Hugging Face's logo

loris3
/
babylm_2024_10m_curriculum_roberta_random

Fill-Mask
Transformers
Safetensors
roberta
Model card Files
xet
 Community
loris3 commited on
Commit
9105b86
·
verified ·
1 Parent(s): d03f6e3

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. checkpoints/checkpoint-3450/config.json +26 -0
  2. checkpoints/checkpoint-3450/model.safetensors +3 -0
  3. checkpoints/checkpoint-3450/optimizer.pt +3 -0
  4. checkpoints/checkpoint-3450/rng_state.pth +3 -0
  5. checkpoints/checkpoint-3450/scheduler.pt +3 -0
  6. checkpoints/checkpoint-3450/trainer_state.json +576 -0
  7. checkpoints/checkpoint-3450/training_args.bin +3 -0
checkpoints/checkpoint-3450/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-3450/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b60e19c43e23f096675a238ce334145dc2ff5125a71e8dc2df424bbd3ba225
3
+ size 504150808
checkpoints/checkpoint-3450/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf6f1a93f5769713d620606190fdbeaf74b06831d5981b86dc6cb37bfbf878b
3
+ size 1008422138
checkpoints/checkpoint-3450/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf2f82fa28f61ddc874b9136fe02051374abb94adea146b1f3bb0e51cb2c4fb
3
+ size 14244
checkpoints/checkpoint-3450/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3312537a98c0a24c49948e9034e0dc85c213f955658302b4a489f2fd37390295
3
+ size 1064
checkpoints/checkpoint-3450/trainer_state.json ADDED
@@ -0,0 +1,576 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.998697351280938,
5
+ "eval_steps": 500,
6
+ "global_step": 3450,
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": 64.51876068115234,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 10.5808,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.17368649587494572,
20
+ "grad_norm": 46.88249588012695,
21
+ "learning_rate": 5e-06,
22
+ "loss": 9.4375,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.26052974381241856,
27
+ "grad_norm": 37.17626190185547,
28
+ "learning_rate": 7.5e-06,
29
+ "loss": 8.5182,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.34737299174989145,
34
+ "grad_norm": 36.42595291137695,
35
+ "learning_rate": 1e-05,
36
+ "loss": 7.8819,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.4342162396873643,
41
+ "grad_norm": 37.513221740722656,
42
+ "learning_rate": 1.25e-05,
43
+ "loss": 7.3998,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.5210594876248371,
48
+ "grad_norm": 37.72527313232422,
49
+ "learning_rate": 1.5e-05,
50
+ "loss": 6.9285,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.60790273556231,
55
+ "grad_norm": 25.45908546447754,
56
+ "learning_rate": 1.7500000000000002e-05,
57
+ "loss": 6.4779,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.6947459834997829,
62
+ "grad_norm": 19.964221954345703,
63
+ "learning_rate": 2e-05,
64
+ "loss": 6.0723,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.7815892314372558,
69
+ "grad_norm": 22.95414924621582,
70
+ "learning_rate": 2.2499999999999998e-05,
71
+ "loss": 5.7359,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.8684324793747286,
76
+ "grad_norm": 25.838315963745117,
77
+ "learning_rate": 2.5e-05,
78
+ "loss": 5.5306,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.9552757273122015,
83
+ "grad_norm": 20.025278091430664,
84
+ "learning_rate": 2.75e-05,
85
+ "loss": 5.3827,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.998697351280938,
90
+ "eval_accuracy": 0.0,
91
+ "eval_loss": 5.815488815307617,
92
+ "eval_normalizer": 136811.0,
93
+ "eval_runtime": 103.9161,
94
+ "eval_samples_per_second": 567.285,
95
+ "eval_steps_per_second": 1.116,
96
+ "step": 575
97
+ },
98
+ {
99
+ "epoch": 1.0434216239687364,
100
+ "grad_norm": 24.807146072387695,
101
+ "learning_rate": 3e-05,
102
+ "loss": 5.3056,
103
+ "step": 600
104
+ },
105
+ {
106
+ "epoch": 1.1302648719062094,
107
+ "grad_norm": 24.356752395629883,
108
+ "learning_rate": 3.2500000000000004e-05,
109
+ "loss": 5.1787,
110
+ "step": 650
111
+ },
112
+ {
113
+ "epoch": 1.2171081198436822,
114
+ "grad_norm": 34.20137023925781,
115
+ "learning_rate": 3.5000000000000004e-05,
116
+ "loss": 5.0808,
117
+ "step": 700
118
+ },
119
+ {
120
+ "epoch": 1.303951367781155,
121
+ "grad_norm": 20.841449737548828,
122
+ "learning_rate": 3.75e-05,
123
+ "loss": 5.0151,
124
+ "step": 750
125
+ },
126
+ {
127
+ "epoch": 1.390794615718628,
128
+ "grad_norm": 17.446142196655273,
129
+ "learning_rate": 4e-05,
130
+ "loss": 4.9479,
131
+ "step": 800
132
+ },
133
+ {
134
+ "epoch": 1.4776378636561007,
135
+ "grad_norm": 21.755874633789062,
136
+ "learning_rate": 4.25e-05,
137
+ "loss": 4.8636,
138
+ "step": 850
139
+ },
140
+ {
141
+ "epoch": 1.5644811115935737,
142
+ "grad_norm": 23.59573745727539,
143
+ "learning_rate": 4.4999999999999996e-05,
144
+ "loss": 4.8055,
145
+ "step": 900
146
+ },
147
+ {
148
+ "epoch": 1.6513243595310465,
149
+ "grad_norm": 29.339677810668945,
150
+ "learning_rate": 4.75e-05,
151
+ "loss": 4.7349,
152
+ "step": 950
153
+ },
154
+ {
155
+ "epoch": 1.7381676074685193,
156
+ "grad_norm": 19.896867752075195,
157
+ "learning_rate": 5e-05,
158
+ "loss": 4.6511,
159
+ "step": 1000
160
+ },
161
+ {
162
+ "epoch": 1.825010855405992,
163
+ "grad_norm": 25.321279525756836,
164
+ "learning_rate": 5.25e-05,
165
+ "loss": 4.6093,
166
+ "step": 1050
167
+ },
168
+ {
169
+ "epoch": 1.911854103343465,
170
+ "grad_norm": 24.375009536743164,
171
+ "learning_rate": 5.5e-05,
172
+ "loss": 4.5466,
173
+ "step": 1100
174
+ },
175
+ {
176
+ "epoch": 1.998697351280938,
177
+ "grad_norm": 19.765535354614258,
178
+ "learning_rate": 5.75e-05,
179
+ "loss": 4.4822,
180
+ "step": 1150
181
+ },
182
+ {
183
+ "epoch": 1.998697351280938,
184
+ "eval_accuracy": 0.0,
185
+ "eval_loss": 5.009335041046143,
186
+ "eval_normalizer": 136797.0,
187
+ "eval_runtime": 106.1852,
188
+ "eval_samples_per_second": 555.162,
189
+ "eval_steps_per_second": 1.092,
190
+ "step": 1150
191
+ },
192
+ {
193
+ "epoch": 2.086843247937473,
194
+ "grad_norm": 22.055421829223633,
195
+ "learning_rate": 6e-05,
196
+ "loss": 4.4112,
197
+ "step": 1200
198
+ },
199
+ {
200
+ "epoch": 2.1736864958749456,
201
+ "grad_norm": 22.794734954833984,
202
+ "learning_rate": 6.25e-05,
203
+ "loss": 4.342,
204
+ "step": 1250
205
+ },
206
+ {
207
+ "epoch": 2.260529743812419,
208
+ "grad_norm": 22.201148986816406,
209
+ "learning_rate": 6.500000000000001e-05,
210
+ "loss": 4.2642,
211
+ "step": 1300
212
+ },
213
+ {
214
+ "epoch": 2.3473729917498916,
215
+ "grad_norm": 26.878231048583984,
216
+ "learning_rate": 6.75e-05,
217
+ "loss": 4.21,
218
+ "step": 1350
219
+ },
220
+ {
221
+ "epoch": 2.4342162396873643,
222
+ "grad_norm": 26.893157958984375,
223
+ "learning_rate": 7.000000000000001e-05,
224
+ "loss": 4.1912,
225
+ "step": 1400
226
+ },
227
+ {
228
+ "epoch": 2.521059487624837,
229
+ "grad_norm": 22.139896392822266,
230
+ "learning_rate": 7.25e-05,
231
+ "loss": 4.1345,
232
+ "step": 1450
233
+ },
234
+ {
235
+ "epoch": 2.60790273556231,
236
+ "grad_norm": 22.048015594482422,
237
+ "learning_rate": 7.5e-05,
238
+ "loss": 4.0536,
239
+ "step": 1500
240
+ },
241
+ {
242
+ "epoch": 2.694745983499783,
243
+ "grad_norm": 20.372922897338867,
244
+ "learning_rate": 7.75e-05,
245
+ "loss": 4.0141,
246
+ "step": 1550
247
+ },
248
+ {
249
+ "epoch": 2.781589231437256,
250
+ "grad_norm": 23.150230407714844,
251
+ "learning_rate": 8e-05,
252
+ "loss": 3.9682,
253
+ "step": 1600
254
+ },
255
+ {
256
+ "epoch": 2.8684324793747287,
257
+ "grad_norm": 23.635217666625977,
258
+ "learning_rate": 8.25e-05,
259
+ "loss": 3.9323,
260
+ "step": 1650
261
+ },
262
+ {
263
+ "epoch": 2.9552757273122015,
264
+ "grad_norm": 23.827754974365234,
265
+ "learning_rate": 8.5e-05,
266
+ "loss": 3.8978,
267
+ "step": 1700
268
+ },
269
+ {
270
+ "epoch": 2.998697351280938,
271
+ "eval_accuracy": 0.0,
272
+ "eval_loss": 4.390091896057129,
273
+ "eval_normalizer": 135800.0,
274
+ "eval_runtime": 102.8052,
275
+ "eval_samples_per_second": 573.414,
276
+ "eval_steps_per_second": 1.128,
277
+ "step": 1725
278
+ },
279
+ {
280
+ "epoch": 3.0434216239687366,
281
+ "grad_norm": 23.427833557128906,
282
+ "learning_rate": 8.75e-05,
283
+ "loss": 3.8416,
284
+ "step": 1750
285
+ },
286
+ {
287
+ "epoch": 3.1302648719062094,
288
+ "grad_norm": 22.676321029663086,
289
+ "learning_rate": 8.999999999999999e-05,
290
+ "loss": 3.7893,
291
+ "step": 1800
292
+ },
293
+ {
294
+ "epoch": 3.217108119843682,
295
+ "grad_norm": 21.082340240478516,
296
+ "learning_rate": 9.25e-05,
297
+ "loss": 3.7538,
298
+ "step": 1850
299
+ },
300
+ {
301
+ "epoch": 3.303951367781155,
302
+ "grad_norm": 22.935646057128906,
303
+ "learning_rate": 9.5e-05,
304
+ "loss": 3.7105,
305
+ "step": 1900
306
+ },
307
+ {
308
+ "epoch": 3.3907946157186277,
309
+ "grad_norm": 17.609500885009766,
310
+ "learning_rate": 9.750000000000001e-05,
311
+ "loss": 3.6724,
312
+ "step": 1950
313
+ },
314
+ {
315
+ "epoch": 3.477637863656101,
316
+ "grad_norm": 24.803913116455078,
317
+ "learning_rate": 0.0001,
318
+ "loss": 3.6343,
319
+ "step": 2000
320
+ },
321
+ {
322
+ "epoch": 3.5644811115935737,
323
+ "grad_norm": 23.1530704498291,
324
+ "learning_rate": 0.0001025,
325
+ "loss": 3.5885,
326
+ "step": 2050
327
+ },
328
+ {
329
+ "epoch": 3.6513243595310465,
330
+ "grad_norm": 18.984954833984375,
331
+ "learning_rate": 0.000105,
332
+ "loss": 3.5862,
333
+ "step": 2100
334
+ },
335
+ {
336
+ "epoch": 3.7381676074685193,
337
+ "grad_norm": 24.13288688659668,
338
+ "learning_rate": 0.0001075,
339
+ "loss": 3.5399,
340
+ "step": 2150
341
+ },
342
+ {
343
+ "epoch": 3.825010855405992,
344
+ "grad_norm": 20.114696502685547,
345
+ "learning_rate": 0.00011,
346
+ "loss": 3.5134,
347
+ "step": 2200
348
+ },
349
+ {
350
+ "epoch": 3.9118541033434653,
351
+ "grad_norm": 21.485876083374023,
352
+ "learning_rate": 0.00011250000000000001,
353
+ "loss": 3.5002,
354
+ "step": 2250
355
+ },
356
+ {
357
+ "epoch": 3.998697351280938,
358
+ "grad_norm": 19.5527286529541,
359
+ "learning_rate": 0.000115,
360
+ "loss": 3.4823,
361
+ "step": 2300
362
+ },
363
+ {
364
+ "epoch": 3.998697351280938,
365
+ "eval_accuracy": 0.0,
366
+ "eval_loss": 3.955526828765869,
367
+ "eval_normalizer": 136953.0,
368
+ "eval_runtime": 103.399,
369
+ "eval_samples_per_second": 570.122,
370
+ "eval_steps_per_second": 1.122,
371
+ "step": 2300
372
+ },
373
+ {
374
+ "epoch": 4.086843247937473,
375
+ "grad_norm": 20.296035766601562,
376
+ "learning_rate": 0.0001175,
377
+ "loss": 3.4443,
378
+ "step": 2350
379
+ },
380
+ {
381
+ "epoch": 4.173686495874946,
382
+ "grad_norm": 23.345937728881836,
383
+ "learning_rate": 0.00012,
384
+ "loss": 3.4204,
385
+ "step": 2400
386
+ },
387
+ {
388
+ "epoch": 4.260529743812419,
389
+ "grad_norm": 20.19176483154297,
390
+ "learning_rate": 0.0001225,
391
+ "loss": 3.3671,
392
+ "step": 2450
393
+ },
394
+ {
395
+ "epoch": 4.347372991749891,
396
+ "grad_norm": 18.96110725402832,
397
+ "learning_rate": 0.000125,
398
+ "loss": 3.372,
399
+ "step": 2500
400
+ },
401
+ {
402
+ "epoch": 4.434216239687364,
403
+ "grad_norm": 19.05695915222168,
404
+ "learning_rate": 0.0001275,
405
+ "loss": 3.3274,
406
+ "step": 2550
407
+ },
408
+ {
409
+ "epoch": 4.521059487624838,
410
+ "grad_norm": 19.250852584838867,
411
+ "learning_rate": 0.00013000000000000002,
412
+ "loss": 3.3274,
413
+ "step": 2600
414
+ },
415
+ {
416
+ "epoch": 4.60790273556231,
417
+ "grad_norm": 18.30086326599121,
418
+ "learning_rate": 0.00013250000000000002,
419
+ "loss": 3.2973,
420
+ "step": 2650
421
+ },
422
+ {
423
+ "epoch": 4.694745983499783,
424
+ "grad_norm": 18.18668556213379,
425
+ "learning_rate": 0.000135,
426
+ "loss": 3.2728,
427
+ "step": 2700
428
+ },
429
+ {
430
+ "epoch": 4.7815892314372554,
431
+ "grad_norm": 20.339557647705078,
432
+ "learning_rate": 0.0001375,
433
+ "loss": 3.2655,
434
+ "step": 2750
435
+ },
436
+ {
437
+ "epoch": 4.868432479374729,
438
+ "grad_norm": 18.8162841796875,
439
+ "learning_rate": 0.00014000000000000001,
440
+ "loss": 3.2437,
441
+ "step": 2800
442
+ },
443
+ {
444
+ "epoch": 4.955275727312202,
445
+ "grad_norm": 22.74474334716797,
446
+ "learning_rate": 0.0001425,
447
+ "loss": 3.2268,
448
+ "step": 2850
449
+ },
450
+ {
451
+ "epoch": 4.998697351280938,
452
+ "eval_accuracy": 0.0,
453
+ "eval_loss": 3.7116966247558594,
454
+ "eval_normalizer": 136898.0,
455
+ "eval_runtime": 102.1707,
456
+ "eval_samples_per_second": 576.976,
457
+ "eval_steps_per_second": 1.135,
458
+ "step": 2875
459
+ },
460
+ {
461
+ "epoch": 5.043421623968737,
462
+ "grad_norm": 19.14987564086914,
463
+ "learning_rate": 0.000145,
464
+ "loss": 3.2086,
465
+ "step": 2900
466
+ },
467
+ {
468
+ "epoch": 5.130264871906209,
469
+ "grad_norm": 20.017988204956055,
470
+ "learning_rate": 0.0001475,
471
+ "loss": 3.1762,
472
+ "step": 2950
473
+ },
474
+ {
475
+ "epoch": 5.217108119843682,
476
+ "grad_norm": 19.542016983032227,
477
+ "learning_rate": 0.00015,
478
+ "loss": 3.1541,
479
+ "step": 3000
480
+ },
481
+ {
482
+ "epoch": 5.303951367781155,
483
+ "grad_norm": 19.774423599243164,
484
+ "learning_rate": 0.0001525,
485
+ "loss": 3.1478,
486
+ "step": 3050
487
+ },
488
+ {
489
+ "epoch": 5.390794615718628,
490
+ "grad_norm": 17.859071731567383,
491
+ "learning_rate": 0.000155,
492
+ "loss": 3.1161,
493
+ "step": 3100
494
+ },
495
+ {
496
+ "epoch": 5.477637863656101,
497
+ "grad_norm": 19.971141815185547,
498
+ "learning_rate": 0.0001575,
499
+ "loss": 3.1557,
500
+ "step": 3150
501
+ },
502
+ {
503
+ "epoch": 5.564481111593573,
504
+ "grad_norm": 20.248157501220703,
505
+ "learning_rate": 0.00016,
506
+ "loss": 3.1065,
507
+ "step": 3200
508
+ },
509
+ {
510
+ "epoch": 5.6513243595310465,
511
+ "grad_norm": 18.28225326538086,
512
+ "learning_rate": 0.00016250000000000002,
513
+ "loss": 3.0919,
514
+ "step": 3250
515
+ },
516
+ {
517
+ "epoch": 5.738167607468519,
518
+ "grad_norm": 18.790512084960938,
519
+ "learning_rate": 0.000165,
520
+ "loss": 3.0674,
521
+ "step": 3300
522
+ },
523
+ {
524
+ "epoch": 5.825010855405992,
525
+ "grad_norm": 19.873552322387695,
526
+ "learning_rate": 0.0001675,
527
+ "loss": 3.0937,
528
+ "step": 3350
529
+ },
530
+ {
531
+ "epoch": 5.911854103343465,
532
+ "grad_norm": 16.722440719604492,
533
+ "learning_rate": 0.00017,
534
+ "loss": 3.051,
535
+ "step": 3400
536
+ },
537
+ {
538
+ "epoch": 5.998697351280938,
539
+ "grad_norm": 20.395442962646484,
540
+ "learning_rate": 0.0001725,
541
+ "loss": 3.0683,
542
+ "step": 3450
543
+ },
544
+ {
545
+ "epoch": 5.998697351280938,
546
+ "eval_accuracy": 0.0,
547
+ "eval_loss": 3.523391008377075,
548
+ "eval_normalizer": 136004.0,
549
+ "eval_runtime": 104.2937,
550
+ "eval_samples_per_second": 565.23,
551
+ "eval_steps_per_second": 1.112,
552
+ "step": 3450
553
+ }
554
+ ],
555
+ "logging_steps": 50,
556
+ "max_steps": 5750,
557
+ "num_input_tokens_seen": 0,
558
+ "num_train_epochs": 10,
559
+ "save_steps": 500,
560
+ "stateful_callbacks": {
561
+ "TrainerControl": {
562
+ "args": {
563
+ "should_epoch_stop": false,
564
+ "should_evaluate": false,
565
+ "should_log": false,
566
+ "should_save": true,
567
+ "should_training_stop": false
568
+ },
569
+ "attributes": {}
570
+ }
571
+ },
572
+ "total_flos": 5.540745776219259e+17,
573
+ "train_batch_size": 128,
574
+ "trial_name": null,
575
+ "trial_params": null
576
+ }
checkpoints/checkpoint-3450/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70088d65e5801098d4101207af477ddb2535731647b91a260697c3242af10928
3
+ size 5368