habibi26 commited on
Commit
a83891b
1 Parent(s): 6877f14

Training in progress, epoch 0

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9936034115138592,
3
+ "total_flos": 1.0638717415807058e+19,
4
+ "train_loss": 0.580430903835514,
5
+ "train_runtime": 949.3813,
6
+ "train_samples_per_second": 142.198,
7
+ "train_steps_per_second": 1.109
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd14add15b11a72a10f176e8bb68374c3aad8669ee57e74e8ad50388a2217c6c
3
  size 349878736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea8a4b52b9192292e295133ab66d1431c1695f80ded6e0aa1e24ff697098a92
3
  size 349878736
runs/Jun12_04-27-17_65ff55f6246e/events.out.tfevents.1718166451.65ff55f6246e.34.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:857c831d1d6c16f2c4c3b21683269f5053cdae00470a5fbda8a766af653c2141
3
+ size 12829
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9936034115138592,
3
+ "total_flos": 1.0638717415807058e+19,
4
+ "train_loss": 0.580430903835514,
5
+ "train_runtime": 949.3813,
6
+ "train_samples_per_second": 142.198,
7
+ "train_steps_per_second": 1.109
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,804 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.961,
3
+ "best_model_checkpoint": "clip-vit-base-patch32-finetuned-eurosat/checkpoint-1053",
4
+ "epoch": 2.9936034115138592,
5
+ "eval_steps": 500,
6
+ "global_step": 1053,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.028429282160625444,
13
+ "grad_norm": 12.128193855285645,
14
+ "learning_rate": 4.716981132075472e-06,
15
+ "loss": 2.3369,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.05685856432125089,
20
+ "grad_norm": 19.345117568969727,
21
+ "learning_rate": 9.433962264150944e-06,
22
+ "loss": 2.0309,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.08528784648187633,
27
+ "grad_norm": 39.82497787475586,
28
+ "learning_rate": 1.4150943396226415e-05,
29
+ "loss": 1.466,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.11371712864250177,
34
+ "grad_norm": 39.60441589355469,
35
+ "learning_rate": 1.8867924528301888e-05,
36
+ "loss": 1.2444,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.14214641080312723,
41
+ "grad_norm": 40.64250946044922,
42
+ "learning_rate": 2.358490566037736e-05,
43
+ "loss": 1.0176,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.17057569296375266,
48
+ "grad_norm": 39.66933822631836,
49
+ "learning_rate": 2.830188679245283e-05,
50
+ "loss": 0.9046,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.19900497512437812,
55
+ "grad_norm": 30.824308395385742,
56
+ "learning_rate": 3.30188679245283e-05,
57
+ "loss": 0.8737,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.22743425728500355,
62
+ "grad_norm": 26.433198928833008,
63
+ "learning_rate": 3.7735849056603776e-05,
64
+ "loss": 0.8393,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.255863539445629,
69
+ "grad_norm": 21.772321701049805,
70
+ "learning_rate": 4.245283018867925e-05,
71
+ "loss": 0.8792,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.28429282160625446,
76
+ "grad_norm": 23.111845016479492,
77
+ "learning_rate": 4.716981132075472e-05,
78
+ "loss": 0.9117,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.31272210376687987,
83
+ "grad_norm": 18.194908142089844,
84
+ "learning_rate": 4.978880675818374e-05,
85
+ "loss": 0.7778,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.3411513859275053,
90
+ "grad_norm": 20.22426986694336,
91
+ "learning_rate": 4.9260823653643085e-05,
92
+ "loss": 0.8241,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.3695806680881308,
97
+ "grad_norm": 21.78709602355957,
98
+ "learning_rate": 4.8732840549102435e-05,
99
+ "loss": 0.7939,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.39800995024875624,
104
+ "grad_norm": 19.71605682373047,
105
+ "learning_rate": 4.820485744456177e-05,
106
+ "loss": 0.876,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.42643923240938164,
111
+ "grad_norm": 18.039392471313477,
112
+ "learning_rate": 4.767687434002112e-05,
113
+ "loss": 0.768,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.4548685145700071,
118
+ "grad_norm": 19.62349510192871,
119
+ "learning_rate": 4.7148891235480466e-05,
120
+ "loss": 0.7447,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.48329779673063256,
125
+ "grad_norm": 15.236215591430664,
126
+ "learning_rate": 4.662090813093981e-05,
127
+ "loss": 0.8356,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.511727078891258,
132
+ "grad_norm": 19.196414947509766,
133
+ "learning_rate": 4.609292502639916e-05,
134
+ "loss": 0.8388,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.5401563610518835,
139
+ "grad_norm": 23.391098022460938,
140
+ "learning_rate": 4.55649419218585e-05,
141
+ "loss": 0.8099,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.5685856432125089,
146
+ "grad_norm": 14.287452697753906,
147
+ "learning_rate": 4.503695881731785e-05,
148
+ "loss": 0.7713,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.5970149253731343,
153
+ "grad_norm": 21.557052612304688,
154
+ "learning_rate": 4.45089757127772e-05,
155
+ "loss": 0.7324,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.6254442075337597,
160
+ "grad_norm": 18.124984741210938,
161
+ "learning_rate": 4.398099260823654e-05,
162
+ "loss": 0.7383,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.6538734896943852,
167
+ "grad_norm": 20.559268951416016,
168
+ "learning_rate": 4.3453009503695884e-05,
169
+ "loss": 0.728,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.6823027718550106,
174
+ "grad_norm": 16.50807762145996,
175
+ "learning_rate": 4.292502639915523e-05,
176
+ "loss": 0.7594,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.7107320540156361,
181
+ "grad_norm": 18.29205894470215,
182
+ "learning_rate": 4.239704329461457e-05,
183
+ "loss": 0.7597,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.7391613361762616,
188
+ "grad_norm": 17.540321350097656,
189
+ "learning_rate": 4.186906019007392e-05,
190
+ "loss": 0.6979,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.767590618336887,
195
+ "grad_norm": 18.201658248901367,
196
+ "learning_rate": 4.1341077085533265e-05,
197
+ "loss": 0.7461,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.7960199004975125,
202
+ "grad_norm": 17.44607162475586,
203
+ "learning_rate": 4.081309398099261e-05,
204
+ "loss": 0.6786,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.8244491826581379,
209
+ "grad_norm": 14.286916732788086,
210
+ "learning_rate": 4.028511087645195e-05,
211
+ "loss": 0.6731,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.8528784648187633,
216
+ "grad_norm": 13.381218910217285,
217
+ "learning_rate": 3.97571277719113e-05,
218
+ "loss": 0.6752,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.8813077469793887,
223
+ "grad_norm": 11.218981742858887,
224
+ "learning_rate": 3.9229144667370646e-05,
225
+ "loss": 0.6389,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.9097370291400142,
230
+ "grad_norm": 11.469705581665039,
231
+ "learning_rate": 3.870116156282999e-05,
232
+ "loss": 0.643,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.9381663113006397,
237
+ "grad_norm": 17.61397933959961,
238
+ "learning_rate": 3.817317845828934e-05,
239
+ "loss": 0.6538,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.9665955934612651,
244
+ "grad_norm": 15.262922286987305,
245
+ "learning_rate": 3.764519535374868e-05,
246
+ "loss": 0.6231,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.9950248756218906,
251
+ "grad_norm": 15.590916633605957,
252
+ "learning_rate": 3.711721224920803e-05,
253
+ "loss": 0.6556,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.997867803837953,
258
+ "eval_accuracy": 0.9068,
259
+ "eval_loss": 0.28233855962753296,
260
+ "eval_runtime": 15.6893,
261
+ "eval_samples_per_second": 318.688,
262
+ "eval_steps_per_second": 10.007,
263
+ "step": 351
264
+ },
265
+ {
266
+ "epoch": 1.023454157782516,
267
+ "grad_norm": 14.132500648498535,
268
+ "learning_rate": 3.658922914466738e-05,
269
+ "loss": 0.5939,
270
+ "step": 360
271
+ },
272
+ {
273
+ "epoch": 1.0518834399431414,
274
+ "grad_norm": 14.34232234954834,
275
+ "learning_rate": 3.6061246040126714e-05,
276
+ "loss": 0.5661,
277
+ "step": 370
278
+ },
279
+ {
280
+ "epoch": 1.080312722103767,
281
+ "grad_norm": 23.517648696899414,
282
+ "learning_rate": 3.5533262935586064e-05,
283
+ "loss": 0.6292,
284
+ "step": 380
285
+ },
286
+ {
287
+ "epoch": 1.1087420042643923,
288
+ "grad_norm": 10.964395523071289,
289
+ "learning_rate": 3.500527983104541e-05,
290
+ "loss": 0.5544,
291
+ "step": 390
292
+ },
293
+ {
294
+ "epoch": 1.1371712864250179,
295
+ "grad_norm": 12.745725631713867,
296
+ "learning_rate": 3.447729672650475e-05,
297
+ "loss": 0.5386,
298
+ "step": 400
299
+ },
300
+ {
301
+ "epoch": 1.1656005685856432,
302
+ "grad_norm": 13.943474769592285,
303
+ "learning_rate": 3.3949313621964095e-05,
304
+ "loss": 0.5936,
305
+ "step": 410
306
+ },
307
+ {
308
+ "epoch": 1.1940298507462686,
309
+ "grad_norm": 16.283620834350586,
310
+ "learning_rate": 3.3421330517423445e-05,
311
+ "loss": 0.5046,
312
+ "step": 420
313
+ },
314
+ {
315
+ "epoch": 1.2224591329068941,
316
+ "grad_norm": 12.565506935119629,
317
+ "learning_rate": 3.289334741288279e-05,
318
+ "loss": 0.578,
319
+ "step": 430
320
+ },
321
+ {
322
+ "epoch": 1.2508884150675195,
323
+ "grad_norm": 12.695046424865723,
324
+ "learning_rate": 3.236536430834213e-05,
325
+ "loss": 0.5875,
326
+ "step": 440
327
+ },
328
+ {
329
+ "epoch": 1.279317697228145,
330
+ "grad_norm": 15.638214111328125,
331
+ "learning_rate": 3.183738120380148e-05,
332
+ "loss": 0.5058,
333
+ "step": 450
334
+ },
335
+ {
336
+ "epoch": 1.3077469793887704,
337
+ "grad_norm": 13.463284492492676,
338
+ "learning_rate": 3.130939809926082e-05,
339
+ "loss": 0.5279,
340
+ "step": 460
341
+ },
342
+ {
343
+ "epoch": 1.336176261549396,
344
+ "grad_norm": 10.782665252685547,
345
+ "learning_rate": 3.078141499472017e-05,
346
+ "loss": 0.542,
347
+ "step": 470
348
+ },
349
+ {
350
+ "epoch": 1.3646055437100213,
351
+ "grad_norm": 18.311925888061523,
352
+ "learning_rate": 3.0253431890179517e-05,
353
+ "loss": 0.5147,
354
+ "step": 480
355
+ },
356
+ {
357
+ "epoch": 1.3930348258706466,
358
+ "grad_norm": 12.827178955078125,
359
+ "learning_rate": 2.972544878563886e-05,
360
+ "loss": 0.5325,
361
+ "step": 490
362
+ },
363
+ {
364
+ "epoch": 1.4214641080312722,
365
+ "grad_norm": 13.880022048950195,
366
+ "learning_rate": 2.9197465681098207e-05,
367
+ "loss": 0.5294,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 1.4498933901918978,
372
+ "grad_norm": 15.585273742675781,
373
+ "learning_rate": 2.8669482576557548e-05,
374
+ "loss": 0.532,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 1.4783226723525231,
379
+ "grad_norm": 12.55144214630127,
380
+ "learning_rate": 2.8141499472016898e-05,
381
+ "loss": 0.52,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 1.5067519545131485,
386
+ "grad_norm": 13.474200248718262,
387
+ "learning_rate": 2.7613516367476245e-05,
388
+ "loss": 0.5257,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 1.535181236673774,
393
+ "grad_norm": 12.359495162963867,
394
+ "learning_rate": 2.7085533262935585e-05,
395
+ "loss": 0.5541,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 1.5636105188343994,
400
+ "grad_norm": 12.825304985046387,
401
+ "learning_rate": 2.6557550158394935e-05,
402
+ "loss": 0.4987,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 1.5920398009950247,
407
+ "grad_norm": 10.33250904083252,
408
+ "learning_rate": 2.6029567053854276e-05,
409
+ "loss": 0.4908,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 1.6204690831556503,
414
+ "grad_norm": 13.17313289642334,
415
+ "learning_rate": 2.5501583949313622e-05,
416
+ "loss": 0.4884,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 1.6488983653162759,
421
+ "grad_norm": 12.920696258544922,
422
+ "learning_rate": 2.497360084477297e-05,
423
+ "loss": 0.4873,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 1.6773276474769012,
428
+ "grad_norm": 11.354279518127441,
429
+ "learning_rate": 2.4445617740232313e-05,
430
+ "loss": 0.4974,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 1.7057569296375266,
435
+ "grad_norm": 13.763202667236328,
436
+ "learning_rate": 2.391763463569166e-05,
437
+ "loss": 0.4398,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 1.7341862117981521,
442
+ "grad_norm": 8.816915512084961,
443
+ "learning_rate": 2.3389651531151003e-05,
444
+ "loss": 0.4761,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 1.7626154939587777,
449
+ "grad_norm": 13.627618789672852,
450
+ "learning_rate": 2.286166842661035e-05,
451
+ "loss": 0.469,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 1.7910447761194028,
456
+ "grad_norm": 17.703720092773438,
457
+ "learning_rate": 2.2333685322069694e-05,
458
+ "loss": 0.4148,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 1.8194740582800284,
463
+ "grad_norm": 9.903636932373047,
464
+ "learning_rate": 2.180570221752904e-05,
465
+ "loss": 0.4824,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 1.847903340440654,
470
+ "grad_norm": 10.972967147827148,
471
+ "learning_rate": 2.1277719112988384e-05,
472
+ "loss": 0.4282,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 1.8763326226012793,
477
+ "grad_norm": 12.979598045349121,
478
+ "learning_rate": 2.074973600844773e-05,
479
+ "loss": 0.5252,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 1.9047619047619047,
484
+ "grad_norm": 11.675236701965332,
485
+ "learning_rate": 2.0221752903907075e-05,
486
+ "loss": 0.4225,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 1.9331911869225302,
491
+ "grad_norm": 13.110438346862793,
492
+ "learning_rate": 1.9693769799366422e-05,
493
+ "loss": 0.4313,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 1.9616204690831558,
498
+ "grad_norm": 8.968453407287598,
499
+ "learning_rate": 1.9165786694825765e-05,
500
+ "loss": 0.4725,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 1.9900497512437811,
505
+ "grad_norm": 13.918693542480469,
506
+ "learning_rate": 1.863780359028511e-05,
507
+ "loss": 0.4659,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 1.9985785358919688,
512
+ "eval_accuracy": 0.9474,
513
+ "eval_loss": 0.15807794034481049,
514
+ "eval_runtime": 15.4621,
515
+ "eval_samples_per_second": 323.371,
516
+ "eval_steps_per_second": 10.154,
517
+ "step": 703
518
+ },
519
+ {
520
+ "epoch": 2.0184790334044065,
521
+ "grad_norm": 10.97941780090332,
522
+ "learning_rate": 1.810982048574446e-05,
523
+ "loss": 0.4331,
524
+ "step": 710
525
+ },
526
+ {
527
+ "epoch": 2.046908315565032,
528
+ "grad_norm": 12.966859817504883,
529
+ "learning_rate": 1.7581837381203803e-05,
530
+ "loss": 0.4168,
531
+ "step": 720
532
+ },
533
+ {
534
+ "epoch": 2.0753375977256576,
535
+ "grad_norm": 13.996347427368164,
536
+ "learning_rate": 1.7053854276663146e-05,
537
+ "loss": 0.3803,
538
+ "step": 730
539
+ },
540
+ {
541
+ "epoch": 2.1037668798862827,
542
+ "grad_norm": 11.576925277709961,
543
+ "learning_rate": 1.6525871172122493e-05,
544
+ "loss": 0.3876,
545
+ "step": 740
546
+ },
547
+ {
548
+ "epoch": 2.1321961620469083,
549
+ "grad_norm": 13.173456192016602,
550
+ "learning_rate": 1.5997888067581837e-05,
551
+ "loss": 0.3753,
552
+ "step": 750
553
+ },
554
+ {
555
+ "epoch": 2.160625444207534,
556
+ "grad_norm": 10.2720365524292,
557
+ "learning_rate": 1.5469904963041184e-05,
558
+ "loss": 0.3442,
559
+ "step": 760
560
+ },
561
+ {
562
+ "epoch": 2.189054726368159,
563
+ "grad_norm": 12.404537200927734,
564
+ "learning_rate": 1.4941921858500529e-05,
565
+ "loss": 0.3509,
566
+ "step": 770
567
+ },
568
+ {
569
+ "epoch": 2.2174840085287846,
570
+ "grad_norm": 12.196104049682617,
571
+ "learning_rate": 1.4413938753959874e-05,
572
+ "loss": 0.3653,
573
+ "step": 780
574
+ },
575
+ {
576
+ "epoch": 2.24591329068941,
577
+ "grad_norm": 10.60234546661377,
578
+ "learning_rate": 1.388595564941922e-05,
579
+ "loss": 0.4059,
580
+ "step": 790
581
+ },
582
+ {
583
+ "epoch": 2.2743425728500357,
584
+ "grad_norm": 11.045681953430176,
585
+ "learning_rate": 1.3357972544878563e-05,
586
+ "loss": 0.3827,
587
+ "step": 800
588
+ },
589
+ {
590
+ "epoch": 2.302771855010661,
591
+ "grad_norm": 11.341653823852539,
592
+ "learning_rate": 1.2829989440337912e-05,
593
+ "loss": 0.3632,
594
+ "step": 810
595
+ },
596
+ {
597
+ "epoch": 2.3312011371712864,
598
+ "grad_norm": 9.08681869506836,
599
+ "learning_rate": 1.2302006335797255e-05,
600
+ "loss": 0.3687,
601
+ "step": 820
602
+ },
603
+ {
604
+ "epoch": 2.359630419331912,
605
+ "grad_norm": 11.295198440551758,
606
+ "learning_rate": 1.17740232312566e-05,
607
+ "loss": 0.3599,
608
+ "step": 830
609
+ },
610
+ {
611
+ "epoch": 2.388059701492537,
612
+ "grad_norm": 9.960636138916016,
613
+ "learning_rate": 1.1246040126715946e-05,
614
+ "loss": 0.3642,
615
+ "step": 840
616
+ },
617
+ {
618
+ "epoch": 2.4164889836531627,
619
+ "grad_norm": 12.375933647155762,
620
+ "learning_rate": 1.0718057022175291e-05,
621
+ "loss": 0.3472,
622
+ "step": 850
623
+ },
624
+ {
625
+ "epoch": 2.4449182658137882,
626
+ "grad_norm": 10.313027381896973,
627
+ "learning_rate": 1.0190073917634636e-05,
628
+ "loss": 0.3668,
629
+ "step": 860
630
+ },
631
+ {
632
+ "epoch": 2.473347547974414,
633
+ "grad_norm": 11.329744338989258,
634
+ "learning_rate": 9.662090813093982e-06,
635
+ "loss": 0.3144,
636
+ "step": 870
637
+ },
638
+ {
639
+ "epoch": 2.501776830135039,
640
+ "grad_norm": 11.012008666992188,
641
+ "learning_rate": 9.134107708553327e-06,
642
+ "loss": 0.3482,
643
+ "step": 880
644
+ },
645
+ {
646
+ "epoch": 2.5302061122956645,
647
+ "grad_norm": 8.074384689331055,
648
+ "learning_rate": 8.606124604012672e-06,
649
+ "loss": 0.3472,
650
+ "step": 890
651
+ },
652
+ {
653
+ "epoch": 2.55863539445629,
654
+ "grad_norm": 11.275156021118164,
655
+ "learning_rate": 8.078141499472017e-06,
656
+ "loss": 0.3527,
657
+ "step": 900
658
+ },
659
+ {
660
+ "epoch": 2.587064676616915,
661
+ "grad_norm": 11.760042190551758,
662
+ "learning_rate": 7.5501583949313625e-06,
663
+ "loss": 0.3503,
664
+ "step": 910
665
+ },
666
+ {
667
+ "epoch": 2.6154939587775408,
668
+ "grad_norm": 9.786343574523926,
669
+ "learning_rate": 7.022175290390708e-06,
670
+ "loss": 0.3338,
671
+ "step": 920
672
+ },
673
+ {
674
+ "epoch": 2.6439232409381663,
675
+ "grad_norm": 10.899317741394043,
676
+ "learning_rate": 6.494192185850054e-06,
677
+ "loss": 0.3648,
678
+ "step": 930
679
+ },
680
+ {
681
+ "epoch": 2.672352523098792,
682
+ "grad_norm": 9.24864673614502,
683
+ "learning_rate": 5.966209081309398e-06,
684
+ "loss": 0.3346,
685
+ "step": 940
686
+ },
687
+ {
688
+ "epoch": 2.7007818052594175,
689
+ "grad_norm": 10.97048282623291,
690
+ "learning_rate": 5.438225976768744e-06,
691
+ "loss": 0.338,
692
+ "step": 950
693
+ },
694
+ {
695
+ "epoch": 2.7292110874200426,
696
+ "grad_norm": 9.632309913635254,
697
+ "learning_rate": 4.910242872228089e-06,
698
+ "loss": 0.2918,
699
+ "step": 960
700
+ },
701
+ {
702
+ "epoch": 2.757640369580668,
703
+ "grad_norm": 9.58181381225586,
704
+ "learning_rate": 4.382259767687434e-06,
705
+ "loss": 0.3197,
706
+ "step": 970
707
+ },
708
+ {
709
+ "epoch": 2.7860696517412933,
710
+ "grad_norm": 11.46987247467041,
711
+ "learning_rate": 3.854276663146779e-06,
712
+ "loss": 0.2981,
713
+ "step": 980
714
+ },
715
+ {
716
+ "epoch": 2.814498933901919,
717
+ "grad_norm": 14.371786117553711,
718
+ "learning_rate": 3.326293558606125e-06,
719
+ "loss": 0.327,
720
+ "step": 990
721
+ },
722
+ {
723
+ "epoch": 2.8429282160625444,
724
+ "grad_norm": 11.488155364990234,
725
+ "learning_rate": 2.79831045406547e-06,
726
+ "loss": 0.3284,
727
+ "step": 1000
728
+ },
729
+ {
730
+ "epoch": 2.87135749822317,
731
+ "grad_norm": 13.239998817443848,
732
+ "learning_rate": 2.2703273495248154e-06,
733
+ "loss": 0.3365,
734
+ "step": 1010
735
+ },
736
+ {
737
+ "epoch": 2.8997867803837956,
738
+ "grad_norm": 10.396666526794434,
739
+ "learning_rate": 1.7423442449841606e-06,
740
+ "loss": 0.3238,
741
+ "step": 1020
742
+ },
743
+ {
744
+ "epoch": 2.9282160625444207,
745
+ "grad_norm": 12.260651588439941,
746
+ "learning_rate": 1.2143611404435059e-06,
747
+ "loss": 0.3026,
748
+ "step": 1030
749
+ },
750
+ {
751
+ "epoch": 2.9566453447050463,
752
+ "grad_norm": 9.99549674987793,
753
+ "learning_rate": 6.863780359028511e-07,
754
+ "loss": 0.2994,
755
+ "step": 1040
756
+ },
757
+ {
758
+ "epoch": 2.9850746268656714,
759
+ "grad_norm": 9.32156753540039,
760
+ "learning_rate": 1.5839493136219642e-07,
761
+ "loss": 0.2639,
762
+ "step": 1050
763
+ },
764
+ {
765
+ "epoch": 2.9936034115138592,
766
+ "eval_accuracy": 0.961,
767
+ "eval_loss": 0.11085611581802368,
768
+ "eval_runtime": 15.421,
769
+ "eval_samples_per_second": 324.234,
770
+ "eval_steps_per_second": 10.181,
771
+ "step": 1053
772
+ },
773
+ {
774
+ "epoch": 2.9936034115138592,
775
+ "step": 1053,
776
+ "total_flos": 1.0638717415807058e+19,
777
+ "train_loss": 0.580430903835514,
778
+ "train_runtime": 949.3813,
779
+ "train_samples_per_second": 142.198,
780
+ "train_steps_per_second": 1.109
781
+ }
782
+ ],
783
+ "logging_steps": 10,
784
+ "max_steps": 1053,
785
+ "num_input_tokens_seen": 0,
786
+ "num_train_epochs": 3,
787
+ "save_steps": 500,
788
+ "stateful_callbacks": {
789
+ "TrainerControl": {
790
+ "args": {
791
+ "should_epoch_stop": false,
792
+ "should_evaluate": false,
793
+ "should_log": false,
794
+ "should_save": true,
795
+ "should_training_stop": true
796
+ },
797
+ "attributes": {}
798
+ }
799
+ },
800
+ "total_flos": 1.0638717415807058e+19,
801
+ "train_batch_size": 32,
802
+ "trial_name": null,
803
+ "trial_params": null
804
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dfc4640fed2b80e2d69ad29ef3f6565192536c0b796d9590445cf9e11809213
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e77c0635fe18fdcd029c5f2aacb5b537670fd7be347e30a5738553507f182463
3
  size 5176