vuongnhathien commited on
Commit
998fd89
1 Parent(s): 77170eb

End of training

Browse files
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9467196819085487
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 [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.2207
36
- - Accuracy: 0.9467
37
 
38
  ## Model description
39
 
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.946031746031746
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 [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2200
36
+ - Accuracy: 0.9460
37
 
38
  ## Model description
39
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 4.09349935387607e+19,
4
+ "train_loss": 0.36333368386432624,
5
+ "train_runtime": 19367.8979,
6
+ "train_samples_per_second": 9.077,
7
+ "train_steps_per_second": 0.567
8
+ }
runs/May28_05-46-44_d277c9523585/events.out.tfevents.1716894887.d277c9523585.24.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fed4255e9e8f237015125dad367c3c02aacf53c85cd3629e70314ef1275b0ee
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 4.09349935387607e+19,
4
+ "train_loss": 0.36333368386432624,
5
+ "train_runtime": 19367.8979,
6
+ "train_samples_per_second": 9.077,
7
+ "train_steps_per_second": 0.567
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,883 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.22072996199131012,
3
+ "best_model_checkpoint": "./convnext-base-wd1e-8-2e-5/checkpoint-10990",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10990,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09,
13
+ "grad_norm": 18.85420036315918,
14
+ "learning_rate": 1.999591450398846e-05,
15
+ "loss": 2.8171,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.18,
20
+ "grad_norm": 28.546306610107422,
21
+ "learning_rate": 1.9983661354209365e-05,
22
+ "loss": 1.7712,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.27,
27
+ "grad_norm": 28.488494873046875,
28
+ "learning_rate": 1.9963250562701624e-05,
29
+ "loss": 1.3111,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.36,
34
+ "grad_norm": 27.985355377197266,
35
+ "learning_rate": 1.9934698807106706e-05,
36
+ "loss": 1.024,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.45,
41
+ "grad_norm": 20.874189376831055,
42
+ "learning_rate": 1.9898029417041328e-05,
43
+ "loss": 0.9096,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.55,
48
+ "grad_norm": 20.992918014526367,
49
+ "learning_rate": 1.9853272355034854e-05,
50
+ "loss": 0.7615,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.64,
55
+ "grad_norm": 20.678836822509766,
56
+ "learning_rate": 1.9800464192046956e-05,
57
+ "loss": 0.7798,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.73,
62
+ "grad_norm": 20.038610458374023,
63
+ "learning_rate": 1.973964807758548e-05,
64
+ "loss": 0.6927,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.82,
69
+ "grad_norm": 23.2023868560791,
70
+ "learning_rate": 1.967087370444905e-05,
71
+ "loss": 0.6137,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.91,
76
+ "grad_norm": 19.863248825073242,
77
+ "learning_rate": 1.9594197268123087e-05,
78
+ "loss": 0.6642,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 1.0,
83
+ "eval_accuracy": 0.8946322067594433,
84
+ "eval_loss": 0.38488638401031494,
85
+ "eval_runtime": 107.4706,
86
+ "eval_samples_per_second": 23.402,
87
+ "eval_steps_per_second": 1.47,
88
+ "step": 1099
89
+ },
90
+ {
91
+ "epoch": 1.0,
92
+ "grad_norm": 62.42153549194336,
93
+ "learning_rate": 1.950968142086255e-05,
94
+ "loss": 0.6664,
95
+ "step": 1100
96
+ },
97
+ {
98
+ "epoch": 1.09,
99
+ "grad_norm": 9.604940414428711,
100
+ "learning_rate": 1.9417395220498815e-05,
101
+ "loss": 0.5709,
102
+ "step": 1200
103
+ },
104
+ {
105
+ "epoch": 1.18,
106
+ "grad_norm": 18.934337615966797,
107
+ "learning_rate": 1.9317414074012588e-05,
108
+ "loss": 0.4944,
109
+ "step": 1300
110
+ },
111
+ {
112
+ "epoch": 1.27,
113
+ "grad_norm": 20.69709014892578,
114
+ "learning_rate": 1.920981967591891e-05,
115
+ "loss": 0.5209,
116
+ "step": 1400
117
+ },
118
+ {
119
+ "epoch": 1.36,
120
+ "grad_norm": 33.886619567871094,
121
+ "learning_rate": 1.9094699941514634e-05,
122
+ "loss": 0.4758,
123
+ "step": 1500
124
+ },
125
+ {
126
+ "epoch": 1.46,
127
+ "grad_norm": 24.116291046142578,
128
+ "learning_rate": 1.8972148935042912e-05,
129
+ "loss": 0.4422,
130
+ "step": 1600
131
+ },
132
+ {
133
+ "epoch": 1.55,
134
+ "grad_norm": 27.108684539794922,
135
+ "learning_rate": 1.8842266792833374e-05,
136
+ "loss": 0.5052,
137
+ "step": 1700
138
+ },
139
+ {
140
+ "epoch": 1.64,
141
+ "grad_norm": 37.22698211669922,
142
+ "learning_rate": 1.870515964148081e-05,
143
+ "loss": 0.5054,
144
+ "step": 1800
145
+ },
146
+ {
147
+ "epoch": 1.73,
148
+ "grad_norm": 20.40926170349121,
149
+ "learning_rate": 1.8560939511129225e-05,
150
+ "loss": 0.4867,
151
+ "step": 1900
152
+ },
153
+ {
154
+ "epoch": 1.82,
155
+ "grad_norm": 27.881574630737305,
156
+ "learning_rate": 1.840972424393209e-05,
157
+ "loss": 0.4333,
158
+ "step": 2000
159
+ },
160
+ {
161
+ "epoch": 1.91,
162
+ "grad_norm": 14.44858455657959,
163
+ "learning_rate": 1.8251637397763597e-05,
164
+ "loss": 0.4658,
165
+ "step": 2100
166
+ },
167
+ {
168
+ "epoch": 2.0,
169
+ "eval_accuracy": 0.9165009940357853,
170
+ "eval_loss": 0.2898237407207489,
171
+ "eval_runtime": 108.8832,
172
+ "eval_samples_per_second": 23.098,
173
+ "eval_steps_per_second": 1.451,
174
+ "step": 2198
175
+ },
176
+ {
177
+ "epoch": 2.0,
178
+ "grad_norm": 23.801347732543945,
179
+ "learning_rate": 1.808680814525966e-05,
180
+ "loss": 0.4546,
181
+ "step": 2200
182
+ },
183
+ {
184
+ "epoch": 2.09,
185
+ "grad_norm": 20.20176887512207,
186
+ "learning_rate": 1.7915371168271e-05,
187
+ "loss": 0.3855,
188
+ "step": 2300
189
+ },
190
+ {
191
+ "epoch": 2.18,
192
+ "grad_norm": 35.17919921875,
193
+ "learning_rate": 1.773746654781478e-05,
194
+ "loss": 0.4138,
195
+ "step": 2400
196
+ },
197
+ {
198
+ "epoch": 2.27,
199
+ "grad_norm": 19.36662483215332,
200
+ "learning_rate": 1.755323964961445e-05,
201
+ "loss": 0.3929,
202
+ "step": 2500
203
+ },
204
+ {
205
+ "epoch": 2.37,
206
+ "grad_norm": 21.20980453491211,
207
+ "learning_rate": 1.736284100532157e-05,
208
+ "loss": 0.3887,
209
+ "step": 2600
210
+ },
211
+ {
212
+ "epoch": 2.46,
213
+ "grad_norm": 17.784828186035156,
214
+ "learning_rate": 1.7166426189516524e-05,
215
+ "loss": 0.3988,
216
+ "step": 2700
217
+ },
218
+ {
219
+ "epoch": 2.55,
220
+ "grad_norm": 15.224771499633789,
221
+ "learning_rate": 1.696415569258862e-05,
222
+ "loss": 0.3724,
223
+ "step": 2800
224
+ },
225
+ {
226
+ "epoch": 2.64,
227
+ "grad_norm": 32.63229751586914,
228
+ "learning_rate": 1.6756194789599547e-05,
229
+ "loss": 0.406,
230
+ "step": 2900
231
+ },
232
+ {
233
+ "epoch": 2.73,
234
+ "grad_norm": 17.206344604492188,
235
+ "learning_rate": 1.6542713405237254e-05,
236
+ "loss": 0.3689,
237
+ "step": 3000
238
+ },
239
+ {
240
+ "epoch": 2.82,
241
+ "grad_norm": 27.567245483398438,
242
+ "learning_rate": 1.6323885974970606e-05,
243
+ "loss": 0.3841,
244
+ "step": 3100
245
+ },
246
+ {
247
+ "epoch": 2.91,
248
+ "grad_norm": 41.00786590576172,
249
+ "learning_rate": 1.6099891302518326e-05,
250
+ "loss": 0.3675,
251
+ "step": 3200
252
+ },
253
+ {
254
+ "epoch": 3.0,
255
+ "eval_accuracy": 0.9304174950298211,
256
+ "eval_loss": 0.24960491061210632,
257
+ "eval_runtime": 106.8163,
258
+ "eval_samples_per_second": 23.545,
259
+ "eval_steps_per_second": 1.479,
260
+ "step": 3297
261
+ },
262
+ {
263
+ "epoch": 3.0,
264
+ "grad_norm": 23.188814163208008,
265
+ "learning_rate": 1.5870912413748585e-05,
266
+ "loss": 0.3788,
267
+ "step": 3300
268
+ },
269
+ {
270
+ "epoch": 3.09,
271
+ "grad_norm": 30.5658016204834,
272
+ "learning_rate": 1.563713640712875e-05,
273
+ "loss": 0.3049,
274
+ "step": 3400
275
+ },
276
+ {
277
+ "epoch": 3.18,
278
+ "grad_norm": 15.625422477722168,
279
+ "learning_rate": 1.5398754300847346e-05,
280
+ "loss": 0.3273,
281
+ "step": 3500
282
+ },
283
+ {
284
+ "epoch": 3.28,
285
+ "grad_norm": 8.019862174987793,
286
+ "learning_rate": 1.5155960876733255e-05,
287
+ "loss": 0.3523,
288
+ "step": 3600
289
+ },
290
+ {
291
+ "epoch": 3.37,
292
+ "grad_norm": 25.53868865966797,
293
+ "learning_rate": 1.4908954521099656e-05,
294
+ "loss": 0.3003,
295
+ "step": 3700
296
+ },
297
+ {
298
+ "epoch": 3.46,
299
+ "grad_norm": 13.111063003540039,
300
+ "learning_rate": 1.46579370626427e-05,
301
+ "loss": 0.3354,
302
+ "step": 3800
303
+ },
304
+ {
305
+ "epoch": 3.55,
306
+ "grad_norm": 17.303651809692383,
307
+ "learning_rate": 1.4403113607527451e-05,
308
+ "loss": 0.3388,
309
+ "step": 3900
310
+ },
311
+ {
312
+ "epoch": 3.64,
313
+ "grad_norm": 33.83345413208008,
314
+ "learning_rate": 1.414469237179582e-05,
315
+ "loss": 0.3382,
316
+ "step": 4000
317
+ },
318
+ {
319
+ "epoch": 3.73,
320
+ "grad_norm": 28.170040130615234,
321
+ "learning_rate": 1.3882884511233381e-05,
322
+ "loss": 0.3522,
323
+ "step": 4100
324
+ },
325
+ {
326
+ "epoch": 3.82,
327
+ "grad_norm": 2.074608564376831,
328
+ "learning_rate": 1.3617903948834155e-05,
329
+ "loss": 0.3237,
330
+ "step": 4200
331
+ },
332
+ {
333
+ "epoch": 3.91,
334
+ "grad_norm": 15.362191200256348,
335
+ "learning_rate": 1.334996720000431e-05,
336
+ "loss": 0.3174,
337
+ "step": 4300
338
+ },
339
+ {
340
+ "epoch": 4.0,
341
+ "eval_accuracy": 0.9411530815109344,
342
+ "eval_loss": 0.2325742095708847,
343
+ "eval_runtime": 108.4122,
344
+ "eval_samples_per_second": 23.198,
345
+ "eval_steps_per_second": 1.457,
346
+ "step": 4396
347
+ },
348
+ {
349
+ "epoch": 4.0,
350
+ "grad_norm": 19.770036697387695,
351
+ "learning_rate": 1.3079293195647582e-05,
352
+ "loss": 0.3204,
353
+ "step": 4400
354
+ },
355
+ {
356
+ "epoch": 4.09,
357
+ "grad_norm": 16.560823440551758,
358
+ "learning_rate": 1.2806103103277017e-05,
359
+ "loss": 0.2899,
360
+ "step": 4500
361
+ },
362
+ {
363
+ "epoch": 4.19,
364
+ "grad_norm": 25.254541397094727,
365
+ "learning_rate": 1.2530620146299168e-05,
366
+ "loss": 0.2782,
367
+ "step": 4600
368
+ },
369
+ {
370
+ "epoch": 4.28,
371
+ "grad_norm": 20.078277587890625,
372
+ "learning_rate": 1.2253069421618434e-05,
373
+ "loss": 0.2908,
374
+ "step": 4700
375
+ },
376
+ {
377
+ "epoch": 4.37,
378
+ "grad_norm": 9.352935791015625,
379
+ "learning_rate": 1.1973677715710547e-05,
380
+ "loss": 0.2804,
381
+ "step": 4800
382
+ },
383
+ {
384
+ "epoch": 4.46,
385
+ "grad_norm": 23.662412643432617,
386
+ "learning_rate": 1.1692673319315541e-05,
387
+ "loss": 0.2707,
388
+ "step": 4900
389
+ },
390
+ {
391
+ "epoch": 4.55,
392
+ "grad_norm": 27.34366798400879,
393
+ "learning_rate": 1.1410285840901554e-05,
394
+ "loss": 0.2717,
395
+ "step": 5000
396
+ },
397
+ {
398
+ "epoch": 4.64,
399
+ "grad_norm": 19.72267723083496,
400
+ "learning_rate": 1.112674601905194e-05,
401
+ "loss": 0.2604,
402
+ "step": 5100
403
+ },
404
+ {
405
+ "epoch": 4.73,
406
+ "grad_norm": 37.95018768310547,
407
+ "learning_rate": 1.084228553392895e-05,
408
+ "loss": 0.3012,
409
+ "step": 5200
410
+ },
411
+ {
412
+ "epoch": 4.82,
413
+ "grad_norm": 16.562606811523438,
414
+ "learning_rate": 1.0557136817968075e-05,
415
+ "loss": 0.2882,
416
+ "step": 5300
417
+ },
418
+ {
419
+ "epoch": 4.91,
420
+ "grad_norm": 2.053151845932007,
421
+ "learning_rate": 1.0271532865957658e-05,
422
+ "loss": 0.3106,
423
+ "step": 5400
424
+ },
425
+ {
426
+ "epoch": 5.0,
427
+ "eval_accuracy": 0.9435387673956263,
428
+ "eval_loss": 0.2301262468099594,
429
+ "eval_runtime": 107.4067,
430
+ "eval_samples_per_second": 23.416,
431
+ "eval_steps_per_second": 1.471,
432
+ "step": 5495
433
+ },
434
+ {
435
+ "epoch": 5.0,
436
+ "grad_norm": 6.48727560043335,
437
+ "learning_rate": 9.98570704465907e-06,
438
+ "loss": 0.2853,
439
+ "step": 5500
440
+ },
441
+ {
442
+ "epoch": 5.1,
443
+ "grad_norm": 19.252519607543945,
444
+ "learning_rate": 9.699892902122887e-06,
445
+ "loss": 0.2327,
446
+ "step": 5600
447
+ },
448
+ {
449
+ "epoch": 5.19,
450
+ "grad_norm": 6.616147518157959,
451
+ "learning_rate": 9.414323976856991e-06,
452
+ "loss": 0.2412,
453
+ "step": 5700
454
+ },
455
+ {
456
+ "epoch": 5.28,
457
+ "grad_norm": 24.550338745117188,
458
+ "learning_rate": 9.12923360700241e-06,
459
+ "loss": 0.2438,
460
+ "step": 5800
461
+ },
462
+ {
463
+ "epoch": 5.37,
464
+ "grad_norm": 0.5674369931221008,
465
+ "learning_rate": 8.844854739672947e-06,
466
+ "loss": 0.2175,
467
+ "step": 5900
468
+ },
469
+ {
470
+ "epoch": 5.46,
471
+ "grad_norm": 17.81463050842285,
472
+ "learning_rate": 8.561419740614251e-06,
473
+ "loss": 0.2442,
474
+ "step": 6000
475
+ },
476
+ {
477
+ "epoch": 5.55,
478
+ "grad_norm": 20.672290802001953,
479
+ "learning_rate": 8.27916020433795e-06,
480
+ "loss": 0.2423,
481
+ "step": 6100
482
+ },
483
+ {
484
+ "epoch": 5.64,
485
+ "grad_norm": 9.923518180847168,
486
+ "learning_rate": 7.99830676488599e-06,
487
+ "loss": 0.2537,
488
+ "step": 6200
489
+ },
490
+ {
491
+ "epoch": 5.73,
492
+ "grad_norm": 41.107269287109375,
493
+ "learning_rate": 7.719088907379705e-06,
494
+ "loss": 0.2555,
495
+ "step": 6300
496
+ },
497
+ {
498
+ "epoch": 5.82,
499
+ "grad_norm": 24.59263038635254,
500
+ "learning_rate": 7.441734780507741e-06,
501
+ "loss": 0.2303,
502
+ "step": 6400
503
+ },
504
+ {
505
+ "epoch": 5.91,
506
+ "grad_norm": 15.823193550109863,
507
+ "learning_rate": 7.16647101010591e-06,
508
+ "loss": 0.2678,
509
+ "step": 6500
510
+ },
511
+ {
512
+ "epoch": 6.0,
513
+ "eval_accuracy": 0.9431411530815109,
514
+ "eval_loss": 0.23032429814338684,
515
+ "eval_runtime": 107.9379,
516
+ "eval_samples_per_second": 23.3,
517
+ "eval_steps_per_second": 1.464,
518
+ "step": 6594
519
+ },
520
+ {
521
+ "epoch": 6.01,
522
+ "grad_norm": 2.0771257877349854,
523
+ "learning_rate": 6.893522513981445e-06,
524
+ "loss": 0.2379,
525
+ "step": 6600
526
+ },
527
+ {
528
+ "epoch": 6.1,
529
+ "grad_norm": 28.53963279724121,
530
+ "learning_rate": 6.623112318132794e-06,
531
+ "loss": 0.2651,
532
+ "step": 6700
533
+ },
534
+ {
535
+ "epoch": 6.19,
536
+ "grad_norm": 18.732324600219727,
537
+ "learning_rate": 6.355461374515279e-06,
538
+ "loss": 0.2332,
539
+ "step": 6800
540
+ },
541
+ {
542
+ "epoch": 6.28,
543
+ "grad_norm": 1.8658305406570435,
544
+ "learning_rate": 6.090788380501436e-06,
545
+ "loss": 0.2196,
546
+ "step": 6900
547
+ },
548
+ {
549
+ "epoch": 6.37,
550
+ "grad_norm": 10.409640312194824,
551
+ "learning_rate": 5.829309600183536e-06,
552
+ "loss": 0.2048,
553
+ "step": 7000
554
+ },
555
+ {
556
+ "epoch": 6.46,
557
+ "grad_norm": 13.740955352783203,
558
+ "learning_rate": 5.571238687664398e-06,
559
+ "loss": 0.2776,
560
+ "step": 7100
561
+ },
562
+ {
563
+ "epoch": 6.55,
564
+ "grad_norm": 11.248075485229492,
565
+ "learning_rate": 5.316786512480792e-06,
566
+ "loss": 0.1773,
567
+ "step": 7200
568
+ },
569
+ {
570
+ "epoch": 6.64,
571
+ "grad_norm": 4.135138511657715,
572
+ "learning_rate": 5.066160987302075e-06,
573
+ "loss": 0.2077,
574
+ "step": 7300
575
+ },
576
+ {
577
+ "epoch": 6.73,
578
+ "grad_norm": 27.468730926513672,
579
+ "learning_rate": 4.819566898044951e-06,
580
+ "loss": 0.1922,
581
+ "step": 7400
582
+ },
583
+ {
584
+ "epoch": 6.82,
585
+ "grad_norm": 8.280457496643066,
586
+ "learning_rate": 4.5772057365430435e-06,
587
+ "loss": 0.1982,
588
+ "step": 7500
589
+ },
590
+ {
591
+ "epoch": 6.92,
592
+ "grad_norm": 15.988367080688477,
593
+ "learning_rate": 4.339275535908096e-06,
594
+ "loss": 0.2503,
595
+ "step": 7600
596
+ },
597
+ {
598
+ "epoch": 7.0,
599
+ "eval_accuracy": 0.9427435387673956,
600
+ "eval_loss": 0.22976447641849518,
601
+ "eval_runtime": 107.3436,
602
+ "eval_samples_per_second": 23.429,
603
+ "eval_steps_per_second": 1.472,
604
+ "step": 7693
605
+ },
606
+ {
607
+ "epoch": 7.01,
608
+ "grad_norm": 22.717308044433594,
609
+ "learning_rate": 4.105970708717244e-06,
610
+ "loss": 0.2103,
611
+ "step": 7700
612
+ },
613
+ {
614
+ "epoch": 7.1,
615
+ "grad_norm": 0.365151584148407,
616
+ "learning_rate": 3.877481888158677e-06,
617
+ "loss": 0.2023,
618
+ "step": 7800
619
+ },
620
+ {
621
+ "epoch": 7.19,
622
+ "grad_norm": 11.08658504486084,
623
+ "learning_rate": 3.6539957722654195e-06,
624
+ "loss": 0.1878,
625
+ "step": 7900
626
+ },
627
+ {
628
+ "epoch": 7.28,
629
+ "grad_norm": 2.89919114112854,
630
+ "learning_rate": 3.4356949713644915e-06,
631
+ "loss": 0.2046,
632
+ "step": 8000
633
+ },
634
+ {
635
+ "epoch": 7.37,
636
+ "grad_norm": 1.526982069015503,
637
+ "learning_rate": 3.222757858866166e-06,
638
+ "loss": 0.2073,
639
+ "step": 8100
640
+ },
641
+ {
642
+ "epoch": 7.46,
643
+ "grad_norm": 23.598388671875,
644
+ "learning_rate": 3.015358425515215e-06,
645
+ "loss": 0.1774,
646
+ "step": 8200
647
+ },
648
+ {
649
+ "epoch": 7.55,
650
+ "grad_norm": 41.74139404296875,
651
+ "learning_rate": 2.8136661372231887e-06,
652
+ "loss": 0.201,
653
+ "step": 8300
654
+ },
655
+ {
656
+ "epoch": 7.64,
657
+ "grad_norm": 8.005784034729004,
658
+ "learning_rate": 2.6178457965979543e-06,
659
+ "loss": 0.2074,
660
+ "step": 8400
661
+ },
662
+ {
663
+ "epoch": 7.73,
664
+ "grad_norm": 14.387943267822266,
665
+ "learning_rate": 2.4280574082836406e-06,
666
+ "loss": 0.1943,
667
+ "step": 8500
668
+ },
669
+ {
670
+ "epoch": 7.83,
671
+ "grad_norm": 20.383352279663086,
672
+ "learning_rate": 2.244456048220943e-06,
673
+ "loss": 0.1917,
674
+ "step": 8600
675
+ },
676
+ {
677
+ "epoch": 7.92,
678
+ "grad_norm": 0.6621111631393433,
679
+ "learning_rate": 2.067191736934715e-06,
680
+ "loss": 0.2204,
681
+ "step": 8700
682
+ },
683
+ {
684
+ "epoch": 8.0,
685
+ "eval_accuracy": 0.945924453280318,
686
+ "eval_loss": 0.22159598767757416,
687
+ "eval_runtime": 108.3116,
688
+ "eval_samples_per_second": 23.22,
689
+ "eval_steps_per_second": 1.459,
690
+ "step": 8792
691
+ },
692
+ {
693
+ "epoch": 8.01,
694
+ "grad_norm": 18.94173240661621,
695
+ "learning_rate": 1.8964093169522991e-06,
696
+ "loss": 0.2453,
697
+ "step": 8800
698
+ },
699
+ {
700
+ "epoch": 8.1,
701
+ "grad_norm": 26.928571701049805,
702
+ "learning_rate": 1.7322483344528385e-06,
703
+ "loss": 0.2176,
704
+ "step": 8900
705
+ },
706
+ {
707
+ "epoch": 8.19,
708
+ "grad_norm": 1.4977689981460571,
709
+ "learning_rate": 1.57484292524418e-06,
710
+ "loss": 0.1887,
711
+ "step": 9000
712
+ },
713
+ {
714
+ "epoch": 8.28,
715
+ "grad_norm": 0.4014904797077179,
716
+ "learning_rate": 1.4243217051606285e-06,
717
+ "loss": 0.1675,
718
+ "step": 9100
719
+ },
720
+ {
721
+ "epoch": 8.37,
722
+ "grad_norm": 2.714075803756714,
723
+ "learning_rate": 1.2808076649710444e-06,
724
+ "loss": 0.1964,
725
+ "step": 9200
726
+ },
727
+ {
728
+ "epoch": 8.46,
729
+ "grad_norm": 3.391688823699951,
730
+ "learning_rate": 1.1444180698831864e-06,
731
+ "loss": 0.1636,
732
+ "step": 9300
733
+ },
734
+ {
735
+ "epoch": 8.55,
736
+ "grad_norm": 7.2056145668029785,
737
+ "learning_rate": 1.0152643637264036e-06,
738
+ "loss": 0.1679,
739
+ "step": 9400
740
+ },
741
+ {
742
+ "epoch": 8.64,
743
+ "grad_norm": 6.323690414428711,
744
+ "learning_rate": 8.934520778909728e-07,
745
+ "loss": 0.215,
746
+ "step": 9500
747
+ },
748
+ {
749
+ "epoch": 8.74,
750
+ "grad_norm": 10.003203392028809,
751
+ "learning_rate": 7.790807450984805e-07,
752
+ "loss": 0.169,
753
+ "step": 9600
754
+ },
755
+ {
756
+ "epoch": 8.83,
757
+ "grad_norm": 0.6530151963233948,
758
+ "learning_rate": 6.7224381807372e-07,
759
+ "loss": 0.2152,
760
+ "step": 9700
761
+ },
762
+ {
763
+ "epoch": 8.92,
764
+ "grad_norm": 1.6361758708953857,
765
+ "learning_rate": 5.730285931845381e-07,
766
+ "loss": 0.2013,
767
+ "step": 9800
768
+ },
769
+ {
770
+ "epoch": 9.0,
771
+ "eval_accuracy": 0.9463220675944334,
772
+ "eval_loss": 0.22236517071723938,
773
+ "eval_runtime": 107.9608,
774
+ "eval_samples_per_second": 23.295,
775
+ "eval_steps_per_second": 1.463,
776
+ "step": 9891
777
+ },
778
+ {
779
+ "epoch": 9.01,
780
+ "grad_norm": 30.111351013183594,
781
+ "learning_rate": 4.815161391120505e-07,
782
+ "loss": 0.1982,
783
+ "step": 9900
784
+ },
785
+ {
786
+ "epoch": 9.1,
787
+ "grad_norm": 2.49858021736145,
788
+ "learning_rate": 3.977812306094797e-07,
789
+ "loss": 0.2057,
790
+ "step": 10000
791
+ },
792
+ {
793
+ "epoch": 9.19,
794
+ "grad_norm": 35.6863899230957,
795
+ "learning_rate": 3.2189228740377e-07,
796
+ "loss": 0.2417,
797
+ "step": 10100
798
+ },
799
+ {
800
+ "epoch": 9.28,
801
+ "grad_norm": 20.32947540283203,
802
+ "learning_rate": 2.539113182898778e-07,
803
+ "loss": 0.1596,
804
+ "step": 10200
805
+ },
806
+ {
807
+ "epoch": 9.37,
808
+ "grad_norm": 16.59613609313965,
809
+ "learning_rate": 1.9389387046343855e-07,
810
+ "loss": 0.1952,
811
+ "step": 10300
812
+ },
813
+ {
814
+ "epoch": 9.46,
815
+ "grad_norm": 3.6704962253570557,
816
+ "learning_rate": 1.4188898413319495e-07,
817
+ "loss": 0.1823,
818
+ "step": 10400
819
+ },
820
+ {
821
+ "epoch": 9.55,
822
+ "grad_norm": 7.785726070404053,
823
+ "learning_rate": 9.793915245028595e-08,
824
+ "loss": 0.2017,
825
+ "step": 10500
826
+ },
827
+ {
828
+ "epoch": 9.65,
829
+ "grad_norm": 2.0824966430664062,
830
+ "learning_rate": 6.208028678711842e-08,
831
+ "loss": 0.2237,
832
+ "step": 10600
833
+ },
834
+ {
835
+ "epoch": 9.74,
836
+ "grad_norm": 17.7388858795166,
837
+ "learning_rate": 3.4341687394222614e-08,
838
+ "loss": 0.1938,
839
+ "step": 10700
840
+ },
841
+ {
842
+ "epoch": 9.83,
843
+ "grad_norm": 31.48530387878418,
844
+ "learning_rate": 1.4746019459035422e-08,
845
+ "loss": 0.1843,
846
+ "step": 10800
847
+ },
848
+ {
849
+ "epoch": 9.92,
850
+ "grad_norm": 21.949007034301758,
851
+ "learning_rate": 3.3092945861967764e-09,
852
+ "loss": 0.1808,
853
+ "step": 10900
854
+ },
855
+ {
856
+ "epoch": 10.0,
857
+ "eval_accuracy": 0.9467196819085487,
858
+ "eval_loss": 0.22072996199131012,
859
+ "eval_runtime": 107.7576,
860
+ "eval_samples_per_second": 23.339,
861
+ "eval_steps_per_second": 1.466,
862
+ "step": 10990
863
+ },
864
+ {
865
+ "epoch": 10.0,
866
+ "step": 10990,
867
+ "total_flos": 4.09349935387607e+19,
868
+ "train_loss": 0.36333368386432624,
869
+ "train_runtime": 19367.8979,
870
+ "train_samples_per_second": 9.077,
871
+ "train_steps_per_second": 0.567
872
+ }
873
+ ],
874
+ "logging_steps": 100,
875
+ "max_steps": 10990,
876
+ "num_input_tokens_seen": 0,
877
+ "num_train_epochs": 10,
878
+ "save_steps": 500,
879
+ "total_flos": 4.09349935387607e+19,
880
+ "train_batch_size": 16,
881
+ "trial_name": null,
882
+ "trial_params": null
883
+ }