reiprasetya-study commited on
Commit
946d863
·
verified ·
1 Parent(s): 40231c6

Upload folder using huggingface_hub

Browse files
checkpoints/checkpoint-19425/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5p-220m",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": false,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.43.4",
31
+ "use_cache": true,
32
+ "vocab_size": 32100
33
+ }
checkpoints/checkpoint-19425/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.43.4"
8
+ }
checkpoints/checkpoint-19425/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/checkpoint-19425/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75082ea1a0a071e8a628b825f02acf7c60a488b533b0c883ea85e48b9cd355b9
3
+ size 891558696
checkpoints/checkpoint-19425/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be93710cb90be510f75072cc25df960d925df2023386dcb0f03a2a37f6b52b52
3
+ size 1783272762
checkpoints/checkpoint-19425/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b8e351893d1be07ce2a7713d1c87ac3cf1e86008947dc679bf4954d1be6325
3
+ size 14244
checkpoints/checkpoint-19425/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c61732b02b4228d21a32979b53d38c06494e50bb15604e7dab1b96986ed3b23a
3
+ size 1064
checkpoints/checkpoint-19425/special_tokens_map.json ADDED
@@ -0,0 +1,753 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<extra_id_99>",
5
+ "lstrip": true,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<extra_id_98>",
12
+ "lstrip": true,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<extra_id_97>",
19
+ "lstrip": true,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<extra_id_96>",
26
+ "lstrip": true,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<extra_id_95>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<extra_id_94>",
40
+ "lstrip": true,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<extra_id_93>",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<extra_id_92>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<extra_id_91>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<extra_id_90>",
68
+ "lstrip": true,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<extra_id_89>",
75
+ "lstrip": true,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<extra_id_88>",
82
+ "lstrip": true,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<extra_id_87>",
89
+ "lstrip": true,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<extra_id_86>",
96
+ "lstrip": true,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<extra_id_85>",
103
+ "lstrip": true,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<extra_id_84>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<extra_id_83>",
117
+ "lstrip": true,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<extra_id_82>",
124
+ "lstrip": true,
125
+ "normalized": true,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<extra_id_81>",
131
+ "lstrip": true,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<extra_id_80>",
138
+ "lstrip": true,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<extra_id_79>",
145
+ "lstrip": true,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<extra_id_78>",
152
+ "lstrip": true,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<extra_id_77>",
159
+ "lstrip": true,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<extra_id_76>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<extra_id_75>",
173
+ "lstrip": true,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<extra_id_74>",
180
+ "lstrip": true,
181
+ "normalized": true,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<extra_id_73>",
187
+ "lstrip": true,
188
+ "normalized": true,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<extra_id_72>",
194
+ "lstrip": true,
195
+ "normalized": true,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<extra_id_71>",
201
+ "lstrip": true,
202
+ "normalized": true,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<extra_id_70>",
208
+ "lstrip": true,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<extra_id_69>",
215
+ "lstrip": true,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<extra_id_68>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<extra_id_67>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<extra_id_66>",
236
+ "lstrip": true,
237
+ "normalized": true,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<extra_id_65>",
243
+ "lstrip": true,
244
+ "normalized": true,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<extra_id_64>",
250
+ "lstrip": true,
251
+ "normalized": true,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<extra_id_63>",
257
+ "lstrip": true,
258
+ "normalized": true,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<extra_id_62>",
264
+ "lstrip": true,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<extra_id_61>",
271
+ "lstrip": true,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<extra_id_60>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<extra_id_59>",
285
+ "lstrip": true,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<extra_id_58>",
292
+ "lstrip": true,
293
+ "normalized": true,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<extra_id_57>",
299
+ "lstrip": true,
300
+ "normalized": true,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<extra_id_56>",
306
+ "lstrip": true,
307
+ "normalized": true,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<extra_id_55>",
313
+ "lstrip": true,
314
+ "normalized": true,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<extra_id_54>",
320
+ "lstrip": true,
321
+ "normalized": true,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<extra_id_53>",
327
+ "lstrip": true,
328
+ "normalized": true,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<extra_id_52>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<extra_id_51>",
341
+ "lstrip": true,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<extra_id_50>",
348
+ "lstrip": true,
349
+ "normalized": true,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<extra_id_49>",
355
+ "lstrip": true,
356
+ "normalized": true,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<extra_id_48>",
362
+ "lstrip": true,
363
+ "normalized": true,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<extra_id_47>",
369
+ "lstrip": true,
370
+ "normalized": true,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<extra_id_46>",
376
+ "lstrip": true,
377
+ "normalized": true,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<extra_id_45>",
383
+ "lstrip": true,
384
+ "normalized": true,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<extra_id_44>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<extra_id_43>",
397
+ "lstrip": true,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "<extra_id_42>",
404
+ "lstrip": true,
405
+ "normalized": true,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<extra_id_41>",
411
+ "lstrip": true,
412
+ "normalized": true,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<extra_id_40>",
418
+ "lstrip": true,
419
+ "normalized": true,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<extra_id_39>",
425
+ "lstrip": true,
426
+ "normalized": true,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<extra_id_38>",
432
+ "lstrip": true,
433
+ "normalized": true,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<extra_id_37>",
439
+ "lstrip": true,
440
+ "normalized": true,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<extra_id_36>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "<extra_id_35>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "<extra_id_34>",
460
+ "lstrip": true,
461
+ "normalized": true,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "<extra_id_33>",
467
+ "lstrip": true,
468
+ "normalized": true,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "<extra_id_32>",
474
+ "lstrip": true,
475
+ "normalized": true,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "<extra_id_31>",
481
+ "lstrip": true,
482
+ "normalized": true,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "<extra_id_30>",
488
+ "lstrip": true,
489
+ "normalized": true,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "<extra_id_29>",
495
+ "lstrip": true,
496
+ "normalized": true,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "<extra_id_28>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "<extra_id_27>",
509
+ "lstrip": true,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "<extra_id_26>",
516
+ "lstrip": true,
517
+ "normalized": true,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "<extra_id_25>",
523
+ "lstrip": true,
524
+ "normalized": true,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "<extra_id_24>",
530
+ "lstrip": true,
531
+ "normalized": true,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "<extra_id_23>",
537
+ "lstrip": true,
538
+ "normalized": true,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "<extra_id_22>",
544
+ "lstrip": true,
545
+ "normalized": true,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "<extra_id_21>",
551
+ "lstrip": true,
552
+ "normalized": true,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "<extra_id_20>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "<extra_id_19>",
565
+ "lstrip": true,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "<extra_id_18>",
572
+ "lstrip": true,
573
+ "normalized": true,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "<extra_id_17>",
579
+ "lstrip": true,
580
+ "normalized": true,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "<extra_id_16>",
586
+ "lstrip": true,
587
+ "normalized": true,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<extra_id_15>",
593
+ "lstrip": true,
594
+ "normalized": true,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "<extra_id_14>",
600
+ "lstrip": true,
601
+ "normalized": true,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<extra_id_13>",
607
+ "lstrip": true,
608
+ "normalized": true,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "<extra_id_12>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "<extra_id_11>",
621
+ "lstrip": true,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "<extra_id_10>",
628
+ "lstrip": true,
629
+ "normalized": true,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "<extra_id_9>",
635
+ "lstrip": true,
636
+ "normalized": true,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "<extra_id_8>",
642
+ "lstrip": true,
643
+ "normalized": true,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "<extra_id_7>",
649
+ "lstrip": true,
650
+ "normalized": true,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "<extra_id_6>",
656
+ "lstrip": true,
657
+ "normalized": true,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "<extra_id_5>",
663
+ "lstrip": true,
664
+ "normalized": true,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "<extra_id_4>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "<extra_id_3>",
677
+ "lstrip": true,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "<extra_id_2>",
684
+ "lstrip": true,
685
+ "normalized": true,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "<extra_id_1>",
691
+ "lstrip": true,
692
+ "normalized": true,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "<extra_id_0>",
698
+ "lstrip": true,
699
+ "normalized": true,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ }
703
+ ],
704
+ "bos_token": {
705
+ "content": "<s>",
706
+ "lstrip": false,
707
+ "normalized": true,
708
+ "rstrip": false,
709
+ "single_word": false
710
+ },
711
+ "cls_token": {
712
+ "content": "<s>",
713
+ "lstrip": false,
714
+ "normalized": true,
715
+ "rstrip": false,
716
+ "single_word": false
717
+ },
718
+ "eos_token": {
719
+ "content": "</s>",
720
+ "lstrip": false,
721
+ "normalized": true,
722
+ "rstrip": false,
723
+ "single_word": false
724
+ },
725
+ "mask_token": {
726
+ "content": "<mask>",
727
+ "lstrip": true,
728
+ "normalized": true,
729
+ "rstrip": false,
730
+ "single_word": false
731
+ },
732
+ "pad_token": {
733
+ "content": "<pad>",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false
738
+ },
739
+ "sep_token": {
740
+ "content": "</s>",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false
745
+ },
746
+ "unk_token": {
747
+ "content": "<unk>",
748
+ "lstrip": false,
749
+ "normalized": true,
750
+ "rstrip": false,
751
+ "single_word": false
752
+ }
753
+ }
checkpoints/checkpoint-19425/tokenizer_config.json ADDED
@@ -0,0 +1,958 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32000": {
45
+ "content": "<extra_id_99>",
46
+ "lstrip": true,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32001": {
53
+ "content": "<extra_id_98>",
54
+ "lstrip": true,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32002": {
61
+ "content": "<extra_id_97>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32003": {
69
+ "content": "<extra_id_96>",
70
+ "lstrip": true,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32004": {
77
+ "content": "<extra_id_95>",
78
+ "lstrip": true,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32005": {
85
+ "content": "<extra_id_94>",
86
+ "lstrip": true,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32006": {
93
+ "content": "<extra_id_93>",
94
+ "lstrip": true,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32007": {
101
+ "content": "<extra_id_92>",
102
+ "lstrip": true,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32008": {
109
+ "content": "<extra_id_91>",
110
+ "lstrip": true,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32009": {
117
+ "content": "<extra_id_90>",
118
+ "lstrip": true,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32010": {
125
+ "content": "<extra_id_89>",
126
+ "lstrip": true,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32011": {
133
+ "content": "<extra_id_88>",
134
+ "lstrip": true,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32012": {
141
+ "content": "<extra_id_87>",
142
+ "lstrip": true,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32013": {
149
+ "content": "<extra_id_86>",
150
+ "lstrip": true,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32014": {
157
+ "content": "<extra_id_85>",
158
+ "lstrip": true,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32015": {
165
+ "content": "<extra_id_84>",
166
+ "lstrip": true,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32016": {
173
+ "content": "<extra_id_83>",
174
+ "lstrip": true,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32017": {
181
+ "content": "<extra_id_82>",
182
+ "lstrip": true,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32018": {
189
+ "content": "<extra_id_81>",
190
+ "lstrip": true,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32019": {
197
+ "content": "<extra_id_80>",
198
+ "lstrip": true,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32020": {
205
+ "content": "<extra_id_79>",
206
+ "lstrip": true,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32021": {
213
+ "content": "<extra_id_78>",
214
+ "lstrip": true,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32022": {
221
+ "content": "<extra_id_77>",
222
+ "lstrip": true,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32023": {
229
+ "content": "<extra_id_76>",
230
+ "lstrip": true,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32024": {
237
+ "content": "<extra_id_75>",
238
+ "lstrip": true,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32025": {
245
+ "content": "<extra_id_74>",
246
+ "lstrip": true,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32026": {
253
+ "content": "<extra_id_73>",
254
+ "lstrip": true,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32027": {
261
+ "content": "<extra_id_72>",
262
+ "lstrip": true,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32028": {
269
+ "content": "<extra_id_71>",
270
+ "lstrip": true,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32029": {
277
+ "content": "<extra_id_70>",
278
+ "lstrip": true,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32030": {
285
+ "content": "<extra_id_69>",
286
+ "lstrip": true,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32031": {
293
+ "content": "<extra_id_68>",
294
+ "lstrip": true,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32032": {
301
+ "content": "<extra_id_67>",
302
+ "lstrip": true,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32033": {
309
+ "content": "<extra_id_66>",
310
+ "lstrip": true,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32034": {
317
+ "content": "<extra_id_65>",
318
+ "lstrip": true,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32035": {
325
+ "content": "<extra_id_64>",
326
+ "lstrip": true,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32036": {
333
+ "content": "<extra_id_63>",
334
+ "lstrip": true,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32037": {
341
+ "content": "<extra_id_62>",
342
+ "lstrip": true,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32038": {
349
+ "content": "<extra_id_61>",
350
+ "lstrip": true,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32039": {
357
+ "content": "<extra_id_60>",
358
+ "lstrip": true,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32040": {
365
+ "content": "<extra_id_59>",
366
+ "lstrip": true,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32041": {
373
+ "content": "<extra_id_58>",
374
+ "lstrip": true,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32042": {
381
+ "content": "<extra_id_57>",
382
+ "lstrip": true,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32043": {
389
+ "content": "<extra_id_56>",
390
+ "lstrip": true,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32044": {
397
+ "content": "<extra_id_55>",
398
+ "lstrip": true,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32045": {
405
+ "content": "<extra_id_54>",
406
+ "lstrip": true,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32046": {
413
+ "content": "<extra_id_53>",
414
+ "lstrip": true,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32047": {
421
+ "content": "<extra_id_52>",
422
+ "lstrip": true,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32048": {
429
+ "content": "<extra_id_51>",
430
+ "lstrip": true,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32049": {
437
+ "content": "<extra_id_50>",
438
+ "lstrip": true,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32050": {
445
+ "content": "<extra_id_49>",
446
+ "lstrip": true,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32051": {
453
+ "content": "<extra_id_48>",
454
+ "lstrip": true,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32052": {
461
+ "content": "<extra_id_47>",
462
+ "lstrip": true,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32053": {
469
+ "content": "<extra_id_46>",
470
+ "lstrip": true,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32054": {
477
+ "content": "<extra_id_45>",
478
+ "lstrip": true,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32055": {
485
+ "content": "<extra_id_44>",
486
+ "lstrip": true,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32056": {
493
+ "content": "<extra_id_43>",
494
+ "lstrip": true,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32057": {
501
+ "content": "<extra_id_42>",
502
+ "lstrip": true,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32058": {
509
+ "content": "<extra_id_41>",
510
+ "lstrip": true,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32059": {
517
+ "content": "<extra_id_40>",
518
+ "lstrip": true,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32060": {
525
+ "content": "<extra_id_39>",
526
+ "lstrip": true,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32061": {
533
+ "content": "<extra_id_38>",
534
+ "lstrip": true,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32062": {
541
+ "content": "<extra_id_37>",
542
+ "lstrip": true,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32063": {
549
+ "content": "<extra_id_36>",
550
+ "lstrip": true,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32064": {
557
+ "content": "<extra_id_35>",
558
+ "lstrip": true,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32065": {
565
+ "content": "<extra_id_34>",
566
+ "lstrip": true,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32066": {
573
+ "content": "<extra_id_33>",
574
+ "lstrip": true,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32067": {
581
+ "content": "<extra_id_32>",
582
+ "lstrip": true,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32068": {
589
+ "content": "<extra_id_31>",
590
+ "lstrip": true,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32069": {
597
+ "content": "<extra_id_30>",
598
+ "lstrip": true,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32070": {
605
+ "content": "<extra_id_29>",
606
+ "lstrip": true,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32071": {
613
+ "content": "<extra_id_28>",
614
+ "lstrip": true,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32072": {
621
+ "content": "<extra_id_27>",
622
+ "lstrip": true,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32073": {
629
+ "content": "<extra_id_26>",
630
+ "lstrip": true,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32074": {
637
+ "content": "<extra_id_25>",
638
+ "lstrip": true,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32075": {
645
+ "content": "<extra_id_24>",
646
+ "lstrip": true,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32076": {
653
+ "content": "<extra_id_23>",
654
+ "lstrip": true,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32077": {
661
+ "content": "<extra_id_22>",
662
+ "lstrip": true,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32078": {
669
+ "content": "<extra_id_21>",
670
+ "lstrip": true,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32079": {
677
+ "content": "<extra_id_20>",
678
+ "lstrip": true,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32080": {
685
+ "content": "<extra_id_19>",
686
+ "lstrip": true,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32081": {
693
+ "content": "<extra_id_18>",
694
+ "lstrip": true,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32082": {
701
+ "content": "<extra_id_17>",
702
+ "lstrip": true,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32083": {
709
+ "content": "<extra_id_16>",
710
+ "lstrip": true,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32084": {
717
+ "content": "<extra_id_15>",
718
+ "lstrip": true,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32085": {
725
+ "content": "<extra_id_14>",
726
+ "lstrip": true,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32086": {
733
+ "content": "<extra_id_13>",
734
+ "lstrip": true,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32087": {
741
+ "content": "<extra_id_12>",
742
+ "lstrip": true,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32088": {
749
+ "content": "<extra_id_11>",
750
+ "lstrip": true,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32089": {
757
+ "content": "<extra_id_10>",
758
+ "lstrip": true,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32090": {
765
+ "content": "<extra_id_9>",
766
+ "lstrip": true,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32091": {
773
+ "content": "<extra_id_8>",
774
+ "lstrip": true,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32092": {
781
+ "content": "<extra_id_7>",
782
+ "lstrip": true,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32093": {
789
+ "content": "<extra_id_6>",
790
+ "lstrip": true,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32094": {
797
+ "content": "<extra_id_5>",
798
+ "lstrip": true,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32095": {
805
+ "content": "<extra_id_4>",
806
+ "lstrip": true,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32096": {
813
+ "content": "<extra_id_3>",
814
+ "lstrip": true,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32097": {
821
+ "content": "<extra_id_2>",
822
+ "lstrip": true,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32098": {
829
+ "content": "<extra_id_1>",
830
+ "lstrip": true,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32099": {
837
+ "content": "<extra_id_0>",
838
+ "lstrip": true,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ }
844
+ },
845
+ "additional_special_tokens": [
846
+ "<extra_id_99>",
847
+ "<extra_id_98>",
848
+ "<extra_id_97>",
849
+ "<extra_id_96>",
850
+ "<extra_id_95>",
851
+ "<extra_id_94>",
852
+ "<extra_id_93>",
853
+ "<extra_id_92>",
854
+ "<extra_id_91>",
855
+ "<extra_id_90>",
856
+ "<extra_id_89>",
857
+ "<extra_id_88>",
858
+ "<extra_id_87>",
859
+ "<extra_id_86>",
860
+ "<extra_id_85>",
861
+ "<extra_id_84>",
862
+ "<extra_id_83>",
863
+ "<extra_id_82>",
864
+ "<extra_id_81>",
865
+ "<extra_id_80>",
866
+ "<extra_id_79>",
867
+ "<extra_id_78>",
868
+ "<extra_id_77>",
869
+ "<extra_id_76>",
870
+ "<extra_id_75>",
871
+ "<extra_id_74>",
872
+ "<extra_id_73>",
873
+ "<extra_id_72>",
874
+ "<extra_id_71>",
875
+ "<extra_id_70>",
876
+ "<extra_id_69>",
877
+ "<extra_id_68>",
878
+ "<extra_id_67>",
879
+ "<extra_id_66>",
880
+ "<extra_id_65>",
881
+ "<extra_id_64>",
882
+ "<extra_id_63>",
883
+ "<extra_id_62>",
884
+ "<extra_id_61>",
885
+ "<extra_id_60>",
886
+ "<extra_id_59>",
887
+ "<extra_id_58>",
888
+ "<extra_id_57>",
889
+ "<extra_id_56>",
890
+ "<extra_id_55>",
891
+ "<extra_id_54>",
892
+ "<extra_id_53>",
893
+ "<extra_id_52>",
894
+ "<extra_id_51>",
895
+ "<extra_id_50>",
896
+ "<extra_id_49>",
897
+ "<extra_id_48>",
898
+ "<extra_id_47>",
899
+ "<extra_id_46>",
900
+ "<extra_id_45>",
901
+ "<extra_id_44>",
902
+ "<extra_id_43>",
903
+ "<extra_id_42>",
904
+ "<extra_id_41>",
905
+ "<extra_id_40>",
906
+ "<extra_id_39>",
907
+ "<extra_id_38>",
908
+ "<extra_id_37>",
909
+ "<extra_id_36>",
910
+ "<extra_id_35>",
911
+ "<extra_id_34>",
912
+ "<extra_id_33>",
913
+ "<extra_id_32>",
914
+ "<extra_id_31>",
915
+ "<extra_id_30>",
916
+ "<extra_id_29>",
917
+ "<extra_id_28>",
918
+ "<extra_id_27>",
919
+ "<extra_id_26>",
920
+ "<extra_id_25>",
921
+ "<extra_id_24>",
922
+ "<extra_id_23>",
923
+ "<extra_id_22>",
924
+ "<extra_id_21>",
925
+ "<extra_id_20>",
926
+ "<extra_id_19>",
927
+ "<extra_id_18>",
928
+ "<extra_id_17>",
929
+ "<extra_id_16>",
930
+ "<extra_id_15>",
931
+ "<extra_id_14>",
932
+ "<extra_id_13>",
933
+ "<extra_id_12>",
934
+ "<extra_id_11>",
935
+ "<extra_id_10>",
936
+ "<extra_id_9>",
937
+ "<extra_id_8>",
938
+ "<extra_id_7>",
939
+ "<extra_id_6>",
940
+ "<extra_id_5>",
941
+ "<extra_id_4>",
942
+ "<extra_id_3>",
943
+ "<extra_id_2>",
944
+ "<extra_id_1>",
945
+ "<extra_id_0>"
946
+ ],
947
+ "bos_token": "<s>",
948
+ "clean_up_tokenization_spaces": true,
949
+ "cls_token": "<s>",
950
+ "eos_token": "</s>",
951
+ "errors": "replace",
952
+ "mask_token": "<mask>",
953
+ "model_max_length": 512,
954
+ "pad_token": "<pad>",
955
+ "sep_token": "</s>",
956
+ "tokenizer_class": "RobertaTokenizer",
957
+ "unk_token": "<unk>"
958
+ }
checkpoints/checkpoint-19425/trainer_state.json ADDED
@@ -0,0 +1,2901 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.999356582164458,
5
+ "eval_steps": 1000,
6
+ "global_step": 19425,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.012868356710848025,
13
+ "grad_norm": 5.15623140335083,
14
+ "learning_rate": 4.987387387387388e-05,
15
+ "loss": 1.7328,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.02573671342169605,
20
+ "grad_norm": 4.769791603088379,
21
+ "learning_rate": 4.9745173745173744e-05,
22
+ "loss": 1.3827,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.03860507013254407,
27
+ "grad_norm": 3.983968734741211,
28
+ "learning_rate": 4.9616473616473616e-05,
29
+ "loss": 1.2993,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.0514734268433921,
34
+ "grad_norm": 4.153149127960205,
35
+ "learning_rate": 4.9487773487773494e-05,
36
+ "loss": 1.2884,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.06434178355424013,
41
+ "grad_norm": 3.8115487098693848,
42
+ "learning_rate": 4.935907335907336e-05,
43
+ "loss": 1.2803,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.07721014026508814,
48
+ "grad_norm": 4.397896766662598,
49
+ "learning_rate": 4.923037323037323e-05,
50
+ "loss": 1.2442,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.09007849697593617,
55
+ "grad_norm": 4.619286060333252,
56
+ "learning_rate": 4.91016731016731e-05,
57
+ "loss": 1.2187,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.1029468536867842,
62
+ "grad_norm": 4.834469795227051,
63
+ "learning_rate": 4.8972972972972974e-05,
64
+ "loss": 1.1784,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.11581521039763222,
69
+ "grad_norm": 3.5152344703674316,
70
+ "learning_rate": 4.8844272844272846e-05,
71
+ "loss": 1.162,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.12868356710848025,
76
+ "grad_norm": 4.991385459899902,
77
+ "learning_rate": 4.871557271557272e-05,
78
+ "loss": 1.2053,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.14155192381932827,
83
+ "grad_norm": 3.806436538696289,
84
+ "learning_rate": 4.8589446589446594e-05,
85
+ "loss": 1.1554,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.15442028053017628,
90
+ "grad_norm": 4.663485050201416,
91
+ "learning_rate": 4.8460746460746466e-05,
92
+ "loss": 1.135,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.16728863724102433,
97
+ "grad_norm": 4.0664238929748535,
98
+ "learning_rate": 4.833204633204633e-05,
99
+ "loss": 1.1372,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.18015699395187235,
104
+ "grad_norm": 3.8850207328796387,
105
+ "learning_rate": 4.82033462033462e-05,
106
+ "loss": 1.0818,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.19302535066272036,
111
+ "grad_norm": 3.971874713897705,
112
+ "learning_rate": 4.807464607464608e-05,
113
+ "loss": 1.1086,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.2058937073735684,
118
+ "grad_norm": 3.79402232170105,
119
+ "learning_rate": 4.7945945945945946e-05,
120
+ "loss": 1.1449,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.21876206408441642,
125
+ "grad_norm": 4.102041721343994,
126
+ "learning_rate": 4.781724581724582e-05,
127
+ "loss": 1.1066,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.23163042079526444,
132
+ "grad_norm": 4.198806285858154,
133
+ "learning_rate": 4.768854568854569e-05,
134
+ "loss": 1.1604,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.24449877750611246,
139
+ "grad_norm": 3.196410655975342,
140
+ "learning_rate": 4.755984555984556e-05,
141
+ "loss": 1.1193,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.2573671342169605,
146
+ "grad_norm": 4.250946521759033,
147
+ "learning_rate": 4.743114543114543e-05,
148
+ "loss": 1.1378,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.2573671342169605,
153
+ "eval_loss": 1.026713252067566,
154
+ "eval_runtime": 189.3511,
155
+ "eval_samples_per_second": 102.592,
156
+ "eval_steps_per_second": 10.261,
157
+ "step": 1000
158
+ },
159
+ {
160
+ "epoch": 0.2702354909278085,
161
+ "grad_norm": 3.319427251815796,
162
+ "learning_rate": 4.7302445302445304e-05,
163
+ "loss": 1.0153,
164
+ "step": 1050
165
+ },
166
+ {
167
+ "epoch": 0.28310384763865654,
168
+ "grad_norm": 3.8477160930633545,
169
+ "learning_rate": 4.7173745173745175e-05,
170
+ "loss": 1.0782,
171
+ "step": 1100
172
+ },
173
+ {
174
+ "epoch": 0.29597220434950455,
175
+ "grad_norm": 3.674345016479492,
176
+ "learning_rate": 4.704504504504505e-05,
177
+ "loss": 1.0935,
178
+ "step": 1150
179
+ },
180
+ {
181
+ "epoch": 0.30884056106035257,
182
+ "grad_norm": 3.0566294193267822,
183
+ "learning_rate": 4.691634491634492e-05,
184
+ "loss": 1.1357,
185
+ "step": 1200
186
+ },
187
+ {
188
+ "epoch": 0.32170891777120064,
189
+ "grad_norm": 3.81984806060791,
190
+ "learning_rate": 4.678764478764479e-05,
191
+ "loss": 1.0254,
192
+ "step": 1250
193
+ },
194
+ {
195
+ "epoch": 0.33457727448204866,
196
+ "grad_norm": 4.312713623046875,
197
+ "learning_rate": 4.665894465894466e-05,
198
+ "loss": 1.0809,
199
+ "step": 1300
200
+ },
201
+ {
202
+ "epoch": 0.3474456311928967,
203
+ "grad_norm": 4.260924339294434,
204
+ "learning_rate": 4.653024453024453e-05,
205
+ "loss": 1.1019,
206
+ "step": 1350
207
+ },
208
+ {
209
+ "epoch": 0.3603139879037447,
210
+ "grad_norm": 3.334003448486328,
211
+ "learning_rate": 4.6401544401544405e-05,
212
+ "loss": 1.0271,
213
+ "step": 1400
214
+ },
215
+ {
216
+ "epoch": 0.3731823446145927,
217
+ "grad_norm": 3.480570077896118,
218
+ "learning_rate": 4.6272844272844277e-05,
219
+ "loss": 1.0714,
220
+ "step": 1450
221
+ },
222
+ {
223
+ "epoch": 0.3860507013254407,
224
+ "grad_norm": 3.051344871520996,
225
+ "learning_rate": 4.614414414414415e-05,
226
+ "loss": 1.0437,
227
+ "step": 1500
228
+ },
229
+ {
230
+ "epoch": 0.39891905803628874,
231
+ "grad_norm": 3.3421928882598877,
232
+ "learning_rate": 4.601544401544402e-05,
233
+ "loss": 1.0486,
234
+ "step": 1550
235
+ },
236
+ {
237
+ "epoch": 0.4117874147471368,
238
+ "grad_norm": 3.3062002658843994,
239
+ "learning_rate": 4.588674388674389e-05,
240
+ "loss": 1.067,
241
+ "step": 1600
242
+ },
243
+ {
244
+ "epoch": 0.42465577145798483,
245
+ "grad_norm": 3.173940420150757,
246
+ "learning_rate": 4.575804375804376e-05,
247
+ "loss": 1.0349,
248
+ "step": 1650
249
+ },
250
+ {
251
+ "epoch": 0.43752412816883285,
252
+ "grad_norm": 3.4759039878845215,
253
+ "learning_rate": 4.562934362934363e-05,
254
+ "loss": 1.0471,
255
+ "step": 1700
256
+ },
257
+ {
258
+ "epoch": 0.45039248487968087,
259
+ "grad_norm": 3.4710917472839355,
260
+ "learning_rate": 4.55006435006435e-05,
261
+ "loss": 1.0891,
262
+ "step": 1750
263
+ },
264
+ {
265
+ "epoch": 0.4632608415905289,
266
+ "grad_norm": 3.515437602996826,
267
+ "learning_rate": 4.537194337194338e-05,
268
+ "loss": 1.0072,
269
+ "step": 1800
270
+ },
271
+ {
272
+ "epoch": 0.4761291983013769,
273
+ "grad_norm": 3.6845717430114746,
274
+ "learning_rate": 4.524324324324324e-05,
275
+ "loss": 1.0141,
276
+ "step": 1850
277
+ },
278
+ {
279
+ "epoch": 0.4889975550122249,
280
+ "grad_norm": 4.084773540496826,
281
+ "learning_rate": 4.5114543114543114e-05,
282
+ "loss": 1.003,
283
+ "step": 1900
284
+ },
285
+ {
286
+ "epoch": 0.5018659117230729,
287
+ "grad_norm": 3.49133038520813,
288
+ "learning_rate": 4.4985842985842986e-05,
289
+ "loss": 1.056,
290
+ "step": 1950
291
+ },
292
+ {
293
+ "epoch": 0.514734268433921,
294
+ "grad_norm": 3.321465015411377,
295
+ "learning_rate": 4.485714285714286e-05,
296
+ "loss": 1.0146,
297
+ "step": 2000
298
+ },
299
+ {
300
+ "epoch": 0.514734268433921,
301
+ "eval_loss": 0.9642198085784912,
302
+ "eval_runtime": 189.3709,
303
+ "eval_samples_per_second": 102.582,
304
+ "eval_steps_per_second": 10.26,
305
+ "step": 2000
306
+ },
307
+ {
308
+ "epoch": 0.527602625144769,
309
+ "grad_norm": 4.292445182800293,
310
+ "learning_rate": 4.472844272844273e-05,
311
+ "loss": 1.079,
312
+ "step": 2050
313
+ },
314
+ {
315
+ "epoch": 0.540470981855617,
316
+ "grad_norm": 3.905832529067993,
317
+ "learning_rate": 4.45997425997426e-05,
318
+ "loss": 0.9615,
319
+ "step": 2100
320
+ },
321
+ {
322
+ "epoch": 0.5533393385664651,
323
+ "grad_norm": 3.985164165496826,
324
+ "learning_rate": 4.447104247104247e-05,
325
+ "loss": 1.0643,
326
+ "step": 2150
327
+ },
328
+ {
329
+ "epoch": 0.5662076952773131,
330
+ "grad_norm": 3.4493820667266846,
331
+ "learning_rate": 4.4342342342342344e-05,
332
+ "loss": 1.0075,
333
+ "step": 2200
334
+ },
335
+ {
336
+ "epoch": 0.5790760519881611,
337
+ "grad_norm": 3.188607931137085,
338
+ "learning_rate": 4.4213642213642216e-05,
339
+ "loss": 0.9822,
340
+ "step": 2250
341
+ },
342
+ {
343
+ "epoch": 0.5919444086990091,
344
+ "grad_norm": 4.343353748321533,
345
+ "learning_rate": 4.408494208494209e-05,
346
+ "loss": 1.0451,
347
+ "step": 2300
348
+ },
349
+ {
350
+ "epoch": 0.6048127654098572,
351
+ "grad_norm": 5.567046642303467,
352
+ "learning_rate": 4.395624195624196e-05,
353
+ "loss": 0.9741,
354
+ "step": 2350
355
+ },
356
+ {
357
+ "epoch": 0.6176811221207051,
358
+ "grad_norm": 3.7193870544433594,
359
+ "learning_rate": 4.382754182754183e-05,
360
+ "loss": 1.0067,
361
+ "step": 2400
362
+ },
363
+ {
364
+ "epoch": 0.6305494788315532,
365
+ "grad_norm": 3.9916462898254395,
366
+ "learning_rate": 4.36988416988417e-05,
367
+ "loss": 1.0139,
368
+ "step": 2450
369
+ },
370
+ {
371
+ "epoch": 0.6434178355424013,
372
+ "grad_norm": 2.9249072074890137,
373
+ "learning_rate": 4.3570141570141574e-05,
374
+ "loss": 0.9773,
375
+ "step": 2500
376
+ },
377
+ {
378
+ "epoch": 0.6562861922532492,
379
+ "grad_norm": 3.220916748046875,
380
+ "learning_rate": 4.3441441441441445e-05,
381
+ "loss": 0.9802,
382
+ "step": 2550
383
+ },
384
+ {
385
+ "epoch": 0.6691545489640973,
386
+ "grad_norm": 3.6743297576904297,
387
+ "learning_rate": 4.331274131274132e-05,
388
+ "loss": 0.9568,
389
+ "step": 2600
390
+ },
391
+ {
392
+ "epoch": 0.6820229056749453,
393
+ "grad_norm": 3.846135377883911,
394
+ "learning_rate": 4.318404118404119e-05,
395
+ "loss": 1.0341,
396
+ "step": 2650
397
+ },
398
+ {
399
+ "epoch": 0.6948912623857934,
400
+ "grad_norm": 3.933671236038208,
401
+ "learning_rate": 4.305534105534106e-05,
402
+ "loss": 1.0272,
403
+ "step": 2700
404
+ },
405
+ {
406
+ "epoch": 0.7077596190966413,
407
+ "grad_norm": 4.287942409515381,
408
+ "learning_rate": 4.2926640926640925e-05,
409
+ "loss": 0.9458,
410
+ "step": 2750
411
+ },
412
+ {
413
+ "epoch": 0.7206279758074894,
414
+ "grad_norm": 3.385679006576538,
415
+ "learning_rate": 4.2797940797940796e-05,
416
+ "loss": 1.013,
417
+ "step": 2800
418
+ },
419
+ {
420
+ "epoch": 0.7334963325183375,
421
+ "grad_norm": 3.283371925354004,
422
+ "learning_rate": 4.2669240669240675e-05,
423
+ "loss": 0.9173,
424
+ "step": 2850
425
+ },
426
+ {
427
+ "epoch": 0.7463646892291854,
428
+ "grad_norm": 3.90366268157959,
429
+ "learning_rate": 4.254054054054054e-05,
430
+ "loss": 0.9605,
431
+ "step": 2900
432
+ },
433
+ {
434
+ "epoch": 0.7592330459400335,
435
+ "grad_norm": 3.5078847408294678,
436
+ "learning_rate": 4.241184041184041e-05,
437
+ "loss": 1.0341,
438
+ "step": 2950
439
+ },
440
+ {
441
+ "epoch": 0.7721014026508815,
442
+ "grad_norm": 3.1368582248687744,
443
+ "learning_rate": 4.228314028314029e-05,
444
+ "loss": 0.9344,
445
+ "step": 3000
446
+ },
447
+ {
448
+ "epoch": 0.7721014026508815,
449
+ "eval_loss": 0.9136499762535095,
450
+ "eval_runtime": 189.3685,
451
+ "eval_samples_per_second": 102.583,
452
+ "eval_steps_per_second": 10.26,
453
+ "step": 3000
454
+ },
455
+ {
456
+ "epoch": 0.7849697593617295,
457
+ "grad_norm": 3.6094772815704346,
458
+ "learning_rate": 4.2154440154440154e-05,
459
+ "loss": 0.9633,
460
+ "step": 3050
461
+ },
462
+ {
463
+ "epoch": 0.7978381160725775,
464
+ "grad_norm": 3.157749652862549,
465
+ "learning_rate": 4.2025740025740026e-05,
466
+ "loss": 0.9851,
467
+ "step": 3100
468
+ },
469
+ {
470
+ "epoch": 0.8107064727834256,
471
+ "grad_norm": 2.6654834747314453,
472
+ "learning_rate": 4.18970398970399e-05,
473
+ "loss": 0.9317,
474
+ "step": 3150
475
+ },
476
+ {
477
+ "epoch": 0.8235748294942736,
478
+ "grad_norm": 3.4694721698760986,
479
+ "learning_rate": 4.176833976833977e-05,
480
+ "loss": 0.9166,
481
+ "step": 3200
482
+ },
483
+ {
484
+ "epoch": 0.8364431862051216,
485
+ "grad_norm": 4.163283824920654,
486
+ "learning_rate": 4.163963963963964e-05,
487
+ "loss": 1.0012,
488
+ "step": 3250
489
+ },
490
+ {
491
+ "epoch": 0.8493115429159697,
492
+ "grad_norm": 2.8416895866394043,
493
+ "learning_rate": 4.151093951093951e-05,
494
+ "loss": 0.9063,
495
+ "step": 3300
496
+ },
497
+ {
498
+ "epoch": 0.8621798996268176,
499
+ "grad_norm": 2.7988712787628174,
500
+ "learning_rate": 4.1382239382239384e-05,
501
+ "loss": 0.9155,
502
+ "step": 3350
503
+ },
504
+ {
505
+ "epoch": 0.8750482563376657,
506
+ "grad_norm": 2.930269241333008,
507
+ "learning_rate": 4.1253539253539256e-05,
508
+ "loss": 0.9897,
509
+ "step": 3400
510
+ },
511
+ {
512
+ "epoch": 0.8879166130485137,
513
+ "grad_norm": 3.0751140117645264,
514
+ "learning_rate": 4.112483912483913e-05,
515
+ "loss": 0.9355,
516
+ "step": 3450
517
+ },
518
+ {
519
+ "epoch": 0.9007849697593617,
520
+ "grad_norm": 4.277087688446045,
521
+ "learning_rate": 4.0996138996139e-05,
522
+ "loss": 0.945,
523
+ "step": 3500
524
+ },
525
+ {
526
+ "epoch": 0.9136533264702098,
527
+ "grad_norm": 4.510545253753662,
528
+ "learning_rate": 4.086743886743887e-05,
529
+ "loss": 0.97,
530
+ "step": 3550
531
+ },
532
+ {
533
+ "epoch": 0.9265216831810578,
534
+ "grad_norm": 3.1346421241760254,
535
+ "learning_rate": 4.073873873873874e-05,
536
+ "loss": 0.9602,
537
+ "step": 3600
538
+ },
539
+ {
540
+ "epoch": 0.9393900398919058,
541
+ "grad_norm": 2.9139790534973145,
542
+ "learning_rate": 4.0610038610038614e-05,
543
+ "loss": 0.939,
544
+ "step": 3650
545
+ },
546
+ {
547
+ "epoch": 0.9522583966027538,
548
+ "grad_norm": 3.7701892852783203,
549
+ "learning_rate": 4.0481338481338485e-05,
550
+ "loss": 0.9806,
551
+ "step": 3700
552
+ },
553
+ {
554
+ "epoch": 0.9651267533136019,
555
+ "grad_norm": 3.3391294479370117,
556
+ "learning_rate": 4.035263835263836e-05,
557
+ "loss": 0.9835,
558
+ "step": 3750
559
+ },
560
+ {
561
+ "epoch": 0.9779951100244498,
562
+ "grad_norm": 4.155078887939453,
563
+ "learning_rate": 4.022393822393822e-05,
564
+ "loss": 0.9921,
565
+ "step": 3800
566
+ },
567
+ {
568
+ "epoch": 0.9908634667352979,
569
+ "grad_norm": 3.9210457801818848,
570
+ "learning_rate": 4.00952380952381e-05,
571
+ "loss": 0.9831,
572
+ "step": 3850
573
+ },
574
+ {
575
+ "epoch": 1.0037318234461459,
576
+ "grad_norm": 2.388692855834961,
577
+ "learning_rate": 3.996653796653797e-05,
578
+ "loss": 0.8888,
579
+ "step": 3900
580
+ },
581
+ {
582
+ "epoch": 1.016600180156994,
583
+ "grad_norm": 3.42979097366333,
584
+ "learning_rate": 3.983783783783784e-05,
585
+ "loss": 0.76,
586
+ "step": 3950
587
+ },
588
+ {
589
+ "epoch": 1.029468536867842,
590
+ "grad_norm": 3.304460048675537,
591
+ "learning_rate": 3.970913770913771e-05,
592
+ "loss": 0.752,
593
+ "step": 4000
594
+ },
595
+ {
596
+ "epoch": 1.029468536867842,
597
+ "eval_loss": 0.8883536458015442,
598
+ "eval_runtime": 189.2819,
599
+ "eval_samples_per_second": 102.63,
600
+ "eval_steps_per_second": 10.265,
601
+ "step": 4000
602
+ },
603
+ {
604
+ "epoch": 1.04233689357869,
605
+ "grad_norm": 3.8564417362213135,
606
+ "learning_rate": 3.9580437580437587e-05,
607
+ "loss": 0.7679,
608
+ "step": 4050
609
+ },
610
+ {
611
+ "epoch": 1.055205250289538,
612
+ "grad_norm": 3.680621385574341,
613
+ "learning_rate": 3.945173745173745e-05,
614
+ "loss": 0.7563,
615
+ "step": 4100
616
+ },
617
+ {
618
+ "epoch": 1.068073607000386,
619
+ "grad_norm": 3.4106550216674805,
620
+ "learning_rate": 3.932303732303732e-05,
621
+ "loss": 0.7149,
622
+ "step": 4150
623
+ },
624
+ {
625
+ "epoch": 1.080941963711234,
626
+ "grad_norm": 3.5690340995788574,
627
+ "learning_rate": 3.9194337194337195e-05,
628
+ "loss": 0.7185,
629
+ "step": 4200
630
+ },
631
+ {
632
+ "epoch": 1.0938103204220821,
633
+ "grad_norm": 3.215930700302124,
634
+ "learning_rate": 3.9065637065637066e-05,
635
+ "loss": 0.762,
636
+ "step": 4250
637
+ },
638
+ {
639
+ "epoch": 1.1066786771329302,
640
+ "grad_norm": 3.48146390914917,
641
+ "learning_rate": 3.893693693693694e-05,
642
+ "loss": 0.744,
643
+ "step": 4300
644
+ },
645
+ {
646
+ "epoch": 1.119547033843778,
647
+ "grad_norm": 3.667818069458008,
648
+ "learning_rate": 3.880823680823681e-05,
649
+ "loss": 0.7564,
650
+ "step": 4350
651
+ },
652
+ {
653
+ "epoch": 1.1324153905546261,
654
+ "grad_norm": 4.029824256896973,
655
+ "learning_rate": 3.867953667953668e-05,
656
+ "loss": 0.7631,
657
+ "step": 4400
658
+ },
659
+ {
660
+ "epoch": 1.1452837472654742,
661
+ "grad_norm": 3.8039183616638184,
662
+ "learning_rate": 3.855083655083655e-05,
663
+ "loss": 0.7635,
664
+ "step": 4450
665
+ },
666
+ {
667
+ "epoch": 1.1581521039763223,
668
+ "grad_norm": 2.8013832569122314,
669
+ "learning_rate": 3.8422136422136424e-05,
670
+ "loss": 0.6891,
671
+ "step": 4500
672
+ },
673
+ {
674
+ "epoch": 1.1710204606871701,
675
+ "grad_norm": 3.721989631652832,
676
+ "learning_rate": 3.8293436293436296e-05,
677
+ "loss": 0.763,
678
+ "step": 4550
679
+ },
680
+ {
681
+ "epoch": 1.1838888173980182,
682
+ "grad_norm": 2.802401304244995,
683
+ "learning_rate": 3.816473616473617e-05,
684
+ "loss": 0.7624,
685
+ "step": 4600
686
+ },
687
+ {
688
+ "epoch": 1.1967571741088663,
689
+ "grad_norm": 3.3529865741729736,
690
+ "learning_rate": 3.803603603603604e-05,
691
+ "loss": 0.7673,
692
+ "step": 4650
693
+ },
694
+ {
695
+ "epoch": 1.2096255308197144,
696
+ "grad_norm": 3.866051197052002,
697
+ "learning_rate": 3.790733590733591e-05,
698
+ "loss": 0.7713,
699
+ "step": 4700
700
+ },
701
+ {
702
+ "epoch": 1.2224938875305624,
703
+ "grad_norm": 3.5920650959014893,
704
+ "learning_rate": 3.777863577863578e-05,
705
+ "loss": 0.7484,
706
+ "step": 4750
707
+ },
708
+ {
709
+ "epoch": 1.2353622442414103,
710
+ "grad_norm": 4.17499303817749,
711
+ "learning_rate": 3.7649935649935654e-05,
712
+ "loss": 0.7279,
713
+ "step": 4800
714
+ },
715
+ {
716
+ "epoch": 1.2482306009522584,
717
+ "grad_norm": 4.160298824310303,
718
+ "learning_rate": 3.752123552123552e-05,
719
+ "loss": 0.7442,
720
+ "step": 4850
721
+ },
722
+ {
723
+ "epoch": 1.2610989576631064,
724
+ "grad_norm": 5.012088775634766,
725
+ "learning_rate": 3.73925353925354e-05,
726
+ "loss": 0.7322,
727
+ "step": 4900
728
+ },
729
+ {
730
+ "epoch": 1.2739673143739545,
731
+ "grad_norm": 2.925732135772705,
732
+ "learning_rate": 3.726383526383527e-05,
733
+ "loss": 0.7284,
734
+ "step": 4950
735
+ },
736
+ {
737
+ "epoch": 1.2868356710848023,
738
+ "grad_norm": 3.843261241912842,
739
+ "learning_rate": 3.7135135135135134e-05,
740
+ "loss": 0.7816,
741
+ "step": 5000
742
+ },
743
+ {
744
+ "epoch": 1.2868356710848023,
745
+ "eval_loss": 0.8717387914657593,
746
+ "eval_runtime": 189.4604,
747
+ "eval_samples_per_second": 102.533,
748
+ "eval_steps_per_second": 10.255,
749
+ "step": 5000
750
+ },
751
+ {
752
+ "epoch": 1.2997040277956504,
753
+ "grad_norm": 3.363952398300171,
754
+ "learning_rate": 3.7006435006435005e-05,
755
+ "loss": 0.7719,
756
+ "step": 5050
757
+ },
758
+ {
759
+ "epoch": 1.3125723845064985,
760
+ "grad_norm": 3.3399648666381836,
761
+ "learning_rate": 3.6877734877734884e-05,
762
+ "loss": 0.7282,
763
+ "step": 5100
764
+ },
765
+ {
766
+ "epoch": 1.3254407412173466,
767
+ "grad_norm": 3.1839489936828613,
768
+ "learning_rate": 3.674903474903475e-05,
769
+ "loss": 0.7269,
770
+ "step": 5150
771
+ },
772
+ {
773
+ "epoch": 1.3383090979281946,
774
+ "grad_norm": 4.2268266677856445,
775
+ "learning_rate": 3.662033462033462e-05,
776
+ "loss": 0.7438,
777
+ "step": 5200
778
+ },
779
+ {
780
+ "epoch": 1.3511774546390427,
781
+ "grad_norm": 3.201995611190796,
782
+ "learning_rate": 3.649163449163449e-05,
783
+ "loss": 0.7396,
784
+ "step": 5250
785
+ },
786
+ {
787
+ "epoch": 1.3640458113498906,
788
+ "grad_norm": 2.455885887145996,
789
+ "learning_rate": 3.636293436293436e-05,
790
+ "loss": 0.7292,
791
+ "step": 5300
792
+ },
793
+ {
794
+ "epoch": 1.3769141680607386,
795
+ "grad_norm": 3.5545082092285156,
796
+ "learning_rate": 3.6234234234234235e-05,
797
+ "loss": 0.7118,
798
+ "step": 5350
799
+ },
800
+ {
801
+ "epoch": 1.3897825247715867,
802
+ "grad_norm": 3.1645827293395996,
803
+ "learning_rate": 3.6105534105534106e-05,
804
+ "loss": 0.7368,
805
+ "step": 5400
806
+ },
807
+ {
808
+ "epoch": 1.4026508814824348,
809
+ "grad_norm": 4.050566673278809,
810
+ "learning_rate": 3.597683397683398e-05,
811
+ "loss": 0.7368,
812
+ "step": 5450
813
+ },
814
+ {
815
+ "epoch": 1.4155192381932826,
816
+ "grad_norm": 3.393502950668335,
817
+ "learning_rate": 3.584813384813385e-05,
818
+ "loss": 0.7496,
819
+ "step": 5500
820
+ },
821
+ {
822
+ "epoch": 1.4283875949041307,
823
+ "grad_norm": 2.807429790496826,
824
+ "learning_rate": 3.571943371943372e-05,
825
+ "loss": 0.7224,
826
+ "step": 5550
827
+ },
828
+ {
829
+ "epoch": 1.4412559516149788,
830
+ "grad_norm": 3.8620431423187256,
831
+ "learning_rate": 3.559073359073359e-05,
832
+ "loss": 0.7135,
833
+ "step": 5600
834
+ },
835
+ {
836
+ "epoch": 1.4541243083258268,
837
+ "grad_norm": 3.6501224040985107,
838
+ "learning_rate": 3.5462033462033465e-05,
839
+ "loss": 0.7158,
840
+ "step": 5650
841
+ },
842
+ {
843
+ "epoch": 1.466992665036675,
844
+ "grad_norm": 3.178494453430176,
845
+ "learning_rate": 3.5333333333333336e-05,
846
+ "loss": 0.7122,
847
+ "step": 5700
848
+ },
849
+ {
850
+ "epoch": 1.4798610217475228,
851
+ "grad_norm": 3.163177251815796,
852
+ "learning_rate": 3.520463320463321e-05,
853
+ "loss": 0.7268,
854
+ "step": 5750
855
+ },
856
+ {
857
+ "epoch": 1.4927293784583708,
858
+ "grad_norm": 3.3929202556610107,
859
+ "learning_rate": 3.507593307593308e-05,
860
+ "loss": 0.7099,
861
+ "step": 5800
862
+ },
863
+ {
864
+ "epoch": 1.505597735169219,
865
+ "grad_norm": 4.053615570068359,
866
+ "learning_rate": 3.494723294723295e-05,
867
+ "loss": 0.7291,
868
+ "step": 5850
869
+ },
870
+ {
871
+ "epoch": 1.5184660918800668,
872
+ "grad_norm": 3.453657865524292,
873
+ "learning_rate": 3.4818532818532816e-05,
874
+ "loss": 0.7373,
875
+ "step": 5900
876
+ },
877
+ {
878
+ "epoch": 1.5313344485909148,
879
+ "grad_norm": 3.537903070449829,
880
+ "learning_rate": 3.4689832689832694e-05,
881
+ "loss": 0.7311,
882
+ "step": 5950
883
+ },
884
+ {
885
+ "epoch": 1.544202805301763,
886
+ "grad_norm": 3.1102797985076904,
887
+ "learning_rate": 3.4561132561132566e-05,
888
+ "loss": 0.7702,
889
+ "step": 6000
890
+ },
891
+ {
892
+ "epoch": 1.544202805301763,
893
+ "eval_loss": 0.856028139591217,
894
+ "eval_runtime": 189.5266,
895
+ "eval_samples_per_second": 102.497,
896
+ "eval_steps_per_second": 10.252,
897
+ "step": 6000
898
+ },
899
+ {
900
+ "epoch": 1.557071162012611,
901
+ "grad_norm": 3.3603110313415527,
902
+ "learning_rate": 3.443243243243243e-05,
903
+ "loss": 0.748,
904
+ "step": 6050
905
+ },
906
+ {
907
+ "epoch": 1.569939518723459,
908
+ "grad_norm": 3.154524326324463,
909
+ "learning_rate": 3.43037323037323e-05,
910
+ "loss": 0.7241,
911
+ "step": 6100
912
+ },
913
+ {
914
+ "epoch": 1.5828078754343071,
915
+ "grad_norm": 3.641023874282837,
916
+ "learning_rate": 3.417503217503218e-05,
917
+ "loss": 0.7564,
918
+ "step": 6150
919
+ },
920
+ {
921
+ "epoch": 1.5956762321451552,
922
+ "grad_norm": 2.77715802192688,
923
+ "learning_rate": 3.4046332046332045e-05,
924
+ "loss": 0.709,
925
+ "step": 6200
926
+ },
927
+ {
928
+ "epoch": 1.608544588856003,
929
+ "grad_norm": 3.438999652862549,
930
+ "learning_rate": 3.391763191763192e-05,
931
+ "loss": 0.7545,
932
+ "step": 6250
933
+ },
934
+ {
935
+ "epoch": 1.6214129455668511,
936
+ "grad_norm": 4.376018524169922,
937
+ "learning_rate": 3.378893178893179e-05,
938
+ "loss": 0.7435,
939
+ "step": 6300
940
+ },
941
+ {
942
+ "epoch": 1.6342813022776992,
943
+ "grad_norm": 3.45723819732666,
944
+ "learning_rate": 3.366023166023166e-05,
945
+ "loss": 0.7191,
946
+ "step": 6350
947
+ },
948
+ {
949
+ "epoch": 1.647149658988547,
950
+ "grad_norm": 3.0947272777557373,
951
+ "learning_rate": 3.353153153153153e-05,
952
+ "loss": 0.7376,
953
+ "step": 6400
954
+ },
955
+ {
956
+ "epoch": 1.660018015699395,
957
+ "grad_norm": 4.219300746917725,
958
+ "learning_rate": 3.3402831402831403e-05,
959
+ "loss": 0.7567,
960
+ "step": 6450
961
+ },
962
+ {
963
+ "epoch": 1.6728863724102432,
964
+ "grad_norm": 3.1860275268554688,
965
+ "learning_rate": 3.3274131274131275e-05,
966
+ "loss": 0.7771,
967
+ "step": 6500
968
+ },
969
+ {
970
+ "epoch": 1.6857547291210913,
971
+ "grad_norm": 2.766604423522949,
972
+ "learning_rate": 3.314543114543115e-05,
973
+ "loss": 0.7504,
974
+ "step": 6550
975
+ },
976
+ {
977
+ "epoch": 1.6986230858319393,
978
+ "grad_norm": 3.745673894882202,
979
+ "learning_rate": 3.301673101673102e-05,
980
+ "loss": 0.7389,
981
+ "step": 6600
982
+ },
983
+ {
984
+ "epoch": 1.7114914425427874,
985
+ "grad_norm": 3.8440420627593994,
986
+ "learning_rate": 3.288803088803089e-05,
987
+ "loss": 0.7298,
988
+ "step": 6650
989
+ },
990
+ {
991
+ "epoch": 1.7243597992536355,
992
+ "grad_norm": 3.5810177326202393,
993
+ "learning_rate": 3.276190476190477e-05,
994
+ "loss": 0.7602,
995
+ "step": 6700
996
+ },
997
+ {
998
+ "epoch": 1.7372281559644833,
999
+ "grad_norm": 3.4311060905456543,
1000
+ "learning_rate": 3.263320463320463e-05,
1001
+ "loss": 0.74,
1002
+ "step": 6750
1003
+ },
1004
+ {
1005
+ "epoch": 1.7500965126753314,
1006
+ "grad_norm": 2.345510721206665,
1007
+ "learning_rate": 3.250450450450451e-05,
1008
+ "loss": 0.733,
1009
+ "step": 6800
1010
+ },
1011
+ {
1012
+ "epoch": 1.7629648693861792,
1013
+ "grad_norm": 3.014230251312256,
1014
+ "learning_rate": 3.2375804375804375e-05,
1015
+ "loss": 0.7469,
1016
+ "step": 6850
1017
+ },
1018
+ {
1019
+ "epoch": 1.7758332260970273,
1020
+ "grad_norm": 2.7299680709838867,
1021
+ "learning_rate": 3.224710424710425e-05,
1022
+ "loss": 0.7183,
1023
+ "step": 6900
1024
+ },
1025
+ {
1026
+ "epoch": 1.7887015828078754,
1027
+ "grad_norm": 3.163944721221924,
1028
+ "learning_rate": 3.2118404118404125e-05,
1029
+ "loss": 0.763,
1030
+ "step": 6950
1031
+ },
1032
+ {
1033
+ "epoch": 1.8015699395187235,
1034
+ "grad_norm": 3.4352288246154785,
1035
+ "learning_rate": 3.198970398970399e-05,
1036
+ "loss": 0.7653,
1037
+ "step": 7000
1038
+ },
1039
+ {
1040
+ "epoch": 1.8015699395187235,
1041
+ "eval_loss": 0.8297092914581299,
1042
+ "eval_runtime": 189.396,
1043
+ "eval_samples_per_second": 102.568,
1044
+ "eval_steps_per_second": 10.259,
1045
+ "step": 7000
1046
+ },
1047
+ {
1048
+ "epoch": 1.8144382962295715,
1049
+ "grad_norm": 4.164456844329834,
1050
+ "learning_rate": 3.186100386100386e-05,
1051
+ "loss": 0.7168,
1052
+ "step": 7050
1053
+ },
1054
+ {
1055
+ "epoch": 1.8273066529404196,
1056
+ "grad_norm": 3.9557299613952637,
1057
+ "learning_rate": 3.173230373230373e-05,
1058
+ "loss": 0.7689,
1059
+ "step": 7100
1060
+ },
1061
+ {
1062
+ "epoch": 1.8401750096512677,
1063
+ "grad_norm": 3.7688467502593994,
1064
+ "learning_rate": 3.1603603603603605e-05,
1065
+ "loss": 0.7101,
1066
+ "step": 7150
1067
+ },
1068
+ {
1069
+ "epoch": 1.8530433663621155,
1070
+ "grad_norm": 3.025460720062256,
1071
+ "learning_rate": 3.1474903474903476e-05,
1072
+ "loss": 0.7311,
1073
+ "step": 7200
1074
+ },
1075
+ {
1076
+ "epoch": 1.8659117230729636,
1077
+ "grad_norm": 3.369191884994507,
1078
+ "learning_rate": 3.134620334620335e-05,
1079
+ "loss": 0.7063,
1080
+ "step": 7250
1081
+ },
1082
+ {
1083
+ "epoch": 1.8787800797838115,
1084
+ "grad_norm": 3.8419950008392334,
1085
+ "learning_rate": 3.121750321750322e-05,
1086
+ "loss": 0.7228,
1087
+ "step": 7300
1088
+ },
1089
+ {
1090
+ "epoch": 1.8916484364946595,
1091
+ "grad_norm": 4.265018939971924,
1092
+ "learning_rate": 3.108880308880309e-05,
1093
+ "loss": 0.7699,
1094
+ "step": 7350
1095
+ },
1096
+ {
1097
+ "epoch": 1.9045167932055076,
1098
+ "grad_norm": 3.287287712097168,
1099
+ "learning_rate": 3.096010296010296e-05,
1100
+ "loss": 0.7496,
1101
+ "step": 7400
1102
+ },
1103
+ {
1104
+ "epoch": 1.9173851499163557,
1105
+ "grad_norm": 4.200809001922607,
1106
+ "learning_rate": 3.0831402831402834e-05,
1107
+ "loss": 0.7039,
1108
+ "step": 7450
1109
+ },
1110
+ {
1111
+ "epoch": 1.9302535066272037,
1112
+ "grad_norm": 2.8199522495269775,
1113
+ "learning_rate": 3.07027027027027e-05,
1114
+ "loss": 0.7166,
1115
+ "step": 7500
1116
+ },
1117
+ {
1118
+ "epoch": 1.9431218633380518,
1119
+ "grad_norm": 3.1593542098999023,
1120
+ "learning_rate": 3.057400257400258e-05,
1121
+ "loss": 0.7288,
1122
+ "step": 7550
1123
+ },
1124
+ {
1125
+ "epoch": 1.9559902200488999,
1126
+ "grad_norm": 3.7583165168762207,
1127
+ "learning_rate": 3.044530244530245e-05,
1128
+ "loss": 0.7184,
1129
+ "step": 7600
1130
+ },
1131
+ {
1132
+ "epoch": 1.9688585767597477,
1133
+ "grad_norm": 2.7919719219207764,
1134
+ "learning_rate": 3.0316602316602317e-05,
1135
+ "loss": 0.7414,
1136
+ "step": 7650
1137
+ },
1138
+ {
1139
+ "epoch": 1.9817269334705958,
1140
+ "grad_norm": 3.475163459777832,
1141
+ "learning_rate": 3.018790218790219e-05,
1142
+ "loss": 0.6855,
1143
+ "step": 7700
1144
+ },
1145
+ {
1146
+ "epoch": 1.9945952901814439,
1147
+ "grad_norm": 3.133477210998535,
1148
+ "learning_rate": 3.0059202059202064e-05,
1149
+ "loss": 0.715,
1150
+ "step": 7750
1151
+ },
1152
+ {
1153
+ "epoch": 2.0074636468922917,
1154
+ "grad_norm": 2.9434854984283447,
1155
+ "learning_rate": 2.9930501930501932e-05,
1156
+ "loss": 0.6191,
1157
+ "step": 7800
1158
+ },
1159
+ {
1160
+ "epoch": 2.02033200360314,
1161
+ "grad_norm": 3.8272597789764404,
1162
+ "learning_rate": 2.9801801801801804e-05,
1163
+ "loss": 0.5678,
1164
+ "step": 7850
1165
+ },
1166
+ {
1167
+ "epoch": 2.033200360313988,
1168
+ "grad_norm": 3.036975860595703,
1169
+ "learning_rate": 2.9673101673101672e-05,
1170
+ "loss": 0.5251,
1171
+ "step": 7900
1172
+ },
1173
+ {
1174
+ "epoch": 2.046068717024836,
1175
+ "grad_norm": 3.401226758956909,
1176
+ "learning_rate": 2.9544401544401547e-05,
1177
+ "loss": 0.554,
1178
+ "step": 7950
1179
+ },
1180
+ {
1181
+ "epoch": 2.058937073735684,
1182
+ "grad_norm": 3.0268912315368652,
1183
+ "learning_rate": 2.941570141570142e-05,
1184
+ "loss": 0.5595,
1185
+ "step": 8000
1186
+ },
1187
+ {
1188
+ "epoch": 2.058937073735684,
1189
+ "eval_loss": 0.8340552449226379,
1190
+ "eval_runtime": 189.3362,
1191
+ "eval_samples_per_second": 102.601,
1192
+ "eval_steps_per_second": 10.262,
1193
+ "step": 8000
1194
+ },
1195
+ {
1196
+ "epoch": 2.071805430446532,
1197
+ "grad_norm": 3.2826826572418213,
1198
+ "learning_rate": 2.9287001287001287e-05,
1199
+ "loss": 0.537,
1200
+ "step": 8050
1201
+ },
1202
+ {
1203
+ "epoch": 2.08467378715738,
1204
+ "grad_norm": 3.539940357208252,
1205
+ "learning_rate": 2.915830115830116e-05,
1206
+ "loss": 0.5392,
1207
+ "step": 8100
1208
+ },
1209
+ {
1210
+ "epoch": 2.0975421438682282,
1211
+ "grad_norm": 3.780297040939331,
1212
+ "learning_rate": 2.9032175032175036e-05,
1213
+ "loss": 0.5642,
1214
+ "step": 8150
1215
+ },
1216
+ {
1217
+ "epoch": 2.110410500579076,
1218
+ "grad_norm": 3.1283602714538574,
1219
+ "learning_rate": 2.8903474903474904e-05,
1220
+ "loss": 0.5538,
1221
+ "step": 8200
1222
+ },
1223
+ {
1224
+ "epoch": 2.123278857289924,
1225
+ "grad_norm": 2.545053243637085,
1226
+ "learning_rate": 2.8774774774774775e-05,
1227
+ "loss": 0.4843,
1228
+ "step": 8250
1229
+ },
1230
+ {
1231
+ "epoch": 2.136147214000772,
1232
+ "grad_norm": 3.5739200115203857,
1233
+ "learning_rate": 2.864607464607465e-05,
1234
+ "loss": 0.5477,
1235
+ "step": 8300
1236
+ },
1237
+ {
1238
+ "epoch": 2.14901557071162,
1239
+ "grad_norm": 2.904505491256714,
1240
+ "learning_rate": 2.851737451737452e-05,
1241
+ "loss": 0.5377,
1242
+ "step": 8350
1243
+ },
1244
+ {
1245
+ "epoch": 2.161883927422468,
1246
+ "grad_norm": 4.482571601867676,
1247
+ "learning_rate": 2.838867438867439e-05,
1248
+ "loss": 0.5404,
1249
+ "step": 8400
1250
+ },
1251
+ {
1252
+ "epoch": 2.1747522841333162,
1253
+ "grad_norm": 3.0093982219696045,
1254
+ "learning_rate": 2.825997425997426e-05,
1255
+ "loss": 0.5446,
1256
+ "step": 8450
1257
+ },
1258
+ {
1259
+ "epoch": 2.1876206408441643,
1260
+ "grad_norm": 5.678364276885986,
1261
+ "learning_rate": 2.8131274131274134e-05,
1262
+ "loss": 0.5632,
1263
+ "step": 8500
1264
+ },
1265
+ {
1266
+ "epoch": 2.2004889975550124,
1267
+ "grad_norm": 3.4848239421844482,
1268
+ "learning_rate": 2.8002574002574005e-05,
1269
+ "loss": 0.5451,
1270
+ "step": 8550
1271
+ },
1272
+ {
1273
+ "epoch": 2.2133573542658604,
1274
+ "grad_norm": 3.782041549682617,
1275
+ "learning_rate": 2.7873873873873873e-05,
1276
+ "loss": 0.5654,
1277
+ "step": 8600
1278
+ },
1279
+ {
1280
+ "epoch": 2.226225710976708,
1281
+ "grad_norm": 3.711773157119751,
1282
+ "learning_rate": 2.774517374517375e-05,
1283
+ "loss": 0.5549,
1284
+ "step": 8650
1285
+ },
1286
+ {
1287
+ "epoch": 2.239094067687556,
1288
+ "grad_norm": 3.105684518814087,
1289
+ "learning_rate": 2.761647361647362e-05,
1290
+ "loss": 0.5741,
1291
+ "step": 8700
1292
+ },
1293
+ {
1294
+ "epoch": 2.251962424398404,
1295
+ "grad_norm": 3.3493452072143555,
1296
+ "learning_rate": 2.7487773487773488e-05,
1297
+ "loss": 0.5474,
1298
+ "step": 8750
1299
+ },
1300
+ {
1301
+ "epoch": 2.2648307811092523,
1302
+ "grad_norm": 2.916020631790161,
1303
+ "learning_rate": 2.7359073359073363e-05,
1304
+ "loss": 0.5704,
1305
+ "step": 8800
1306
+ },
1307
+ {
1308
+ "epoch": 2.2776991378201004,
1309
+ "grad_norm": 2.867391347885132,
1310
+ "learning_rate": 2.7230373230373228e-05,
1311
+ "loss": 0.5116,
1312
+ "step": 8850
1313
+ },
1314
+ {
1315
+ "epoch": 2.2905674945309484,
1316
+ "grad_norm": 3.349109649658203,
1317
+ "learning_rate": 2.7101673101673103e-05,
1318
+ "loss": 0.5523,
1319
+ "step": 8900
1320
+ },
1321
+ {
1322
+ "epoch": 2.3034358512417965,
1323
+ "grad_norm": 3.198293685913086,
1324
+ "learning_rate": 2.6972972972972978e-05,
1325
+ "loss": 0.5437,
1326
+ "step": 8950
1327
+ },
1328
+ {
1329
+ "epoch": 2.3163042079526446,
1330
+ "grad_norm": 3.9013428688049316,
1331
+ "learning_rate": 2.6844272844272843e-05,
1332
+ "loss": 0.5501,
1333
+ "step": 9000
1334
+ },
1335
+ {
1336
+ "epoch": 2.3163042079526446,
1337
+ "eval_loss": 0.8361700773239136,
1338
+ "eval_runtime": 189.4593,
1339
+ "eval_samples_per_second": 102.534,
1340
+ "eval_steps_per_second": 10.256,
1341
+ "step": 9000
1342
+ },
1343
+ {
1344
+ "epoch": 2.3291725646634927,
1345
+ "grad_norm": 2.5401031970977783,
1346
+ "learning_rate": 2.6715572715572718e-05,
1347
+ "loss": 0.5441,
1348
+ "step": 9050
1349
+ },
1350
+ {
1351
+ "epoch": 2.3420409213743403,
1352
+ "grad_norm": 3.330003261566162,
1353
+ "learning_rate": 2.6586872586872586e-05,
1354
+ "loss": 0.5292,
1355
+ "step": 9100
1356
+ },
1357
+ {
1358
+ "epoch": 2.3549092780851884,
1359
+ "grad_norm": 3.724376916885376,
1360
+ "learning_rate": 2.6458172458172458e-05,
1361
+ "loss": 0.5555,
1362
+ "step": 9150
1363
+ },
1364
+ {
1365
+ "epoch": 2.3677776347960364,
1366
+ "grad_norm": 3.3693745136260986,
1367
+ "learning_rate": 2.6329472329472333e-05,
1368
+ "loss": 0.5638,
1369
+ "step": 9200
1370
+ },
1371
+ {
1372
+ "epoch": 2.3806459915068845,
1373
+ "grad_norm": 3.3780782222747803,
1374
+ "learning_rate": 2.62007722007722e-05,
1375
+ "loss": 0.5724,
1376
+ "step": 9250
1377
+ },
1378
+ {
1379
+ "epoch": 2.3935143482177326,
1380
+ "grad_norm": 3.949384927749634,
1381
+ "learning_rate": 2.6072072072072072e-05,
1382
+ "loss": 0.5548,
1383
+ "step": 9300
1384
+ },
1385
+ {
1386
+ "epoch": 2.4063827049285806,
1387
+ "grad_norm": 3.7752134799957275,
1388
+ "learning_rate": 2.5943371943371947e-05,
1389
+ "loss": 0.5401,
1390
+ "step": 9350
1391
+ },
1392
+ {
1393
+ "epoch": 2.4192510616394287,
1394
+ "grad_norm": 4.018200874328613,
1395
+ "learning_rate": 2.5814671814671816e-05,
1396
+ "loss": 0.5154,
1397
+ "step": 9400
1398
+ },
1399
+ {
1400
+ "epoch": 2.432119418350277,
1401
+ "grad_norm": 2.818852186203003,
1402
+ "learning_rate": 2.5685971685971687e-05,
1403
+ "loss": 0.5317,
1404
+ "step": 9450
1405
+ },
1406
+ {
1407
+ "epoch": 2.444987775061125,
1408
+ "grad_norm": 3.676013946533203,
1409
+ "learning_rate": 2.5557271557271556e-05,
1410
+ "loss": 0.5683,
1411
+ "step": 9500
1412
+ },
1413
+ {
1414
+ "epoch": 2.4578561317719725,
1415
+ "grad_norm": 3.144169807434082,
1416
+ "learning_rate": 2.542857142857143e-05,
1417
+ "loss": 0.5491,
1418
+ "step": 9550
1419
+ },
1420
+ {
1421
+ "epoch": 2.4707244884828206,
1422
+ "grad_norm": 3.605506658554077,
1423
+ "learning_rate": 2.5299871299871302e-05,
1424
+ "loss": 0.5733,
1425
+ "step": 9600
1426
+ },
1427
+ {
1428
+ "epoch": 2.4835928451936686,
1429
+ "grad_norm": 3.2025864124298096,
1430
+ "learning_rate": 2.517117117117117e-05,
1431
+ "loss": 0.5581,
1432
+ "step": 9650
1433
+ },
1434
+ {
1435
+ "epoch": 2.4964612019045167,
1436
+ "grad_norm": 3.0987846851348877,
1437
+ "learning_rate": 2.5042471042471045e-05,
1438
+ "loss": 0.5246,
1439
+ "step": 9700
1440
+ },
1441
+ {
1442
+ "epoch": 2.5093295586153648,
1443
+ "grad_norm": 2.3385045528411865,
1444
+ "learning_rate": 2.4913770913770914e-05,
1445
+ "loss": 0.5643,
1446
+ "step": 9750
1447
+ },
1448
+ {
1449
+ "epoch": 2.522197915326213,
1450
+ "grad_norm": 3.4975156784057617,
1451
+ "learning_rate": 2.4785070785070785e-05,
1452
+ "loss": 0.5793,
1453
+ "step": 9800
1454
+ },
1455
+ {
1456
+ "epoch": 2.535066272037061,
1457
+ "grad_norm": 3.657727003097534,
1458
+ "learning_rate": 2.465637065637066e-05,
1459
+ "loss": 0.561,
1460
+ "step": 9850
1461
+ },
1462
+ {
1463
+ "epoch": 2.547934628747909,
1464
+ "grad_norm": 3.558779001235962,
1465
+ "learning_rate": 2.452767052767053e-05,
1466
+ "loss": 0.5442,
1467
+ "step": 9900
1468
+ },
1469
+ {
1470
+ "epoch": 2.560802985458757,
1471
+ "grad_norm": 3.5756425857543945,
1472
+ "learning_rate": 2.43989703989704e-05,
1473
+ "loss": 0.5467,
1474
+ "step": 9950
1475
+ },
1476
+ {
1477
+ "epoch": 2.5736713421696047,
1478
+ "grad_norm": 4.302220821380615,
1479
+ "learning_rate": 2.427027027027027e-05,
1480
+ "loss": 0.5322,
1481
+ "step": 10000
1482
+ },
1483
+ {
1484
+ "epoch": 2.5736713421696047,
1485
+ "eval_loss": 0.8265257477760315,
1486
+ "eval_runtime": 189.4664,
1487
+ "eval_samples_per_second": 102.53,
1488
+ "eval_steps_per_second": 10.255,
1489
+ "step": 10000
1490
+ },
1491
+ {
1492
+ "epoch": 2.586539698880453,
1493
+ "grad_norm": 3.3012359142303467,
1494
+ "learning_rate": 2.4141570141570143e-05,
1495
+ "loss": 0.542,
1496
+ "step": 10050
1497
+ },
1498
+ {
1499
+ "epoch": 2.599408055591301,
1500
+ "grad_norm": 3.0096490383148193,
1501
+ "learning_rate": 2.4012870012870015e-05,
1502
+ "loss": 0.5641,
1503
+ "step": 10100
1504
+ },
1505
+ {
1506
+ "epoch": 2.612276412302149,
1507
+ "grad_norm": 3.803586006164551,
1508
+ "learning_rate": 2.3884169884169886e-05,
1509
+ "loss": 0.5375,
1510
+ "step": 10150
1511
+ },
1512
+ {
1513
+ "epoch": 2.625144769012997,
1514
+ "grad_norm": 3.69391131401062,
1515
+ "learning_rate": 2.3755469755469755e-05,
1516
+ "loss": 0.5579,
1517
+ "step": 10200
1518
+ },
1519
+ {
1520
+ "epoch": 2.638013125723845,
1521
+ "grad_norm": 3.184783458709717,
1522
+ "learning_rate": 2.362676962676963e-05,
1523
+ "loss": 0.5185,
1524
+ "step": 10250
1525
+ },
1526
+ {
1527
+ "epoch": 2.650881482434693,
1528
+ "grad_norm": 3.191938638687134,
1529
+ "learning_rate": 2.34980694980695e-05,
1530
+ "loss": 0.5644,
1531
+ "step": 10300
1532
+ },
1533
+ {
1534
+ "epoch": 2.663749839145541,
1535
+ "grad_norm": 2.8819658756256104,
1536
+ "learning_rate": 2.336936936936937e-05,
1537
+ "loss": 0.5318,
1538
+ "step": 10350
1539
+ },
1540
+ {
1541
+ "epoch": 2.6766181958563893,
1542
+ "grad_norm": 2.8010735511779785,
1543
+ "learning_rate": 2.324066924066924e-05,
1544
+ "loss": 0.5286,
1545
+ "step": 10400
1546
+ },
1547
+ {
1548
+ "epoch": 2.689486552567237,
1549
+ "grad_norm": 3.6001551151275635,
1550
+ "learning_rate": 2.3111969111969113e-05,
1551
+ "loss": 0.5699,
1552
+ "step": 10450
1553
+ },
1554
+ {
1555
+ "epoch": 2.7023549092780854,
1556
+ "grad_norm": 3.6811742782592773,
1557
+ "learning_rate": 2.2983268983268984e-05,
1558
+ "loss": 0.5693,
1559
+ "step": 10500
1560
+ },
1561
+ {
1562
+ "epoch": 2.715223265988933,
1563
+ "grad_norm": 3.8935017585754395,
1564
+ "learning_rate": 2.2854568854568856e-05,
1565
+ "loss": 0.5471,
1566
+ "step": 10550
1567
+ },
1568
+ {
1569
+ "epoch": 2.728091622699781,
1570
+ "grad_norm": 4.385620594024658,
1571
+ "learning_rate": 2.2725868725868727e-05,
1572
+ "loss": 0.5496,
1573
+ "step": 10600
1574
+ },
1575
+ {
1576
+ "epoch": 2.740959979410629,
1577
+ "grad_norm": 3.178663730621338,
1578
+ "learning_rate": 2.2597168597168596e-05,
1579
+ "loss": 0.5669,
1580
+ "step": 10650
1581
+ },
1582
+ {
1583
+ "epoch": 2.7538283361214773,
1584
+ "grad_norm": 2.5699925422668457,
1585
+ "learning_rate": 2.246846846846847e-05,
1586
+ "loss": 0.5445,
1587
+ "step": 10700
1588
+ },
1589
+ {
1590
+ "epoch": 2.7666966928323253,
1591
+ "grad_norm": 3.409348964691162,
1592
+ "learning_rate": 2.2339768339768342e-05,
1593
+ "loss": 0.5195,
1594
+ "step": 10750
1595
+ },
1596
+ {
1597
+ "epoch": 2.7795650495431734,
1598
+ "grad_norm": 3.578507900238037,
1599
+ "learning_rate": 2.221106821106821e-05,
1600
+ "loss": 0.5664,
1601
+ "step": 10800
1602
+ },
1603
+ {
1604
+ "epoch": 2.7924334062540215,
1605
+ "grad_norm": 3.959843873977661,
1606
+ "learning_rate": 2.2082368082368082e-05,
1607
+ "loss": 0.5509,
1608
+ "step": 10850
1609
+ },
1610
+ {
1611
+ "epoch": 2.8053017629648695,
1612
+ "grad_norm": 4.0397868156433105,
1613
+ "learning_rate": 2.1953667953667957e-05,
1614
+ "loss": 0.5287,
1615
+ "step": 10900
1616
+ },
1617
+ {
1618
+ "epoch": 2.8181701196757176,
1619
+ "grad_norm": 4.056464195251465,
1620
+ "learning_rate": 2.1824967824967825e-05,
1621
+ "loss": 0.5493,
1622
+ "step": 10950
1623
+ },
1624
+ {
1625
+ "epoch": 2.8310384763865653,
1626
+ "grad_norm": 2.7274129390716553,
1627
+ "learning_rate": 2.1696267696267697e-05,
1628
+ "loss": 0.5536,
1629
+ "step": 11000
1630
+ },
1631
+ {
1632
+ "epoch": 2.8310384763865653,
1633
+ "eval_loss": 0.8111644983291626,
1634
+ "eval_runtime": 189.4072,
1635
+ "eval_samples_per_second": 102.562,
1636
+ "eval_steps_per_second": 10.258,
1637
+ "step": 11000
1638
+ },
1639
+ {
1640
+ "epoch": 2.8439068330974133,
1641
+ "grad_norm": 4.217979907989502,
1642
+ "learning_rate": 2.156756756756757e-05,
1643
+ "loss": 0.5206,
1644
+ "step": 11050
1645
+ },
1646
+ {
1647
+ "epoch": 2.8567751898082614,
1648
+ "grad_norm": 3.4003894329071045,
1649
+ "learning_rate": 2.143886743886744e-05,
1650
+ "loss": 0.5389,
1651
+ "step": 11100
1652
+ },
1653
+ {
1654
+ "epoch": 2.8696435465191095,
1655
+ "grad_norm": 3.1953563690185547,
1656
+ "learning_rate": 2.1310167310167312e-05,
1657
+ "loss": 0.5533,
1658
+ "step": 11150
1659
+ },
1660
+ {
1661
+ "epoch": 2.8825119032299575,
1662
+ "grad_norm": 4.147376537322998,
1663
+ "learning_rate": 2.1181467181467183e-05,
1664
+ "loss": 0.5537,
1665
+ "step": 11200
1666
+ },
1667
+ {
1668
+ "epoch": 2.8953802599408056,
1669
+ "grad_norm": 3.726901054382324,
1670
+ "learning_rate": 2.105276705276705e-05,
1671
+ "loss": 0.527,
1672
+ "step": 11250
1673
+ },
1674
+ {
1675
+ "epoch": 2.9082486166516537,
1676
+ "grad_norm": 3.210848331451416,
1677
+ "learning_rate": 2.0924066924066927e-05,
1678
+ "loss": 0.5561,
1679
+ "step": 11300
1680
+ },
1681
+ {
1682
+ "epoch": 2.9211169733625018,
1683
+ "grad_norm": 4.512522220611572,
1684
+ "learning_rate": 2.0795366795366798e-05,
1685
+ "loss": 0.5642,
1686
+ "step": 11350
1687
+ },
1688
+ {
1689
+ "epoch": 2.93398533007335,
1690
+ "grad_norm": 3.112410545349121,
1691
+ "learning_rate": 2.0666666666666666e-05,
1692
+ "loss": 0.5678,
1693
+ "step": 11400
1694
+ },
1695
+ {
1696
+ "epoch": 2.9468536867841975,
1697
+ "grad_norm": 3.0859549045562744,
1698
+ "learning_rate": 2.0537966537966538e-05,
1699
+ "loss": 0.5203,
1700
+ "step": 11450
1701
+ },
1702
+ {
1703
+ "epoch": 2.9597220434950455,
1704
+ "grad_norm": 2.518927812576294,
1705
+ "learning_rate": 2.0409266409266413e-05,
1706
+ "loss": 0.5326,
1707
+ "step": 11500
1708
+ },
1709
+ {
1710
+ "epoch": 2.9725904002058936,
1711
+ "grad_norm": 3.686985492706299,
1712
+ "learning_rate": 2.028056628056628e-05,
1713
+ "loss": 0.5419,
1714
+ "step": 11550
1715
+ },
1716
+ {
1717
+ "epoch": 2.9854587569167417,
1718
+ "grad_norm": 3.1635522842407227,
1719
+ "learning_rate": 2.0151866151866153e-05,
1720
+ "loss": 0.5593,
1721
+ "step": 11600
1722
+ },
1723
+ {
1724
+ "epoch": 2.9983271136275897,
1725
+ "grad_norm": 3.734297037124634,
1726
+ "learning_rate": 2.0023166023166024e-05,
1727
+ "loss": 0.5233,
1728
+ "step": 11650
1729
+ },
1730
+ {
1731
+ "epoch": 3.011195470338438,
1732
+ "grad_norm": 4.363897800445557,
1733
+ "learning_rate": 1.9894465894465893e-05,
1734
+ "loss": 0.3853,
1735
+ "step": 11700
1736
+ },
1737
+ {
1738
+ "epoch": 3.024063827049286,
1739
+ "grad_norm": 3.380840539932251,
1740
+ "learning_rate": 1.9765765765765768e-05,
1741
+ "loss": 0.4048,
1742
+ "step": 11750
1743
+ },
1744
+ {
1745
+ "epoch": 3.036932183760134,
1746
+ "grad_norm": 2.8301613330841064,
1747
+ "learning_rate": 1.963706563706564e-05,
1748
+ "loss": 0.4104,
1749
+ "step": 11800
1750
+ },
1751
+ {
1752
+ "epoch": 3.049800540470982,
1753
+ "grad_norm": 3.5483977794647217,
1754
+ "learning_rate": 1.9508365508365508e-05,
1755
+ "loss": 0.4002,
1756
+ "step": 11850
1757
+ },
1758
+ {
1759
+ "epoch": 3.0626688971818297,
1760
+ "grad_norm": 3.0657596588134766,
1761
+ "learning_rate": 1.937966537966538e-05,
1762
+ "loss": 0.3955,
1763
+ "step": 11900
1764
+ },
1765
+ {
1766
+ "epoch": 3.0755372538926777,
1767
+ "grad_norm": 3.3583223819732666,
1768
+ "learning_rate": 1.9250965250965254e-05,
1769
+ "loss": 0.4258,
1770
+ "step": 11950
1771
+ },
1772
+ {
1773
+ "epoch": 3.088405610603526,
1774
+ "grad_norm": 2.8227546215057373,
1775
+ "learning_rate": 1.9122265122265122e-05,
1776
+ "loss": 0.4279,
1777
+ "step": 12000
1778
+ },
1779
+ {
1780
+ "epoch": 3.088405610603526,
1781
+ "eval_loss": 0.8435577154159546,
1782
+ "eval_runtime": 189.2953,
1783
+ "eval_samples_per_second": 102.623,
1784
+ "eval_steps_per_second": 10.264,
1785
+ "step": 12000
1786
+ },
1787
+ {
1788
+ "epoch": 3.101273967314374,
1789
+ "grad_norm": 3.359844923019409,
1790
+ "learning_rate": 1.8993564993564994e-05,
1791
+ "loss": 0.4204,
1792
+ "step": 12050
1793
+ },
1794
+ {
1795
+ "epoch": 3.114142324025222,
1796
+ "grad_norm": 3.8054656982421875,
1797
+ "learning_rate": 1.8864864864864866e-05,
1798
+ "loss": 0.419,
1799
+ "step": 12100
1800
+ },
1801
+ {
1802
+ "epoch": 3.12701068073607,
1803
+ "grad_norm": 3.396296977996826,
1804
+ "learning_rate": 1.8736164736164737e-05,
1805
+ "loss": 0.4167,
1806
+ "step": 12150
1807
+ },
1808
+ {
1809
+ "epoch": 3.139879037446918,
1810
+ "grad_norm": 3.7082102298736572,
1811
+ "learning_rate": 1.860746460746461e-05,
1812
+ "loss": 0.4047,
1813
+ "step": 12200
1814
+ },
1815
+ {
1816
+ "epoch": 3.152747394157766,
1817
+ "grad_norm": 3.589115619659424,
1818
+ "learning_rate": 1.847876447876448e-05,
1819
+ "loss": 0.4245,
1820
+ "step": 12250
1821
+ },
1822
+ {
1823
+ "epoch": 3.1656157508686142,
1824
+ "grad_norm": 4.928313732147217,
1825
+ "learning_rate": 1.835006435006435e-05,
1826
+ "loss": 0.4054,
1827
+ "step": 12300
1828
+ },
1829
+ {
1830
+ "epoch": 3.178484107579462,
1831
+ "grad_norm": 3.3157694339752197,
1832
+ "learning_rate": 1.8221364221364224e-05,
1833
+ "loss": 0.3828,
1834
+ "step": 12350
1835
+ },
1836
+ {
1837
+ "epoch": 3.19135246429031,
1838
+ "grad_norm": 2.832195997238159,
1839
+ "learning_rate": 1.8092664092664095e-05,
1840
+ "loss": 0.3985,
1841
+ "step": 12400
1842
+ },
1843
+ {
1844
+ "epoch": 3.204220821001158,
1845
+ "grad_norm": 3.6316025257110596,
1846
+ "learning_rate": 1.7963963963963963e-05,
1847
+ "loss": 0.4009,
1848
+ "step": 12450
1849
+ },
1850
+ {
1851
+ "epoch": 3.217089177712006,
1852
+ "grad_norm": 2.810399293899536,
1853
+ "learning_rate": 1.7835263835263835e-05,
1854
+ "loss": 0.3942,
1855
+ "step": 12500
1856
+ },
1857
+ {
1858
+ "epoch": 3.229957534422854,
1859
+ "grad_norm": 4.077607154846191,
1860
+ "learning_rate": 1.770656370656371e-05,
1861
+ "loss": 0.4139,
1862
+ "step": 12550
1863
+ },
1864
+ {
1865
+ "epoch": 3.2428258911337022,
1866
+ "grad_norm": 4.511129856109619,
1867
+ "learning_rate": 1.7577863577863578e-05,
1868
+ "loss": 0.4151,
1869
+ "step": 12600
1870
+ },
1871
+ {
1872
+ "epoch": 3.2556942478445503,
1873
+ "grad_norm": 4.129230976104736,
1874
+ "learning_rate": 1.744916344916345e-05,
1875
+ "loss": 0.4174,
1876
+ "step": 12650
1877
+ },
1878
+ {
1879
+ "epoch": 3.2685626045553984,
1880
+ "grad_norm": 2.6795713901519775,
1881
+ "learning_rate": 1.732046332046332e-05,
1882
+ "loss": 0.4305,
1883
+ "step": 12700
1884
+ },
1885
+ {
1886
+ "epoch": 3.2814309612662464,
1887
+ "grad_norm": 3.7392494678497314,
1888
+ "learning_rate": 1.7191763191763193e-05,
1889
+ "loss": 0.4221,
1890
+ "step": 12750
1891
+ },
1892
+ {
1893
+ "epoch": 3.294299317977094,
1894
+ "grad_norm": 3.319235324859619,
1895
+ "learning_rate": 1.7063063063063065e-05,
1896
+ "loss": 0.4506,
1897
+ "step": 12800
1898
+ },
1899
+ {
1900
+ "epoch": 3.3071676746879426,
1901
+ "grad_norm": 3.564242362976074,
1902
+ "learning_rate": 1.6934362934362936e-05,
1903
+ "loss": 0.4287,
1904
+ "step": 12850
1905
+ },
1906
+ {
1907
+ "epoch": 3.32003603139879,
1908
+ "grad_norm": 4.851574420928955,
1909
+ "learning_rate": 1.6805662805662805e-05,
1910
+ "loss": 0.4002,
1911
+ "step": 12900
1912
+ },
1913
+ {
1914
+ "epoch": 3.3329043881096383,
1915
+ "grad_norm": 3.396198034286499,
1916
+ "learning_rate": 1.667696267696268e-05,
1917
+ "loss": 0.3979,
1918
+ "step": 12950
1919
+ },
1920
+ {
1921
+ "epoch": 3.3457727448204864,
1922
+ "grad_norm": 2.8444738388061523,
1923
+ "learning_rate": 1.654826254826255e-05,
1924
+ "loss": 0.4015,
1925
+ "step": 13000
1926
+ },
1927
+ {
1928
+ "epoch": 3.3457727448204864,
1929
+ "eval_loss": 0.8406257033348083,
1930
+ "eval_runtime": 189.5238,
1931
+ "eval_samples_per_second": 102.499,
1932
+ "eval_steps_per_second": 10.252,
1933
+ "step": 13000
1934
+ },
1935
+ {
1936
+ "epoch": 3.3586411015313344,
1937
+ "grad_norm": 3.6319420337677,
1938
+ "learning_rate": 1.641956241956242e-05,
1939
+ "loss": 0.4175,
1940
+ "step": 13050
1941
+ },
1942
+ {
1943
+ "epoch": 3.3715094582421825,
1944
+ "grad_norm": 3.819413900375366,
1945
+ "learning_rate": 1.629086229086229e-05,
1946
+ "loss": 0.4132,
1947
+ "step": 13100
1948
+ },
1949
+ {
1950
+ "epoch": 3.3843778149530306,
1951
+ "grad_norm": 3.5537872314453125,
1952
+ "learning_rate": 1.6162162162162163e-05,
1953
+ "loss": 0.4347,
1954
+ "step": 13150
1955
+ },
1956
+ {
1957
+ "epoch": 3.3972461716638787,
1958
+ "grad_norm": 3.193889617919922,
1959
+ "learning_rate": 1.6033462033462034e-05,
1960
+ "loss": 0.4082,
1961
+ "step": 13200
1962
+ },
1963
+ {
1964
+ "epoch": 3.4101145283747267,
1965
+ "grad_norm": 2.0629472732543945,
1966
+ "learning_rate": 1.5904761904761906e-05,
1967
+ "loss": 0.4157,
1968
+ "step": 13250
1969
+ },
1970
+ {
1971
+ "epoch": 3.422982885085575,
1972
+ "grad_norm": 3.1376850605010986,
1973
+ "learning_rate": 1.5776061776061777e-05,
1974
+ "loss": 0.4063,
1975
+ "step": 13300
1976
+ },
1977
+ {
1978
+ "epoch": 3.4358512417964224,
1979
+ "grad_norm": 3.6547293663024902,
1980
+ "learning_rate": 1.5647361647361646e-05,
1981
+ "loss": 0.4006,
1982
+ "step": 13350
1983
+ },
1984
+ {
1985
+ "epoch": 3.4487195985072705,
1986
+ "grad_norm": 3.7299160957336426,
1987
+ "learning_rate": 1.551866151866152e-05,
1988
+ "loss": 0.4103,
1989
+ "step": 13400
1990
+ },
1991
+ {
1992
+ "epoch": 3.4615879552181186,
1993
+ "grad_norm": 4.016064167022705,
1994
+ "learning_rate": 1.5389961389961392e-05,
1995
+ "loss": 0.4128,
1996
+ "step": 13450
1997
+ },
1998
+ {
1999
+ "epoch": 3.4744563119289666,
2000
+ "grad_norm": 3.9914636611938477,
2001
+ "learning_rate": 1.526126126126126e-05,
2002
+ "loss": 0.4417,
2003
+ "step": 13500
2004
+ },
2005
+ {
2006
+ "epoch": 3.4873246686398147,
2007
+ "grad_norm": 3.342193126678467,
2008
+ "learning_rate": 1.5132561132561132e-05,
2009
+ "loss": 0.4369,
2010
+ "step": 13550
2011
+ },
2012
+ {
2013
+ "epoch": 3.500193025350663,
2014
+ "grad_norm": 3.600562810897827,
2015
+ "learning_rate": 1.5003861003861005e-05,
2016
+ "loss": 0.4186,
2017
+ "step": 13600
2018
+ },
2019
+ {
2020
+ "epoch": 3.513061382061511,
2021
+ "grad_norm": 2.986332654953003,
2022
+ "learning_rate": 1.4875160875160877e-05,
2023
+ "loss": 0.4109,
2024
+ "step": 13650
2025
+ },
2026
+ {
2027
+ "epoch": 3.525929738772359,
2028
+ "grad_norm": 3.3687069416046143,
2029
+ "learning_rate": 1.4746460746460747e-05,
2030
+ "loss": 0.4193,
2031
+ "step": 13700
2032
+ },
2033
+ {
2034
+ "epoch": 3.538798095483207,
2035
+ "grad_norm": 3.519691228866577,
2036
+ "learning_rate": 1.4617760617760617e-05,
2037
+ "loss": 0.4046,
2038
+ "step": 13750
2039
+ },
2040
+ {
2041
+ "epoch": 3.5516664521940546,
2042
+ "grad_norm": 2.984351396560669,
2043
+ "learning_rate": 1.448906048906049e-05,
2044
+ "loss": 0.4013,
2045
+ "step": 13800
2046
+ },
2047
+ {
2048
+ "epoch": 3.5645348089049027,
2049
+ "grad_norm": 4.0301899909973145,
2050
+ "learning_rate": 1.4360360360360362e-05,
2051
+ "loss": 0.425,
2052
+ "step": 13850
2053
+ },
2054
+ {
2055
+ "epoch": 3.577403165615751,
2056
+ "grad_norm": 3.606745481491089,
2057
+ "learning_rate": 1.4231660231660232e-05,
2058
+ "loss": 0.395,
2059
+ "step": 13900
2060
+ },
2061
+ {
2062
+ "epoch": 3.590271522326599,
2063
+ "grad_norm": 3.490335702896118,
2064
+ "learning_rate": 1.4102960102960103e-05,
2065
+ "loss": 0.4104,
2066
+ "step": 13950
2067
+ },
2068
+ {
2069
+ "epoch": 3.603139879037447,
2070
+ "grad_norm": 4.385608673095703,
2071
+ "learning_rate": 1.3974259974259976e-05,
2072
+ "loss": 0.4235,
2073
+ "step": 14000
2074
+ },
2075
+ {
2076
+ "epoch": 3.603139879037447,
2077
+ "eval_loss": 0.8373395800590515,
2078
+ "eval_runtime": 189.5425,
2079
+ "eval_samples_per_second": 102.489,
2080
+ "eval_steps_per_second": 10.251,
2081
+ "step": 14000
2082
+ },
2083
+ {
2084
+ "epoch": 3.616008235748295,
2085
+ "grad_norm": 3.1057236194610596,
2086
+ "learning_rate": 1.3845559845559846e-05,
2087
+ "loss": 0.4055,
2088
+ "step": 14050
2089
+ },
2090
+ {
2091
+ "epoch": 3.628876592459143,
2092
+ "grad_norm": 3.3940112590789795,
2093
+ "learning_rate": 1.3716859716859718e-05,
2094
+ "loss": 0.3916,
2095
+ "step": 14100
2096
+ },
2097
+ {
2098
+ "epoch": 3.641744949169991,
2099
+ "grad_norm": 3.4843504428863525,
2100
+ "learning_rate": 1.3588159588159588e-05,
2101
+ "loss": 0.4483,
2102
+ "step": 14150
2103
+ },
2104
+ {
2105
+ "epoch": 3.654613305880839,
2106
+ "grad_norm": 4.122684001922607,
2107
+ "learning_rate": 1.3462033462033463e-05,
2108
+ "loss": 0.4241,
2109
+ "step": 14200
2110
+ },
2111
+ {
2112
+ "epoch": 3.667481662591687,
2113
+ "grad_norm": 3.975159168243408,
2114
+ "learning_rate": 1.3333333333333333e-05,
2115
+ "loss": 0.417,
2116
+ "step": 14250
2117
+ },
2118
+ {
2119
+ "epoch": 3.680350019302535,
2120
+ "grad_norm": 4.270761966705322,
2121
+ "learning_rate": 1.3204633204633205e-05,
2122
+ "loss": 0.4137,
2123
+ "step": 14300
2124
+ },
2125
+ {
2126
+ "epoch": 3.693218376013383,
2127
+ "grad_norm": 2.448530673980713,
2128
+ "learning_rate": 1.307850707850708e-05,
2129
+ "loss": 0.4277,
2130
+ "step": 14350
2131
+ },
2132
+ {
2133
+ "epoch": 3.706086732724231,
2134
+ "grad_norm": 3.0755138397216797,
2135
+ "learning_rate": 1.294980694980695e-05,
2136
+ "loss": 0.4003,
2137
+ "step": 14400
2138
+ },
2139
+ {
2140
+ "epoch": 3.718955089435079,
2141
+ "grad_norm": 3.795004367828369,
2142
+ "learning_rate": 1.282110682110682e-05,
2143
+ "loss": 0.4128,
2144
+ "step": 14450
2145
+ },
2146
+ {
2147
+ "epoch": 3.731823446145927,
2148
+ "grad_norm": 3.655588150024414,
2149
+ "learning_rate": 1.2692406692406693e-05,
2150
+ "loss": 0.4243,
2151
+ "step": 14500
2152
+ },
2153
+ {
2154
+ "epoch": 3.7446918028567753,
2155
+ "grad_norm": 3.4732940196990967,
2156
+ "learning_rate": 1.2563706563706565e-05,
2157
+ "loss": 0.432,
2158
+ "step": 14550
2159
+ },
2160
+ {
2161
+ "epoch": 3.7575601595676233,
2162
+ "grad_norm": 3.737543821334839,
2163
+ "learning_rate": 1.2435006435006435e-05,
2164
+ "loss": 0.4214,
2165
+ "step": 14600
2166
+ },
2167
+ {
2168
+ "epoch": 3.7704285162784714,
2169
+ "grad_norm": 4.61754035949707,
2170
+ "learning_rate": 1.2306306306306308e-05,
2171
+ "loss": 0.4075,
2172
+ "step": 14650
2173
+ },
2174
+ {
2175
+ "epoch": 3.783296872989319,
2176
+ "grad_norm": 3.1483190059661865,
2177
+ "learning_rate": 1.2177606177606178e-05,
2178
+ "loss": 0.4136,
2179
+ "step": 14700
2180
+ },
2181
+ {
2182
+ "epoch": 3.7961652297001676,
2183
+ "grad_norm": 3.9902536869049072,
2184
+ "learning_rate": 1.204890604890605e-05,
2185
+ "loss": 0.399,
2186
+ "step": 14750
2187
+ },
2188
+ {
2189
+ "epoch": 3.809033586411015,
2190
+ "grad_norm": 3.6237611770629883,
2191
+ "learning_rate": 1.1920205920205921e-05,
2192
+ "loss": 0.4144,
2193
+ "step": 14800
2194
+ },
2195
+ {
2196
+ "epoch": 3.8219019431218633,
2197
+ "grad_norm": 4.140763282775879,
2198
+ "learning_rate": 1.1791505791505791e-05,
2199
+ "loss": 0.4009,
2200
+ "step": 14850
2201
+ },
2202
+ {
2203
+ "epoch": 3.8347702998327113,
2204
+ "grad_norm": 3.700617790222168,
2205
+ "learning_rate": 1.1662805662805663e-05,
2206
+ "loss": 0.3993,
2207
+ "step": 14900
2208
+ },
2209
+ {
2210
+ "epoch": 3.8476386565435594,
2211
+ "grad_norm": 3.43810772895813,
2212
+ "learning_rate": 1.1534105534105535e-05,
2213
+ "loss": 0.4153,
2214
+ "step": 14950
2215
+ },
2216
+ {
2217
+ "epoch": 3.8605070132544075,
2218
+ "grad_norm": 3.04858136177063,
2219
+ "learning_rate": 1.1405405405405406e-05,
2220
+ "loss": 0.4056,
2221
+ "step": 15000
2222
+ },
2223
+ {
2224
+ "epoch": 3.8605070132544075,
2225
+ "eval_loss": 0.8282376527786255,
2226
+ "eval_runtime": 189.5165,
2227
+ "eval_samples_per_second": 102.503,
2228
+ "eval_steps_per_second": 10.252,
2229
+ "step": 15000
2230
+ },
2231
+ {
2232
+ "epoch": 3.8733753699652556,
2233
+ "grad_norm": 3.8784329891204834,
2234
+ "learning_rate": 1.1276705276705276e-05,
2235
+ "loss": 0.3866,
2236
+ "step": 15050
2237
+ },
2238
+ {
2239
+ "epoch": 3.8862437266761036,
2240
+ "grad_norm": 3.622274398803711,
2241
+ "learning_rate": 1.114800514800515e-05,
2242
+ "loss": 0.4208,
2243
+ "step": 15100
2244
+ },
2245
+ {
2246
+ "epoch": 3.8991120833869513,
2247
+ "grad_norm": 3.2869110107421875,
2248
+ "learning_rate": 1.101930501930502e-05,
2249
+ "loss": 0.4302,
2250
+ "step": 15150
2251
+ },
2252
+ {
2253
+ "epoch": 3.9119804400977998,
2254
+ "grad_norm": 2.9988114833831787,
2255
+ "learning_rate": 1.0890604890604891e-05,
2256
+ "loss": 0.4153,
2257
+ "step": 15200
2258
+ },
2259
+ {
2260
+ "epoch": 3.9248487968086474,
2261
+ "grad_norm": 3.2975871562957764,
2262
+ "learning_rate": 1.0761904761904763e-05,
2263
+ "loss": 0.4178,
2264
+ "step": 15250
2265
+ },
2266
+ {
2267
+ "epoch": 3.9377171535194955,
2268
+ "grad_norm": 2.9260878562927246,
2269
+ "learning_rate": 1.0633204633204634e-05,
2270
+ "loss": 0.4048,
2271
+ "step": 15300
2272
+ },
2273
+ {
2274
+ "epoch": 3.9505855102303435,
2275
+ "grad_norm": 3.6288230419158936,
2276
+ "learning_rate": 1.0504504504504504e-05,
2277
+ "loss": 0.4007,
2278
+ "step": 15350
2279
+ },
2280
+ {
2281
+ "epoch": 3.9634538669411916,
2282
+ "grad_norm": 4.0753173828125,
2283
+ "learning_rate": 1.0375804375804377e-05,
2284
+ "loss": 0.397,
2285
+ "step": 15400
2286
+ },
2287
+ {
2288
+ "epoch": 3.9763222236520397,
2289
+ "grad_norm": 3.9990575313568115,
2290
+ "learning_rate": 1.0247104247104247e-05,
2291
+ "loss": 0.4043,
2292
+ "step": 15450
2293
+ },
2294
+ {
2295
+ "epoch": 3.9891905803628878,
2296
+ "grad_norm": 3.895235776901245,
2297
+ "learning_rate": 1.0118404118404119e-05,
2298
+ "loss": 0.4147,
2299
+ "step": 15500
2300
+ },
2301
+ {
2302
+ "epoch": 4.002058937073736,
2303
+ "grad_norm": 3.6188671588897705,
2304
+ "learning_rate": 9.98970398970399e-06,
2305
+ "loss": 0.4038,
2306
+ "step": 15550
2307
+ },
2308
+ {
2309
+ "epoch": 4.0149272937845835,
2310
+ "grad_norm": 2.461876392364502,
2311
+ "learning_rate": 9.861003861003862e-06,
2312
+ "loss": 0.3183,
2313
+ "step": 15600
2314
+ },
2315
+ {
2316
+ "epoch": 4.027795650495432,
2317
+ "grad_norm": 3.0858776569366455,
2318
+ "learning_rate": 9.732303732303732e-06,
2319
+ "loss": 0.3477,
2320
+ "step": 15650
2321
+ },
2322
+ {
2323
+ "epoch": 4.04066400720628,
2324
+ "grad_norm": 3.3975493907928467,
2325
+ "learning_rate": 9.603603603603605e-06,
2326
+ "loss": 0.3225,
2327
+ "step": 15700
2328
+ },
2329
+ {
2330
+ "epoch": 4.053532363917128,
2331
+ "grad_norm": 3.6678659915924072,
2332
+ "learning_rate": 9.474903474903475e-06,
2333
+ "loss": 0.3294,
2334
+ "step": 15750
2335
+ },
2336
+ {
2337
+ "epoch": 4.066400720627976,
2338
+ "grad_norm": 3.5393424034118652,
2339
+ "learning_rate": 9.346203346203347e-06,
2340
+ "loss": 0.3421,
2341
+ "step": 15800
2342
+ },
2343
+ {
2344
+ "epoch": 4.079269077338824,
2345
+ "grad_norm": 3.039139747619629,
2346
+ "learning_rate": 9.217503217503218e-06,
2347
+ "loss": 0.328,
2348
+ "step": 15850
2349
+ },
2350
+ {
2351
+ "epoch": 4.092137434049672,
2352
+ "grad_norm": 4.036282062530518,
2353
+ "learning_rate": 9.08880308880309e-06,
2354
+ "loss": 0.3287,
2355
+ "step": 15900
2356
+ },
2357
+ {
2358
+ "epoch": 4.1050057907605195,
2359
+ "grad_norm": 3.0405406951904297,
2360
+ "learning_rate": 8.96010296010296e-06,
2361
+ "loss": 0.3335,
2362
+ "step": 15950
2363
+ },
2364
+ {
2365
+ "epoch": 4.117874147471368,
2366
+ "grad_norm": 2.893115520477295,
2367
+ "learning_rate": 8.831402831402833e-06,
2368
+ "loss": 0.3092,
2369
+ "step": 16000
2370
+ },
2371
+ {
2372
+ "epoch": 4.117874147471368,
2373
+ "eval_loss": 0.8520528674125671,
2374
+ "eval_runtime": 189.4809,
2375
+ "eval_samples_per_second": 102.522,
2376
+ "eval_steps_per_second": 10.254,
2377
+ "step": 16000
2378
+ },
2379
+ {
2380
+ "epoch": 4.130742504182216,
2381
+ "grad_norm": 4.632415771484375,
2382
+ "learning_rate": 8.702702702702703e-06,
2383
+ "loss": 0.3281,
2384
+ "step": 16050
2385
+ },
2386
+ {
2387
+ "epoch": 4.143610860893064,
2388
+ "grad_norm": 3.4265694618225098,
2389
+ "learning_rate": 8.574002574002575e-06,
2390
+ "loss": 0.3147,
2391
+ "step": 16100
2392
+ },
2393
+ {
2394
+ "epoch": 4.156479217603912,
2395
+ "grad_norm": 2.336419105529785,
2396
+ "learning_rate": 8.445302445302446e-06,
2397
+ "loss": 0.3013,
2398
+ "step": 16150
2399
+ },
2400
+ {
2401
+ "epoch": 4.16934757431476,
2402
+ "grad_norm": 3.3826658725738525,
2403
+ "learning_rate": 8.316602316602316e-06,
2404
+ "loss": 0.3124,
2405
+ "step": 16200
2406
+ },
2407
+ {
2408
+ "epoch": 4.182215931025608,
2409
+ "grad_norm": 2.8319571018218994,
2410
+ "learning_rate": 8.187902187902188e-06,
2411
+ "loss": 0.3503,
2412
+ "step": 16250
2413
+ },
2414
+ {
2415
+ "epoch": 4.1950842877364565,
2416
+ "grad_norm": 5.399038314819336,
2417
+ "learning_rate": 8.05920205920206e-06,
2418
+ "loss": 0.3394,
2419
+ "step": 16300
2420
+ },
2421
+ {
2422
+ "epoch": 4.207952644447304,
2423
+ "grad_norm": 2.59490966796875,
2424
+ "learning_rate": 7.930501930501931e-06,
2425
+ "loss": 0.3317,
2426
+ "step": 16350
2427
+ },
2428
+ {
2429
+ "epoch": 4.220821001158152,
2430
+ "grad_norm": 3.371151924133301,
2431
+ "learning_rate": 7.801801801801801e-06,
2432
+ "loss": 0.3123,
2433
+ "step": 16400
2434
+ },
2435
+ {
2436
+ "epoch": 4.233689357869,
2437
+ "grad_norm": 3.447014808654785,
2438
+ "learning_rate": 7.673101673101674e-06,
2439
+ "loss": 0.3348,
2440
+ "step": 16450
2441
+ },
2442
+ {
2443
+ "epoch": 4.246557714579848,
2444
+ "grad_norm": 4.9008893966674805,
2445
+ "learning_rate": 7.544401544401544e-06,
2446
+ "loss": 0.34,
2447
+ "step": 16500
2448
+ },
2449
+ {
2450
+ "epoch": 4.259426071290696,
2451
+ "grad_norm": 3.1242849826812744,
2452
+ "learning_rate": 7.415701415701416e-06,
2453
+ "loss": 0.3064,
2454
+ "step": 16550
2455
+ },
2456
+ {
2457
+ "epoch": 4.272294428001544,
2458
+ "grad_norm": 4.190210342407227,
2459
+ "learning_rate": 7.287001287001287e-06,
2460
+ "loss": 0.3316,
2461
+ "step": 16600
2462
+ },
2463
+ {
2464
+ "epoch": 4.2851627847123925,
2465
+ "grad_norm": 4.833367824554443,
2466
+ "learning_rate": 7.158301158301159e-06,
2467
+ "loss": 0.3151,
2468
+ "step": 16650
2469
+ },
2470
+ {
2471
+ "epoch": 4.29803114142324,
2472
+ "grad_norm": 3.561443328857422,
2473
+ "learning_rate": 7.02960102960103e-06,
2474
+ "loss": 0.3284,
2475
+ "step": 16700
2476
+ },
2477
+ {
2478
+ "epoch": 4.310899498134089,
2479
+ "grad_norm": 3.202888011932373,
2480
+ "learning_rate": 6.903474903474904e-06,
2481
+ "loss": 0.3361,
2482
+ "step": 16750
2483
+ },
2484
+ {
2485
+ "epoch": 4.323767854844936,
2486
+ "grad_norm": 4.517894744873047,
2487
+ "learning_rate": 6.774774774774775e-06,
2488
+ "loss": 0.3371,
2489
+ "step": 16800
2490
+ },
2491
+ {
2492
+ "epoch": 4.336636211555784,
2493
+ "grad_norm": 3.958711862564087,
2494
+ "learning_rate": 6.646074646074646e-06,
2495
+ "loss": 0.3236,
2496
+ "step": 16850
2497
+ },
2498
+ {
2499
+ "epoch": 4.3495045682666325,
2500
+ "grad_norm": 2.8120596408843994,
2501
+ "learning_rate": 6.517374517374518e-06,
2502
+ "loss": 0.3128,
2503
+ "step": 16900
2504
+ },
2505
+ {
2506
+ "epoch": 4.36237292497748,
2507
+ "grad_norm": 2.320220947265625,
2508
+ "learning_rate": 6.388674388674388e-06,
2509
+ "loss": 0.3079,
2510
+ "step": 16950
2511
+ },
2512
+ {
2513
+ "epoch": 4.375241281688329,
2514
+ "grad_norm": 2.833205223083496,
2515
+ "learning_rate": 6.259974259974261e-06,
2516
+ "loss": 0.3127,
2517
+ "step": 17000
2518
+ },
2519
+ {
2520
+ "epoch": 4.375241281688329,
2521
+ "eval_loss": 0.8534464836120605,
2522
+ "eval_runtime": 189.5459,
2523
+ "eval_samples_per_second": 102.487,
2524
+ "eval_steps_per_second": 10.251,
2525
+ "step": 17000
2526
+ },
2527
+ {
2528
+ "epoch": 4.388109638399176,
2529
+ "grad_norm": 4.218430519104004,
2530
+ "learning_rate": 6.1312741312741316e-06,
2531
+ "loss": 0.3375,
2532
+ "step": 17050
2533
+ },
2534
+ {
2535
+ "epoch": 4.400977995110025,
2536
+ "grad_norm": 3.2581334114074707,
2537
+ "learning_rate": 6.002574002574003e-06,
2538
+ "loss": 0.3081,
2539
+ "step": 17100
2540
+ },
2541
+ {
2542
+ "epoch": 4.413846351820872,
2543
+ "grad_norm": 3.2041099071502686,
2544
+ "learning_rate": 5.873873873873874e-06,
2545
+ "loss": 0.3368,
2546
+ "step": 17150
2547
+ },
2548
+ {
2549
+ "epoch": 4.426714708531721,
2550
+ "grad_norm": 4.340978622436523,
2551
+ "learning_rate": 5.7451737451737455e-06,
2552
+ "loss": 0.3404,
2553
+ "step": 17200
2554
+ },
2555
+ {
2556
+ "epoch": 4.4395830652425685,
2557
+ "grad_norm": 4.946235179901123,
2558
+ "learning_rate": 5.616473616473616e-06,
2559
+ "loss": 0.3199,
2560
+ "step": 17250
2561
+ },
2562
+ {
2563
+ "epoch": 4.452451421953416,
2564
+ "grad_norm": 3.671445846557617,
2565
+ "learning_rate": 5.487773487773488e-06,
2566
+ "loss": 0.3137,
2567
+ "step": 17300
2568
+ },
2569
+ {
2570
+ "epoch": 4.465319778664265,
2571
+ "grad_norm": 4.509451389312744,
2572
+ "learning_rate": 5.3590733590733595e-06,
2573
+ "loss": 0.332,
2574
+ "step": 17350
2575
+ },
2576
+ {
2577
+ "epoch": 4.478188135375112,
2578
+ "grad_norm": 3.3261749744415283,
2579
+ "learning_rate": 5.23037323037323e-06,
2580
+ "loss": 0.3339,
2581
+ "step": 17400
2582
+ },
2583
+ {
2584
+ "epoch": 4.491056492085961,
2585
+ "grad_norm": 3.5157628059387207,
2586
+ "learning_rate": 5.101673101673102e-06,
2587
+ "loss": 0.3256,
2588
+ "step": 17450
2589
+ },
2590
+ {
2591
+ "epoch": 4.503924848796808,
2592
+ "grad_norm": 3.7138776779174805,
2593
+ "learning_rate": 4.9729729729729735e-06,
2594
+ "loss": 0.3278,
2595
+ "step": 17500
2596
+ },
2597
+ {
2598
+ "epoch": 4.516793205507657,
2599
+ "grad_norm": 3.2979509830474854,
2600
+ "learning_rate": 4.844272844272844e-06,
2601
+ "loss": 0.3249,
2602
+ "step": 17550
2603
+ },
2604
+ {
2605
+ "epoch": 4.529661562218505,
2606
+ "grad_norm": 3.117856740951538,
2607
+ "learning_rate": 4.715572715572716e-06,
2608
+ "loss": 0.3174,
2609
+ "step": 17600
2610
+ },
2611
+ {
2612
+ "epoch": 4.542529918929353,
2613
+ "grad_norm": 3.44389009475708,
2614
+ "learning_rate": 4.586872586872587e-06,
2615
+ "loss": 0.3072,
2616
+ "step": 17650
2617
+ },
2618
+ {
2619
+ "epoch": 4.555398275640201,
2620
+ "grad_norm": 4.093995094299316,
2621
+ "learning_rate": 4.458172458172458e-06,
2622
+ "loss": 0.3118,
2623
+ "step": 17700
2624
+ },
2625
+ {
2626
+ "epoch": 4.568266632351049,
2627
+ "grad_norm": 2.943690061569214,
2628
+ "learning_rate": 4.32947232947233e-06,
2629
+ "loss": 0.3123,
2630
+ "step": 17750
2631
+ },
2632
+ {
2633
+ "epoch": 4.581134989061897,
2634
+ "grad_norm": 3.0897843837738037,
2635
+ "learning_rate": 4.200772200772201e-06,
2636
+ "loss": 0.3194,
2637
+ "step": 17800
2638
+ },
2639
+ {
2640
+ "epoch": 4.5940033457727445,
2641
+ "grad_norm": 3.8259048461914062,
2642
+ "learning_rate": 4.072072072072072e-06,
2643
+ "loss": 0.3321,
2644
+ "step": 17850
2645
+ },
2646
+ {
2647
+ "epoch": 4.606871702483593,
2648
+ "grad_norm": 4.632271766662598,
2649
+ "learning_rate": 3.943371943371944e-06,
2650
+ "loss": 0.3223,
2651
+ "step": 17900
2652
+ },
2653
+ {
2654
+ "epoch": 4.619740059194441,
2655
+ "grad_norm": 3.449892282485962,
2656
+ "learning_rate": 3.814671814671815e-06,
2657
+ "loss": 0.3152,
2658
+ "step": 17950
2659
+ },
2660
+ {
2661
+ "epoch": 4.632608415905289,
2662
+ "grad_norm": 4.951483726501465,
2663
+ "learning_rate": 3.685971685971686e-06,
2664
+ "loss": 0.3333,
2665
+ "step": 18000
2666
+ },
2667
+ {
2668
+ "epoch": 4.632608415905289,
2669
+ "eval_loss": 0.8536800742149353,
2670
+ "eval_runtime": 189.5498,
2671
+ "eval_samples_per_second": 102.485,
2672
+ "eval_steps_per_second": 10.251,
2673
+ "step": 18000
2674
+ },
2675
+ {
2676
+ "epoch": 4.645476772616137,
2677
+ "grad_norm": 2.879723310470581,
2678
+ "learning_rate": 3.5572715572715578e-06,
2679
+ "loss": 0.3311,
2680
+ "step": 18050
2681
+ },
2682
+ {
2683
+ "epoch": 4.658345129326985,
2684
+ "grad_norm": 2.263468027114868,
2685
+ "learning_rate": 3.428571428571429e-06,
2686
+ "loss": 0.3288,
2687
+ "step": 18100
2688
+ },
2689
+ {
2690
+ "epoch": 4.671213486037833,
2691
+ "grad_norm": 4.122782230377197,
2692
+ "learning_rate": 3.2998712998713e-06,
2693
+ "loss": 0.2881,
2694
+ "step": 18150
2695
+ },
2696
+ {
2697
+ "epoch": 4.684081842748681,
2698
+ "grad_norm": 2.713583469390869,
2699
+ "learning_rate": 3.1711711711711718e-06,
2700
+ "loss": 0.335,
2701
+ "step": 18200
2702
+ },
2703
+ {
2704
+ "epoch": 4.696950199459529,
2705
+ "grad_norm": 4.133466720581055,
2706
+ "learning_rate": 3.0424710424710425e-06,
2707
+ "loss": 0.3389,
2708
+ "step": 18250
2709
+ },
2710
+ {
2711
+ "epoch": 4.709818556170377,
2712
+ "grad_norm": 3.080181121826172,
2713
+ "learning_rate": 2.9137709137709137e-06,
2714
+ "loss": 0.3049,
2715
+ "step": 18300
2716
+ },
2717
+ {
2718
+ "epoch": 4.722686912881225,
2719
+ "grad_norm": 3.2087597846984863,
2720
+ "learning_rate": 2.7850707850707853e-06,
2721
+ "loss": 0.3021,
2722
+ "step": 18350
2723
+ },
2724
+ {
2725
+ "epoch": 4.735555269592073,
2726
+ "grad_norm": 3.037031888961792,
2727
+ "learning_rate": 2.6563706563706565e-06,
2728
+ "loss": 0.3343,
2729
+ "step": 18400
2730
+ },
2731
+ {
2732
+ "epoch": 4.748423626302921,
2733
+ "grad_norm": 3.936049699783325,
2734
+ "learning_rate": 2.5276705276705277e-06,
2735
+ "loss": 0.351,
2736
+ "step": 18450
2737
+ },
2738
+ {
2739
+ "epoch": 4.761291983013769,
2740
+ "grad_norm": 2.863168239593506,
2741
+ "learning_rate": 2.3989703989703993e-06,
2742
+ "loss": 0.3062,
2743
+ "step": 18500
2744
+ },
2745
+ {
2746
+ "epoch": 4.7741603397246175,
2747
+ "grad_norm": 3.105039358139038,
2748
+ "learning_rate": 2.2702702702702705e-06,
2749
+ "loss": 0.3139,
2750
+ "step": 18550
2751
+ },
2752
+ {
2753
+ "epoch": 4.787028696435465,
2754
+ "grad_norm": 4.5207390785217285,
2755
+ "learning_rate": 2.1415701415701416e-06,
2756
+ "loss": 0.3295,
2757
+ "step": 18600
2758
+ },
2759
+ {
2760
+ "epoch": 4.799897053146314,
2761
+ "grad_norm": 4.3474345207214355,
2762
+ "learning_rate": 2.0128700128700133e-06,
2763
+ "loss": 0.3256,
2764
+ "step": 18650
2765
+ },
2766
+ {
2767
+ "epoch": 4.812765409857161,
2768
+ "grad_norm": 3.58796763420105,
2769
+ "learning_rate": 1.8841698841698844e-06,
2770
+ "loss": 0.32,
2771
+ "step": 18700
2772
+ },
2773
+ {
2774
+ "epoch": 4.825633766568009,
2775
+ "grad_norm": 2.583491325378418,
2776
+ "learning_rate": 1.7554697554697556e-06,
2777
+ "loss": 0.3409,
2778
+ "step": 18750
2779
+ },
2780
+ {
2781
+ "epoch": 4.838502123278857,
2782
+ "grad_norm": 2.490678071975708,
2783
+ "learning_rate": 1.6267696267696266e-06,
2784
+ "loss": 0.3164,
2785
+ "step": 18800
2786
+ },
2787
+ {
2788
+ "epoch": 4.851370479989705,
2789
+ "grad_norm": 2.505882740020752,
2790
+ "learning_rate": 1.4980694980694982e-06,
2791
+ "loss": 0.2992,
2792
+ "step": 18850
2793
+ },
2794
+ {
2795
+ "epoch": 4.864238836700554,
2796
+ "grad_norm": 3.8381474018096924,
2797
+ "learning_rate": 1.371943371943372e-06,
2798
+ "loss": 0.3178,
2799
+ "step": 18900
2800
+ },
2801
+ {
2802
+ "epoch": 4.877107193411401,
2803
+ "grad_norm": 4.065976619720459,
2804
+ "learning_rate": 1.2432432432432434e-06,
2805
+ "loss": 0.312,
2806
+ "step": 18950
2807
+ },
2808
+ {
2809
+ "epoch": 4.88997555012225,
2810
+ "grad_norm": 2.3685247898101807,
2811
+ "learning_rate": 1.1145431145431146e-06,
2812
+ "loss": 0.3103,
2813
+ "step": 19000
2814
+ },
2815
+ {
2816
+ "epoch": 4.88997555012225,
2817
+ "eval_loss": 0.8551310896873474,
2818
+ "eval_runtime": 189.5403,
2819
+ "eval_samples_per_second": 102.49,
2820
+ "eval_steps_per_second": 10.251,
2821
+ "step": 19000
2822
+ },
2823
+ {
2824
+ "epoch": 4.902843906833097,
2825
+ "grad_norm": 1.829939365386963,
2826
+ "learning_rate": 9.85842985842986e-07,
2827
+ "loss": 0.3012,
2828
+ "step": 19050
2829
+ },
2830
+ {
2831
+ "epoch": 4.915712263543945,
2832
+ "grad_norm": 3.9715230464935303,
2833
+ "learning_rate": 8.571428571428572e-07,
2834
+ "loss": 0.3258,
2835
+ "step": 19100
2836
+ },
2837
+ {
2838
+ "epoch": 4.9285806202547935,
2839
+ "grad_norm": 3.2242319583892822,
2840
+ "learning_rate": 7.284427284427284e-07,
2841
+ "loss": 0.319,
2842
+ "step": 19150
2843
+ },
2844
+ {
2845
+ "epoch": 4.941448976965641,
2846
+ "grad_norm": 2.4675443172454834,
2847
+ "learning_rate": 5.997425997425998e-07,
2848
+ "loss": 0.3183,
2849
+ "step": 19200
2850
+ },
2851
+ {
2852
+ "epoch": 4.95431733367649,
2853
+ "grad_norm": 4.066344738006592,
2854
+ "learning_rate": 4.710424710424711e-07,
2855
+ "loss": 0.3368,
2856
+ "step": 19250
2857
+ },
2858
+ {
2859
+ "epoch": 4.967185690387337,
2860
+ "grad_norm": 3.9160056114196777,
2861
+ "learning_rate": 3.423423423423424e-07,
2862
+ "loss": 0.3002,
2863
+ "step": 19300
2864
+ },
2865
+ {
2866
+ "epoch": 4.980054047098186,
2867
+ "grad_norm": 3.2470641136169434,
2868
+ "learning_rate": 2.1364221364221366e-07,
2869
+ "loss": 0.3168,
2870
+ "step": 19350
2871
+ },
2872
+ {
2873
+ "epoch": 4.992922403809033,
2874
+ "grad_norm": 4.328388690948486,
2875
+ "learning_rate": 8.494208494208495e-08,
2876
+ "loss": 0.3105,
2877
+ "step": 19400
2878
+ }
2879
+ ],
2880
+ "logging_steps": 50,
2881
+ "max_steps": 19425,
2882
+ "num_input_tokens_seen": 0,
2883
+ "num_train_epochs": 5,
2884
+ "save_steps": 1000,
2885
+ "stateful_callbacks": {
2886
+ "TrainerControl": {
2887
+ "args": {
2888
+ "should_epoch_stop": false,
2889
+ "should_evaluate": false,
2890
+ "should_log": false,
2891
+ "should_save": true,
2892
+ "should_training_stop": true
2893
+ },
2894
+ "attributes": {}
2895
+ }
2896
+ },
2897
+ "total_flos": 9.343651794926285e+17,
2898
+ "train_batch_size": 10,
2899
+ "trial_name": null,
2900
+ "trial_params": null
2901
+ }
checkpoints/checkpoint-19425/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2262a8cde4f7b1f1f729f8de2948f3af56db706718e5828327df85ba53fe471
3
+ size 5304
checkpoints/checkpoint-19425/vocab.json ADDED
The diff for this file is too large to render. See raw diff