bliebfl commited on
Commit
402fe9c
1 Parent(s): 4f96cae

Training in progress, epoch 0

Browse files
all_results.json CHANGED
@@ -1,4 +1,13 @@
1
  {
2
- "eval_accuracy": 0.5844425237683665,
3
- "eval_loss": 2.1884803771972656
 
 
 
 
 
 
 
 
 
4
  }
 
1
  {
2
+ "epoch": 2.99,
3
+ "eval_accuracy": 0.8155574762316335,
4
+ "eval_loss": 0.9370825290679932,
5
+ "eval_runtime": 27.7234,
6
+ "eval_samples_per_second": 208.669,
7
+ "eval_steps_per_second": 6.529,
8
+ "total_flos": 3.964011227564194e+18,
9
+ "train_loss": 1.7593435168462042,
10
+ "train_runtime": 1295.0132,
11
+ "train_samples_per_second": 120.603,
12
+ "train_steps_per_second": 0.941
13
  }
eval_results.json CHANGED
@@ -1,4 +1,8 @@
1
  {
2
- "eval_accuracy": 0.5844425237683665,
3
- "eval_loss": 2.1884803771972656
 
 
 
 
4
  }
 
1
  {
2
+ "epoch": 2.99,
3
+ "eval_accuracy": 0.8155574762316335,
4
+ "eval_loss": 0.9370825290679932,
5
+ "eval_runtime": 27.7234,
6
+ "eval_samples_per_second": 208.669,
7
+ "eval_steps_per_second": 6.529
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14a3ca9e763de67931f5ecefb2b07c513c47a4b80c4e4d75d3deeb7e9a22338c
3
  size 112253100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6fdeeeb42a965a4e293c210f0f393bbaf492dcb3b9063ca69757537f65180f
3
  size 112253100
preprocessor_config.json CHANGED
@@ -1,27 +1,22 @@
1
  {
2
- "crop_size": {
3
- "height": 224,
4
- "width": 224
5
- },
6
- "do_center_crop": true,
7
- "do_convert_rgb": true,
8
  "do_normalize": true,
9
  "do_rescale": true,
10
  "do_resize": true,
11
  "image_mean": [
12
- 0.48145466,
13
- 0.4578275,
14
- 0.40821073
15
  ],
16
- "image_processor_type": "CLIPImageProcessor",
17
  "image_std": [
18
- 0.26862954,
19
- 0.26130258,
20
- 0.27577711
21
  ],
22
  "resample": 3,
23
  "rescale_factor": 0.00392156862745098,
24
  "size": {
25
- "shortest_edge": 224
 
26
  }
27
  }
 
1
  {
 
 
 
 
 
 
2
  "do_normalize": true,
3
  "do_rescale": true,
4
  "do_resize": true,
5
  "image_mean": [
6
+ 0.485,
7
+ 0.456,
8
+ 0.406
9
  ],
10
+ "image_processor_type": "ViTImageProcessor",
11
  "image_std": [
12
+ 0.229,
13
+ 0.224,
14
+ 0.225
15
  ],
16
  "resample": 3,
17
  "rescale_factor": 0.00392156862745098,
18
  "size": {
19
+ "height": 224,
20
+ "width": 224
21
  }
22
  }
runs/Dec14_15-25-42_bc148a6f3d4e/events.out.tfevents.1702588011.bc148a6f3d4e.66026.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df2e58879b9f43ade6b924b14ff23a94478377c46312d9b80eb412eceaa30ce
3
+ size 411
runs/Dec14_21-09-06_bc148a6f3d4e/events.out.tfevents.1702588166.bc148a6f3d4e.66026.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86bd88ac5bd5f85f67dc3cacecc45d1f189628e9943402117b7e0d083c4b8fc
3
+ size 36028
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "total_flos": 3.964011227564194e+18,
4
+ "train_loss": 1.7593435168462042,
5
+ "train_runtime": 1295.0132,
6
+ "train_samples_per_second": 120.603,
7
+ "train_steps_per_second": 0.941
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,783 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8155574762316335,
3
+ "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1218",
4
+ "epoch": 2.994468346650277,
5
+ "eval_steps": 500,
6
+ "global_step": 1218,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 4.098360655737704e-06,
14
+ "loss": 2.5241,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 8.196721311475409e-06,
20
+ "loss": 2.3898,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "learning_rate": 1.2295081967213116e-05,
26
+ "loss": 2.4011,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 1.6393442622950818e-05,
32
+ "loss": 2.4128,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.12,
37
+ "learning_rate": 2.0491803278688525e-05,
38
+ "loss": 2.5282,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.15,
43
+ "learning_rate": 2.459016393442623e-05,
44
+ "loss": 2.4022,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.17,
49
+ "learning_rate": 2.8688524590163935e-05,
50
+ "loss": 2.4011,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.2,
55
+ "learning_rate": 3.2786885245901635e-05,
56
+ "loss": 2.4441,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.22,
61
+ "learning_rate": 3.6885245901639346e-05,
62
+ "loss": 2.4701,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.25,
67
+ "learning_rate": 4.098360655737705e-05,
68
+ "loss": 2.3947,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.27,
73
+ "learning_rate": 4.508196721311476e-05,
74
+ "loss": 2.3731,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.3,
79
+ "learning_rate": 4.918032786885246e-05,
80
+ "loss": 2.402,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.32,
85
+ "learning_rate": 4.963503649635037e-05,
86
+ "loss": 2.2692,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.34,
91
+ "learning_rate": 4.9178832116788325e-05,
92
+ "loss": 2.3917,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.37,
97
+ "learning_rate": 4.872262773722628e-05,
98
+ "loss": 2.2329,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.39,
103
+ "learning_rate": 4.8266423357664235e-05,
104
+ "loss": 2.2251,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.42,
109
+ "learning_rate": 4.7810218978102196e-05,
110
+ "loss": 2.119,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.44,
115
+ "learning_rate": 4.7354014598540144e-05,
116
+ "loss": 2.1584,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.47,
121
+ "learning_rate": 4.6897810218978106e-05,
122
+ "loss": 2.2603,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.49,
127
+ "learning_rate": 4.644160583941606e-05,
128
+ "loss": 2.2187,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.52,
133
+ "learning_rate": 4.5985401459854016e-05,
134
+ "loss": 2.1734,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.54,
139
+ "learning_rate": 4.552919708029198e-05,
140
+ "loss": 2.1851,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.57,
145
+ "learning_rate": 4.5072992700729925e-05,
146
+ "loss": 2.0539,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.59,
151
+ "learning_rate": 4.461678832116789e-05,
152
+ "loss": 2.0854,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.61,
157
+ "learning_rate": 4.416058394160584e-05,
158
+ "loss": 2.107,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.64,
163
+ "learning_rate": 4.3704379562043796e-05,
164
+ "loss": 2.0371,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.66,
169
+ "learning_rate": 4.324817518248175e-05,
170
+ "loss": 2.1036,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.69,
175
+ "learning_rate": 4.279197080291971e-05,
176
+ "loss": 2.0236,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.71,
181
+ "learning_rate": 4.233576642335767e-05,
182
+ "loss": 1.9557,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.74,
187
+ "learning_rate": 4.187956204379562e-05,
188
+ "loss": 1.9848,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.76,
193
+ "learning_rate": 4.1423357664233584e-05,
194
+ "loss": 1.9344,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.79,
199
+ "learning_rate": 4.096715328467153e-05,
200
+ "loss": 2.0378,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.81,
205
+ "learning_rate": 4.0510948905109494e-05,
206
+ "loss": 1.9012,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.84,
211
+ "learning_rate": 4.005474452554745e-05,
212
+ "loss": 1.8865,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.86,
217
+ "learning_rate": 3.95985401459854e-05,
218
+ "loss": 1.8976,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.89,
223
+ "learning_rate": 3.914233576642336e-05,
224
+ "loss": 1.9119,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.91,
229
+ "learning_rate": 3.868613138686132e-05,
230
+ "loss": 1.9407,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.93,
235
+ "learning_rate": 3.822992700729927e-05,
236
+ "loss": 1.7041,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.96,
241
+ "learning_rate": 3.777372262773723e-05,
242
+ "loss": 1.8431,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.98,
247
+ "learning_rate": 3.7317518248175184e-05,
248
+ "loss": 1.9174,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 1.0,
253
+ "eval_accuracy": 0.7210025929127053,
254
+ "eval_loss": 1.3900867700576782,
255
+ "eval_runtime": 27.5624,
256
+ "eval_samples_per_second": 209.887,
257
+ "eval_steps_per_second": 6.567,
258
+ "step": 406
259
+ },
260
+ {
261
+ "epoch": 1.01,
262
+ "learning_rate": 3.686131386861314e-05,
263
+ "loss": 1.8769,
264
+ "step": 410
265
+ },
266
+ {
267
+ "epoch": 1.03,
268
+ "learning_rate": 3.64051094890511e-05,
269
+ "loss": 1.8611,
270
+ "step": 420
271
+ },
272
+ {
273
+ "epoch": 1.06,
274
+ "learning_rate": 3.594890510948905e-05,
275
+ "loss": 1.7806,
276
+ "step": 430
277
+ },
278
+ {
279
+ "epoch": 1.08,
280
+ "learning_rate": 3.549270072992701e-05,
281
+ "loss": 1.723,
282
+ "step": 440
283
+ },
284
+ {
285
+ "epoch": 1.11,
286
+ "learning_rate": 3.5036496350364965e-05,
287
+ "loss": 1.6738,
288
+ "step": 450
289
+ },
290
+ {
291
+ "epoch": 1.13,
292
+ "learning_rate": 3.458029197080292e-05,
293
+ "loss": 1.7652,
294
+ "step": 460
295
+ },
296
+ {
297
+ "epoch": 1.16,
298
+ "learning_rate": 3.4124087591240875e-05,
299
+ "loss": 1.8163,
300
+ "step": 470
301
+ },
302
+ {
303
+ "epoch": 1.18,
304
+ "learning_rate": 3.3667883211678836e-05,
305
+ "loss": 1.7474,
306
+ "step": 480
307
+ },
308
+ {
309
+ "epoch": 1.2,
310
+ "learning_rate": 3.321167883211679e-05,
311
+ "loss": 1.754,
312
+ "step": 490
313
+ },
314
+ {
315
+ "epoch": 1.23,
316
+ "learning_rate": 3.2755474452554746e-05,
317
+ "loss": 1.805,
318
+ "step": 500
319
+ },
320
+ {
321
+ "epoch": 1.25,
322
+ "learning_rate": 3.229927007299271e-05,
323
+ "loss": 1.6809,
324
+ "step": 510
325
+ },
326
+ {
327
+ "epoch": 1.28,
328
+ "learning_rate": 3.1843065693430655e-05,
329
+ "loss": 1.6914,
330
+ "step": 520
331
+ },
332
+ {
333
+ "epoch": 1.3,
334
+ "learning_rate": 3.138686131386862e-05,
335
+ "loss": 1.6213,
336
+ "step": 530
337
+ },
338
+ {
339
+ "epoch": 1.33,
340
+ "learning_rate": 3.093065693430657e-05,
341
+ "loss": 1.8014,
342
+ "step": 540
343
+ },
344
+ {
345
+ "epoch": 1.35,
346
+ "learning_rate": 3.0474452554744527e-05,
347
+ "loss": 1.6069,
348
+ "step": 550
349
+ },
350
+ {
351
+ "epoch": 1.38,
352
+ "learning_rate": 3.0018248175182485e-05,
353
+ "loss": 1.6734,
354
+ "step": 560
355
+ },
356
+ {
357
+ "epoch": 1.4,
358
+ "learning_rate": 2.9562043795620443e-05,
359
+ "loss": 1.7384,
360
+ "step": 570
361
+ },
362
+ {
363
+ "epoch": 1.43,
364
+ "learning_rate": 2.9105839416058394e-05,
365
+ "loss": 1.7237,
366
+ "step": 580
367
+ },
368
+ {
369
+ "epoch": 1.45,
370
+ "learning_rate": 2.8649635036496353e-05,
371
+ "loss": 1.7187,
372
+ "step": 590
373
+ },
374
+ {
375
+ "epoch": 1.48,
376
+ "learning_rate": 2.8193430656934304e-05,
377
+ "loss": 1.6708,
378
+ "step": 600
379
+ },
380
+ {
381
+ "epoch": 1.5,
382
+ "learning_rate": 2.7737226277372262e-05,
383
+ "loss": 1.6979,
384
+ "step": 610
385
+ },
386
+ {
387
+ "epoch": 1.52,
388
+ "learning_rate": 2.728102189781022e-05,
389
+ "loss": 1.7762,
390
+ "step": 620
391
+ },
392
+ {
393
+ "epoch": 1.55,
394
+ "learning_rate": 2.6824817518248175e-05,
395
+ "loss": 1.6503,
396
+ "step": 630
397
+ },
398
+ {
399
+ "epoch": 1.57,
400
+ "learning_rate": 2.6368613138686133e-05,
401
+ "loss": 1.5918,
402
+ "step": 640
403
+ },
404
+ {
405
+ "epoch": 1.6,
406
+ "learning_rate": 2.591240875912409e-05,
407
+ "loss": 1.6282,
408
+ "step": 650
409
+ },
410
+ {
411
+ "epoch": 1.62,
412
+ "learning_rate": 2.5456204379562043e-05,
413
+ "loss": 1.5736,
414
+ "step": 660
415
+ },
416
+ {
417
+ "epoch": 1.65,
418
+ "learning_rate": 2.5e-05,
419
+ "loss": 1.5454,
420
+ "step": 670
421
+ },
422
+ {
423
+ "epoch": 1.67,
424
+ "learning_rate": 2.4543795620437956e-05,
425
+ "loss": 1.6593,
426
+ "step": 680
427
+ },
428
+ {
429
+ "epoch": 1.7,
430
+ "learning_rate": 2.4087591240875914e-05,
431
+ "loss": 1.5685,
432
+ "step": 690
433
+ },
434
+ {
435
+ "epoch": 1.72,
436
+ "learning_rate": 2.363138686131387e-05,
437
+ "loss": 1.5265,
438
+ "step": 700
439
+ },
440
+ {
441
+ "epoch": 1.75,
442
+ "learning_rate": 2.3175182481751824e-05,
443
+ "loss": 1.5889,
444
+ "step": 710
445
+ },
446
+ {
447
+ "epoch": 1.77,
448
+ "learning_rate": 2.2718978102189782e-05,
449
+ "loss": 1.5552,
450
+ "step": 720
451
+ },
452
+ {
453
+ "epoch": 1.79,
454
+ "learning_rate": 2.226277372262774e-05,
455
+ "loss": 1.5238,
456
+ "step": 730
457
+ },
458
+ {
459
+ "epoch": 1.82,
460
+ "learning_rate": 2.1806569343065695e-05,
461
+ "loss": 1.6708,
462
+ "step": 740
463
+ },
464
+ {
465
+ "epoch": 1.84,
466
+ "learning_rate": 2.135036496350365e-05,
467
+ "loss": 1.5535,
468
+ "step": 750
469
+ },
470
+ {
471
+ "epoch": 1.87,
472
+ "learning_rate": 2.0894160583941608e-05,
473
+ "loss": 1.6004,
474
+ "step": 760
475
+ },
476
+ {
477
+ "epoch": 1.89,
478
+ "learning_rate": 2.0437956204379563e-05,
479
+ "loss": 1.5265,
480
+ "step": 770
481
+ },
482
+ {
483
+ "epoch": 1.92,
484
+ "learning_rate": 1.9981751824817518e-05,
485
+ "loss": 1.5925,
486
+ "step": 780
487
+ },
488
+ {
489
+ "epoch": 1.94,
490
+ "learning_rate": 1.9525547445255476e-05,
491
+ "loss": 1.513,
492
+ "step": 790
493
+ },
494
+ {
495
+ "epoch": 1.97,
496
+ "learning_rate": 1.906934306569343e-05,
497
+ "loss": 1.6098,
498
+ "step": 800
499
+ },
500
+ {
501
+ "epoch": 1.99,
502
+ "learning_rate": 1.861313868613139e-05,
503
+ "loss": 1.5653,
504
+ "step": 810
505
+ },
506
+ {
507
+ "epoch": 2.0,
508
+ "eval_accuracy": 0.7937770095073465,
509
+ "eval_loss": 1.035827875137329,
510
+ "eval_runtime": 28.5917,
511
+ "eval_samples_per_second": 202.331,
512
+ "eval_steps_per_second": 6.331,
513
+ "step": 813
514
+ },
515
+ {
516
+ "epoch": 2.02,
517
+ "learning_rate": 1.8156934306569344e-05,
518
+ "loss": 1.4894,
519
+ "step": 820
520
+ },
521
+ {
522
+ "epoch": 2.04,
523
+ "learning_rate": 1.7700729927007302e-05,
524
+ "loss": 1.3743,
525
+ "step": 830
526
+ },
527
+ {
528
+ "epoch": 2.07,
529
+ "learning_rate": 1.7244525547445257e-05,
530
+ "loss": 1.5641,
531
+ "step": 840
532
+ },
533
+ {
534
+ "epoch": 2.09,
535
+ "learning_rate": 1.678832116788321e-05,
536
+ "loss": 1.5444,
537
+ "step": 850
538
+ },
539
+ {
540
+ "epoch": 2.11,
541
+ "learning_rate": 1.633211678832117e-05,
542
+ "loss": 1.514,
543
+ "step": 860
544
+ },
545
+ {
546
+ "epoch": 2.14,
547
+ "learning_rate": 1.5875912408759125e-05,
548
+ "loss": 1.5504,
549
+ "step": 870
550
+ },
551
+ {
552
+ "epoch": 2.16,
553
+ "learning_rate": 1.541970802919708e-05,
554
+ "loss": 1.5201,
555
+ "step": 880
556
+ },
557
+ {
558
+ "epoch": 2.19,
559
+ "learning_rate": 1.496350364963504e-05,
560
+ "loss": 1.5385,
561
+ "step": 890
562
+ },
563
+ {
564
+ "epoch": 2.21,
565
+ "learning_rate": 1.4507299270072994e-05,
566
+ "loss": 1.4317,
567
+ "step": 900
568
+ },
569
+ {
570
+ "epoch": 2.24,
571
+ "learning_rate": 1.4051094890510949e-05,
572
+ "loss": 1.4826,
573
+ "step": 910
574
+ },
575
+ {
576
+ "epoch": 2.26,
577
+ "learning_rate": 1.3594890510948904e-05,
578
+ "loss": 1.4028,
579
+ "step": 920
580
+ },
581
+ {
582
+ "epoch": 2.29,
583
+ "learning_rate": 1.3138686131386862e-05,
584
+ "loss": 1.4444,
585
+ "step": 930
586
+ },
587
+ {
588
+ "epoch": 2.31,
589
+ "learning_rate": 1.2682481751824818e-05,
590
+ "loss": 1.4388,
591
+ "step": 940
592
+ },
593
+ {
594
+ "epoch": 2.34,
595
+ "learning_rate": 1.2226277372262775e-05,
596
+ "loss": 1.4685,
597
+ "step": 950
598
+ },
599
+ {
600
+ "epoch": 2.36,
601
+ "learning_rate": 1.177007299270073e-05,
602
+ "loss": 1.4684,
603
+ "step": 960
604
+ },
605
+ {
606
+ "epoch": 2.38,
607
+ "learning_rate": 1.1313868613138686e-05,
608
+ "loss": 1.4367,
609
+ "step": 970
610
+ },
611
+ {
612
+ "epoch": 2.41,
613
+ "learning_rate": 1.0857664233576643e-05,
614
+ "loss": 1.4243,
615
+ "step": 980
616
+ },
617
+ {
618
+ "epoch": 2.43,
619
+ "learning_rate": 1.04014598540146e-05,
620
+ "loss": 1.3886,
621
+ "step": 990
622
+ },
623
+ {
624
+ "epoch": 2.46,
625
+ "learning_rate": 9.945255474452556e-06,
626
+ "loss": 1.4465,
627
+ "step": 1000
628
+ },
629
+ {
630
+ "epoch": 2.48,
631
+ "learning_rate": 9.48905109489051e-06,
632
+ "loss": 1.4956,
633
+ "step": 1010
634
+ },
635
+ {
636
+ "epoch": 2.51,
637
+ "learning_rate": 9.032846715328467e-06,
638
+ "loss": 1.4303,
639
+ "step": 1020
640
+ },
641
+ {
642
+ "epoch": 2.53,
643
+ "learning_rate": 8.576642335766425e-06,
644
+ "loss": 1.5446,
645
+ "step": 1030
646
+ },
647
+ {
648
+ "epoch": 2.56,
649
+ "learning_rate": 8.12043795620438e-06,
650
+ "loss": 1.4384,
651
+ "step": 1040
652
+ },
653
+ {
654
+ "epoch": 2.58,
655
+ "learning_rate": 7.664233576642336e-06,
656
+ "loss": 1.406,
657
+ "step": 1050
658
+ },
659
+ {
660
+ "epoch": 2.61,
661
+ "learning_rate": 7.208029197080292e-06,
662
+ "loss": 1.3875,
663
+ "step": 1060
664
+ },
665
+ {
666
+ "epoch": 2.63,
667
+ "learning_rate": 6.751824817518249e-06,
668
+ "loss": 1.4809,
669
+ "step": 1070
670
+ },
671
+ {
672
+ "epoch": 2.66,
673
+ "learning_rate": 6.295620437956205e-06,
674
+ "loss": 1.4816,
675
+ "step": 1080
676
+ },
677
+ {
678
+ "epoch": 2.68,
679
+ "learning_rate": 5.839416058394161e-06,
680
+ "loss": 1.4504,
681
+ "step": 1090
682
+ },
683
+ {
684
+ "epoch": 2.7,
685
+ "learning_rate": 5.3832116788321165e-06,
686
+ "loss": 1.3895,
687
+ "step": 1100
688
+ },
689
+ {
690
+ "epoch": 2.73,
691
+ "learning_rate": 4.927007299270074e-06,
692
+ "loss": 1.3738,
693
+ "step": 1110
694
+ },
695
+ {
696
+ "epoch": 2.75,
697
+ "learning_rate": 4.4708029197080295e-06,
698
+ "loss": 1.4794,
699
+ "step": 1120
700
+ },
701
+ {
702
+ "epoch": 2.78,
703
+ "learning_rate": 4.014598540145985e-06,
704
+ "loss": 1.4486,
705
+ "step": 1130
706
+ },
707
+ {
708
+ "epoch": 2.8,
709
+ "learning_rate": 3.5583941605839416e-06,
710
+ "loss": 1.4103,
711
+ "step": 1140
712
+ },
713
+ {
714
+ "epoch": 2.83,
715
+ "learning_rate": 3.102189781021898e-06,
716
+ "loss": 1.341,
717
+ "step": 1150
718
+ },
719
+ {
720
+ "epoch": 2.85,
721
+ "learning_rate": 2.6459854014598542e-06,
722
+ "loss": 1.507,
723
+ "step": 1160
724
+ },
725
+ {
726
+ "epoch": 2.88,
727
+ "learning_rate": 2.1897810218978103e-06,
728
+ "loss": 1.4404,
729
+ "step": 1170
730
+ },
731
+ {
732
+ "epoch": 2.9,
733
+ "learning_rate": 1.7335766423357664e-06,
734
+ "loss": 1.5609,
735
+ "step": 1180
736
+ },
737
+ {
738
+ "epoch": 2.93,
739
+ "learning_rate": 1.2773722627737227e-06,
740
+ "loss": 1.3595,
741
+ "step": 1190
742
+ },
743
+ {
744
+ "epoch": 2.95,
745
+ "learning_rate": 8.211678832116789e-07,
746
+ "loss": 1.3526,
747
+ "step": 1200
748
+ },
749
+ {
750
+ "epoch": 2.97,
751
+ "learning_rate": 3.6496350364963505e-07,
752
+ "loss": 1.4324,
753
+ "step": 1210
754
+ },
755
+ {
756
+ "epoch": 2.99,
757
+ "eval_accuracy": 0.8155574762316335,
758
+ "eval_loss": 0.9370825290679932,
759
+ "eval_runtime": 28.5559,
760
+ "eval_samples_per_second": 202.585,
761
+ "eval_steps_per_second": 6.338,
762
+ "step": 1218
763
+ },
764
+ {
765
+ "epoch": 2.99,
766
+ "step": 1218,
767
+ "total_flos": 3.964011227564194e+18,
768
+ "train_loss": 1.7593435168462042,
769
+ "train_runtime": 1295.0132,
770
+ "train_samples_per_second": 120.603,
771
+ "train_steps_per_second": 0.941
772
+ }
773
+ ],
774
+ "logging_steps": 10,
775
+ "max_steps": 1218,
776
+ "num_input_tokens_seen": 0,
777
+ "num_train_epochs": 3,
778
+ "save_steps": 500,
779
+ "total_flos": 3.964011227564194e+18,
780
+ "train_batch_size": 32,
781
+ "trial_name": null,
782
+ "trial_params": null
783
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec17a337e7134b0cc23e76d04dfd8d88bd4991ed9400fdb08c34caacf1651179
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b817e7cf58621d108aadfeb2f1e40ef5edbacea71e62361ef175c45a4e19ee
3
  size 4792