Hugging Face's logo

loris3
/
babylm_2024_10m_curriculum_roberta_source_difficulty

Fill-Mask
Transformers
Safetensors
roberta
Model card Files
xet
Community
loris3 commited on
Commit
58ba776
·
verified ·
1 Parent(s): e3e1359

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. checkpoints/checkpoint-3276/config.json +26 -0
  2. checkpoints/checkpoint-3276/model.safetensors +3 -0
  3. checkpoints/checkpoint-3276/optimizer.pt +3 -0
  4. checkpoints/checkpoint-3276/rng_state.pth +3 -0
  5. checkpoints/checkpoint-3276/scheduler.pt +3 -0
  6. checkpoints/checkpoint-3276/trainer_state.json +548 -0
  7. checkpoints/checkpoint-3276/training_args.bin +3 -0
checkpoints/checkpoint-3276/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.47.0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoints/checkpoint-3276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ead36e20cf0d0f599c2418475af06b9d4634126d8cf001e7ccc76ddcaf1c66
3
+ size 504150808
checkpoints/checkpoint-3276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1445e229706d40f654e99b8134094749bc6174d11e809948edba909764f7174
3
+ size 1008422138
checkpoints/checkpoint-3276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:994dadf27574ac0df34bc3c47903eb3b9ae554987e69caf6c20d2fc88ef73d3a
3
+ size 14244
checkpoints/checkpoint-3276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627b2eaf3bfee99547a299cbd822795cbfd3dc9673c29647c2fed16150ead690
3
+ size 1064
checkpoints/checkpoint-3276/trainer_state.json ADDED
@@ -0,0 +1,548 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.998697351280938,
5
+ "eval_steps": 500,
6
+ "global_step": 3276,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08684324793747286,
13
+ "grad_norm": 119.13929748535156,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 10.2285,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.17368649587494572,
20
+ "grad_norm": 69.53515625,
21
+ "learning_rate": 5e-06,
22
+ "loss": 7.8282,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.26052974381241856,
27
+ "grad_norm": 38.81575393676758,
28
+ "learning_rate": 7.5e-06,
29
+ "loss": 6.1856,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.34737299174989145,
34
+ "grad_norm": 35.44122314453125,
35
+ "learning_rate": 1e-05,
36
+ "loss": 5.5474,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.4342162396873643,
41
+ "grad_norm": 45.1701545715332,
42
+ "learning_rate": 1.25e-05,
43
+ "loss": 5.0381,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.5210594876248371,
48
+ "grad_norm": 32.618980407714844,
49
+ "learning_rate": 1.5e-05,
50
+ "loss": 4.6559,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.60790273556231,
55
+ "grad_norm": 27.301441192626953,
56
+ "learning_rate": 1.7500000000000002e-05,
57
+ "loss": 4.2472,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.6947459834997829,
62
+ "grad_norm": 20.96350860595703,
63
+ "learning_rate": 2e-05,
64
+ "loss": 3.888,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.7815892314372558,
69
+ "grad_norm": 21.377185821533203,
70
+ "learning_rate": 2.2499999999999998e-05,
71
+ "loss": 3.5698,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.8684324793747286,
76
+ "grad_norm": 19.703227996826172,
77
+ "learning_rate": 2.5e-05,
78
+ "loss": 3.3225,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.9552757273122015,
83
+ "grad_norm": 25.189373016357422,
84
+ "learning_rate": 2.75e-05,
85
+ "loss": 3.1904,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.998697351280938,
90
+ "eval_accuracy": 0.0,
91
+ "eval_loss": 6.819223880767822,
92
+ "eval_normalizer": 136811.0,
93
+ "eval_runtime": 95.7843,
94
+ "eval_samples_per_second": 615.445,
95
+ "eval_steps_per_second": 1.211,
96
+ "step": 575
97
+ },
98
+ {
99
+ "epoch": 1.0434216239687364,
100
+ "grad_norm": 24.1675968170166,
101
+ "learning_rate": 3e-05,
102
+ "loss": 3.095,
103
+ "step": 600
104
+ },
105
+ {
106
+ "epoch": 1.1302648719062094,
107
+ "grad_norm": 18.355623245239258,
108
+ "learning_rate": 3.2500000000000004e-05,
109
+ "loss": 2.9629,
110
+ "step": 650
111
+ },
112
+ {
113
+ "epoch": 1.2171081198436822,
114
+ "grad_norm": 24.27044677734375,
115
+ "learning_rate": 3.5000000000000004e-05,
116
+ "loss": 2.8883,
117
+ "step": 700
118
+ },
119
+ {
120
+ "epoch": 1.303951367781155,
121
+ "grad_norm": 17.9877986907959,
122
+ "learning_rate": 3.75e-05,
123
+ "loss": 2.8165,
124
+ "step": 750
125
+ },
126
+ {
127
+ "epoch": 1.390794615718628,
128
+ "grad_norm": 27.353044509887695,
129
+ "learning_rate": 4e-05,
130
+ "loss": 2.7525,
131
+ "step": 800
132
+ },
133
+ {
134
+ "epoch": 1.4776378636561007,
135
+ "grad_norm": 22.09605598449707,
136
+ "learning_rate": 4.25e-05,
137
+ "loss": 2.6736,
138
+ "step": 850
139
+ },
140
+ {
141
+ "epoch": 1.5644811115935737,
142
+ "grad_norm": 21.224653244018555,
143
+ "learning_rate": 4.4999999999999996e-05,
144
+ "loss": 2.6135,
145
+ "step": 900
146
+ },
147
+ {
148
+ "epoch": 1.6513243595310465,
149
+ "grad_norm": 21.1419620513916,
150
+ "learning_rate": 4.75e-05,
151
+ "loss": 2.5637,
152
+ "step": 950
153
+ },
154
+ {
155
+ "epoch": 1.7381676074685193,
156
+ "grad_norm": 18.591278076171875,
157
+ "learning_rate": 5e-05,
158
+ "loss": 2.4905,
159
+ "step": 1000
160
+ },
161
+ {
162
+ "epoch": 1.825010855405992,
163
+ "grad_norm": 19.953432083129883,
164
+ "learning_rate": 5.25e-05,
165
+ "loss": 2.4256,
166
+ "step": 1050
167
+ },
168
+ {
169
+ "epoch": 1.911854103343465,
170
+ "grad_norm": 18.62944221496582,
171
+ "learning_rate": 5.5e-05,
172
+ "loss": 2.3984,
173
+ "step": 1100
174
+ },
175
+ {
176
+ "epoch": 1.998697351280938,
177
+ "grad_norm": 19.104263305664062,
178
+ "learning_rate": 5.75e-05,
179
+ "loss": 2.3322,
180
+ "step": 1150
181
+ },
182
+ {
183
+ "epoch": 1.998697351280938,
184
+ "eval_accuracy": 0.0,
185
+ "eval_loss": 6.3023457527160645,
186
+ "eval_normalizer": 136797.0,
187
+ "eval_runtime": 96.2451,
188
+ "eval_samples_per_second": 612.499,
189
+ "eval_steps_per_second": 1.205,
190
+ "step": 1150
191
+ },
192
+ {
193
+ "epoch": 2.086843247937473,
194
+ "grad_norm": 25.047359466552734,
195
+ "learning_rate": 6e-05,
196
+ "loss": 5.8229,
197
+ "step": 1200
198
+ },
199
+ {
200
+ "epoch": 2.1736864958749456,
201
+ "grad_norm": 29.961374282836914,
202
+ "learning_rate": 6.25e-05,
203
+ "loss": 5.0367,
204
+ "step": 1250
205
+ },
206
+ {
207
+ "epoch": 2.260529743812419,
208
+ "grad_norm": 26.177074432373047,
209
+ "learning_rate": 6.500000000000001e-05,
210
+ "loss": 4.739,
211
+ "step": 1300
212
+ },
213
+ {
214
+ "epoch": 2.3473729917498916,
215
+ "grad_norm": 25.611238479614258,
216
+ "learning_rate": 6.75e-05,
217
+ "loss": 4.5423,
218
+ "step": 1350
219
+ },
220
+ {
221
+ "epoch": 2.4342162396873643,
222
+ "grad_norm": 26.324779510498047,
223
+ "learning_rate": 7.000000000000001e-05,
224
+ "loss": 4.4232,
225
+ "step": 1400
226
+ },
227
+ {
228
+ "epoch": 2.521059487624837,
229
+ "grad_norm": 28.05305290222168,
230
+ "learning_rate": 7.25e-05,
231
+ "loss": 4.3058,
232
+ "step": 1450
233
+ },
234
+ {
235
+ "epoch": 2.60790273556231,
236
+ "grad_norm": 21.828216552734375,
237
+ "learning_rate": 7.5e-05,
238
+ "loss": 4.2192,
239
+ "step": 1500
240
+ },
241
+ {
242
+ "epoch": 2.694745983499783,
243
+ "grad_norm": 25.824861526489258,
244
+ "learning_rate": 7.75e-05,
245
+ "loss": 4.1252,
246
+ "step": 1550
247
+ },
248
+ {
249
+ "epoch": 2.781589231437256,
250
+ "grad_norm": 32.99074172973633,
251
+ "learning_rate": 8e-05,
252
+ "loss": 4.0529,
253
+ "step": 1600
254
+ },
255
+ {
256
+ "epoch": 2.847590099869735,
257
+ "eval_accuracy": 0.0,
258
+ "eval_loss": 6.029520034790039,
259
+ "eval_normalizer": 135800.0,
260
+ "eval_runtime": 99.1551,
261
+ "eval_samples_per_second": 594.523,
262
+ "eval_steps_per_second": 1.17,
263
+ "step": 1638
264
+ },
265
+ {
266
+ "epoch": 3.0208423795049937,
267
+ "grad_norm": 25.763500213623047,
268
+ "learning_rate": 8.25e-05,
269
+ "loss": 3.9997,
270
+ "step": 1650
271
+ },
272
+ {
273
+ "epoch": 3.1076856274424665,
274
+ "grad_norm": 22.946069717407227,
275
+ "learning_rate": 8.5e-05,
276
+ "loss": 3.9354,
277
+ "step": 1700
278
+ },
279
+ {
280
+ "epoch": 3.1945288753799392,
281
+ "grad_norm": 24.897716522216797,
282
+ "learning_rate": 8.75e-05,
283
+ "loss": 3.8814,
284
+ "step": 1750
285
+ },
286
+ {
287
+ "epoch": 3.281372123317412,
288
+ "grad_norm": 28.476097106933594,
289
+ "learning_rate": 8.999999999999999e-05,
290
+ "loss": 3.8065,
291
+ "step": 1800
292
+ },
293
+ {
294
+ "epoch": 3.368215371254885,
295
+ "grad_norm": 23.84947967529297,
296
+ "learning_rate": 9.25e-05,
297
+ "loss": 3.7591,
298
+ "step": 1850
299
+ },
300
+ {
301
+ "epoch": 3.455058619192358,
302
+ "grad_norm": 26.41289710998535,
303
+ "learning_rate": 9.5e-05,
304
+ "loss": 3.7122,
305
+ "step": 1900
306
+ },
307
+ {
308
+ "epoch": 3.541901867129831,
309
+ "grad_norm": 21.178028106689453,
310
+ "learning_rate": 9.750000000000001e-05,
311
+ "loss": 3.6551,
312
+ "step": 1950
313
+ },
314
+ {
315
+ "epoch": 3.6287451150673036,
316
+ "grad_norm": 26.34974479675293,
317
+ "learning_rate": 0.0001,
318
+ "loss": 3.6142,
319
+ "step": 2000
320
+ },
321
+ {
322
+ "epoch": 3.7155883630047764,
323
+ "grad_norm": 24.118379592895508,
324
+ "learning_rate": 0.0001025,
325
+ "loss": 3.5733,
326
+ "step": 2050
327
+ },
328
+ {
329
+ "epoch": 3.802431610942249,
330
+ "grad_norm": 22.377361297607422,
331
+ "learning_rate": 0.000105,
332
+ "loss": 3.5317,
333
+ "step": 2100
334
+ },
335
+ {
336
+ "epoch": 3.847590099869735,
337
+ "eval_accuracy": 0.0,
338
+ "eval_loss": 6.078055381774902,
339
+ "eval_normalizer": 136953.0,
340
+ "eval_runtime": 98.2046,
341
+ "eval_samples_per_second": 600.277,
342
+ "eval_steps_per_second": 1.181,
343
+ "step": 2126
344
+ },
345
+ {
346
+ "epoch": 4.041684759009987,
347
+ "grad_norm": 28.407474517822266,
348
+ "learning_rate": 0.0001075,
349
+ "loss": 4.0317,
350
+ "step": 2150
351
+ },
352
+ {
353
+ "epoch": 4.12852800694746,
354
+ "grad_norm": 24.021642684936523,
355
+ "learning_rate": 0.00011,
356
+ "loss": 4.2086,
357
+ "step": 2200
358
+ },
359
+ {
360
+ "epoch": 4.215371254884933,
361
+ "grad_norm": 27.256893157958984,
362
+ "learning_rate": 0.00011250000000000001,
363
+ "loss": 4.0794,
364
+ "step": 2250
365
+ },
366
+ {
367
+ "epoch": 4.302214502822405,
368
+ "grad_norm": 24.082077026367188,
369
+ "learning_rate": 0.000115,
370
+ "loss": 3.9449,
371
+ "step": 2300
372
+ },
373
+ {
374
+ "epoch": 4.3890577507598785,
375
+ "grad_norm": 28.5674991607666,
376
+ "learning_rate": 0.0001175,
377
+ "loss": 3.8689,
378
+ "step": 2350
379
+ },
380
+ {
381
+ "epoch": 4.475900998697352,
382
+ "grad_norm": 27.761144638061523,
383
+ "learning_rate": 0.00012,
384
+ "loss": 3.7839,
385
+ "step": 2400
386
+ },
387
+ {
388
+ "epoch": 4.562744246634824,
389
+ "grad_norm": 23.79894256591797,
390
+ "learning_rate": 0.0001225,
391
+ "loss": 3.707,
392
+ "step": 2450
393
+ },
394
+ {
395
+ "epoch": 4.649587494572297,
396
+ "grad_norm": 25.150774002075195,
397
+ "learning_rate": 0.000125,
398
+ "loss": 3.6834,
399
+ "step": 2500
400
+ },
401
+ {
402
+ "epoch": 4.73643074250977,
403
+ "grad_norm": 27.177146911621094,
404
+ "learning_rate": 0.0001275,
405
+ "loss": 3.6331,
406
+ "step": 2550
407
+ },
408
+ {
409
+ "epoch": 4.823273990447243,
410
+ "grad_norm": 29.18802833557129,
411
+ "learning_rate": 0.00013000000000000002,
412
+ "loss": 3.5894,
413
+ "step": 2600
414
+ },
415
+ {
416
+ "epoch": 4.910117238384716,
417
+ "grad_norm": 24.752147674560547,
418
+ "learning_rate": 0.00013250000000000002,
419
+ "loss": 3.5717,
420
+ "step": 2650
421
+ },
422
+ {
423
+ "epoch": 4.996960486322188,
424
+ "grad_norm": 23.449617385864258,
425
+ "learning_rate": 0.000135,
426
+ "loss": 3.4916,
427
+ "step": 2700
428
+ },
429
+ {
430
+ "epoch": 4.998697351280938,
431
+ "eval_accuracy": 0.0,
432
+ "eval_loss": 5.327279090881348,
433
+ "eval_normalizer": 136898.0,
434
+ "eval_runtime": 98.1897,
435
+ "eval_samples_per_second": 600.369,
436
+ "eval_steps_per_second": 1.181,
437
+ "step": 2701
438
+ },
439
+ {
440
+ "epoch": 5.085106382978723,
441
+ "grad_norm": 23.818960189819336,
442
+ "learning_rate": 0.0001375,
443
+ "loss": 3.536,
444
+ "step": 2750
445
+ },
446
+ {
447
+ "epoch": 5.171949630916196,
448
+ "grad_norm": 23.798330307006836,
449
+ "learning_rate": 0.00014000000000000001,
450
+ "loss": 3.4725,
451
+ "step": 2800
452
+ },
453
+ {
454
+ "epoch": 5.2587928788536695,
455
+ "grad_norm": 25.093759536743164,
456
+ "learning_rate": 0.0001425,
457
+ "loss": 3.4741,
458
+ "step": 2850
459
+ },
460
+ {
461
+ "epoch": 5.345636126791142,
462
+ "grad_norm": 23.182748794555664,
463
+ "learning_rate": 0.000145,
464
+ "loss": 3.4182,
465
+ "step": 2900
466
+ },
467
+ {
468
+ "epoch": 5.432479374728615,
469
+ "grad_norm": 26.840492248535156,
470
+ "learning_rate": 0.0001475,
471
+ "loss": 3.3759,
472
+ "step": 2950
473
+ },
474
+ {
475
+ "epoch": 5.519322622666087,
476
+ "grad_norm": 24.039644241333008,
477
+ "learning_rate": 0.00015,
478
+ "loss": 3.3526,
479
+ "step": 3000
480
+ },
481
+ {
482
+ "epoch": 5.606165870603561,
483
+ "grad_norm": 25.59815216064453,
484
+ "learning_rate": 0.0001525,
485
+ "loss": 3.3416,
486
+ "step": 3050
487
+ },
488
+ {
489
+ "epoch": 5.693009118541033,
490
+ "grad_norm": 29.411540985107422,
491
+ "learning_rate": 0.000155,
492
+ "loss": 3.3155,
493
+ "step": 3100
494
+ },
495
+ {
496
+ "epoch": 5.779852366478506,
497
+ "grad_norm": 26.35207176208496,
498
+ "learning_rate": 0.0001575,
499
+ "loss": 3.2879,
500
+ "step": 3150
501
+ },
502
+ {
503
+ "epoch": 5.866695614415979,
504
+ "grad_norm": 23.549055099487305,
505
+ "learning_rate": 0.00016,
506
+ "loss": 3.2693,
507
+ "step": 3200
508
+ },
509
+ {
510
+ "epoch": 5.953538862353452,
511
+ "grad_norm": 22.051862716674805,
512
+ "learning_rate": 0.00016250000000000002,
513
+ "loss": 3.2552,
514
+ "step": 3250
515
+ },
516
+ {
517
+ "epoch": 5.998697351280938,
518
+ "eval_accuracy": 0.0,
519
+ "eval_loss": 5.376891613006592,
520
+ "eval_normalizer": 136004.0,
521
+ "eval_runtime": 98.0527,
522
+ "eval_samples_per_second": 601.207,
523
+ "eval_steps_per_second": 1.183,
524
+ "step": 3276
525
+ }
526
+ ],
527
+ "logging_steps": 50,
528
+ "max_steps": 5750,
529
+ "num_input_tokens_seen": 0,
530
+ "num_train_epochs": 10,
531
+ "save_steps": 500,
532
+ "stateful_callbacks": {
533
+ "TrainerControl": {
534
+ "args": {
535
+ "should_epoch_stop": false,
536
+ "should_evaluate": false,
537
+ "should_log": false,
538
+ "should_save": true,
539
+ "should_training_stop": false
540
+ },
541
+ "attributes": {}
542
+ }
543
+ },
544
+ "total_flos": 2.0376383054598874e+17,
545
+ "train_batch_size": 128,
546
+ "trial_name": null,
547
+ "trial_params": null
548
+ }
checkpoints/checkpoint-3276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2eb3a10fbbc23b7e9459aec997464606f0d6188a9a2dfdf7ab9d2150b17bd3d
3
+ size 5432