BilalMuftuoglu commited on
Commit
5072c1d
1 Parent(s): 68bfe79

End of training

Browse files
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9302325581395349
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3331
36
- - Accuracy: 0.9302
37
 
38
  ## Model description
39
 
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9534883720930233
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2509
36
+ - Accuracy: 0.9535
37
 
38
  ## Model description
39
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_accuracy": 0.9534883720930233,
4
+ "eval_loss": 0.25086623430252075,
5
+ "eval_runtime": 0.7108,
6
+ "eval_samples_per_second": 60.499,
7
+ "eval_steps_per_second": 2.814,
8
+ "total_flos": 1.8667587341684736e+18,
9
+ "train_loss": 0.16236644983291626,
10
+ "train_runtime": 1253.5555,
11
+ "train_samples_per_second": 19.225,
12
+ "train_steps_per_second": 0.16
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_accuracy": 0.9534883720930233,
4
+ "eval_loss": 0.25086623430252075,
5
+ "eval_runtime": 0.7108,
6
+ "eval_samples_per_second": 60.499,
7
+ "eval_steps_per_second": 2.814
8
+ }
runs/May20_18-47-50_b94dbfcd7693/events.out.tfevents.1716232204.b94dbfcd7693.1289.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3489ab2788fe242abee032462435c6958bb75d0b8ac3cf219441506d3a994134
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "total_flos": 1.8667587341684736e+18,
4
+ "train_loss": 0.16236644983291626,
5
+ "train_runtime": 1253.5555,
6
+ "train_samples_per_second": 19.225,
7
+ "train_steps_per_second": 0.16
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9534883720930233,
3
+ "best_model_checkpoint": "beit-base-patch16-224-75-fold4/checkpoint-144",
4
+ "epoch": 100.0,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.7906976744186046,
14
+ "eval_loss": 0.5130478143692017,
15
+ "eval_runtime": 0.6812,
16
+ "eval_samples_per_second": 63.124,
17
+ "eval_steps_per_second": 2.936,
18
+ "step": 2
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7906976744186046,
23
+ "eval_loss": 0.4860553443431854,
24
+ "eval_runtime": 0.6922,
25
+ "eval_samples_per_second": 62.12,
26
+ "eval_steps_per_second": 2.889,
27
+ "step": 4
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.7906976744186046,
32
+ "eval_loss": 0.4775117039680481,
33
+ "eval_runtime": 0.677,
34
+ "eval_samples_per_second": 63.512,
35
+ "eval_steps_per_second": 2.954,
36
+ "step": 6
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.7906976744186046,
41
+ "eval_loss": 0.44188791513442993,
42
+ "eval_runtime": 0.6577,
43
+ "eval_samples_per_second": 65.382,
44
+ "eval_steps_per_second": 3.041,
45
+ "step": 8
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "grad_norm": 7.749820709228516,
50
+ "learning_rate": 2.5e-05,
51
+ "loss": 0.4909,
52
+ "step": 10
53
+ },
54
+ {
55
+ "epoch": 5.0,
56
+ "eval_accuracy": 0.8604651162790697,
57
+ "eval_loss": 0.36715349555015564,
58
+ "eval_runtime": 0.6592,
59
+ "eval_samples_per_second": 65.227,
60
+ "eval_steps_per_second": 3.034,
61
+ "step": 10
62
+ },
63
+ {
64
+ "epoch": 6.0,
65
+ "eval_accuracy": 0.8837209302325582,
66
+ "eval_loss": 0.3301140367984772,
67
+ "eval_runtime": 0.6452,
68
+ "eval_samples_per_second": 66.649,
69
+ "eval_steps_per_second": 3.1,
70
+ "step": 12
71
+ },
72
+ {
73
+ "epoch": 7.0,
74
+ "eval_accuracy": 0.8837209302325582,
75
+ "eval_loss": 0.3130995035171509,
76
+ "eval_runtime": 0.6545,
77
+ "eval_samples_per_second": 65.699,
78
+ "eval_steps_per_second": 3.056,
79
+ "step": 14
80
+ },
81
+ {
82
+ "epoch": 8.0,
83
+ "eval_accuracy": 0.8604651162790697,
84
+ "eval_loss": 0.4535352885723114,
85
+ "eval_runtime": 0.669,
86
+ "eval_samples_per_second": 64.28,
87
+ "eval_steps_per_second": 2.99,
88
+ "step": 16
89
+ },
90
+ {
91
+ "epoch": 9.0,
92
+ "eval_accuracy": 0.8372093023255814,
93
+ "eval_loss": 0.30879294872283936,
94
+ "eval_runtime": 0.6641,
95
+ "eval_samples_per_second": 64.754,
96
+ "eval_steps_per_second": 3.012,
97
+ "step": 18
98
+ },
99
+ {
100
+ "epoch": 10.0,
101
+ "grad_norm": 7.826290130615234,
102
+ "learning_rate": 5e-05,
103
+ "loss": 0.3473,
104
+ "step": 20
105
+ },
106
+ {
107
+ "epoch": 10.0,
108
+ "eval_accuracy": 0.8837209302325582,
109
+ "eval_loss": 0.4452756345272064,
110
+ "eval_runtime": 0.6608,
111
+ "eval_samples_per_second": 65.074,
112
+ "eval_steps_per_second": 3.027,
113
+ "step": 20
114
+ },
115
+ {
116
+ "epoch": 11.0,
117
+ "eval_accuracy": 0.8604651162790697,
118
+ "eval_loss": 0.42338627576828003,
119
+ "eval_runtime": 0.6819,
120
+ "eval_samples_per_second": 63.056,
121
+ "eval_steps_per_second": 2.933,
122
+ "step": 22
123
+ },
124
+ {
125
+ "epoch": 12.0,
126
+ "eval_accuracy": 0.8837209302325582,
127
+ "eval_loss": 0.3600829541683197,
128
+ "eval_runtime": 0.6913,
129
+ "eval_samples_per_second": 62.204,
130
+ "eval_steps_per_second": 2.893,
131
+ "step": 24
132
+ },
133
+ {
134
+ "epoch": 13.0,
135
+ "eval_accuracy": 0.9069767441860465,
136
+ "eval_loss": 0.36579060554504395,
137
+ "eval_runtime": 0.6967,
138
+ "eval_samples_per_second": 61.723,
139
+ "eval_steps_per_second": 2.871,
140
+ "step": 26
141
+ },
142
+ {
143
+ "epoch": 14.0,
144
+ "eval_accuracy": 0.8837209302325582,
145
+ "eval_loss": 0.30810949206352234,
146
+ "eval_runtime": 0.6695,
147
+ "eval_samples_per_second": 64.231,
148
+ "eval_steps_per_second": 2.988,
149
+ "step": 28
150
+ },
151
+ {
152
+ "epoch": 15.0,
153
+ "grad_norm": 4.6172356605529785,
154
+ "learning_rate": 4.722222222222222e-05,
155
+ "loss": 0.2903,
156
+ "step": 30
157
+ },
158
+ {
159
+ "epoch": 15.0,
160
+ "eval_accuracy": 0.8837209302325582,
161
+ "eval_loss": 0.41277334094047546,
162
+ "eval_runtime": 0.6574,
163
+ "eval_samples_per_second": 65.405,
164
+ "eval_steps_per_second": 3.042,
165
+ "step": 30
166
+ },
167
+ {
168
+ "epoch": 16.0,
169
+ "eval_accuracy": 0.8604651162790697,
170
+ "eval_loss": 0.2554984986782074,
171
+ "eval_runtime": 0.6511,
172
+ "eval_samples_per_second": 66.044,
173
+ "eval_steps_per_second": 3.072,
174
+ "step": 32
175
+ },
176
+ {
177
+ "epoch": 17.0,
178
+ "eval_accuracy": 0.8837209302325582,
179
+ "eval_loss": 0.3340766429901123,
180
+ "eval_runtime": 0.6603,
181
+ "eval_samples_per_second": 65.12,
182
+ "eval_steps_per_second": 3.029,
183
+ "step": 34
184
+ },
185
+ {
186
+ "epoch": 18.0,
187
+ "eval_accuracy": 0.8837209302325582,
188
+ "eval_loss": 0.24271325767040253,
189
+ "eval_runtime": 0.6653,
190
+ "eval_samples_per_second": 64.632,
191
+ "eval_steps_per_second": 3.006,
192
+ "step": 36
193
+ },
194
+ {
195
+ "epoch": 19.0,
196
+ "eval_accuracy": 0.8372093023255814,
197
+ "eval_loss": 0.4324667751789093,
198
+ "eval_runtime": 0.6702,
199
+ "eval_samples_per_second": 64.158,
200
+ "eval_steps_per_second": 2.984,
201
+ "step": 38
202
+ },
203
+ {
204
+ "epoch": 20.0,
205
+ "grad_norm": 5.741236209869385,
206
+ "learning_rate": 4.4444444444444447e-05,
207
+ "loss": 0.2673,
208
+ "step": 40
209
+ },
210
+ {
211
+ "epoch": 20.0,
212
+ "eval_accuracy": 0.9069767441860465,
213
+ "eval_loss": 0.2636508643627167,
214
+ "eval_runtime": 0.6682,
215
+ "eval_samples_per_second": 64.354,
216
+ "eval_steps_per_second": 2.993,
217
+ "step": 40
218
+ },
219
+ {
220
+ "epoch": 21.0,
221
+ "eval_accuracy": 0.8837209302325582,
222
+ "eval_loss": 0.29191523790359497,
223
+ "eval_runtime": 0.6857,
224
+ "eval_samples_per_second": 62.706,
225
+ "eval_steps_per_second": 2.917,
226
+ "step": 42
227
+ },
228
+ {
229
+ "epoch": 22.0,
230
+ "eval_accuracy": 0.8837209302325582,
231
+ "eval_loss": 0.31388339400291443,
232
+ "eval_runtime": 0.6588,
233
+ "eval_samples_per_second": 65.266,
234
+ "eval_steps_per_second": 3.036,
235
+ "step": 44
236
+ },
237
+ {
238
+ "epoch": 23.0,
239
+ "eval_accuracy": 0.8837209302325582,
240
+ "eval_loss": 0.24111181497573853,
241
+ "eval_runtime": 0.6531,
242
+ "eval_samples_per_second": 65.842,
243
+ "eval_steps_per_second": 3.062,
244
+ "step": 46
245
+ },
246
+ {
247
+ "epoch": 24.0,
248
+ "eval_accuracy": 0.9069767441860465,
249
+ "eval_loss": 0.464458167552948,
250
+ "eval_runtime": 0.6616,
251
+ "eval_samples_per_second": 64.999,
252
+ "eval_steps_per_second": 3.023,
253
+ "step": 48
254
+ },
255
+ {
256
+ "epoch": 25.0,
257
+ "grad_norm": 14.516473770141602,
258
+ "learning_rate": 4.166666666666667e-05,
259
+ "loss": 0.2103,
260
+ "step": 50
261
+ },
262
+ {
263
+ "epoch": 25.0,
264
+ "eval_accuracy": 0.8604651162790697,
265
+ "eval_loss": 0.508436918258667,
266
+ "eval_runtime": 0.6628,
267
+ "eval_samples_per_second": 64.877,
268
+ "eval_steps_per_second": 3.018,
269
+ "step": 50
270
+ },
271
+ {
272
+ "epoch": 26.0,
273
+ "eval_accuracy": 0.9069767441860465,
274
+ "eval_loss": 0.23078864812850952,
275
+ "eval_runtime": 0.6774,
276
+ "eval_samples_per_second": 63.482,
277
+ "eval_steps_per_second": 2.953,
278
+ "step": 52
279
+ },
280
+ {
281
+ "epoch": 27.0,
282
+ "eval_accuracy": 0.8604651162790697,
283
+ "eval_loss": 0.3450285494327545,
284
+ "eval_runtime": 0.6606,
285
+ "eval_samples_per_second": 65.094,
286
+ "eval_steps_per_second": 3.028,
287
+ "step": 54
288
+ },
289
+ {
290
+ "epoch": 28.0,
291
+ "eval_accuracy": 0.8604651162790697,
292
+ "eval_loss": 0.34442028403282166,
293
+ "eval_runtime": 0.6628,
294
+ "eval_samples_per_second": 64.873,
295
+ "eval_steps_per_second": 3.017,
296
+ "step": 56
297
+ },
298
+ {
299
+ "epoch": 29.0,
300
+ "eval_accuracy": 0.9069767441860465,
301
+ "eval_loss": 0.2546083629131317,
302
+ "eval_runtime": 0.6779,
303
+ "eval_samples_per_second": 63.434,
304
+ "eval_steps_per_second": 2.95,
305
+ "step": 58
306
+ },
307
+ {
308
+ "epoch": 30.0,
309
+ "grad_norm": 5.658456802368164,
310
+ "learning_rate": 3.888888888888889e-05,
311
+ "loss": 0.1673,
312
+ "step": 60
313
+ },
314
+ {
315
+ "epoch": 30.0,
316
+ "eval_accuracy": 0.813953488372093,
317
+ "eval_loss": 0.9117240905761719,
318
+ "eval_runtime": 0.6726,
319
+ "eval_samples_per_second": 63.93,
320
+ "eval_steps_per_second": 2.973,
321
+ "step": 60
322
+ },
323
+ {
324
+ "epoch": 31.0,
325
+ "eval_accuracy": 0.813953488372093,
326
+ "eval_loss": 0.8437220454216003,
327
+ "eval_runtime": 0.6672,
328
+ "eval_samples_per_second": 64.452,
329
+ "eval_steps_per_second": 2.998,
330
+ "step": 62
331
+ },
332
+ {
333
+ "epoch": 32.0,
334
+ "eval_accuracy": 0.8372093023255814,
335
+ "eval_loss": 0.6758245825767517,
336
+ "eval_runtime": 0.6742,
337
+ "eval_samples_per_second": 63.775,
338
+ "eval_steps_per_second": 2.966,
339
+ "step": 64
340
+ },
341
+ {
342
+ "epoch": 33.0,
343
+ "eval_accuracy": 0.813953488372093,
344
+ "eval_loss": 0.8019335269927979,
345
+ "eval_runtime": 0.6637,
346
+ "eval_samples_per_second": 64.793,
347
+ "eval_steps_per_second": 3.014,
348
+ "step": 66
349
+ },
350
+ {
351
+ "epoch": 34.0,
352
+ "eval_accuracy": 0.8837209302325582,
353
+ "eval_loss": 0.3364037275314331,
354
+ "eval_runtime": 0.6581,
355
+ "eval_samples_per_second": 65.339,
356
+ "eval_steps_per_second": 3.039,
357
+ "step": 68
358
+ },
359
+ {
360
+ "epoch": 35.0,
361
+ "grad_norm": 3.4963107109069824,
362
+ "learning_rate": 3.611111111111111e-05,
363
+ "loss": 0.1677,
364
+ "step": 70
365
+ },
366
+ {
367
+ "epoch": 35.0,
368
+ "eval_accuracy": 0.8837209302325582,
369
+ "eval_loss": 0.2928450107574463,
370
+ "eval_runtime": 0.6586,
371
+ "eval_samples_per_second": 65.287,
372
+ "eval_steps_per_second": 3.037,
373
+ "step": 70
374
+ },
375
+ {
376
+ "epoch": 36.0,
377
+ "eval_accuracy": 0.9069767441860465,
378
+ "eval_loss": 0.2546534240245819,
379
+ "eval_runtime": 0.6709,
380
+ "eval_samples_per_second": 64.096,
381
+ "eval_steps_per_second": 2.981,
382
+ "step": 72
383
+ },
384
+ {
385
+ "epoch": 37.0,
386
+ "eval_accuracy": 0.8837209302325582,
387
+ "eval_loss": 0.2968655228614807,
388
+ "eval_runtime": 0.6643,
389
+ "eval_samples_per_second": 64.731,
390
+ "eval_steps_per_second": 3.011,
391
+ "step": 74
392
+ },
393
+ {
394
+ "epoch": 38.0,
395
+ "eval_accuracy": 0.8837209302325582,
396
+ "eval_loss": 0.5706415772438049,
397
+ "eval_runtime": 0.6641,
398
+ "eval_samples_per_second": 64.754,
399
+ "eval_steps_per_second": 3.012,
400
+ "step": 76
401
+ },
402
+ {
403
+ "epoch": 39.0,
404
+ "eval_accuracy": 0.8837209302325582,
405
+ "eval_loss": 0.700643002986908,
406
+ "eval_runtime": 0.6643,
407
+ "eval_samples_per_second": 64.734,
408
+ "eval_steps_per_second": 3.011,
409
+ "step": 78
410
+ },
411
+ {
412
+ "epoch": 40.0,
413
+ "grad_norm": 7.142909049987793,
414
+ "learning_rate": 3.3333333333333335e-05,
415
+ "loss": 0.1407,
416
+ "step": 80
417
+ },
418
+ {
419
+ "epoch": 40.0,
420
+ "eval_accuracy": 0.8837209302325582,
421
+ "eval_loss": 0.43211764097213745,
422
+ "eval_runtime": 0.6641,
423
+ "eval_samples_per_second": 64.75,
424
+ "eval_steps_per_second": 3.012,
425
+ "step": 80
426
+ },
427
+ {
428
+ "epoch": 41.0,
429
+ "eval_accuracy": 0.8837209302325582,
430
+ "eval_loss": 0.43662115931510925,
431
+ "eval_runtime": 0.6788,
432
+ "eval_samples_per_second": 63.344,
433
+ "eval_steps_per_second": 2.946,
434
+ "step": 82
435
+ },
436
+ {
437
+ "epoch": 42.0,
438
+ "eval_accuracy": 0.8837209302325582,
439
+ "eval_loss": 0.39564797282218933,
440
+ "eval_runtime": 0.6577,
441
+ "eval_samples_per_second": 65.376,
442
+ "eval_steps_per_second": 3.041,
443
+ "step": 84
444
+ },
445
+ {
446
+ "epoch": 43.0,
447
+ "eval_accuracy": 0.8372093023255814,
448
+ "eval_loss": 0.22897183895111084,
449
+ "eval_runtime": 0.6605,
450
+ "eval_samples_per_second": 65.097,
451
+ "eval_steps_per_second": 3.028,
452
+ "step": 86
453
+ },
454
+ {
455
+ "epoch": 44.0,
456
+ "eval_accuracy": 0.8837209302325582,
457
+ "eval_loss": 0.36646950244903564,
458
+ "eval_runtime": 0.6649,
459
+ "eval_samples_per_second": 64.671,
460
+ "eval_steps_per_second": 3.008,
461
+ "step": 88
462
+ },
463
+ {
464
+ "epoch": 45.0,
465
+ "grad_norm": 5.7567524909973145,
466
+ "learning_rate": 3.055555555555556e-05,
467
+ "loss": 0.1474,
468
+ "step": 90
469
+ },
470
+ {
471
+ "epoch": 45.0,
472
+ "eval_accuracy": 0.8604651162790697,
473
+ "eval_loss": 0.4464525580406189,
474
+ "eval_runtime": 0.6626,
475
+ "eval_samples_per_second": 64.895,
476
+ "eval_steps_per_second": 3.018,
477
+ "step": 90
478
+ },
479
+ {
480
+ "epoch": 46.0,
481
+ "eval_accuracy": 0.8604651162790697,
482
+ "eval_loss": 0.7278981804847717,
483
+ "eval_runtime": 0.666,
484
+ "eval_samples_per_second": 64.563,
485
+ "eval_steps_per_second": 3.003,
486
+ "step": 92
487
+ },
488
+ {
489
+ "epoch": 47.0,
490
+ "eval_accuracy": 0.8604651162790697,
491
+ "eval_loss": 0.5259287357330322,
492
+ "eval_runtime": 0.6797,
493
+ "eval_samples_per_second": 63.263,
494
+ "eval_steps_per_second": 2.942,
495
+ "step": 94
496
+ },
497
+ {
498
+ "epoch": 48.0,
499
+ "eval_accuracy": 0.8837209302325582,
500
+ "eval_loss": 0.5832454562187195,
501
+ "eval_runtime": 0.6814,
502
+ "eval_samples_per_second": 63.101,
503
+ "eval_steps_per_second": 2.935,
504
+ "step": 96
505
+ },
506
+ {
507
+ "epoch": 49.0,
508
+ "eval_accuracy": 0.8837209302325582,
509
+ "eval_loss": 0.73279869556427,
510
+ "eval_runtime": 0.6725,
511
+ "eval_samples_per_second": 63.937,
512
+ "eval_steps_per_second": 2.974,
513
+ "step": 98
514
+ },
515
+ {
516
+ "epoch": 50.0,
517
+ "grad_norm": 6.381649971008301,
518
+ "learning_rate": 2.777777777777778e-05,
519
+ "loss": 0.1344,
520
+ "step": 100
521
+ },
522
+ {
523
+ "epoch": 50.0,
524
+ "eval_accuracy": 0.8837209302325582,
525
+ "eval_loss": 0.3890153169631958,
526
+ "eval_runtime": 0.666,
527
+ "eval_samples_per_second": 64.569,
528
+ "eval_steps_per_second": 3.003,
529
+ "step": 100
530
+ },
531
+ {
532
+ "epoch": 51.0,
533
+ "eval_accuracy": 0.8837209302325582,
534
+ "eval_loss": 0.26422181725502014,
535
+ "eval_runtime": 0.6656,
536
+ "eval_samples_per_second": 64.601,
537
+ "eval_steps_per_second": 3.005,
538
+ "step": 102
539
+ },
540
+ {
541
+ "epoch": 52.0,
542
+ "eval_accuracy": 0.9069767441860465,
543
+ "eval_loss": 0.3710338771343231,
544
+ "eval_runtime": 0.6608,
545
+ "eval_samples_per_second": 65.077,
546
+ "eval_steps_per_second": 3.027,
547
+ "step": 104
548
+ },
549
+ {
550
+ "epoch": 53.0,
551
+ "eval_accuracy": 0.9069767441860465,
552
+ "eval_loss": 0.47727954387664795,
553
+ "eval_runtime": 0.6628,
554
+ "eval_samples_per_second": 64.873,
555
+ "eval_steps_per_second": 3.017,
556
+ "step": 106
557
+ },
558
+ {
559
+ "epoch": 54.0,
560
+ "eval_accuracy": 0.9302325581395349,
561
+ "eval_loss": 0.3628208339214325,
562
+ "eval_runtime": 0.662,
563
+ "eval_samples_per_second": 64.957,
564
+ "eval_steps_per_second": 3.021,
565
+ "step": 108
566
+ },
567
+ {
568
+ "epoch": 55.0,
569
+ "grad_norm": 3.1835520267486572,
570
+ "learning_rate": 2.5e-05,
571
+ "loss": 0.1166,
572
+ "step": 110
573
+ },
574
+ {
575
+ "epoch": 55.0,
576
+ "eval_accuracy": 0.9069767441860465,
577
+ "eval_loss": 0.43894824385643005,
578
+ "eval_runtime": 0.6643,
579
+ "eval_samples_per_second": 64.727,
580
+ "eval_steps_per_second": 3.011,
581
+ "step": 110
582
+ },
583
+ {
584
+ "epoch": 56.0,
585
+ "eval_accuracy": 0.9069767441860465,
586
+ "eval_loss": 0.48127347230911255,
587
+ "eval_runtime": 0.6668,
588
+ "eval_samples_per_second": 64.488,
589
+ "eval_steps_per_second": 2.999,
590
+ "step": 112
591
+ },
592
+ {
593
+ "epoch": 57.0,
594
+ "eval_accuracy": 0.9069767441860465,
595
+ "eval_loss": 0.5327816009521484,
596
+ "eval_runtime": 0.6663,
597
+ "eval_samples_per_second": 64.537,
598
+ "eval_steps_per_second": 3.002,
599
+ "step": 114
600
+ },
601
+ {
602
+ "epoch": 58.0,
603
+ "eval_accuracy": 0.9069767441860465,
604
+ "eval_loss": 0.5341907739639282,
605
+ "eval_runtime": 0.6645,
606
+ "eval_samples_per_second": 64.71,
607
+ "eval_steps_per_second": 3.01,
608
+ "step": 116
609
+ },
610
+ {
611
+ "epoch": 59.0,
612
+ "eval_accuracy": 0.9069767441860465,
613
+ "eval_loss": 0.48921194672584534,
614
+ "eval_runtime": 0.6577,
615
+ "eval_samples_per_second": 65.38,
616
+ "eval_steps_per_second": 3.041,
617
+ "step": 118
618
+ },
619
+ {
620
+ "epoch": 60.0,
621
+ "grad_norm": 3.6190884113311768,
622
+ "learning_rate": 2.2222222222222223e-05,
623
+ "loss": 0.097,
624
+ "step": 120
625
+ },
626
+ {
627
+ "epoch": 60.0,
628
+ "eval_accuracy": 0.9069767441860465,
629
+ "eval_loss": 0.5857459902763367,
630
+ "eval_runtime": 0.6713,
631
+ "eval_samples_per_second": 64.059,
632
+ "eval_steps_per_second": 2.979,
633
+ "step": 120
634
+ },
635
+ {
636
+ "epoch": 61.0,
637
+ "eval_accuracy": 0.9069767441860465,
638
+ "eval_loss": 0.6681368350982666,
639
+ "eval_runtime": 0.6655,
640
+ "eval_samples_per_second": 64.61,
641
+ "eval_steps_per_second": 3.005,
642
+ "step": 122
643
+ },
644
+ {
645
+ "epoch": 62.0,
646
+ "eval_accuracy": 0.9069767441860465,
647
+ "eval_loss": 0.5946548581123352,
648
+ "eval_runtime": 0.6669,
649
+ "eval_samples_per_second": 64.482,
650
+ "eval_steps_per_second": 2.999,
651
+ "step": 124
652
+ },
653
+ {
654
+ "epoch": 63.0,
655
+ "eval_accuracy": 0.9069767441860465,
656
+ "eval_loss": 0.47492873668670654,
657
+ "eval_runtime": 0.6758,
658
+ "eval_samples_per_second": 63.633,
659
+ "eval_steps_per_second": 2.96,
660
+ "step": 126
661
+ },
662
+ {
663
+ "epoch": 64.0,
664
+ "eval_accuracy": 0.8837209302325582,
665
+ "eval_loss": 0.6091283559799194,
666
+ "eval_runtime": 0.6685,
667
+ "eval_samples_per_second": 64.325,
668
+ "eval_steps_per_second": 2.992,
669
+ "step": 128
670
+ },
671
+ {
672
+ "epoch": 65.0,
673
+ "grad_norm": 4.258938789367676,
674
+ "learning_rate": 1.9444444444444445e-05,
675
+ "loss": 0.1076,
676
+ "step": 130
677
+ },
678
+ {
679
+ "epoch": 65.0,
680
+ "eval_accuracy": 0.8604651162790697,
681
+ "eval_loss": 0.9725148677825928,
682
+ "eval_runtime": 0.6743,
683
+ "eval_samples_per_second": 63.766,
684
+ "eval_steps_per_second": 2.966,
685
+ "step": 130
686
+ },
687
+ {
688
+ "epoch": 66.0,
689
+ "eval_accuracy": 0.813953488372093,
690
+ "eval_loss": 1.1372181177139282,
691
+ "eval_runtime": 0.6651,
692
+ "eval_samples_per_second": 64.656,
693
+ "eval_steps_per_second": 3.007,
694
+ "step": 132
695
+ },
696
+ {
697
+ "epoch": 67.0,
698
+ "eval_accuracy": 0.8604651162790697,
699
+ "eval_loss": 0.7108578085899353,
700
+ "eval_runtime": 0.6618,
701
+ "eval_samples_per_second": 64.972,
702
+ "eval_steps_per_second": 3.022,
703
+ "step": 134
704
+ },
705
+ {
706
+ "epoch": 68.0,
707
+ "eval_accuracy": 0.9302325581395349,
708
+ "eval_loss": 0.35486963391304016,
709
+ "eval_runtime": 0.66,
710
+ "eval_samples_per_second": 65.147,
711
+ "eval_steps_per_second": 3.03,
712
+ "step": 136
713
+ },
714
+ {
715
+ "epoch": 69.0,
716
+ "eval_accuracy": 0.9302325581395349,
717
+ "eval_loss": 0.27090850472450256,
718
+ "eval_runtime": 0.6636,
719
+ "eval_samples_per_second": 64.795,
720
+ "eval_steps_per_second": 3.014,
721
+ "step": 138
722
+ },
723
+ {
724
+ "epoch": 70.0,
725
+ "grad_norm": 2.5122122764587402,
726
+ "learning_rate": 1.6666666666666667e-05,
727
+ "loss": 0.0914,
728
+ "step": 140
729
+ },
730
+ {
731
+ "epoch": 70.0,
732
+ "eval_accuracy": 0.9302325581395349,
733
+ "eval_loss": 0.3316062092781067,
734
+ "eval_runtime": 0.6617,
735
+ "eval_samples_per_second": 64.984,
736
+ "eval_steps_per_second": 3.023,
737
+ "step": 140
738
+ },
739
+ {
740
+ "epoch": 71.0,
741
+ "eval_accuracy": 0.9302325581395349,
742
+ "eval_loss": 0.317620187997818,
743
+ "eval_runtime": 0.6589,
744
+ "eval_samples_per_second": 65.263,
745
+ "eval_steps_per_second": 3.035,
746
+ "step": 142
747
+ },
748
+ {
749
+ "epoch": 72.0,
750
+ "eval_accuracy": 0.9534883720930233,
751
+ "eval_loss": 0.25086623430252075,
752
+ "eval_runtime": 0.661,
753
+ "eval_samples_per_second": 65.051,
754
+ "eval_steps_per_second": 3.026,
755
+ "step": 144
756
+ },
757
+ {
758
+ "epoch": 73.0,
759
+ "eval_accuracy": 0.9069767441860465,
760
+ "eval_loss": 0.22562167048454285,
761
+ "eval_runtime": 0.6643,
762
+ "eval_samples_per_second": 64.732,
763
+ "eval_steps_per_second": 3.011,
764
+ "step": 146
765
+ },
766
+ {
767
+ "epoch": 74.0,
768
+ "eval_accuracy": 0.9069767441860465,
769
+ "eval_loss": 0.2569940388202667,
770
+ "eval_runtime": 0.6668,
771
+ "eval_samples_per_second": 64.488,
772
+ "eval_steps_per_second": 2.999,
773
+ "step": 148
774
+ },
775
+ {
776
+ "epoch": 75.0,
777
+ "grad_norm": 4.068800449371338,
778
+ "learning_rate": 1.388888888888889e-05,
779
+ "loss": 0.0815,
780
+ "step": 150
781
+ },
782
+ {
783
+ "epoch": 75.0,
784
+ "eval_accuracy": 0.9534883720930233,
785
+ "eval_loss": 0.3081124424934387,
786
+ "eval_runtime": 0.6629,
787
+ "eval_samples_per_second": 64.862,
788
+ "eval_steps_per_second": 3.017,
789
+ "step": 150
790
+ },
791
+ {
792
+ "epoch": 76.0,
793
+ "eval_accuracy": 0.9302325581395349,
794
+ "eval_loss": 0.4198541045188904,
795
+ "eval_runtime": 0.6549,
796
+ "eval_samples_per_second": 65.657,
797
+ "eval_steps_per_second": 3.054,
798
+ "step": 152
799
+ },
800
+ {
801
+ "epoch": 77.0,
802
+ "eval_accuracy": 0.9302325581395349,
803
+ "eval_loss": 0.432374507188797,
804
+ "eval_runtime": 0.6731,
805
+ "eval_samples_per_second": 63.882,
806
+ "eval_steps_per_second": 2.971,
807
+ "step": 154
808
+ },
809
+ {
810
+ "epoch": 78.0,
811
+ "eval_accuracy": 0.9302325581395349,
812
+ "eval_loss": 0.39275258779525757,
813
+ "eval_runtime": 0.6597,
814
+ "eval_samples_per_second": 65.176,
815
+ "eval_steps_per_second": 3.031,
816
+ "step": 156
817
+ },
818
+ {
819
+ "epoch": 79.0,
820
+ "eval_accuracy": 0.9302325581395349,
821
+ "eval_loss": 0.3700079023838043,
822
+ "eval_runtime": 0.6605,
823
+ "eval_samples_per_second": 65.106,
824
+ "eval_steps_per_second": 3.028,
825
+ "step": 158
826
+ },
827
+ {
828
+ "epoch": 80.0,
829
+ "grad_norm": 3.1357898712158203,
830
+ "learning_rate": 1.1111111111111112e-05,
831
+ "loss": 0.0878,
832
+ "step": 160
833
+ },
834
+ {
835
+ "epoch": 80.0,
836
+ "eval_accuracy": 0.9302325581395349,
837
+ "eval_loss": 0.38116565346717834,
838
+ "eval_runtime": 0.7043,
839
+ "eval_samples_per_second": 61.055,
840
+ "eval_steps_per_second": 2.84,
841
+ "step": 160
842
+ },
843
+ {
844
+ "epoch": 81.0,
845
+ "eval_accuracy": 0.9302325581395349,
846
+ "eval_loss": 0.4299600422382355,
847
+ "eval_runtime": 0.6661,
848
+ "eval_samples_per_second": 64.555,
849
+ "eval_steps_per_second": 3.003,
850
+ "step": 162
851
+ },
852
+ {
853
+ "epoch": 82.0,
854
+ "eval_accuracy": 0.9302325581395349,
855
+ "eval_loss": 0.4289122223854065,
856
+ "eval_runtime": 0.7043,
857
+ "eval_samples_per_second": 61.056,
858
+ "eval_steps_per_second": 2.84,
859
+ "step": 164
860
+ },
861
+ {
862
+ "epoch": 83.0,
863
+ "eval_accuracy": 0.9302325581395349,
864
+ "eval_loss": 0.41245317459106445,
865
+ "eval_runtime": 0.662,
866
+ "eval_samples_per_second": 64.956,
867
+ "eval_steps_per_second": 3.021,
868
+ "step": 166
869
+ },
870
+ {
871
+ "epoch": 84.0,
872
+ "eval_accuracy": 0.9302325581395349,
873
+ "eval_loss": 0.43505820631980896,
874
+ "eval_runtime": 0.6683,
875
+ "eval_samples_per_second": 64.34,
876
+ "eval_steps_per_second": 2.993,
877
+ "step": 168
878
+ },
879
+ {
880
+ "epoch": 85.0,
881
+ "grad_norm": 3.3373324871063232,
882
+ "learning_rate": 8.333333333333334e-06,
883
+ "loss": 0.0725,
884
+ "step": 170
885
+ },
886
+ {
887
+ "epoch": 85.0,
888
+ "eval_accuracy": 0.9302325581395349,
889
+ "eval_loss": 0.5045635104179382,
890
+ "eval_runtime": 0.6522,
891
+ "eval_samples_per_second": 65.933,
892
+ "eval_steps_per_second": 3.067,
893
+ "step": 170
894
+ },
895
+ {
896
+ "epoch": 86.0,
897
+ "eval_accuracy": 0.9069767441860465,
898
+ "eval_loss": 0.5692218542098999,
899
+ "eval_runtime": 0.6625,
900
+ "eval_samples_per_second": 64.905,
901
+ "eval_steps_per_second": 3.019,
902
+ "step": 172
903
+ },
904
+ {
905
+ "epoch": 87.0,
906
+ "eval_accuracy": 0.9069767441860465,
907
+ "eval_loss": 0.5486466884613037,
908
+ "eval_runtime": 0.6685,
909
+ "eval_samples_per_second": 64.327,
910
+ "eval_steps_per_second": 2.992,
911
+ "step": 174
912
+ },
913
+ {
914
+ "epoch": 88.0,
915
+ "eval_accuracy": 0.9302325581395349,
916
+ "eval_loss": 0.5309974551200867,
917
+ "eval_runtime": 0.6589,
918
+ "eval_samples_per_second": 65.259,
919
+ "eval_steps_per_second": 3.035,
920
+ "step": 176
921
+ },
922
+ {
923
+ "epoch": 89.0,
924
+ "eval_accuracy": 0.9302325581395349,
925
+ "eval_loss": 0.4661545753479004,
926
+ "eval_runtime": 0.6663,
927
+ "eval_samples_per_second": 64.535,
928
+ "eval_steps_per_second": 3.002,
929
+ "step": 178
930
+ },
931
+ {
932
+ "epoch": 90.0,
933
+ "grad_norm": 3.57021427154541,
934
+ "learning_rate": 5.555555555555556e-06,
935
+ "loss": 0.0944,
936
+ "step": 180
937
+ },
938
+ {
939
+ "epoch": 90.0,
940
+ "eval_accuracy": 0.9302325581395349,
941
+ "eval_loss": 0.40696418285369873,
942
+ "eval_runtime": 0.6586,
943
+ "eval_samples_per_second": 65.291,
944
+ "eval_steps_per_second": 3.037,
945
+ "step": 180
946
+ },
947
+ {
948
+ "epoch": 91.0,
949
+ "eval_accuracy": 0.9302325581395349,
950
+ "eval_loss": 0.3767591118812561,
951
+ "eval_runtime": 0.6608,
952
+ "eval_samples_per_second": 65.074,
953
+ "eval_steps_per_second": 3.027,
954
+ "step": 182
955
+ },
956
+ {
957
+ "epoch": 92.0,
958
+ "eval_accuracy": 0.9302325581395349,
959
+ "eval_loss": 0.3884381651878357,
960
+ "eval_runtime": 0.6611,
961
+ "eval_samples_per_second": 65.043,
962
+ "eval_steps_per_second": 3.025,
963
+ "step": 184
964
+ },
965
+ {
966
+ "epoch": 93.0,
967
+ "eval_accuracy": 0.9302325581395349,
968
+ "eval_loss": 0.3850724995136261,
969
+ "eval_runtime": 0.6655,
970
+ "eval_samples_per_second": 64.611,
971
+ "eval_steps_per_second": 3.005,
972
+ "step": 186
973
+ },
974
+ {
975
+ "epoch": 94.0,
976
+ "eval_accuracy": 0.9302325581395349,
977
+ "eval_loss": 0.37587684392929077,
978
+ "eval_runtime": 0.6694,
979
+ "eval_samples_per_second": 64.238,
980
+ "eval_steps_per_second": 2.988,
981
+ "step": 188
982
+ },
983
+ {
984
+ "epoch": 95.0,
985
+ "grad_norm": 2.757040023803711,
986
+ "learning_rate": 2.777777777777778e-06,
987
+ "loss": 0.0739,
988
+ "step": 190
989
+ },
990
+ {
991
+ "epoch": 95.0,
992
+ "eval_accuracy": 0.9302325581395349,
993
+ "eval_loss": 0.3608282804489136,
994
+ "eval_runtime": 0.6628,
995
+ "eval_samples_per_second": 64.873,
996
+ "eval_steps_per_second": 3.017,
997
+ "step": 190
998
+ },
999
+ {
1000
+ "epoch": 96.0,
1001
+ "eval_accuracy": 0.9302325581395349,
1002
+ "eval_loss": 0.34555718302726746,
1003
+ "eval_runtime": 0.6719,
1004
+ "eval_samples_per_second": 63.999,
1005
+ "eval_steps_per_second": 2.977,
1006
+ "step": 192
1007
+ },
1008
+ {
1009
+ "epoch": 97.0,
1010
+ "eval_accuracy": 0.9302325581395349,
1011
+ "eval_loss": 0.3360309302806854,
1012
+ "eval_runtime": 0.6604,
1013
+ "eval_samples_per_second": 65.116,
1014
+ "eval_steps_per_second": 3.029,
1015
+ "step": 194
1016
+ },
1017
+ {
1018
+ "epoch": 98.0,
1019
+ "eval_accuracy": 0.9302325581395349,
1020
+ "eval_loss": 0.33121442794799805,
1021
+ "eval_runtime": 0.669,
1022
+ "eval_samples_per_second": 64.28,
1023
+ "eval_steps_per_second": 2.99,
1024
+ "step": 196
1025
+ },
1026
+ {
1027
+ "epoch": 99.0,
1028
+ "eval_accuracy": 0.9302325581395349,
1029
+ "eval_loss": 0.3320866823196411,
1030
+ "eval_runtime": 0.6618,
1031
+ "eval_samples_per_second": 64.972,
1032
+ "eval_steps_per_second": 3.022,
1033
+ "step": 198
1034
+ },
1035
+ {
1036
+ "epoch": 100.0,
1037
+ "grad_norm": 1.8462013006210327,
1038
+ "learning_rate": 0.0,
1039
+ "loss": 0.0612,
1040
+ "step": 200
1041
+ },
1042
+ {
1043
+ "epoch": 100.0,
1044
+ "eval_accuracy": 0.9302325581395349,
1045
+ "eval_loss": 0.33314311504364014,
1046
+ "eval_runtime": 0.6673,
1047
+ "eval_samples_per_second": 64.436,
1048
+ "eval_steps_per_second": 2.997,
1049
+ "step": 200
1050
+ },
1051
+ {
1052
+ "epoch": 100.0,
1053
+ "step": 200,
1054
+ "total_flos": 1.8667587341684736e+18,
1055
+ "train_loss": 0.16236644983291626,
1056
+ "train_runtime": 1253.5555,
1057
+ "train_samples_per_second": 19.225,
1058
+ "train_steps_per_second": 0.16
1059
+ },
1060
+ {
1061
+ "epoch": 100.0,
1062
+ "eval_accuracy": 0.9534883720930233,
1063
+ "eval_loss": 0.25086623430252075,
1064
+ "eval_runtime": 0.7108,
1065
+ "eval_samples_per_second": 60.499,
1066
+ "eval_steps_per_second": 2.814,
1067
+ "step": 200
1068
+ }
1069
+ ],
1070
+ "logging_steps": 10,
1071
+ "max_steps": 200,
1072
+ "num_input_tokens_seen": 0,
1073
+ "num_train_epochs": 100,
1074
+ "save_steps": 500,
1075
+ "total_flos": 1.8667587341684736e+18,
1076
+ "train_batch_size": 32,
1077
+ "trial_name": null,
1078
+ "trial_params": null
1079
+ }