JEdward7777 commited on
Commit
dc0e58d
·
1 Parent(s): 02855a3

End of training

Browse files
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 40.0,
3
- "eval_accuracy": 1.0,
4
- "eval_loss": 0.04307302460074425,
5
- "eval_runtime": 7.4924,
6
- "eval_samples_per_second": 5.339,
7
- "eval_steps_per_second": 0.267,
8
- "total_flos": 3.579662466809856e+17,
9
- "train_loss": 0.17003339926401775,
10
- "train_runtime": 8221.5625,
11
- "train_samples_per_second": 1.751,
12
- "train_steps_per_second": 0.015
13
  }
 
1
  {
2
  "epoch": 40.0,
3
+ "eval_accuracy": 0.9767441860465116,
4
+ "eval_loss": 0.14032752811908722,
5
+ "eval_runtime": 2.9988,
6
+ "eval_samples_per_second": 14.339,
7
+ "eval_steps_per_second": 0.667,
8
+ "total_flos": 3.7685890970025984e+17,
9
+ "train_loss": 0.15792271693547566,
10
+ "train_runtime": 1762.7321,
11
+ "train_samples_per_second": 8.6,
12
+ "train_steps_per_second": 0.068
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 40.0,
3
- "eval_accuracy": 1.0,
4
- "eval_loss": 0.04307302460074425,
5
- "eval_runtime": 7.4924,
6
- "eval_samples_per_second": 5.339,
7
- "eval_steps_per_second": 0.267
8
  }
 
1
  {
2
  "epoch": 40.0,
3
+ "eval_accuracy": 0.9767441860465116,
4
+ "eval_loss": 0.14032752811908722,
5
+ "eval_runtime": 2.9988,
6
+ "eval_samples_per_second": 14.339,
7
+ "eval_steps_per_second": 0.667
8
  }
runs/Sep28_11-08-12_9ba91903bbce/events.out.tfevents.1664365403.9ba91903bbce.65.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3947326fd65896420d05f35b45e2681576af7edf961ca0382038c5c9df77a7b
3
+ size 357
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 40.0,
3
- "total_flos": 3.579662466809856e+17,
4
- "train_loss": 0.17003339926401775,
5
- "train_runtime": 8221.5625,
6
- "train_samples_per_second": 1.751,
7
- "train_steps_per_second": 0.015
8
  }
 
1
  {
2
  "epoch": 40.0,
3
+ "total_flos": 3.7685890970025984e+17,
4
+ "train_loss": 0.15792271693547566,
5
+ "train_runtime": 1762.7321,
6
+ "train_samples_per_second": 8.6,
7
+ "train_steps_per_second": 0.068
8
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 1.0,
3
- "best_model_checkpoint": "delivery_truck_classification\\checkpoint-18",
4
  "epoch": 40.0,
5
  "global_step": 120,
6
  "is_hyper_param_search": false,
@@ -9,413 +9,413 @@
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "eval_accuracy": 0.95,
13
- "eval_loss": 0.16261602938175201,
14
- "eval_runtime": 8.6031,
15
- "eval_samples_per_second": 4.649,
16
- "eval_steps_per_second": 0.232,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 2.0,
21
- "eval_accuracy": 0.95,
22
- "eval_loss": 0.1592799872159958,
23
- "eval_runtime": 8.1709,
24
- "eval_samples_per_second": 4.895,
25
- "eval_steps_per_second": 0.245,
26
  "step": 6
27
  },
28
  {
29
  "epoch": 3.0,
30
- "eval_accuracy": 0.95,
31
- "eval_loss": 0.13422292470932007,
32
- "eval_runtime": 8.0249,
33
- "eval_samples_per_second": 4.984,
34
- "eval_steps_per_second": 0.249,
35
  "step": 9
36
  },
37
  {
38
  "epoch": 4.0,
39
- "eval_accuracy": 0.975,
40
- "eval_loss": 0.08705286681652069,
41
- "eval_runtime": 8.0216,
42
- "eval_samples_per_second": 4.987,
43
- "eval_steps_per_second": 0.249,
44
  "step": 12
45
  },
46
  {
47
  "epoch": 5.0,
48
- "eval_accuracy": 0.975,
49
- "eval_loss": 0.06115349009633064,
50
- "eval_runtime": 7.8977,
51
- "eval_samples_per_second": 5.065,
52
- "eval_steps_per_second": 0.253,
53
  "step": 15
54
  },
55
  {
56
  "epoch": 6.0,
57
- "eval_accuracy": 1.0,
58
- "eval_loss": 0.04307302460074425,
59
- "eval_runtime": 8.1309,
60
- "eval_samples_per_second": 4.92,
61
- "eval_steps_per_second": 0.246,
62
  "step": 18
63
  },
64
  {
65
  "epoch": 6.67,
66
  "learning_rate": 4.62962962962963e-05,
67
- "loss": 0.2745,
68
  "step": 20
69
  },
70
  {
71
  "epoch": 7.0,
72
- "eval_accuracy": 1.0,
73
- "eval_loss": 0.03329644352197647,
74
- "eval_runtime": 8.4823,
75
- "eval_samples_per_second": 4.716,
76
- "eval_steps_per_second": 0.236,
77
  "step": 21
78
  },
79
  {
80
  "epoch": 8.0,
81
- "eval_accuracy": 1.0,
82
- "eval_loss": 0.048651862889528275,
83
- "eval_runtime": 7.9701,
84
- "eval_samples_per_second": 5.019,
85
- "eval_steps_per_second": 0.251,
86
  "step": 24
87
  },
88
  {
89
  "epoch": 9.0,
90
- "eval_accuracy": 1.0,
91
- "eval_loss": 0.045587461441755295,
92
- "eval_runtime": 7.8557,
93
- "eval_samples_per_second": 5.092,
94
- "eval_steps_per_second": 0.255,
95
  "step": 27
96
  },
97
  {
98
  "epoch": 10.0,
99
- "eval_accuracy": 1.0,
100
- "eval_loss": 0.02726823464035988,
101
- "eval_runtime": 8.1787,
102
- "eval_samples_per_second": 4.891,
103
- "eval_steps_per_second": 0.245,
104
  "step": 30
105
  },
106
  {
107
  "epoch": 11.0,
108
- "eval_accuracy": 1.0,
109
- "eval_loss": 0.017963390797376633,
110
- "eval_runtime": 8.3083,
111
- "eval_samples_per_second": 4.814,
112
- "eval_steps_per_second": 0.241,
113
  "step": 33
114
  },
115
  {
116
  "epoch": 12.0,
117
- "eval_accuracy": 1.0,
118
- "eval_loss": 0.016819924116134644,
119
- "eval_runtime": 8.1002,
120
- "eval_samples_per_second": 4.938,
121
- "eval_steps_per_second": 0.247,
122
  "step": 36
123
  },
124
  {
125
  "epoch": 13.0,
126
- "eval_accuracy": 1.0,
127
- "eval_loss": 0.031003978103399277,
128
- "eval_runtime": 8.1225,
129
- "eval_samples_per_second": 4.925,
130
- "eval_steps_per_second": 0.246,
131
  "step": 39
132
  },
133
  {
134
  "epoch": 13.33,
135
  "learning_rate": 3.7037037037037037e-05,
136
- "loss": 0.1782,
137
  "step": 40
138
  },
139
  {
140
  "epoch": 14.0,
141
- "eval_accuracy": 0.975,
142
- "eval_loss": 0.043801963329315186,
143
- "eval_runtime": 8.6445,
144
- "eval_samples_per_second": 4.627,
145
- "eval_steps_per_second": 0.231,
146
  "step": 42
147
  },
148
  {
149
  "epoch": 15.0,
150
- "eval_accuracy": 0.975,
151
- "eval_loss": 0.07503340393304825,
152
- "eval_runtime": 7.8763,
153
- "eval_samples_per_second": 5.079,
154
- "eval_steps_per_second": 0.254,
155
  "step": 45
156
  },
157
  {
158
  "epoch": 16.0,
159
- "eval_accuracy": 0.975,
160
- "eval_loss": 0.03957166522741318,
161
- "eval_runtime": 8.3356,
162
- "eval_samples_per_second": 4.799,
163
- "eval_steps_per_second": 0.24,
164
  "step": 48
165
  },
166
  {
167
  "epoch": 17.0,
168
- "eval_accuracy": 1.0,
169
- "eval_loss": 0.017652835696935654,
170
- "eval_runtime": 7.9389,
171
- "eval_samples_per_second": 5.038,
172
- "eval_steps_per_second": 0.252,
173
  "step": 51
174
  },
175
  {
176
  "epoch": 18.0,
177
- "eval_accuracy": 1.0,
178
- "eval_loss": 0.02170238085091114,
179
- "eval_runtime": 8.0236,
180
- "eval_samples_per_second": 4.985,
181
- "eval_steps_per_second": 0.249,
182
  "step": 54
183
  },
184
  {
185
  "epoch": 19.0,
186
- "eval_accuracy": 1.0,
187
- "eval_loss": 0.011599823832511902,
188
- "eval_runtime": 8.0424,
189
- "eval_samples_per_second": 4.974,
190
- "eval_steps_per_second": 0.249,
191
  "step": 57
192
  },
193
  {
194
  "epoch": 20.0,
195
  "learning_rate": 2.777777777777778e-05,
196
- "loss": 0.1624,
197
  "step": 60
198
  },
199
  {
200
  "epoch": 20.0,
201
- "eval_accuracy": 1.0,
202
- "eval_loss": 0.008052630349993706,
203
- "eval_runtime": 8.0111,
204
- "eval_samples_per_second": 4.993,
205
- "eval_steps_per_second": 0.25,
206
  "step": 60
207
  },
208
  {
209
  "epoch": 21.0,
210
- "eval_accuracy": 1.0,
211
- "eval_loss": 0.006596912629902363,
212
- "eval_runtime": 8.4146,
213
- "eval_samples_per_second": 4.754,
214
- "eval_steps_per_second": 0.238,
215
  "step": 63
216
  },
217
  {
218
  "epoch": 22.0,
219
- "eval_accuracy": 1.0,
220
- "eval_loss": 0.008253499865531921,
221
- "eval_runtime": 8.4625,
222
- "eval_samples_per_second": 4.727,
223
- "eval_steps_per_second": 0.236,
224
  "step": 66
225
  },
226
  {
227
  "epoch": 23.0,
228
- "eval_accuracy": 1.0,
229
- "eval_loss": 0.012594206258654594,
230
- "eval_runtime": 8.1933,
231
- "eval_samples_per_second": 4.882,
232
- "eval_steps_per_second": 0.244,
233
  "step": 69
234
  },
235
  {
236
  "epoch": 24.0,
237
- "eval_accuracy": 1.0,
238
- "eval_loss": 0.015849163755774498,
239
- "eval_runtime": 7.9982,
240
- "eval_samples_per_second": 5.001,
241
- "eval_steps_per_second": 0.25,
242
  "step": 72
243
  },
244
  {
245
  "epoch": 25.0,
246
- "eval_accuracy": 1.0,
247
- "eval_loss": 0.01883917860686779,
248
- "eval_runtime": 7.9429,
249
- "eval_samples_per_second": 5.036,
250
- "eval_steps_per_second": 0.252,
251
  "step": 75
252
  },
253
  {
254
  "epoch": 26.0,
255
- "eval_accuracy": 1.0,
256
- "eval_loss": 0.014945434406399727,
257
- "eval_runtime": 8.0615,
258
- "eval_samples_per_second": 4.962,
259
- "eval_steps_per_second": 0.248,
260
  "step": 78
261
  },
262
  {
263
  "epoch": 26.67,
264
  "learning_rate": 1.8518518518518518e-05,
265
- "loss": 0.1475,
266
  "step": 80
267
  },
268
  {
269
  "epoch": 27.0,
270
- "eval_accuracy": 1.0,
271
- "eval_loss": 0.010075708851218224,
272
- "eval_runtime": 8.0344,
273
- "eval_samples_per_second": 4.979,
274
- "eval_steps_per_second": 0.249,
275
  "step": 81
276
  },
277
  {
278
  "epoch": 28.0,
279
- "eval_accuracy": 1.0,
280
- "eval_loss": 0.006395348347723484,
281
- "eval_runtime": 7.9204,
282
- "eval_samples_per_second": 5.05,
283
- "eval_steps_per_second": 0.253,
284
  "step": 84
285
  },
286
  {
287
  "epoch": 29.0,
288
- "eval_accuracy": 1.0,
289
- "eval_loss": 0.004969631787389517,
290
- "eval_runtime": 8.1818,
291
- "eval_samples_per_second": 4.889,
292
- "eval_steps_per_second": 0.244,
293
  "step": 87
294
  },
295
  {
296
  "epoch": 30.0,
297
- "eval_accuracy": 1.0,
298
- "eval_loss": 0.005222103092819452,
299
- "eval_runtime": 7.9872,
300
- "eval_samples_per_second": 5.008,
301
- "eval_steps_per_second": 0.25,
302
  "step": 90
303
  },
304
  {
305
  "epoch": 31.0,
306
- "eval_accuracy": 1.0,
307
- "eval_loss": 0.006443561054766178,
308
- "eval_runtime": 7.9514,
309
- "eval_samples_per_second": 5.031,
310
- "eval_steps_per_second": 0.252,
311
  "step": 93
312
  },
313
  {
314
  "epoch": 32.0,
315
- "eval_accuracy": 1.0,
316
- "eval_loss": 0.006998550146818161,
317
- "eval_runtime": 7.9811,
318
- "eval_samples_per_second": 5.012,
319
- "eval_steps_per_second": 0.251,
320
  "step": 96
321
  },
322
  {
323
  "epoch": 33.0,
324
- "eval_accuracy": 1.0,
325
- "eval_loss": 0.006886245217174292,
326
- "eval_runtime": 7.9804,
327
- "eval_samples_per_second": 5.012,
328
- "eval_steps_per_second": 0.251,
329
  "step": 99
330
  },
331
  {
332
  "epoch": 33.33,
333
  "learning_rate": 9.259259259259259e-06,
334
- "loss": 0.1345,
335
  "step": 100
336
  },
337
  {
338
  "epoch": 34.0,
339
- "eval_accuracy": 1.0,
340
- "eval_loss": 0.005939379800111055,
341
- "eval_runtime": 7.962,
342
- "eval_samples_per_second": 5.024,
343
- "eval_steps_per_second": 0.251,
344
  "step": 102
345
  },
346
  {
347
  "epoch": 35.0,
348
- "eval_accuracy": 1.0,
349
- "eval_loss": 0.004927521105855703,
350
- "eval_runtime": 7.9624,
351
- "eval_samples_per_second": 5.024,
352
- "eval_steps_per_second": 0.251,
353
  "step": 105
354
  },
355
  {
356
  "epoch": 36.0,
357
- "eval_accuracy": 1.0,
358
- "eval_loss": 0.004319839645177126,
359
- "eval_runtime": 8.2724,
360
- "eval_samples_per_second": 4.835,
361
- "eval_steps_per_second": 0.242,
362
  "step": 108
363
  },
364
  {
365
  "epoch": 37.0,
366
- "eval_accuracy": 1.0,
367
- "eval_loss": 0.0039680288173258305,
368
- "eval_runtime": 7.994,
369
- "eval_samples_per_second": 5.004,
370
- "eval_steps_per_second": 0.25,
371
  "step": 111
372
  },
373
  {
374
  "epoch": 38.0,
375
- "eval_accuracy": 1.0,
376
- "eval_loss": 0.003840196877717972,
377
- "eval_runtime": 7.8877,
378
- "eval_samples_per_second": 5.071,
379
- "eval_steps_per_second": 0.254,
380
  "step": 114
381
  },
382
  {
383
  "epoch": 39.0,
384
- "eval_accuracy": 1.0,
385
- "eval_loss": 0.0038244160823524,
386
- "eval_runtime": 8.0172,
387
- "eval_samples_per_second": 4.989,
388
- "eval_steps_per_second": 0.249,
389
  "step": 117
390
  },
391
  {
392
  "epoch": 40.0,
393
  "learning_rate": 0.0,
394
- "loss": 0.1232,
395
  "step": 120
396
  },
397
  {
398
  "epoch": 40.0,
399
- "eval_accuracy": 1.0,
400
- "eval_loss": 0.003828426357358694,
401
- "eval_runtime": 7.9122,
402
- "eval_samples_per_second": 5.055,
403
- "eval_steps_per_second": 0.253,
404
  "step": 120
405
  },
406
  {
407
  "epoch": 40.0,
408
  "step": 120,
409
- "total_flos": 3.579662466809856e+17,
410
- "train_loss": 0.17003339926401775,
411
- "train_runtime": 8221.5625,
412
- "train_samples_per_second": 1.751,
413
- "train_steps_per_second": 0.015
414
  }
415
  ],
416
  "max_steps": 120,
417
  "num_train_epochs": 40,
418
- "total_flos": 3.579662466809856e+17,
419
  "trial_name": null,
420
  "trial_params": null
421
  }
 
1
  {
2
+ "best_metric": 0.9767441860465116,
3
+ "best_model_checkpoint": "delivery_truck_classification/checkpoint-9",
4
  "epoch": 40.0,
5
  "global_step": 120,
6
  "is_hyper_param_search": false,
 
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
+ "eval_accuracy": 0.9534883720930233,
13
+ "eval_loss": 0.1490669548511505,
14
+ "eval_runtime": 2.9917,
15
+ "eval_samples_per_second": 14.373,
16
+ "eval_steps_per_second": 0.669,
17
  "step": 3
18
  },
19
  {
20
  "epoch": 2.0,
21
+ "eval_accuracy": 0.9534883720930233,
22
+ "eval_loss": 0.14621073007583618,
23
+ "eval_runtime": 3.3898,
24
+ "eval_samples_per_second": 12.685,
25
+ "eval_steps_per_second": 0.59,
26
  "step": 6
27
  },
28
  {
29
  "epoch": 3.0,
30
+ "eval_accuracy": 0.9767441860465116,
31
+ "eval_loss": 0.14032752811908722,
32
+ "eval_runtime": 3.2019,
33
+ "eval_samples_per_second": 13.429,
34
+ "eval_steps_per_second": 0.625,
35
  "step": 9
36
  },
37
  {
38
  "epoch": 4.0,
39
+ "eval_accuracy": 0.9767441860465116,
40
+ "eval_loss": 0.14311185479164124,
41
+ "eval_runtime": 2.9749,
42
+ "eval_samples_per_second": 14.455,
43
+ "eval_steps_per_second": 0.672,
44
  "step": 12
45
  },
46
  {
47
  "epoch": 5.0,
48
+ "eval_accuracy": 0.9534883720930233,
49
+ "eval_loss": 0.17613790929317474,
50
+ "eval_runtime": 3.2124,
51
+ "eval_samples_per_second": 13.386,
52
+ "eval_steps_per_second": 0.623,
53
  "step": 15
54
  },
55
  {
56
  "epoch": 6.0,
57
+ "eval_accuracy": 0.9534883720930233,
58
+ "eval_loss": 0.19303567707538605,
59
+ "eval_runtime": 3.2899,
60
+ "eval_samples_per_second": 13.07,
61
+ "eval_steps_per_second": 0.608,
62
  "step": 18
63
  },
64
  {
65
  "epoch": 6.67,
66
  "learning_rate": 4.62962962962963e-05,
67
+ "loss": 0.2637,
68
  "step": 20
69
  },
70
  {
71
  "epoch": 7.0,
72
+ "eval_accuracy": 0.9534883720930233,
73
+ "eval_loss": 0.16774171590805054,
74
+ "eval_runtime": 2.9265,
75
+ "eval_samples_per_second": 14.693,
76
+ "eval_steps_per_second": 0.683,
77
  "step": 21
78
  },
79
  {
80
  "epoch": 8.0,
81
+ "eval_accuracy": 0.9767441860465116,
82
+ "eval_loss": 0.18350879848003387,
83
+ "eval_runtime": 3.3322,
84
+ "eval_samples_per_second": 12.904,
85
+ "eval_steps_per_second": 0.6,
86
  "step": 24
87
  },
88
  {
89
  "epoch": 9.0,
90
+ "eval_accuracy": 0.9534883720930233,
91
+ "eval_loss": 0.18035028874874115,
92
+ "eval_runtime": 3.1848,
93
+ "eval_samples_per_second": 13.501,
94
+ "eval_steps_per_second": 0.628,
95
  "step": 27
96
  },
97
  {
98
  "epoch": 10.0,
99
+ "eval_accuracy": 0.9534883720930233,
100
+ "eval_loss": 0.18557493388652802,
101
+ "eval_runtime": 3.0604,
102
+ "eval_samples_per_second": 14.051,
103
+ "eval_steps_per_second": 0.654,
104
  "step": 30
105
  },
106
  {
107
  "epoch": 11.0,
108
+ "eval_accuracy": 0.9534883720930233,
109
+ "eval_loss": 0.17186354100704193,
110
+ "eval_runtime": 3.2354,
111
+ "eval_samples_per_second": 13.291,
112
+ "eval_steps_per_second": 0.618,
113
  "step": 33
114
  },
115
  {
116
  "epoch": 12.0,
117
+ "eval_accuracy": 0.9534883720930233,
118
+ "eval_loss": 0.16796864569187164,
119
+ "eval_runtime": 3.1706,
120
+ "eval_samples_per_second": 13.562,
121
+ "eval_steps_per_second": 0.631,
122
  "step": 36
123
  },
124
  {
125
  "epoch": 13.0,
126
+ "eval_accuracy": 0.9534883720930233,
127
+ "eval_loss": 0.15706905722618103,
128
+ "eval_runtime": 2.9572,
129
+ "eval_samples_per_second": 14.541,
130
+ "eval_steps_per_second": 0.676,
131
  "step": 39
132
  },
133
  {
134
  "epoch": 13.33,
135
  "learning_rate": 3.7037037037037037e-05,
136
+ "loss": 0.1687,
137
  "step": 40
138
  },
139
  {
140
  "epoch": 14.0,
141
+ "eval_accuracy": 0.9534883720930233,
142
+ "eval_loss": 0.13334713876247406,
143
+ "eval_runtime": 3.2093,
144
+ "eval_samples_per_second": 13.398,
145
+ "eval_steps_per_second": 0.623,
146
  "step": 42
147
  },
148
  {
149
  "epoch": 15.0,
150
+ "eval_accuracy": 0.9534883720930233,
151
+ "eval_loss": 0.12847872078418732,
152
+ "eval_runtime": 3.2531,
153
+ "eval_samples_per_second": 13.218,
154
+ "eval_steps_per_second": 0.615,
155
  "step": 45
156
  },
157
  {
158
  "epoch": 16.0,
159
+ "eval_accuracy": 0.9534883720930233,
160
+ "eval_loss": 0.12928344309329987,
161
+ "eval_runtime": 3.0101,
162
+ "eval_samples_per_second": 14.285,
163
+ "eval_steps_per_second": 0.664,
164
  "step": 48
165
  },
166
  {
167
  "epoch": 17.0,
168
+ "eval_accuracy": 0.9767441860465116,
169
+ "eval_loss": 0.12077976763248444,
170
+ "eval_runtime": 3.2048,
171
+ "eval_samples_per_second": 13.417,
172
+ "eval_steps_per_second": 0.624,
173
  "step": 51
174
  },
175
  {
176
  "epoch": 18.0,
177
+ "eval_accuracy": 0.9767441860465116,
178
+ "eval_loss": 0.1060628667473793,
179
+ "eval_runtime": 3.2421,
180
+ "eval_samples_per_second": 13.263,
181
+ "eval_steps_per_second": 0.617,
182
  "step": 54
183
  },
184
  {
185
  "epoch": 19.0,
186
+ "eval_accuracy": 0.9767441860465116,
187
+ "eval_loss": 0.09775999933481216,
188
+ "eval_runtime": 2.9563,
189
+ "eval_samples_per_second": 14.545,
190
+ "eval_steps_per_second": 0.677,
191
  "step": 57
192
  },
193
  {
194
  "epoch": 20.0,
195
  "learning_rate": 2.777777777777778e-05,
196
+ "loss": 0.1435,
197
  "step": 60
198
  },
199
  {
200
  "epoch": 20.0,
201
+ "eval_accuracy": 0.9534883720930233,
202
+ "eval_loss": 0.11002050340175629,
203
+ "eval_runtime": 3.164,
204
+ "eval_samples_per_second": 13.59,
205
+ "eval_steps_per_second": 0.632,
206
  "step": 60
207
  },
208
  {
209
  "epoch": 21.0,
210
+ "eval_accuracy": 0.9534883720930233,
211
+ "eval_loss": 0.1205144003033638,
212
+ "eval_runtime": 3.223,
213
+ "eval_samples_per_second": 13.342,
214
+ "eval_steps_per_second": 0.621,
215
  "step": 63
216
  },
217
  {
218
  "epoch": 22.0,
219
+ "eval_accuracy": 0.9767441860465116,
220
+ "eval_loss": 0.10268723964691162,
221
+ "eval_runtime": 2.9505,
222
+ "eval_samples_per_second": 14.574,
223
+ "eval_steps_per_second": 0.678,
224
  "step": 66
225
  },
226
  {
227
  "epoch": 23.0,
228
+ "eval_accuracy": 0.9767441860465116,
229
+ "eval_loss": 0.10407420247793198,
230
+ "eval_runtime": 3.2576,
231
+ "eval_samples_per_second": 13.2,
232
+ "eval_steps_per_second": 0.614,
233
  "step": 69
234
  },
235
  {
236
  "epoch": 24.0,
237
+ "eval_accuracy": 0.9767441860465116,
238
+ "eval_loss": 0.10208708792924881,
239
+ "eval_runtime": 3.1867,
240
+ "eval_samples_per_second": 13.494,
241
+ "eval_steps_per_second": 0.628,
242
  "step": 72
243
  },
244
  {
245
  "epoch": 25.0,
246
+ "eval_accuracy": 0.9767441860465116,
247
+ "eval_loss": 0.09740080684423447,
248
+ "eval_runtime": 2.9153,
249
+ "eval_samples_per_second": 14.75,
250
+ "eval_steps_per_second": 0.686,
251
  "step": 75
252
  },
253
  {
254
  "epoch": 26.0,
255
+ "eval_accuracy": 0.9534883720930233,
256
+ "eval_loss": 0.10056695342063904,
257
+ "eval_runtime": 3.2051,
258
+ "eval_samples_per_second": 13.416,
259
+ "eval_steps_per_second": 0.624,
260
  "step": 78
261
  },
262
  {
263
  "epoch": 26.67,
264
  "learning_rate": 1.8518518518518518e-05,
265
+ "loss": 0.1361,
266
  "step": 80
267
  },
268
  {
269
  "epoch": 27.0,
270
+ "eval_accuracy": 0.9534883720930233,
271
+ "eval_loss": 0.10110510140657425,
272
+ "eval_runtime": 3.2233,
273
+ "eval_samples_per_second": 13.34,
274
+ "eval_steps_per_second": 0.62,
275
  "step": 81
276
  },
277
  {
278
  "epoch": 28.0,
279
+ "eval_accuracy": 0.9767441860465116,
280
+ "eval_loss": 0.09926853328943253,
281
+ "eval_runtime": 2.9231,
282
+ "eval_samples_per_second": 14.711,
283
+ "eval_steps_per_second": 0.684,
284
  "step": 84
285
  },
286
  {
287
  "epoch": 29.0,
288
+ "eval_accuracy": 0.9767441860465116,
289
+ "eval_loss": 0.09514892101287842,
290
+ "eval_runtime": 3.1715,
291
+ "eval_samples_per_second": 13.558,
292
+ "eval_steps_per_second": 0.631,
293
  "step": 87
294
  },
295
  {
296
  "epoch": 30.0,
297
+ "eval_accuracy": 0.9767441860465116,
298
+ "eval_loss": 0.09706470370292664,
299
+ "eval_runtime": 3.2972,
300
+ "eval_samples_per_second": 13.041,
301
+ "eval_steps_per_second": 0.607,
302
  "step": 90
303
  },
304
  {
305
  "epoch": 31.0,
306
+ "eval_accuracy": 0.9767441860465116,
307
+ "eval_loss": 0.10362450033426285,
308
+ "eval_runtime": 2.9574,
309
+ "eval_samples_per_second": 14.54,
310
+ "eval_steps_per_second": 0.676,
311
  "step": 93
312
  },
313
  {
314
  "epoch": 32.0,
315
+ "eval_accuracy": 0.9767441860465116,
316
+ "eval_loss": 0.10851310193538666,
317
+ "eval_runtime": 3.2605,
318
+ "eval_samples_per_second": 13.188,
319
+ "eval_steps_per_second": 0.613,
320
  "step": 96
321
  },
322
  {
323
  "epoch": 33.0,
324
+ "eval_accuracy": 0.9767441860465116,
325
+ "eval_loss": 0.10988349467515945,
326
+ "eval_runtime": 3.2152,
327
+ "eval_samples_per_second": 13.374,
328
+ "eval_steps_per_second": 0.622,
329
  "step": 99
330
  },
331
  {
332
  "epoch": 33.33,
333
  "learning_rate": 9.259259259259259e-06,
334
+ "loss": 0.1221,
335
  "step": 100
336
  },
337
  {
338
  "epoch": 34.0,
339
+ "eval_accuracy": 0.9767441860465116,
340
+ "eval_loss": 0.11153779178857803,
341
+ "eval_runtime": 2.9113,
342
+ "eval_samples_per_second": 14.77,
343
+ "eval_steps_per_second": 0.687,
344
  "step": 102
345
  },
346
  {
347
  "epoch": 35.0,
348
+ "eval_accuracy": 0.9767441860465116,
349
+ "eval_loss": 0.11329730600118637,
350
+ "eval_runtime": 3.208,
351
+ "eval_samples_per_second": 13.404,
352
+ "eval_steps_per_second": 0.623,
353
  "step": 105
354
  },
355
  {
356
  "epoch": 36.0,
357
+ "eval_accuracy": 0.9534883720930233,
358
+ "eval_loss": 0.11842045933008194,
359
+ "eval_runtime": 3.2236,
360
+ "eval_samples_per_second": 13.339,
361
+ "eval_steps_per_second": 0.62,
362
  "step": 108
363
  },
364
  {
365
  "epoch": 37.0,
366
+ "eval_accuracy": 0.9534883720930233,
367
+ "eval_loss": 0.12152226269245148,
368
+ "eval_runtime": 2.9306,
369
+ "eval_samples_per_second": 14.673,
370
+ "eval_steps_per_second": 0.682,
371
  "step": 111
372
  },
373
  {
374
  "epoch": 38.0,
375
+ "eval_accuracy": 0.9534883720930233,
376
+ "eval_loss": 0.12237626314163208,
377
+ "eval_runtime": 3.2687,
378
+ "eval_samples_per_second": 13.155,
379
+ "eval_steps_per_second": 0.612,
380
  "step": 114
381
  },
382
  {
383
  "epoch": 39.0,
384
+ "eval_accuracy": 0.9534883720930233,
385
+ "eval_loss": 0.12215745449066162,
386
+ "eval_runtime": 3.2407,
387
+ "eval_samples_per_second": 13.269,
388
+ "eval_steps_per_second": 0.617,
389
  "step": 117
390
  },
391
  {
392
  "epoch": 40.0,
393
  "learning_rate": 0.0,
394
+ "loss": 0.1135,
395
  "step": 120
396
  },
397
  {
398
  "epoch": 40.0,
399
+ "eval_accuracy": 0.9534883720930233,
400
+ "eval_loss": 0.1217384859919548,
401
+ "eval_runtime": 2.9059,
402
+ "eval_samples_per_second": 14.797,
403
+ "eval_steps_per_second": 0.688,
404
  "step": 120
405
  },
406
  {
407
  "epoch": 40.0,
408
  "step": 120,
409
+ "total_flos": 3.7685890970025984e+17,
410
+ "train_loss": 0.15792271693547566,
411
+ "train_runtime": 1762.7321,
412
+ "train_samples_per_second": 8.6,
413
+ "train_steps_per_second": 0.068
414
  }
415
  ],
416
  "max_steps": 120,
417
  "num_train_epochs": 40,
418
+ "total_flos": 3.7685890970025984e+17,
419
  "trial_name": null,
420
  "trial_params": null
421
  }