.8,
186
+ "eval_accuracy": 1.0,
187
+ "eval_loss": 0.061301086097955704,
188
+ "eval_runtime": 3.4257,
189
+ "eval_samples_per_second": 14.888,
190
+ "eval_steps_per_second": 0.584,
191
  "step": 57
192
  },
193
  {
194
+ "epoch": 19.8,
195
  "learning_rate": 2.777777777777778e-05,
196
+ "loss": 0.4731,
197
  "step": 60
198
  },
199
  {
200
+ "epoch": 19.8,
201
+ "eval_accuracy": 1.0,
202
+ "eval_loss": 0.0506136529147625,
203
+ "eval_runtime": 3.7258,
204
+ "eval_samples_per_second": 13.688,
205
+ "eval_steps_per_second": 0.537,
206
  "step": 60
207
  },
208
  {
209
+ "epoch": 20.8,
210
+ "eval_accuracy": 1.0,
211
+ "eval_loss": 0.05875474214553833,
212
+ "eval_runtime": 3.7701,
213
+ "eval_samples_per_second": 13.528,
214
+ "eval_steps_per_second": 0.53,
215
  "step": 63
216
  },
217
  {
218
+ "epoch": 21.8,
219
+ "eval_accuracy": 0.9803921568627451,
220
+ "eval_loss": 0.06549996882677078,
221
+ "eval_runtime": 3.4174,
222
+ "eval_samples_per_second": 14.924,
223
+ "eval_steps_per_second": 0.585,
224
  "step": 66
225
  },
226
  {
227
+ "epoch": 22.8,
228
+ "eval_accuracy": 1.0,
229
+ "eval_loss": 0.05172449350357056,
230
+ "eval_runtime": 3.8113,
231
+ "eval_samples_per_second": 13.381,
232
+ "eval_steps_per_second": 0.525,
233
  "step": 69
234
  },
235
  {
236
+ "epoch": 23.8,
237
+ "eval_accuracy": 1.0,
238
+ "eval_loss": 0.04140729829668999,
239
+ "eval_runtime": 3.8035,
240
+ "eval_samples_per_second": 13.409,
241
+ "eval_steps_per_second": 0.526,
242
  "step": 72
243
  },
244
  {
245
+ "epoch": 24.8,
246
+ "eval_accuracy": 1.0,
247
+ "eval_loss": 0.04080395773053169,
248
+ "eval_runtime": 3.4453,
249
+ "eval_samples_per_second": 14.803,
250
+ "eval_steps_per_second": 0.581,
251
  "step": 75
252
  },
253
  {
254
+ "epoch": 25.8,
255
+ "eval_accuracy": 1.0,
256
+ "eval_loss": 0.041679248213768005,
257
+ "eval_runtime": 3.7337,
258
+ "eval_samples_per_second": 13.66,
259
+ "eval_steps_per_second": 0.536,
260
  "step": 78
261
  },
262
  {
263
+ "epoch": 26.53,
264
  "learning_rate": 1.8518518518518518e-05,
265
+ "loss": 0.4248,
266
  "step": 80
267
  },
268
  {
269
+ "epoch": 26.8,
270
+ "eval_accuracy": 1.0,
271
+ "eval_loss": 0.03893385827541351,
272
+ "eval_runtime": 3.8193,
273
+ "eval_samples_per_second": 13.353,
274
+ "eval_steps_per_second": 0.524,
275
  "step": 81
276
  },
277
  {
278
+ "epoch": 27.8,
279
+ "eval_accuracy": 1.0,
280
+ "eval_loss": 0.03756618872284889,
281
+ "eval_runtime": 3.4098,
282
+ "eval_samples_per_second": 14.957,
283
+ "eval_steps_per_second": 0.587,
284
  "step": 84
285
  },
286
  {
287
+ "epoch": 28.8,
288
+ "eval_accuracy": 1.0,
289
+ "eval_loss": 0.036111168563365936,
290
+ "eval_runtime": 3.7255,
291
+ "eval_samples_per_second": 13.689,
292
+ "eval_steps_per_second": 0.537,
293
  "step": 87
294
  },
295
  {
296
+ "epoch": 29.8,
297
+ "eval_accuracy": 1.0,
298
+ "eval_loss": 0.035053811967372894,
299
+ "eval_runtime": 3.7896,
300
+ "eval_samples_per_second": 13.458,
301
+ "eval_steps_per_second": 0.528,
302
  "step": 90
303
  },
304
  {
305
+ "epoch": 30.8,
306
  "eval_accuracy": 1.0,
307
+ "eval_loss": 0.029912708327174187,
308
+ "eval_runtime": 3.447,
309
+ "eval_samples_per_second": 14.796,
310
+ "eval_steps_per_second": 0.58,
311
  "step": 93
312
  },
313
  {
314
+ "epoch": 31.8,
315
  "eval_accuracy": 1.0,
316
+ "eval_loss": 0.028354115784168243,
317
+ "eval_runtime": 3.8199,
318
+ "eval_samples_per_second": 13.351,
319
+ "eval_steps_per_second": 0.524,
320
  "step": 96
321
  },
322
  {
323
+ "epoch": 32.8,
324
  "eval_accuracy": 1.0,
325
+ "eval_loss": 0.027853690087795258,
326
+ "eval_runtime": 3.7966,
327
+ "eval_samples_per_second": 13.433,
328
+ "eval_steps_per_second": 0.527,
329
  "step": 99
330
  },
331
  {
332
+ "epoch": 33.27,
333
  "learning_rate": 9.259259259259259e-06,
334
+ "loss": 0.3657,
335
  "step": 100
336
  },
337
  {
338
+ "epoch": 33.8,
339
  "eval_accuracy": 1.0,
340
+ "eval_loss": 0.027496235445141792,
341
+ "eval_runtime": 3.4451,
342
+ "eval_samples_per_second": 14.804,
343
+ "eval_steps_per_second": 0.581,
344
  "step": 102
345
  },
346
  {
347
+ "epoch": 34.8,
348
  "eval_accuracy": 1.0,
349
+ "eval_loss": 0.027940476313233376,
350
+ "eval_runtime": 3.7579,
351
+ "eval_samples_per_second": 13.571,
352
+ "eval_steps_per_second": 0.532,
353
  "step": 105
354
  },
355
  {
356
+ "epoch": 35.8,
357
+ "eval_accuracy": 1.0,
358
+ "eval_loss": 0.027937183156609535,
359
+ "eval_runtime": 3.8018,
360
+ "eval_samples_per_second": 13.415,
361
+ "eval_steps_per_second": 0.526,
362
  "step": 108
363
  },
364
  {
365
+ "epoch": 36.8,
366
+ "eval_accuracy": 1.0,
367
+ "eval_loss": 0.02781843952834606,
368
+ "eval_runtime": 3.4196,
369
+ "eval_samples_per_second": 14.914,
370
+ "eval_steps_per_second": 0.585,
371
  "step": 111
372
  },
373
  {
374
+ "epoch": 37.8,
375
+ "eval_accuracy": 1.0,
376
+ "eval_loss": 0.027574485167860985,
377
+ "eval_runtime": 3.7687,
378
+ "eval_samples_per_second": 13.532,
379
+ "eval_steps_per_second": 0.531,
380
  "step": 114
381
  },
382
  {
383
+ "epoch": 38.8,
384
+ "eval_accuracy": 1.0,
385
+ "eval_loss": 0.02744271047413349,
386
+ "eval_runtime": 3.7748,
387
+ "eval_samples_per_second": 13.511,
388
+ "eval_steps_per_second": 0.53,
389
  "step": 117
390
  },
391
  {
392
+ "epoch": 39.8,
393
  "learning_rate": 0.0,
394
+ "loss": 0.3115,
395
  "step": 120
396
  },
397
  {
398
+ "epoch": 39.8,
399
+ "eval_accuracy": 1.0,
400
+ "eval_loss": 0.02739746682345867,
401
+ "eval_runtime": 3.4498,
402
+ "eval_samples_per_second": 14.784,
403
+ "eval_steps_per_second": 0.58,
404
  "step": 120
405
  },
406
  {
407
+ "epoch": 39.8,
408
  "step": 120,
409
+ "total_flos": 4.535730650653655e+17,
410
+ "train_loss": 0.6862462480862935,
411
+ "train_runtime": 1980.068,
412
+ "train_samples_per_second": 9.252,
413
+ "train_steps_per_second": 0.061
414
  }
415
  ],
416
  "max_steps": 120,
417
  "num_train_epochs": 40,
418
+ "total_flos": 4.535730650653655e+17,
419
  "trial_name": null,
420
  "trial_params": null
421
  }