fxwang commited on
Commit
179f60f
1 Parent(s): 2137d2e

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +22 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +921 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-base-patch32",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 512,
10
+ "text_config": {
11
+ "bos_token_id": 0,
12
+ "dropout": 0.0,
13
+ "eos_token_id": 2,
14
+ "model_type": "clip_text_model"
15
+ },
16
+ "torch_dtype": "float32",
17
+ "transformers_version": "4.36.2",
18
+ "vision_config": {
19
+ "dropout": 0.0,
20
+ "model_type": "clip_vision_model"
21
+ }
22
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36869bf8cd0c33c6f38642a9dceba50c3d9fda5ce9d36ed9625698f2c83b65ff
3
+ size 605156676
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3388782bcb101d2feeb7a16efb36332588494bd88a8279771aab3f580708e5d7
3
+ size 1210551612
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854d44a3446226203a88f1fc642af80860bfb849fcb9be9cb5df2b3857efab6f
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d09f3bec470486aa4f00a936c857eeda8fa2574ce0b622ef10c0866365aab599
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,921 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9036144578313253,
5
+ "eval_steps": 500,
6
+ "global_step": 150,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 4.9995000000000005e-05,
14
+ "loss": 1.7049,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 4.999e-05,
20
+ "loss": 2.9872,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 4.9985e-05,
26
+ "loss": 2.1065,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 4.9980000000000006e-05,
32
+ "loss": 2.2636,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 4.9975e-05,
38
+ "loss": 1.8175,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 4.997e-05,
44
+ "loss": 1.5265,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 4.9965e-05,
50
+ "loss": 1.3999,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 4.996e-05,
56
+ "loss": 1.3867,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 4.9955e-05,
62
+ "loss": 1.3329,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 4.995e-05,
68
+ "loss": 1.3145,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 4.9945000000000004e-05,
74
+ "loss": 1.2775,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 4.9940000000000006e-05,
80
+ "loss": 1.2551,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 4.9935e-05,
86
+ "loss": 1.2279,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 4.9930000000000005e-05,
92
+ "loss": 1.1668,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 4.992500000000001e-05,
98
+ "loss": 1.1261,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.1,
103
+ "learning_rate": 4.992e-05,
104
+ "loss": 1.1738,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 4.9915e-05,
110
+ "loss": 1.1098,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.11,
115
+ "learning_rate": 4.991e-05,
116
+ "loss": 1.1268,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 4.9905000000000004e-05,
122
+ "loss": 1.1261,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.12,
127
+ "learning_rate": 4.99e-05,
128
+ "loss": 1.1152,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.13,
133
+ "learning_rate": 4.9895e-05,
134
+ "loss": 1.1345,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 4.9890000000000005e-05,
140
+ "loss": 1.1341,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.14,
145
+ "learning_rate": 4.9885e-05,
146
+ "loss": 1.1288,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 4.9880000000000004e-05,
152
+ "loss": 1.1264,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.15,
157
+ "learning_rate": 4.9875000000000006e-05,
158
+ "loss": 1.0576,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.16,
163
+ "learning_rate": 4.987e-05,
164
+ "loss": 1.0905,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.16,
169
+ "learning_rate": 4.9865e-05,
170
+ "loss": 1.0967,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.17,
175
+ "learning_rate": 4.986e-05,
176
+ "loss": 1.0937,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 4.9855e-05,
182
+ "loss": 1.0597,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.18,
187
+ "learning_rate": 4.9850000000000006e-05,
188
+ "loss": 1.0706,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.19,
193
+ "learning_rate": 4.9845e-05,
194
+ "loss": 1.0608,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.19,
199
+ "learning_rate": 4.9840000000000004e-05,
200
+ "loss": 1.0817,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.2,
205
+ "learning_rate": 4.9835000000000007e-05,
206
+ "loss": 1.0739,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.2,
211
+ "learning_rate": 4.983e-05,
212
+ "loss": 1.0434,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.21,
217
+ "learning_rate": 4.9825000000000005e-05,
218
+ "loss": 1.0168,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.22,
223
+ "learning_rate": 4.982e-05,
224
+ "loss": 1.0351,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.22,
229
+ "learning_rate": 4.9815e-05,
230
+ "loss": 1.0435,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.23,
235
+ "learning_rate": 4.981e-05,
236
+ "loss": 1.0247,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.23,
241
+ "learning_rate": 4.9805e-05,
242
+ "loss": 1.0065,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.24,
247
+ "learning_rate": 4.9800000000000004e-05,
248
+ "loss": 1.0036,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.25,
253
+ "learning_rate": 4.9795e-05,
254
+ "loss": 1.0483,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.25,
259
+ "learning_rate": 4.979e-05,
260
+ "loss": 1.0252,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.26,
265
+ "learning_rate": 4.9785000000000005e-05,
266
+ "loss": 1.0344,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.27,
271
+ "learning_rate": 4.978e-05,
272
+ "loss": 1.0353,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.27,
277
+ "learning_rate": 4.9775000000000004e-05,
278
+ "loss": 1.0381,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.28,
283
+ "learning_rate": 4.977e-05,
284
+ "loss": 0.9899,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.28,
289
+ "learning_rate": 4.9765e-05,
290
+ "loss": 0.9786,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.29,
295
+ "learning_rate": 4.976e-05,
296
+ "loss": 1.0434,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.3,
301
+ "learning_rate": 4.9755e-05,
302
+ "loss": 1.0069,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.3,
307
+ "learning_rate": 4.975e-05,
308
+ "loss": 0.9665,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.31,
313
+ "learning_rate": 4.9745000000000006e-05,
314
+ "loss": 0.9754,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.31,
319
+ "learning_rate": 4.974e-05,
320
+ "loss": 0.9718,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.32,
325
+ "learning_rate": 4.9735000000000004e-05,
326
+ "loss": 0.9828,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.33,
331
+ "learning_rate": 4.973000000000001e-05,
332
+ "loss": 0.996,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.33,
337
+ "learning_rate": 4.9725e-05,
338
+ "loss": 1.026,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.34,
343
+ "learning_rate": 4.972e-05,
344
+ "loss": 0.9832,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.34,
349
+ "learning_rate": 4.9715e-05,
350
+ "loss": 0.9985,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.35,
355
+ "learning_rate": 4.9710000000000003e-05,
356
+ "loss": 1.0145,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.36,
361
+ "learning_rate": 4.9705e-05,
362
+ "loss": 0.9708,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.36,
367
+ "learning_rate": 4.97e-05,
368
+ "loss": 0.9411,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.37,
373
+ "learning_rate": 4.9695000000000004e-05,
374
+ "loss": 0.9774,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.37,
379
+ "learning_rate": 4.969e-05,
380
+ "loss": 1.0044,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.38,
385
+ "learning_rate": 4.9685e-05,
386
+ "loss": 0.9581,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.39,
391
+ "learning_rate": 4.9680000000000005e-05,
392
+ "loss": 1.0007,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.39,
397
+ "learning_rate": 4.967500000000001e-05,
398
+ "loss": 0.9589,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.4,
403
+ "learning_rate": 4.967e-05,
404
+ "loss": 0.9704,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.4,
409
+ "learning_rate": 4.9665e-05,
410
+ "loss": 0.978,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.41,
415
+ "learning_rate": 4.966e-05,
416
+ "loss": 0.9554,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.42,
421
+ "learning_rate": 4.9655000000000005e-05,
422
+ "loss": 0.9433,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.42,
427
+ "learning_rate": 4.965e-05,
428
+ "loss": 0.9905,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.43,
433
+ "learning_rate": 4.9645e-05,
434
+ "loss": 0.9578,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.43,
439
+ "learning_rate": 4.9640000000000006e-05,
440
+ "loss": 0.9069,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.44,
445
+ "learning_rate": 4.9635e-05,
446
+ "loss": 0.9647,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.45,
451
+ "learning_rate": 4.9630000000000004e-05,
452
+ "loss": 0.9377,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.45,
457
+ "learning_rate": 4.962500000000001e-05,
458
+ "loss": 0.9343,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.46,
463
+ "learning_rate": 4.962e-05,
464
+ "loss": 0.9644,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.46,
469
+ "learning_rate": 4.9615e-05,
470
+ "loss": 0.9737,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.47,
475
+ "learning_rate": 4.961e-05,
476
+ "loss": 0.9552,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.48,
481
+ "learning_rate": 4.9605000000000004e-05,
482
+ "loss": 0.9158,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.48,
487
+ "learning_rate": 4.96e-05,
488
+ "loss": 0.9278,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.49,
493
+ "learning_rate": 4.9595e-05,
494
+ "loss": 0.9464,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.49,
499
+ "learning_rate": 4.9590000000000005e-05,
500
+ "loss": 0.9672,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.5,
505
+ "learning_rate": 4.9585e-05,
506
+ "loss": 0.9487,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.51,
511
+ "learning_rate": 4.958e-05,
512
+ "loss": 0.9248,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.51,
517
+ "learning_rate": 4.9575000000000006e-05,
518
+ "loss": 0.9443,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.52,
523
+ "learning_rate": 4.957e-05,
524
+ "loss": 0.9565,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.52,
529
+ "learning_rate": 4.9565e-05,
530
+ "loss": 0.934,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.53,
535
+ "learning_rate": 4.956e-05,
536
+ "loss": 0.9198,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.54,
541
+ "learning_rate": 4.9555e-05,
542
+ "loss": 0.8948,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.54,
547
+ "learning_rate": 4.9550000000000005e-05,
548
+ "loss": 0.9336,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.55,
553
+ "learning_rate": 4.9545e-05,
554
+ "loss": 0.9117,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.55,
559
+ "learning_rate": 4.9540000000000003e-05,
560
+ "loss": 0.876,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.56,
565
+ "learning_rate": 4.9535000000000006e-05,
566
+ "loss": 0.9297,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.57,
571
+ "learning_rate": 4.953e-05,
572
+ "loss": 0.9241,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.57,
577
+ "learning_rate": 4.9525000000000004e-05,
578
+ "loss": 0.9305,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.58,
583
+ "learning_rate": 4.952e-05,
584
+ "loss": 0.9395,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.58,
589
+ "learning_rate": 4.9515e-05,
590
+ "loss": 0.9208,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.59,
595
+ "learning_rate": 4.951e-05,
596
+ "loss": 0.9112,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.6,
601
+ "learning_rate": 4.9505e-05,
602
+ "loss": 0.9159,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.6,
607
+ "learning_rate": 4.9500000000000004e-05,
608
+ "loss": 0.902,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.61,
613
+ "learning_rate": 4.9495e-05,
614
+ "loss": 0.9412,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.61,
619
+ "learning_rate": 4.949e-05,
620
+ "loss": 0.8916,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.62,
625
+ "learning_rate": 4.9485000000000005e-05,
626
+ "loss": 0.8846,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.63,
631
+ "learning_rate": 4.948000000000001e-05,
632
+ "loss": 0.8974,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.63,
637
+ "learning_rate": 4.9475e-05,
638
+ "loss": 0.9332,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.64,
643
+ "learning_rate": 4.947e-05,
644
+ "loss": 0.9,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.64,
649
+ "learning_rate": 4.9465e-05,
650
+ "loss": 0.92,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.65,
655
+ "learning_rate": 4.946e-05,
656
+ "loss": 0.8802,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.66,
661
+ "learning_rate": 4.9455e-05,
662
+ "loss": 0.9199,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.66,
667
+ "learning_rate": 4.945e-05,
668
+ "loss": 0.8872,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.67,
673
+ "learning_rate": 4.9445000000000005e-05,
674
+ "loss": 0.8689,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.67,
679
+ "learning_rate": 4.944e-05,
680
+ "loss": 0.906,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.68,
685
+ "learning_rate": 4.9435000000000004e-05,
686
+ "loss": 0.8725,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.69,
691
+ "learning_rate": 4.9430000000000006e-05,
692
+ "loss": 0.8708,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.69,
697
+ "learning_rate": 4.9425e-05,
698
+ "loss": 0.8726,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.7,
703
+ "learning_rate": 4.942e-05,
704
+ "loss": 0.8584,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.7,
709
+ "learning_rate": 4.9415e-05,
710
+ "loss": 0.9218,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.71,
715
+ "learning_rate": 4.941e-05,
716
+ "loss": 0.8279,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.72,
721
+ "learning_rate": 4.9405e-05,
722
+ "loss": 0.9098,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.72,
727
+ "learning_rate": 4.94e-05,
728
+ "loss": 0.8924,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.73,
733
+ "learning_rate": 4.9395000000000004e-05,
734
+ "loss": 0.8897,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.73,
739
+ "learning_rate": 4.939e-05,
740
+ "loss": 0.876,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.74,
745
+ "learning_rate": 4.9385e-05,
746
+ "loss": 0.912,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.75,
751
+ "learning_rate": 4.9380000000000005e-05,
752
+ "loss": 0.878,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.75,
757
+ "learning_rate": 4.937500000000001e-05,
758
+ "loss": 0.8596,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.76,
763
+ "learning_rate": 4.937e-05,
764
+ "loss": 0.8849,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.77,
769
+ "learning_rate": 4.9365e-05,
770
+ "loss": 0.8471,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.77,
775
+ "learning_rate": 4.936e-05,
776
+ "loss": 0.894,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.78,
781
+ "learning_rate": 4.9355000000000004e-05,
782
+ "loss": 0.9051,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.78,
787
+ "learning_rate": 4.935e-05,
788
+ "loss": 0.8714,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.79,
793
+ "learning_rate": 4.9345e-05,
794
+ "loss": 0.8685,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.8,
799
+ "learning_rate": 4.9340000000000005e-05,
800
+ "loss": 0.8667,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.8,
805
+ "learning_rate": 4.9335e-05,
806
+ "loss": 0.8521,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.81,
811
+ "learning_rate": 4.9330000000000004e-05,
812
+ "loss": 0.8964,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.81,
817
+ "learning_rate": 4.9325000000000006e-05,
818
+ "loss": 0.8463,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.82,
823
+ "learning_rate": 4.932e-05,
824
+ "loss": 0.8626,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.83,
829
+ "learning_rate": 4.9315e-05,
830
+ "loss": 0.84,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.83,
835
+ "learning_rate": 4.931e-05,
836
+ "loss": 0.8535,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.84,
841
+ "learning_rate": 4.9305e-05,
842
+ "loss": 0.8539,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.84,
847
+ "learning_rate": 4.93e-05,
848
+ "loss": 0.849,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.85,
853
+ "learning_rate": 4.9295e-05,
854
+ "loss": 0.8713,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.86,
859
+ "learning_rate": 4.9290000000000004e-05,
860
+ "loss": 0.8493,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.86,
865
+ "learning_rate": 4.928500000000001e-05,
866
+ "loss": 0.8424,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.87,
871
+ "learning_rate": 4.928e-05,
872
+ "loss": 0.8723,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.87,
877
+ "learning_rate": 4.9275000000000005e-05,
878
+ "loss": 0.8732,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.88,
883
+ "learning_rate": 4.927000000000001e-05,
884
+ "loss": 0.8698,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.89,
889
+ "learning_rate": 4.9265e-05,
890
+ "loss": 0.8615,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.89,
895
+ "learning_rate": 4.926e-05,
896
+ "loss": 0.8728,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.9,
901
+ "learning_rate": 4.9255e-05,
902
+ "loss": 0.9018,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.9,
907
+ "learning_rate": 4.9250000000000004e-05,
908
+ "loss": 0.8704,
909
+ "step": 150
910
+ }
911
+ ],
912
+ "logging_steps": 1,
913
+ "max_steps": 10000,
914
+ "num_input_tokens_seen": 0,
915
+ "num_train_epochs": 61,
916
+ "save_steps": 10,
917
+ "total_flos": 1.916845826789376e+16,
918
+ "train_batch_size": 3584,
919
+ "trial_name": null,
920
+ "trial_params": null
921
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ee7910e077f792b02b908404aed653a085dc202bb050d5aacc04eb76a3ff9d
3
+ size 4664