root commited on
Commit
39534cc
·
1 Parent(s): b13881e

Upload trained Java code repair model

Browse files
checkpoint-15000/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "relu",
15
+ "gradient_checkpointing": false,
16
+ "id2label": {
17
+ "0": "LABEL_0"
18
+ },
19
+ "initializer_factor": 1.0,
20
+ "is_encoder_decoder": true,
21
+ "is_gated_act": false,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "layer_norm_epsilon": 1e-06,
26
+ "model_type": "t5",
27
+ "n_positions": 512,
28
+ "num_decoder_layers": 12,
29
+ "num_heads": 12,
30
+ "num_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "relative_attention_max_distance": 128,
34
+ "relative_attention_num_buckets": 32,
35
+ "task_specific_params": {
36
+ "summarization": {
37
+ "early_stopping": true,
38
+ "length_penalty": 2.0,
39
+ "max_length": 200,
40
+ "min_length": 30,
41
+ "no_repeat_ngram_size": 3,
42
+ "num_beams": 4,
43
+ "prefix": "summarize: "
44
+ },
45
+ "translation_en_to_de": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to German: "
50
+ },
51
+ "translation_en_to_fr": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to French: "
56
+ },
57
+ "translation_en_to_ro": {
58
+ "early_stopping": true,
59
+ "max_length": 300,
60
+ "num_beams": 4,
61
+ "prefix": "translate English to Romanian: "
62
+ }
63
+ },
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.55.3",
66
+ "use_cache": true,
67
+ "vocab_size": 32100
68
+ }
checkpoint-15000/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": "4.55.3"
8
+ }
checkpoint-15000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-15000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6a5555df83437ff18f570e5e92853df46d5e8918d1eb213a0808477b4d04b4
3
+ size 891558696
checkpoint-15000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74b35bf7c12b68f3a506e2d318c44eff6614a25b9b45152b1c57f1c85ab785fd
3
+ size 1783276811
checkpoint-15000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636fcc90db86d9ffa8305eb468eadd4b5d07df9460b190443fb21e8a36c14b11
3
+ size 14645
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d8bacaa210f6f55cb4bb7e134a58f475b51bdda4630b9d9c0a020d40a1fbe5
3
+ size 1383
checkpoint-15000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37eccd0532826f4d957c124b2faf3219482ff02b0e7714254493192c75ade8d7
3
+ size 1465
checkpoint-15000/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
+ }
checkpoint-15000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-15000/tokenizer_config.json ADDED
@@ -0,0 +1,960 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
949
+ "cls_token": "<s>",
950
+ "eos_token": "</s>",
951
+ "errors": "replace",
952
+ "extra_special_tokens": {},
953
+ "mask_token": "<mask>",
954
+ "model_max_length": 512,
955
+ "pad_token": "<pad>",
956
+ "sep_token": "</s>",
957
+ "tokenizer_class": "RobertaTokenizer",
958
+ "trim_offsets": true,
959
+ "unk_token": "<unk>"
960
+ }
checkpoint-15000/trainer_state.json ADDED
@@ -0,0 +1,2134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.9457973291437547,
6
+ "eval_steps": 500,
7
+ "global_step": 15000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.009819324430479183,
14
+ "grad_norm": 0.24714912474155426,
15
+ "learning_rate": 4.983961770096884e-05,
16
+ "loss": 0.3447,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.019638648860958365,
21
+ "grad_norm": 0.12986360490322113,
22
+ "learning_rate": 4.967596229379419e-05,
23
+ "loss": 0.0057,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.02945797329143755,
28
+ "grad_norm": 0.13787369430065155,
29
+ "learning_rate": 4.9512306886619534e-05,
30
+ "loss": 0.0041,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.03927729772191673,
35
+ "grad_norm": 0.032512035220861435,
36
+ "learning_rate": 4.9348651479444883e-05,
37
+ "loss": 0.0031,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.049096622152395915,
42
+ "grad_norm": 0.04660605266690254,
43
+ "learning_rate": 4.9184996072270227e-05,
44
+ "loss": 0.0017,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.0589159465828751,
49
+ "grad_norm": 0.12520131468772888,
50
+ "learning_rate": 4.9021340665095576e-05,
51
+ "loss": 0.0023,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.06873527101335428,
56
+ "grad_norm": 0.03921537473797798,
57
+ "learning_rate": 4.8857685257920926e-05,
58
+ "loss": 0.0016,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.07855459544383346,
63
+ "grad_norm": 0.019508639350533485,
64
+ "learning_rate": 4.869402985074627e-05,
65
+ "loss": 0.0015,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.08837391987431265,
70
+ "grad_norm": 0.03215921297669411,
71
+ "learning_rate": 4.853037444357162e-05,
72
+ "loss": 0.0018,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.09819324430479183,
77
+ "grad_norm": 0.01678670570254326,
78
+ "learning_rate": 4.836671903639696e-05,
79
+ "loss": 0.0012,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.10801256873527101,
84
+ "grad_norm": 0.04076138511300087,
85
+ "learning_rate": 4.820306362922231e-05,
86
+ "loss": 0.0013,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.1178318931657502,
91
+ "grad_norm": 0.028516946360468864,
92
+ "learning_rate": 4.803940822204766e-05,
93
+ "loss": 0.001,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.12765121759622938,
98
+ "grad_norm": 0.0024934338871389627,
99
+ "learning_rate": 4.7875752814873006e-05,
100
+ "loss": 0.0013,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.13747054202670855,
105
+ "grad_norm": 0.009505635127425194,
106
+ "learning_rate": 4.7712097407698356e-05,
107
+ "loss": 0.0006,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.14728986645718775,
112
+ "grad_norm": 0.004126217681914568,
113
+ "learning_rate": 4.75484420005237e-05,
114
+ "loss": 0.0009,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.15710919088766692,
119
+ "grad_norm": 0.001864357735030353,
120
+ "learning_rate": 4.738478659334905e-05,
121
+ "loss": 0.0006,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.16692851531814612,
126
+ "grad_norm": 0.05715826526284218,
127
+ "learning_rate": 4.722113118617439e-05,
128
+ "loss": 0.0009,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.1767478397486253,
133
+ "grad_norm": 0.01866191253066063,
134
+ "learning_rate": 4.7057475778999735e-05,
135
+ "loss": 0.0008,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.1865671641791045,
140
+ "grad_norm": 0.02309831976890564,
141
+ "learning_rate": 4.6893820371825085e-05,
142
+ "loss": 0.0009,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.19638648860958366,
147
+ "grad_norm": 0.008644412271678448,
148
+ "learning_rate": 4.6730164964650435e-05,
149
+ "loss": 0.0008,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.20620581304006286,
154
+ "grad_norm": 0.0034850463271141052,
155
+ "learning_rate": 4.656650955747578e-05,
156
+ "loss": 0.0008,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.21602513747054203,
161
+ "grad_norm": 0.015649326145648956,
162
+ "learning_rate": 4.640285415030113e-05,
163
+ "loss": 0.0005,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.2258444619010212,
168
+ "grad_norm": 0.017577216029167175,
169
+ "learning_rate": 4.623919874312648e-05,
170
+ "loss": 0.0005,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.2356637863315004,
175
+ "grad_norm": 0.001943176961503923,
176
+ "learning_rate": 4.607554333595182e-05,
177
+ "loss": 0.0006,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.24548311076197957,
182
+ "grad_norm": 0.013552217744290829,
183
+ "learning_rate": 4.591188792877717e-05,
184
+ "loss": 0.0007,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.25530243519245877,
189
+ "grad_norm": 0.0009095704299397767,
190
+ "learning_rate": 4.574823252160252e-05,
191
+ "loss": 0.0006,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.26512175962293794,
196
+ "grad_norm": 0.12323999404907227,
197
+ "learning_rate": 4.5584577114427864e-05,
198
+ "loss": 0.001,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.2749410840534171,
203
+ "grad_norm": 0.0046529932878911495,
204
+ "learning_rate": 4.5420921707253214e-05,
205
+ "loss": 0.0006,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.28476040848389633,
210
+ "grad_norm": 0.0006078369333408773,
211
+ "learning_rate": 4.525726630007856e-05,
212
+ "loss": 0.0005,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.2945797329143755,
217
+ "grad_norm": 0.0011770805576816201,
218
+ "learning_rate": 4.509361089290391e-05,
219
+ "loss": 0.0003,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.3043990573448547,
224
+ "grad_norm": 0.004274972248822451,
225
+ "learning_rate": 4.492995548572925e-05,
226
+ "loss": 0.0005,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.31421838177533384,
231
+ "grad_norm": 0.0007647090242244303,
232
+ "learning_rate": 4.476630007855459e-05,
233
+ "loss": 0.0007,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.324037706205813,
238
+ "grad_norm": 0.013916688971221447,
239
+ "learning_rate": 4.460264467137994e-05,
240
+ "loss": 0.0005,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.33385703063629224,
245
+ "grad_norm": 0.001363221788778901,
246
+ "learning_rate": 4.443898926420529e-05,
247
+ "loss": 0.0004,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.3436763550667714,
252
+ "grad_norm": 0.00033090286888182163,
253
+ "learning_rate": 4.4275333857030636e-05,
254
+ "loss": 0.0004,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.3534956794972506,
259
+ "grad_norm": 0.000668744498398155,
260
+ "learning_rate": 4.4111678449855986e-05,
261
+ "loss": 0.0006,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.36331500392772975,
266
+ "grad_norm": 0.0539139024913311,
267
+ "learning_rate": 4.394802304268133e-05,
268
+ "loss": 0.0005,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.373134328358209,
273
+ "grad_norm": 0.0008487588493153453,
274
+ "learning_rate": 4.378436763550668e-05,
275
+ "loss": 0.0004,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.38295365278868815,
280
+ "grad_norm": 0.0008443322731181979,
281
+ "learning_rate": 4.362071222833203e-05,
282
+ "loss": 0.0006,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.3927729772191673,
287
+ "grad_norm": 0.00504659116268158,
288
+ "learning_rate": 4.345705682115737e-05,
289
+ "loss": 0.0006,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.4025923016496465,
294
+ "grad_norm": 0.19237877428531647,
295
+ "learning_rate": 4.329340141398272e-05,
296
+ "loss": 0.0003,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.4124116260801257,
301
+ "grad_norm": 0.052810050547122955,
302
+ "learning_rate": 4.312974600680807e-05,
303
+ "loss": 0.0007,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.4222309505106049,
308
+ "grad_norm": 0.0010182256810367107,
309
+ "learning_rate": 4.2966090599633415e-05,
310
+ "loss": 0.0006,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.43205027494108406,
315
+ "grad_norm": 0.008011899888515472,
316
+ "learning_rate": 4.2802435192458765e-05,
317
+ "loss": 0.0004,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.4418695993715632,
322
+ "grad_norm": 0.004001118242740631,
323
+ "learning_rate": 4.263877978528411e-05,
324
+ "loss": 0.0003,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.4516889238020424,
329
+ "grad_norm": 0.0005824828986078501,
330
+ "learning_rate": 4.247512437810945e-05,
331
+ "loss": 0.0004,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.4615082482325216,
336
+ "grad_norm": 0.00035399169428274035,
337
+ "learning_rate": 4.23114689709348e-05,
338
+ "loss": 0.0006,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.4713275726630008,
343
+ "grad_norm": 0.0008132366347126663,
344
+ "learning_rate": 4.2147813563760144e-05,
345
+ "loss": 0.0004,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.48114689709347996,
350
+ "grad_norm": 0.00029086056747473776,
351
+ "learning_rate": 4.1984158156585494e-05,
352
+ "loss": 0.0004,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.49096622152395913,
357
+ "grad_norm": 0.009674192406237125,
358
+ "learning_rate": 4.1820502749410844e-05,
359
+ "loss": 0.0003,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.5007855459544384,
364
+ "grad_norm": 0.0002215866988990456,
365
+ "learning_rate": 4.165684734223619e-05,
366
+ "loss": 0.0003,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.5106048703849175,
371
+ "grad_norm": 0.0003756559453904629,
372
+ "learning_rate": 4.149319193506154e-05,
373
+ "loss": 0.0003,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.5204241948153967,
378
+ "grad_norm": 3.785878652706742e-05,
379
+ "learning_rate": 4.132953652788688e-05,
380
+ "loss": 0.0002,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.5302435192458759,
385
+ "grad_norm": 0.007607210893183947,
386
+ "learning_rate": 4.116588112071223e-05,
387
+ "loss": 0.0003,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.540062843676355,
392
+ "grad_norm": 0.02198871783912182,
393
+ "learning_rate": 4.100222571353758e-05,
394
+ "loss": 0.0002,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.5498821681068342,
399
+ "grad_norm": 0.00041103907278738916,
400
+ "learning_rate": 4.0838570306362923e-05,
401
+ "loss": 0.0002,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.5597014925373134,
406
+ "grad_norm": 0.01565481722354889,
407
+ "learning_rate": 4.067491489918827e-05,
408
+ "loss": 0.0003,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.5695208169677927,
413
+ "grad_norm": 0.0117128761485219,
414
+ "learning_rate": 4.051125949201362e-05,
415
+ "loss": 0.0004,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.5793401413982718,
420
+ "grad_norm": 0.004789320752024651,
421
+ "learning_rate": 4.0347604084838966e-05,
422
+ "loss": 0.0004,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.589159465828751,
427
+ "grad_norm": 0.0011219610460102558,
428
+ "learning_rate": 4.018394867766431e-05,
429
+ "loss": 0.0004,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.5989787902592302,
434
+ "grad_norm": 0.0518529899418354,
435
+ "learning_rate": 4.002029327048966e-05,
436
+ "loss": 0.0004,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.6087981146897093,
441
+ "grad_norm": 0.01609092392027378,
442
+ "learning_rate": 3.9856637863315e-05,
443
+ "loss": 0.0003,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.6186174391201885,
448
+ "grad_norm": 0.002343968488276005,
449
+ "learning_rate": 3.969298245614035e-05,
450
+ "loss": 0.0003,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.6284367635506677,
455
+ "grad_norm": 0.010258428752422333,
456
+ "learning_rate": 3.9529327048965696e-05,
457
+ "loss": 0.0003,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.6382560879811469,
462
+ "grad_norm": 0.0007253732765093446,
463
+ "learning_rate": 3.9365671641791046e-05,
464
+ "loss": 0.0004,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.648075412411626,
469
+ "grad_norm": 0.01221112348139286,
470
+ "learning_rate": 3.9202016234616395e-05,
471
+ "loss": 0.0003,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.6578947368421053,
476
+ "grad_norm": 0.007547037675976753,
477
+ "learning_rate": 3.903836082744174e-05,
478
+ "loss": 0.0004,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.6677140612725845,
483
+ "grad_norm": 0.0037480357568711042,
484
+ "learning_rate": 3.887470542026709e-05,
485
+ "loss": 0.0003,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.6775333857030637,
490
+ "grad_norm": 9.382007556268945e-05,
491
+ "learning_rate": 3.871105001309244e-05,
492
+ "loss": 0.0005,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.6873527101335428,
497
+ "grad_norm": 0.0019377778517082334,
498
+ "learning_rate": 3.854739460591778e-05,
499
+ "loss": 0.0003,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.697172034564022,
504
+ "grad_norm": 0.00031467623193748295,
505
+ "learning_rate": 3.838373919874313e-05,
506
+ "loss": 0.0003,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.7069913589945012,
511
+ "grad_norm": 0.012330332770943642,
512
+ "learning_rate": 3.8220083791568475e-05,
513
+ "loss": 0.0004,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.7168106834249803,
518
+ "grad_norm": 0.43893539905548096,
519
+ "learning_rate": 3.8056428384393825e-05,
520
+ "loss": 0.002,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.7266300078554595,
525
+ "grad_norm": 0.010738670825958252,
526
+ "learning_rate": 3.789277297721917e-05,
527
+ "loss": 0.0008,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.7364493322859387,
532
+ "grad_norm": 0.0009258920326828957,
533
+ "learning_rate": 3.772911757004452e-05,
534
+ "loss": 0.0005,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.746268656716418,
539
+ "grad_norm": 0.002003765432164073,
540
+ "learning_rate": 3.756546216286986e-05,
541
+ "loss": 0.0004,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.7560879811468971,
546
+ "grad_norm": 0.0003309960593469441,
547
+ "learning_rate": 3.740180675569521e-05,
548
+ "loss": 0.0004,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.7659073055773763,
553
+ "grad_norm": 0.014759145677089691,
554
+ "learning_rate": 3.7238151348520554e-05,
555
+ "loss": 0.0004,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.7757266300078555,
560
+ "grad_norm": 0.00703453179448843,
561
+ "learning_rate": 3.7074495941345904e-05,
562
+ "loss": 0.0005,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.7855459544383346,
567
+ "grad_norm": 0.0093814292922616,
568
+ "learning_rate": 3.691084053417125e-05,
569
+ "loss": 0.0004,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.7953652788688138,
574
+ "grad_norm": 0.00033789846929721534,
575
+ "learning_rate": 3.67471851269966e-05,
576
+ "loss": 0.0003,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.805184603299293,
581
+ "grad_norm": 0.004072342533618212,
582
+ "learning_rate": 3.658352971982195e-05,
583
+ "loss": 0.0004,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.8150039277297721,
588
+ "grad_norm": 0.005905472207814455,
589
+ "learning_rate": 3.641987431264729e-05,
590
+ "loss": 0.0004,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.8248232521602514,
595
+ "grad_norm": 0.008759435266256332,
596
+ "learning_rate": 3.625621890547264e-05,
597
+ "loss": 0.0004,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.8346425765907306,
602
+ "grad_norm": 0.01638154312968254,
603
+ "learning_rate": 3.609256349829799e-05,
604
+ "loss": 0.0003,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.8444619010212098,
609
+ "grad_norm": 0.003001204691827297,
610
+ "learning_rate": 3.592890809112333e-05,
611
+ "loss": 0.0004,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.8542812254516889,
616
+ "grad_norm": 0.0006073117256164551,
617
+ "learning_rate": 3.576525268394868e-05,
618
+ "loss": 0.0003,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.8641005498821681,
623
+ "grad_norm": 0.003654340049251914,
624
+ "learning_rate": 3.5601597276774026e-05,
625
+ "loss": 0.0005,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.8739198743126473,
630
+ "grad_norm": 0.2316829115152359,
631
+ "learning_rate": 3.5437941869599376e-05,
632
+ "loss": 0.0005,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.8837391987431265,
637
+ "grad_norm": 0.027139848098158836,
638
+ "learning_rate": 3.527428646242472e-05,
639
+ "loss": 0.0005,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.8935585231736056,
644
+ "grad_norm": 0.004498090595006943,
645
+ "learning_rate": 3.511063105525006e-05,
646
+ "loss": 0.0004,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.9033778476040848,
651
+ "grad_norm": 0.010397707112133503,
652
+ "learning_rate": 3.494697564807541e-05,
653
+ "loss": 0.0003,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.9131971720345641,
658
+ "grad_norm": 0.00014255594578571618,
659
+ "learning_rate": 3.478332024090076e-05,
660
+ "loss": 0.0003,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.9230164964650432,
665
+ "grad_norm": 0.0028459234163165092,
666
+ "learning_rate": 3.4619664833726105e-05,
667
+ "loss": 0.0003,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.9328358208955224,
672
+ "grad_norm": 0.0030736555345356464,
673
+ "learning_rate": 3.4456009426551455e-05,
674
+ "loss": 0.0002,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.9426551453260016,
679
+ "grad_norm": 0.0026709907688200474,
680
+ "learning_rate": 3.4292354019376805e-05,
681
+ "loss": 0.0003,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.9524744697564808,
686
+ "grad_norm": 0.00022516479657497257,
687
+ "learning_rate": 3.412869861220215e-05,
688
+ "loss": 0.0003,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.9622937941869599,
693
+ "grad_norm": 2.6079122108058073e-05,
694
+ "learning_rate": 3.39650432050275e-05,
695
+ "loss": 0.0002,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.9721131186174391,
700
+ "grad_norm": 0.0010724954772740602,
701
+ "learning_rate": 3.380138779785284e-05,
702
+ "loss": 0.0003,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 0.9819324430479183,
707
+ "grad_norm": 0.00028140624635852873,
708
+ "learning_rate": 3.363773239067819e-05,
709
+ "loss": 0.0004,
710
+ "step": 5000
711
+ },
712
+ {
713
+ "epoch": 0.9917517674783974,
714
+ "grad_norm": 0.002564377384260297,
715
+ "learning_rate": 3.347407698350354e-05,
716
+ "loss": 0.0003,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 1.0015710919088767,
721
+ "grad_norm": 0.0027151070535182953,
722
+ "learning_rate": 3.3310421576328884e-05,
723
+ "loss": 0.0002,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 1.011390416339356,
728
+ "grad_norm": 0.0002080993290292099,
729
+ "learning_rate": 3.3146766169154234e-05,
730
+ "loss": 0.0003,
731
+ "step": 5150
732
+ },
733
+ {
734
+ "epoch": 1.021209740769835,
735
+ "grad_norm": 3.149580516037531e-05,
736
+ "learning_rate": 3.298311076197958e-05,
737
+ "loss": 0.0003,
738
+ "step": 5200
739
+ },
740
+ {
741
+ "epoch": 1.0310290652003142,
742
+ "grad_norm": 0.005241520702838898,
743
+ "learning_rate": 3.281945535480492e-05,
744
+ "loss": 0.0003,
745
+ "step": 5250
746
+ },
747
+ {
748
+ "epoch": 1.0408483896307934,
749
+ "grad_norm": 0.005873743910342455,
750
+ "learning_rate": 3.265579994763027e-05,
751
+ "loss": 0.0002,
752
+ "step": 5300
753
+ },
754
+ {
755
+ "epoch": 1.0506677140612726,
756
+ "grad_norm": 0.006296052597463131,
757
+ "learning_rate": 3.2492144540455613e-05,
758
+ "loss": 0.0003,
759
+ "step": 5350
760
+ },
761
+ {
762
+ "epoch": 1.0604870384917517,
763
+ "grad_norm": 0.00039794211625121534,
764
+ "learning_rate": 3.232848913328096e-05,
765
+ "loss": 0.0004,
766
+ "step": 5400
767
+ },
768
+ {
769
+ "epoch": 1.070306362922231,
770
+ "grad_norm": 0.0039017247036099434,
771
+ "learning_rate": 3.216483372610631e-05,
772
+ "loss": 0.0003,
773
+ "step": 5450
774
+ },
775
+ {
776
+ "epoch": 1.08012568735271,
777
+ "grad_norm": 0.002064199186861515,
778
+ "learning_rate": 3.2001178318931656e-05,
779
+ "loss": 0.0003,
780
+ "step": 5500
781
+ },
782
+ {
783
+ "epoch": 1.0899450117831893,
784
+ "grad_norm": 0.0002229887613793835,
785
+ "learning_rate": 3.1837522911757006e-05,
786
+ "loss": 0.0003,
787
+ "step": 5550
788
+ },
789
+ {
790
+ "epoch": 1.0997643362136684,
791
+ "grad_norm": 3.4759577829390764e-05,
792
+ "learning_rate": 3.1673867504582356e-05,
793
+ "loss": 0.0004,
794
+ "step": 5600
795
+ },
796
+ {
797
+ "epoch": 1.1095836606441476,
798
+ "grad_norm": 2.991587643919047e-05,
799
+ "learning_rate": 3.15102120974077e-05,
800
+ "loss": 0.0002,
801
+ "step": 5650
802
+ },
803
+ {
804
+ "epoch": 1.1194029850746268,
805
+ "grad_norm": 0.0017788242548704147,
806
+ "learning_rate": 3.134655669023305e-05,
807
+ "loss": 0.0003,
808
+ "step": 5700
809
+ },
810
+ {
811
+ "epoch": 1.129222309505106,
812
+ "grad_norm": 0.008592754602432251,
813
+ "learning_rate": 3.118290128305839e-05,
814
+ "loss": 0.0003,
815
+ "step": 5750
816
+ },
817
+ {
818
+ "epoch": 1.139041633935585,
819
+ "grad_norm": 0.0017567313043400645,
820
+ "learning_rate": 3.101924587588374e-05,
821
+ "loss": 0.0003,
822
+ "step": 5800
823
+ },
824
+ {
825
+ "epoch": 1.1488609583660645,
826
+ "grad_norm": 8.339332271134481e-05,
827
+ "learning_rate": 3.085559046870909e-05,
828
+ "loss": 0.0002,
829
+ "step": 5850
830
+ },
831
+ {
832
+ "epoch": 1.1586802827965437,
833
+ "grad_norm": 0.00681919464841485,
834
+ "learning_rate": 3.0691935061534435e-05,
835
+ "loss": 0.0003,
836
+ "step": 5900
837
+ },
838
+ {
839
+ "epoch": 1.1684996072270228,
840
+ "grad_norm": 1.7358417608193122e-05,
841
+ "learning_rate": 3.052827965435978e-05,
842
+ "loss": 0.0002,
843
+ "step": 5950
844
+ },
845
+ {
846
+ "epoch": 1.178318931657502,
847
+ "grad_norm": 0.005276073236018419,
848
+ "learning_rate": 3.0364624247185132e-05,
849
+ "loss": 0.0003,
850
+ "step": 6000
851
+ },
852
+ {
853
+ "epoch": 1.1881382560879812,
854
+ "grad_norm": 1.6649060853524134e-05,
855
+ "learning_rate": 3.0200968840010475e-05,
856
+ "loss": 0.0003,
857
+ "step": 6050
858
+ },
859
+ {
860
+ "epoch": 1.1979575805184604,
861
+ "grad_norm": 1.6310365026583895e-05,
862
+ "learning_rate": 3.003731343283582e-05,
863
+ "loss": 0.0001,
864
+ "step": 6100
865
+ },
866
+ {
867
+ "epoch": 1.2077769049489395,
868
+ "grad_norm": 8.225607598433271e-05,
869
+ "learning_rate": 2.987365802566117e-05,
870
+ "loss": 0.0003,
871
+ "step": 6150
872
+ },
873
+ {
874
+ "epoch": 1.2175962293794187,
875
+ "grad_norm": 0.06942308694124222,
876
+ "learning_rate": 2.9710002618486515e-05,
877
+ "loss": 0.0006,
878
+ "step": 6200
879
+ },
880
+ {
881
+ "epoch": 1.2274155538098979,
882
+ "grad_norm": 0.0003915784473065287,
883
+ "learning_rate": 2.9546347211311865e-05,
884
+ "loss": 0.0008,
885
+ "step": 6250
886
+ },
887
+ {
888
+ "epoch": 1.237234878240377,
889
+ "grad_norm": 5.1170645747333765e-05,
890
+ "learning_rate": 2.9382691804137208e-05,
891
+ "loss": 0.0004,
892
+ "step": 6300
893
+ },
894
+ {
895
+ "epoch": 1.2470542026708562,
896
+ "grad_norm": 0.005075642839074135,
897
+ "learning_rate": 2.9219036396962558e-05,
898
+ "loss": 0.0006,
899
+ "step": 6350
900
+ },
901
+ {
902
+ "epoch": 1.2568735271013354,
903
+ "grad_norm": 0.013923396356403828,
904
+ "learning_rate": 2.9055380989787908e-05,
905
+ "loss": 0.0003,
906
+ "step": 6400
907
+ },
908
+ {
909
+ "epoch": 1.2666928515318145,
910
+ "grad_norm": 0.010688439942896366,
911
+ "learning_rate": 2.889172558261325e-05,
912
+ "loss": 0.0004,
913
+ "step": 6450
914
+ },
915
+ {
916
+ "epoch": 1.2765121759622937,
917
+ "grad_norm": 0.005004653707146645,
918
+ "learning_rate": 2.8728070175438597e-05,
919
+ "loss": 0.0002,
920
+ "step": 6500
921
+ },
922
+ {
923
+ "epoch": 1.286331500392773,
924
+ "grad_norm": 0.015412525273859501,
925
+ "learning_rate": 2.8564414768263947e-05,
926
+ "loss": 0.0003,
927
+ "step": 6550
928
+ },
929
+ {
930
+ "epoch": 1.2961508248232523,
931
+ "grad_norm": 0.002696032403036952,
932
+ "learning_rate": 2.840075936108929e-05,
933
+ "loss": 0.0002,
934
+ "step": 6600
935
+ },
936
+ {
937
+ "epoch": 1.3059701492537314,
938
+ "grad_norm": 0.0005274811992421746,
939
+ "learning_rate": 2.823710395391464e-05,
940
+ "loss": 0.0003,
941
+ "step": 6650
942
+ },
943
+ {
944
+ "epoch": 1.3157894736842106,
945
+ "grad_norm": 2.0785410015378147e-05,
946
+ "learning_rate": 2.8073448546739983e-05,
947
+ "loss": 0.0003,
948
+ "step": 6700
949
+ },
950
+ {
951
+ "epoch": 1.3256087981146898,
952
+ "grad_norm": 0.0011626353953033686,
953
+ "learning_rate": 2.7909793139565333e-05,
954
+ "loss": 0.0001,
955
+ "step": 6750
956
+ },
957
+ {
958
+ "epoch": 1.335428122545169,
959
+ "grad_norm": 0.0003097439184784889,
960
+ "learning_rate": 2.774613773239068e-05,
961
+ "loss": 0.0002,
962
+ "step": 6800
963
+ },
964
+ {
965
+ "epoch": 1.3452474469756481,
966
+ "grad_norm": 5.218560909270309e-05,
967
+ "learning_rate": 2.7582482325216026e-05,
968
+ "loss": 0.0002,
969
+ "step": 6850
970
+ },
971
+ {
972
+ "epoch": 1.3550667714061273,
973
+ "grad_norm": 4.878486288362183e-05,
974
+ "learning_rate": 2.7418826918041373e-05,
975
+ "loss": 0.0002,
976
+ "step": 6900
977
+ },
978
+ {
979
+ "epoch": 1.3648860958366065,
980
+ "grad_norm": 1.3592688446806278e-05,
981
+ "learning_rate": 2.7255171510866723e-05,
982
+ "loss": 0.0003,
983
+ "step": 6950
984
+ },
985
+ {
986
+ "epoch": 1.3747054202670856,
987
+ "grad_norm": 0.0010299599962309003,
988
+ "learning_rate": 2.7091516103692066e-05,
989
+ "loss": 0.0003,
990
+ "step": 7000
991
+ },
992
+ {
993
+ "epoch": 1.3845247446975648,
994
+ "grad_norm": 0.005047979764640331,
995
+ "learning_rate": 2.6927860696517416e-05,
996
+ "loss": 0.0003,
997
+ "step": 7050
998
+ },
999
+ {
1000
+ "epoch": 1.394344069128044,
1001
+ "grad_norm": 0.00903361290693283,
1002
+ "learning_rate": 2.676420528934276e-05,
1003
+ "loss": 0.0005,
1004
+ "step": 7100
1005
+ },
1006
+ {
1007
+ "epoch": 1.4041633935585232,
1008
+ "grad_norm": 0.00216244556941092,
1009
+ "learning_rate": 2.660054988216811e-05,
1010
+ "loss": 0.0004,
1011
+ "step": 7150
1012
+ },
1013
+ {
1014
+ "epoch": 1.4139827179890023,
1015
+ "grad_norm": 0.008215115405619144,
1016
+ "learning_rate": 2.6436894474993455e-05,
1017
+ "loss": 0.0003,
1018
+ "step": 7200
1019
+ },
1020
+ {
1021
+ "epoch": 1.4238020424194815,
1022
+ "grad_norm": 0.00024291670706588775,
1023
+ "learning_rate": 2.62732390678188e-05,
1024
+ "loss": 0.0003,
1025
+ "step": 7250
1026
+ },
1027
+ {
1028
+ "epoch": 1.4336213668499607,
1029
+ "grad_norm": 0.004875461105257273,
1030
+ "learning_rate": 2.610958366064415e-05,
1031
+ "loss": 0.0003,
1032
+ "step": 7300
1033
+ },
1034
+ {
1035
+ "epoch": 1.4434406912804398,
1036
+ "grad_norm": 0.000312354473862797,
1037
+ "learning_rate": 2.59459282534695e-05,
1038
+ "loss": 0.0003,
1039
+ "step": 7350
1040
+ },
1041
+ {
1042
+ "epoch": 1.453260015710919,
1043
+ "grad_norm": 8.923052519094199e-05,
1044
+ "learning_rate": 2.578227284629484e-05,
1045
+ "loss": 0.0004,
1046
+ "step": 7400
1047
+ },
1048
+ {
1049
+ "epoch": 1.4630793401413982,
1050
+ "grad_norm": 0.008472305722534657,
1051
+ "learning_rate": 2.561861743912019e-05,
1052
+ "loss": 0.0003,
1053
+ "step": 7450
1054
+ },
1055
+ {
1056
+ "epoch": 1.4728986645718773,
1057
+ "grad_norm": 4.937009362038225e-05,
1058
+ "learning_rate": 2.5454962031945535e-05,
1059
+ "loss": 0.0002,
1060
+ "step": 7500
1061
+ },
1062
+ {
1063
+ "epoch": 1.4827179890023565,
1064
+ "grad_norm": 0.0038520190864801407,
1065
+ "learning_rate": 2.5291306624770885e-05,
1066
+ "loss": 0.0003,
1067
+ "step": 7550
1068
+ },
1069
+ {
1070
+ "epoch": 1.4925373134328357,
1071
+ "grad_norm": 0.002998525742441416,
1072
+ "learning_rate": 2.512765121759623e-05,
1073
+ "loss": 0.0003,
1074
+ "step": 7600
1075
+ },
1076
+ {
1077
+ "epoch": 1.5023566378633149,
1078
+ "grad_norm": 0.0005952705978415906,
1079
+ "learning_rate": 2.4963995810421578e-05,
1080
+ "loss": 0.0003,
1081
+ "step": 7650
1082
+ },
1083
+ {
1084
+ "epoch": 1.512175962293794,
1085
+ "grad_norm": 2.007077455346007e-05,
1086
+ "learning_rate": 2.4800340403246924e-05,
1087
+ "loss": 0.0002,
1088
+ "step": 7700
1089
+ },
1090
+ {
1091
+ "epoch": 1.5219952867242734,
1092
+ "grad_norm": 0.002962449798360467,
1093
+ "learning_rate": 2.463668499607227e-05,
1094
+ "loss": 0.0003,
1095
+ "step": 7750
1096
+ },
1097
+ {
1098
+ "epoch": 1.5318146111547526,
1099
+ "grad_norm": 3.4512224374338984e-05,
1100
+ "learning_rate": 2.447302958889762e-05,
1101
+ "loss": 0.0002,
1102
+ "step": 7800
1103
+ },
1104
+ {
1105
+ "epoch": 1.5416339355852318,
1106
+ "grad_norm": 5.3643165301764384e-05,
1107
+ "learning_rate": 2.4309374181722967e-05,
1108
+ "loss": 0.0002,
1109
+ "step": 7850
1110
+ },
1111
+ {
1112
+ "epoch": 1.551453260015711,
1113
+ "grad_norm": 4.536865890258923e-05,
1114
+ "learning_rate": 2.4145718774548314e-05,
1115
+ "loss": 0.0003,
1116
+ "step": 7900
1117
+ },
1118
+ {
1119
+ "epoch": 1.56127258444619,
1120
+ "grad_norm": 0.0017064092680811882,
1121
+ "learning_rate": 2.3982063367373657e-05,
1122
+ "loss": 0.0003,
1123
+ "step": 7950
1124
+ },
1125
+ {
1126
+ "epoch": 1.5710919088766693,
1127
+ "grad_norm": 0.0028170356526970863,
1128
+ "learning_rate": 2.3818407960199007e-05,
1129
+ "loss": 0.0003,
1130
+ "step": 8000
1131
+ },
1132
+ {
1133
+ "epoch": 1.5809112333071484,
1134
+ "grad_norm": 6.762581324437633e-05,
1135
+ "learning_rate": 2.3654752553024353e-05,
1136
+ "loss": 0.0003,
1137
+ "step": 8050
1138
+ },
1139
+ {
1140
+ "epoch": 1.5907305577376276,
1141
+ "grad_norm": 5.572327063418925e-05,
1142
+ "learning_rate": 2.34910971458497e-05,
1143
+ "loss": 0.0001,
1144
+ "step": 8100
1145
+ },
1146
+ {
1147
+ "epoch": 1.6005498821681068,
1148
+ "grad_norm": 4.8497397074243054e-05,
1149
+ "learning_rate": 2.3327441738675046e-05,
1150
+ "loss": 0.0003,
1151
+ "step": 8150
1152
+ },
1153
+ {
1154
+ "epoch": 1.6103692065985862,
1155
+ "grad_norm": 0.000499077548738569,
1156
+ "learning_rate": 2.3163786331500396e-05,
1157
+ "loss": 0.0003,
1158
+ "step": 8200
1159
+ },
1160
+ {
1161
+ "epoch": 1.6201885310290653,
1162
+ "grad_norm": 0.0007215180085040629,
1163
+ "learning_rate": 2.3000130924325743e-05,
1164
+ "loss": 0.0003,
1165
+ "step": 8250
1166
+ },
1167
+ {
1168
+ "epoch": 1.6300078554595445,
1169
+ "grad_norm": 0.00015634812007192522,
1170
+ "learning_rate": 2.2836475517151086e-05,
1171
+ "loss": 0.0002,
1172
+ "step": 8300
1173
+ },
1174
+ {
1175
+ "epoch": 1.6398271798900237,
1176
+ "grad_norm": 0.010850101709365845,
1177
+ "learning_rate": 2.2672820109976432e-05,
1178
+ "loss": 0.0002,
1179
+ "step": 8350
1180
+ },
1181
+ {
1182
+ "epoch": 1.6496465043205029,
1183
+ "grad_norm": 0.0009706264827400446,
1184
+ "learning_rate": 2.2509164702801782e-05,
1185
+ "loss": 0.0004,
1186
+ "step": 8400
1187
+ },
1188
+ {
1189
+ "epoch": 1.659465828750982,
1190
+ "grad_norm": 3.204784661647864e-05,
1191
+ "learning_rate": 2.234550929562713e-05,
1192
+ "loss": 0.0003,
1193
+ "step": 8450
1194
+ },
1195
+ {
1196
+ "epoch": 1.6692851531814612,
1197
+ "grad_norm": 0.009143730625510216,
1198
+ "learning_rate": 2.2181853888452475e-05,
1199
+ "loss": 0.0003,
1200
+ "step": 8500
1201
+ },
1202
+ {
1203
+ "epoch": 1.6791044776119404,
1204
+ "grad_norm": 0.005089063663035631,
1205
+ "learning_rate": 2.2018198481277822e-05,
1206
+ "loss": 0.0004,
1207
+ "step": 8550
1208
+ },
1209
+ {
1210
+ "epoch": 1.6889238020424195,
1211
+ "grad_norm": 0.0249613169580698,
1212
+ "learning_rate": 2.1854543074103172e-05,
1213
+ "loss": 0.0003,
1214
+ "step": 8600
1215
+ },
1216
+ {
1217
+ "epoch": 1.6987431264728987,
1218
+ "grad_norm": 0.000527512573171407,
1219
+ "learning_rate": 2.1690887666928515e-05,
1220
+ "loss": 0.0003,
1221
+ "step": 8650
1222
+ },
1223
+ {
1224
+ "epoch": 1.7085624509033779,
1225
+ "grad_norm": 0.0011643558973446488,
1226
+ "learning_rate": 2.152723225975386e-05,
1227
+ "loss": 0.0001,
1228
+ "step": 8700
1229
+ },
1230
+ {
1231
+ "epoch": 1.718381775333857,
1232
+ "grad_norm": 0.0030941637232899666,
1233
+ "learning_rate": 2.1363576852579208e-05,
1234
+ "loss": 0.0002,
1235
+ "step": 8750
1236
+ },
1237
+ {
1238
+ "epoch": 1.7282010997643362,
1239
+ "grad_norm": 2.4613122150185518e-05,
1240
+ "learning_rate": 2.1199921445404558e-05,
1241
+ "loss": 0.0002,
1242
+ "step": 8800
1243
+ },
1244
+ {
1245
+ "epoch": 1.7380204241948154,
1246
+ "grad_norm": 0.009969648905098438,
1247
+ "learning_rate": 2.1036266038229905e-05,
1248
+ "loss": 0.0003,
1249
+ "step": 8850
1250
+ },
1251
+ {
1252
+ "epoch": 1.7478397486252946,
1253
+ "grad_norm": 0.0028629146981984377,
1254
+ "learning_rate": 2.087261063105525e-05,
1255
+ "loss": 0.0003,
1256
+ "step": 8900
1257
+ },
1258
+ {
1259
+ "epoch": 1.7576590730557737,
1260
+ "grad_norm": 0.005532170180231333,
1261
+ "learning_rate": 2.0708955223880598e-05,
1262
+ "loss": 0.0002,
1263
+ "step": 8950
1264
+ },
1265
+ {
1266
+ "epoch": 1.767478397486253,
1267
+ "grad_norm": 0.0001023332224576734,
1268
+ "learning_rate": 2.0545299816705944e-05,
1269
+ "loss": 0.0004,
1270
+ "step": 9000
1271
+ },
1272
+ {
1273
+ "epoch": 1.777297721916732,
1274
+ "grad_norm": 0.0016099640633910894,
1275
+ "learning_rate": 2.038164440953129e-05,
1276
+ "loss": 0.0002,
1277
+ "step": 9050
1278
+ },
1279
+ {
1280
+ "epoch": 1.7871170463472112,
1281
+ "grad_norm": 0.00755878584459424,
1282
+ "learning_rate": 2.0217989002356637e-05,
1283
+ "loss": 0.0003,
1284
+ "step": 9100
1285
+ },
1286
+ {
1287
+ "epoch": 1.7969363707776904,
1288
+ "grad_norm": 0.00131377880461514,
1289
+ "learning_rate": 2.0054333595181984e-05,
1290
+ "loss": 0.0003,
1291
+ "step": 9150
1292
+ },
1293
+ {
1294
+ "epoch": 1.8067556952081696,
1295
+ "grad_norm": 0.0066925594583153725,
1296
+ "learning_rate": 1.9890678188007334e-05,
1297
+ "loss": 0.0003,
1298
+ "step": 9200
1299
+ },
1300
+ {
1301
+ "epoch": 1.8165750196386488,
1302
+ "grad_norm": 0.0016435191500931978,
1303
+ "learning_rate": 1.972702278083268e-05,
1304
+ "loss": 0.0004,
1305
+ "step": 9250
1306
+ },
1307
+ {
1308
+ "epoch": 1.826394344069128,
1309
+ "grad_norm": 0.0049284519627690315,
1310
+ "learning_rate": 1.9563367373658027e-05,
1311
+ "loss": 0.0003,
1312
+ "step": 9300
1313
+ },
1314
+ {
1315
+ "epoch": 1.836213668499607,
1316
+ "grad_norm": 0.007083178497850895,
1317
+ "learning_rate": 1.9399711966483373e-05,
1318
+ "loss": 0.0002,
1319
+ "step": 9350
1320
+ },
1321
+ {
1322
+ "epoch": 1.8460329929300863,
1323
+ "grad_norm": 0.003799445927143097,
1324
+ "learning_rate": 1.923605655930872e-05,
1325
+ "loss": 0.0002,
1326
+ "step": 9400
1327
+ },
1328
+ {
1329
+ "epoch": 1.8558523173605654,
1330
+ "grad_norm": 8.943451575760264e-06,
1331
+ "learning_rate": 1.9072401152134066e-05,
1332
+ "loss": 0.0002,
1333
+ "step": 9450
1334
+ },
1335
+ {
1336
+ "epoch": 1.8656716417910446,
1337
+ "grad_norm": 4.004701168014435e-06,
1338
+ "learning_rate": 1.8908745744959413e-05,
1339
+ "loss": 0.0001,
1340
+ "step": 9500
1341
+ },
1342
+ {
1343
+ "epoch": 1.875490966221524,
1344
+ "grad_norm": 0.0016747256740927696,
1345
+ "learning_rate": 1.8745090337784763e-05,
1346
+ "loss": 0.0003,
1347
+ "step": 9550
1348
+ },
1349
+ {
1350
+ "epoch": 1.8853102906520032,
1351
+ "grad_norm": 0.00582944555208087,
1352
+ "learning_rate": 1.858143493061011e-05,
1353
+ "loss": 0.0003,
1354
+ "step": 9600
1355
+ },
1356
+ {
1357
+ "epoch": 1.8951296150824823,
1358
+ "grad_norm": 5.8452515077078715e-06,
1359
+ "learning_rate": 1.8417779523435456e-05,
1360
+ "loss": 0.0002,
1361
+ "step": 9650
1362
+ },
1363
+ {
1364
+ "epoch": 1.9049489395129615,
1365
+ "grad_norm": 2.22074459088617e-06,
1366
+ "learning_rate": 1.8254124116260802e-05,
1367
+ "loss": 0.0003,
1368
+ "step": 9700
1369
+ },
1370
+ {
1371
+ "epoch": 1.9147682639434407,
1372
+ "grad_norm": 0.0001783396874088794,
1373
+ "learning_rate": 1.809046870908615e-05,
1374
+ "loss": 0.0002,
1375
+ "step": 9750
1376
+ },
1377
+ {
1378
+ "epoch": 1.9245875883739199,
1379
+ "grad_norm": 9.459259308641776e-05,
1380
+ "learning_rate": 1.7926813301911495e-05,
1381
+ "loss": 0.0003,
1382
+ "step": 9800
1383
+ },
1384
+ {
1385
+ "epoch": 1.934406912804399,
1386
+ "grad_norm": 0.001501628546975553,
1387
+ "learning_rate": 1.7763157894736842e-05,
1388
+ "loss": 0.0002,
1389
+ "step": 9850
1390
+ },
1391
+ {
1392
+ "epoch": 1.9442262372348782,
1393
+ "grad_norm": 0.008209704421460629,
1394
+ "learning_rate": 1.759950248756219e-05,
1395
+ "loss": 0.0002,
1396
+ "step": 9900
1397
+ },
1398
+ {
1399
+ "epoch": 1.9540455616653576,
1400
+ "grad_norm": 2.8594949981197715e-05,
1401
+ "learning_rate": 1.743584708038754e-05,
1402
+ "loss": 0.0003,
1403
+ "step": 9950
1404
+ },
1405
+ {
1406
+ "epoch": 1.9638648860958368,
1407
+ "grad_norm": 0.0010227253660559654,
1408
+ "learning_rate": 1.7272191673212885e-05,
1409
+ "loss": 0.0002,
1410
+ "step": 10000
1411
+ },
1412
+ {
1413
+ "epoch": 1.973684210526316,
1414
+ "grad_norm": 1.06588067865232e-05,
1415
+ "learning_rate": 1.710853626603823e-05,
1416
+ "loss": 0.0003,
1417
+ "step": 10050
1418
+ },
1419
+ {
1420
+ "epoch": 1.983503534956795,
1421
+ "grad_norm": 0.0035111424513161182,
1422
+ "learning_rate": 1.6944880858863578e-05,
1423
+ "loss": 0.0003,
1424
+ "step": 10100
1425
+ },
1426
+ {
1427
+ "epoch": 1.9933228593872743,
1428
+ "grad_norm": 7.919372001197189e-05,
1429
+ "learning_rate": 1.6781225451688925e-05,
1430
+ "loss": 0.0002,
1431
+ "step": 10150
1432
+ },
1433
+ {
1434
+ "epoch": 2.0031421838177534,
1435
+ "grad_norm": 0.00608315784484148,
1436
+ "learning_rate": 1.661757004451427e-05,
1437
+ "loss": 0.0002,
1438
+ "step": 10200
1439
+ },
1440
+ {
1441
+ "epoch": 2.0129615082482326,
1442
+ "grad_norm": 6.566229330928763e-06,
1443
+ "learning_rate": 1.6453914637339618e-05,
1444
+ "loss": 0.0002,
1445
+ "step": 10250
1446
+ },
1447
+ {
1448
+ "epoch": 2.022780832678712,
1449
+ "grad_norm": 2.852589432222885e-06,
1450
+ "learning_rate": 1.6290259230164964e-05,
1451
+ "loss": 0.0001,
1452
+ "step": 10300
1453
+ },
1454
+ {
1455
+ "epoch": 2.032600157109191,
1456
+ "grad_norm": 2.3466156562790275e-05,
1457
+ "learning_rate": 1.6126603822990314e-05,
1458
+ "loss": 0.0002,
1459
+ "step": 10350
1460
+ },
1461
+ {
1462
+ "epoch": 2.04241948153967,
1463
+ "grad_norm": 0.006443875841796398,
1464
+ "learning_rate": 1.596294841581566e-05,
1465
+ "loss": 0.0004,
1466
+ "step": 10400
1467
+ },
1468
+ {
1469
+ "epoch": 2.0522388059701493,
1470
+ "grad_norm": 0.0006049483199603856,
1471
+ "learning_rate": 1.5799293008641007e-05,
1472
+ "loss": 0.0002,
1473
+ "step": 10450
1474
+ },
1475
+ {
1476
+ "epoch": 2.0620581304006285,
1477
+ "grad_norm": 0.0022505486849695444,
1478
+ "learning_rate": 1.563563760146635e-05,
1479
+ "loss": 0.0002,
1480
+ "step": 10500
1481
+ },
1482
+ {
1483
+ "epoch": 2.0718774548311076,
1484
+ "grad_norm": 4.880329652223736e-05,
1485
+ "learning_rate": 1.54719821942917e-05,
1486
+ "loss": 0.0002,
1487
+ "step": 10550
1488
+ },
1489
+ {
1490
+ "epoch": 2.081696779261587,
1491
+ "grad_norm": 0.006252319552004337,
1492
+ "learning_rate": 1.5308326787117047e-05,
1493
+ "loss": 0.0003,
1494
+ "step": 10600
1495
+ },
1496
+ {
1497
+ "epoch": 2.091516103692066,
1498
+ "grad_norm": 0.0014218160649761558,
1499
+ "learning_rate": 1.5144671379942393e-05,
1500
+ "loss": 0.0004,
1501
+ "step": 10650
1502
+ },
1503
+ {
1504
+ "epoch": 2.101335428122545,
1505
+ "grad_norm": 1.5717498172307387e-05,
1506
+ "learning_rate": 1.498101597276774e-05,
1507
+ "loss": 0.0003,
1508
+ "step": 10700
1509
+ },
1510
+ {
1511
+ "epoch": 2.1111547525530243,
1512
+ "grad_norm": 2.7057717488787603e-06,
1513
+ "learning_rate": 1.4817360565593088e-05,
1514
+ "loss": 0.0003,
1515
+ "step": 10750
1516
+ },
1517
+ {
1518
+ "epoch": 2.1209740769835035,
1519
+ "grad_norm": 0.003399658016860485,
1520
+ "learning_rate": 1.4653705158418435e-05,
1521
+ "loss": 0.0002,
1522
+ "step": 10800
1523
+ },
1524
+ {
1525
+ "epoch": 2.1307934014139827,
1526
+ "grad_norm": 0.0001567010476719588,
1527
+ "learning_rate": 1.4490049751243781e-05,
1528
+ "loss": 0.0002,
1529
+ "step": 10850
1530
+ },
1531
+ {
1532
+ "epoch": 2.140612725844462,
1533
+ "grad_norm": 1.0206712431681808e-05,
1534
+ "learning_rate": 1.432639434406913e-05,
1535
+ "loss": 0.0002,
1536
+ "step": 10900
1537
+ },
1538
+ {
1539
+ "epoch": 2.150432050274941,
1540
+ "grad_norm": 0.0023415617179125547,
1541
+ "learning_rate": 1.4162738936894476e-05,
1542
+ "loss": 0.0003,
1543
+ "step": 10950
1544
+ },
1545
+ {
1546
+ "epoch": 2.16025137470542,
1547
+ "grad_norm": 9.877283446257934e-05,
1548
+ "learning_rate": 1.3999083529719822e-05,
1549
+ "loss": 0.0002,
1550
+ "step": 11000
1551
+ },
1552
+ {
1553
+ "epoch": 2.1700706991358993,
1554
+ "grad_norm": 0.0009852441726252437,
1555
+ "learning_rate": 1.3835428122545169e-05,
1556
+ "loss": 0.0001,
1557
+ "step": 11050
1558
+ },
1559
+ {
1560
+ "epoch": 2.1798900235663785,
1561
+ "grad_norm": 2.5751623979886062e-05,
1562
+ "learning_rate": 1.3671772715370517e-05,
1563
+ "loss": 0.0002,
1564
+ "step": 11100
1565
+ },
1566
+ {
1567
+ "epoch": 2.1897093479968577,
1568
+ "grad_norm": 0.00046911800745874643,
1569
+ "learning_rate": 1.3508117308195864e-05,
1570
+ "loss": 0.0003,
1571
+ "step": 11150
1572
+ },
1573
+ {
1574
+ "epoch": 2.199528672427337,
1575
+ "grad_norm": 2.548624252085574e-05,
1576
+ "learning_rate": 1.334446190102121e-05,
1577
+ "loss": 0.0003,
1578
+ "step": 11200
1579
+ },
1580
+ {
1581
+ "epoch": 2.209347996857816,
1582
+ "grad_norm": 0.00012927035277243704,
1583
+ "learning_rate": 1.3180806493846557e-05,
1584
+ "loss": 0.0002,
1585
+ "step": 11250
1586
+ },
1587
+ {
1588
+ "epoch": 2.219167321288295,
1589
+ "grad_norm": 5.643380973197054e-06,
1590
+ "learning_rate": 1.3017151086671905e-05,
1591
+ "loss": 0.0002,
1592
+ "step": 11300
1593
+ },
1594
+ {
1595
+ "epoch": 2.2289866457187744,
1596
+ "grad_norm": 0.00517466152086854,
1597
+ "learning_rate": 1.2853495679497251e-05,
1598
+ "loss": 0.0003,
1599
+ "step": 11350
1600
+ },
1601
+ {
1602
+ "epoch": 2.2388059701492535,
1603
+ "grad_norm": 0.0007839313475415111,
1604
+ "learning_rate": 1.2689840272322598e-05,
1605
+ "loss": 0.0002,
1606
+ "step": 11400
1607
+ },
1608
+ {
1609
+ "epoch": 2.2486252945797327,
1610
+ "grad_norm": 0.003385524032637477,
1611
+ "learning_rate": 1.2526184865147945e-05,
1612
+ "loss": 0.0002,
1613
+ "step": 11450
1614
+ },
1615
+ {
1616
+ "epoch": 2.258444619010212,
1617
+ "grad_norm": 0.006902114022523165,
1618
+ "learning_rate": 1.2362529457973291e-05,
1619
+ "loss": 0.0002,
1620
+ "step": 11500
1621
+ },
1622
+ {
1623
+ "epoch": 2.268263943440691,
1624
+ "grad_norm": 0.002237598644569516,
1625
+ "learning_rate": 1.219887405079864e-05,
1626
+ "loss": 0.0002,
1627
+ "step": 11550
1628
+ },
1629
+ {
1630
+ "epoch": 2.27808326787117,
1631
+ "grad_norm": 2.9005691430938896e-06,
1632
+ "learning_rate": 1.2035218643623986e-05,
1633
+ "loss": 0.0002,
1634
+ "step": 11600
1635
+ },
1636
+ {
1637
+ "epoch": 2.28790259230165,
1638
+ "grad_norm": 0.0008452658075839281,
1639
+ "learning_rate": 1.1871563236449332e-05,
1640
+ "loss": 0.0002,
1641
+ "step": 11650
1642
+ },
1643
+ {
1644
+ "epoch": 2.297721916732129,
1645
+ "grad_norm": 0.0014033624902367592,
1646
+ "learning_rate": 1.1707907829274679e-05,
1647
+ "loss": 0.0002,
1648
+ "step": 11700
1649
+ },
1650
+ {
1651
+ "epoch": 2.307541241162608,
1652
+ "grad_norm": 0.001146289287135005,
1653
+ "learning_rate": 1.1544252422100027e-05,
1654
+ "loss": 0.0002,
1655
+ "step": 11750
1656
+ },
1657
+ {
1658
+ "epoch": 2.3173605655930873,
1659
+ "grad_norm": 6.133544957265258e-06,
1660
+ "learning_rate": 1.1380597014925374e-05,
1661
+ "loss": 0.0001,
1662
+ "step": 11800
1663
+ },
1664
+ {
1665
+ "epoch": 2.3271798900235665,
1666
+ "grad_norm": 0.0015589894028380513,
1667
+ "learning_rate": 1.121694160775072e-05,
1668
+ "loss": 0.0004,
1669
+ "step": 11850
1670
+ },
1671
+ {
1672
+ "epoch": 2.3369992144540457,
1673
+ "grad_norm": 0.00035342929186299443,
1674
+ "learning_rate": 1.1053286200576067e-05,
1675
+ "loss": 0.0002,
1676
+ "step": 11900
1677
+ },
1678
+ {
1679
+ "epoch": 2.346818538884525,
1680
+ "grad_norm": 1.368164703308139e-05,
1681
+ "learning_rate": 1.0889630793401415e-05,
1682
+ "loss": 0.0003,
1683
+ "step": 11950
1684
+ },
1685
+ {
1686
+ "epoch": 2.356637863315004,
1687
+ "grad_norm": 0.0021006593015044928,
1688
+ "learning_rate": 1.0725975386226761e-05,
1689
+ "loss": 0.0002,
1690
+ "step": 12000
1691
+ },
1692
+ {
1693
+ "epoch": 2.366457187745483,
1694
+ "grad_norm": 7.3638998401293065e-06,
1695
+ "learning_rate": 1.0562319979052108e-05,
1696
+ "loss": 0.0002,
1697
+ "step": 12050
1698
+ },
1699
+ {
1700
+ "epoch": 2.3762765121759624,
1701
+ "grad_norm": 0.006797213107347488,
1702
+ "learning_rate": 1.0398664571877455e-05,
1703
+ "loss": 0.0002,
1704
+ "step": 12100
1705
+ },
1706
+ {
1707
+ "epoch": 2.3860958366064415,
1708
+ "grad_norm": 0.002575602615252137,
1709
+ "learning_rate": 1.0235009164702803e-05,
1710
+ "loss": 0.0004,
1711
+ "step": 12150
1712
+ },
1713
+ {
1714
+ "epoch": 2.3959151610369207,
1715
+ "grad_norm": 0.0026493787299841642,
1716
+ "learning_rate": 1.007135375752815e-05,
1717
+ "loss": 0.0003,
1718
+ "step": 12200
1719
+ },
1720
+ {
1721
+ "epoch": 2.4057344854674,
1722
+ "grad_norm": 5.164716185390716e-06,
1723
+ "learning_rate": 9.907698350353496e-06,
1724
+ "loss": 0.0003,
1725
+ "step": 12250
1726
+ },
1727
+ {
1728
+ "epoch": 2.415553809897879,
1729
+ "grad_norm": 0.0033771705348044634,
1730
+ "learning_rate": 9.744042943178842e-06,
1731
+ "loss": 0.0003,
1732
+ "step": 12300
1733
+ },
1734
+ {
1735
+ "epoch": 2.425373134328358,
1736
+ "grad_norm": 3.062731593672652e-06,
1737
+ "learning_rate": 9.58038753600419e-06,
1738
+ "loss": 0.0003,
1739
+ "step": 12350
1740
+ },
1741
+ {
1742
+ "epoch": 2.4351924587588374,
1743
+ "grad_norm": 0.002900635125115514,
1744
+ "learning_rate": 9.416732128829537e-06,
1745
+ "loss": 0.0002,
1746
+ "step": 12400
1747
+ },
1748
+ {
1749
+ "epoch": 2.4450117831893166,
1750
+ "grad_norm": 0.005432957783341408,
1751
+ "learning_rate": 9.253076721654884e-06,
1752
+ "loss": 0.0003,
1753
+ "step": 12450
1754
+ },
1755
+ {
1756
+ "epoch": 2.4548311076197957,
1757
+ "grad_norm": 0.0060834819450974464,
1758
+ "learning_rate": 9.089421314480232e-06,
1759
+ "loss": 0.0002,
1760
+ "step": 12500
1761
+ },
1762
+ {
1763
+ "epoch": 2.464650432050275,
1764
+ "grad_norm": 0.0003888920182362199,
1765
+ "learning_rate": 8.925765907305578e-06,
1766
+ "loss": 0.0002,
1767
+ "step": 12550
1768
+ },
1769
+ {
1770
+ "epoch": 2.474469756480754,
1771
+ "grad_norm": 0.0008291418780572712,
1772
+ "learning_rate": 8.762110500130925e-06,
1773
+ "loss": 0.0002,
1774
+ "step": 12600
1775
+ },
1776
+ {
1777
+ "epoch": 2.4842890809112332,
1778
+ "grad_norm": 4.13081716033048e-06,
1779
+ "learning_rate": 8.598455092956271e-06,
1780
+ "loss": 0.0002,
1781
+ "step": 12650
1782
+ },
1783
+ {
1784
+ "epoch": 2.4941084053417124,
1785
+ "grad_norm": 0.0027352613396942616,
1786
+ "learning_rate": 8.43479968578162e-06,
1787
+ "loss": 0.0002,
1788
+ "step": 12700
1789
+ },
1790
+ {
1791
+ "epoch": 2.5039277297721916,
1792
+ "grad_norm": 0.004523648414760828,
1793
+ "learning_rate": 8.271144278606966e-06,
1794
+ "loss": 0.0003,
1795
+ "step": 12750
1796
+ },
1797
+ {
1798
+ "epoch": 2.5137470542026707,
1799
+ "grad_norm": 0.0014511903282254934,
1800
+ "learning_rate": 8.107488871432313e-06,
1801
+ "loss": 0.0002,
1802
+ "step": 12800
1803
+ },
1804
+ {
1805
+ "epoch": 2.52356637863315,
1806
+ "grad_norm": 0.001870101667009294,
1807
+ "learning_rate": 7.94383346425766e-06,
1808
+ "loss": 0.0003,
1809
+ "step": 12850
1810
+ },
1811
+ {
1812
+ "epoch": 2.533385703063629,
1813
+ "grad_norm": 1.8049751133730751e-06,
1814
+ "learning_rate": 7.780178057083008e-06,
1815
+ "loss": 0.0002,
1816
+ "step": 12900
1817
+ },
1818
+ {
1819
+ "epoch": 2.5432050274941083,
1820
+ "grad_norm": 2.639750891830772e-05,
1821
+ "learning_rate": 7.616522649908353e-06,
1822
+ "loss": 0.0002,
1823
+ "step": 12950
1824
+ },
1825
+ {
1826
+ "epoch": 2.5530243519245874,
1827
+ "grad_norm": 0.004915285389870405,
1828
+ "learning_rate": 7.452867242733701e-06,
1829
+ "loss": 0.0003,
1830
+ "step": 13000
1831
+ },
1832
+ {
1833
+ "epoch": 2.562843676355067,
1834
+ "grad_norm": 0.0013427536468952894,
1835
+ "learning_rate": 7.289211835559047e-06,
1836
+ "loss": 0.0002,
1837
+ "step": 13050
1838
+ },
1839
+ {
1840
+ "epoch": 2.572663000785546,
1841
+ "grad_norm": 0.006909032352268696,
1842
+ "learning_rate": 7.1255564283843945e-06,
1843
+ "loss": 0.0002,
1844
+ "step": 13100
1845
+ },
1846
+ {
1847
+ "epoch": 2.5824823252160254,
1848
+ "grad_norm": 0.004452712833881378,
1849
+ "learning_rate": 6.961901021209741e-06,
1850
+ "loss": 0.0002,
1851
+ "step": 13150
1852
+ },
1853
+ {
1854
+ "epoch": 2.5923016496465046,
1855
+ "grad_norm": 1.5004067108748131e-06,
1856
+ "learning_rate": 6.798245614035088e-06,
1857
+ "loss": 0.0002,
1858
+ "step": 13200
1859
+ },
1860
+ {
1861
+ "epoch": 2.6021209740769837,
1862
+ "grad_norm": 9.272382158087566e-06,
1863
+ "learning_rate": 6.634590206860435e-06,
1864
+ "loss": 0.0002,
1865
+ "step": 13250
1866
+ },
1867
+ {
1868
+ "epoch": 2.611940298507463,
1869
+ "grad_norm": 0.004868045449256897,
1870
+ "learning_rate": 6.470934799685782e-06,
1871
+ "loss": 0.0002,
1872
+ "step": 13300
1873
+ },
1874
+ {
1875
+ "epoch": 2.621759622937942,
1876
+ "grad_norm": 6.646020665357355e-06,
1877
+ "learning_rate": 6.307279392511129e-06,
1878
+ "loss": 0.0002,
1879
+ "step": 13350
1880
+ },
1881
+ {
1882
+ "epoch": 2.6315789473684212,
1883
+ "grad_norm": 0.0015008870977908373,
1884
+ "learning_rate": 6.143623985336476e-06,
1885
+ "loss": 0.0003,
1886
+ "step": 13400
1887
+ },
1888
+ {
1889
+ "epoch": 2.6413982717989004,
1890
+ "grad_norm": 0.0031040972098708153,
1891
+ "learning_rate": 5.979968578161823e-06,
1892
+ "loss": 0.0003,
1893
+ "step": 13450
1894
+ },
1895
+ {
1896
+ "epoch": 2.6512175962293796,
1897
+ "grad_norm": 0.0015553946141153574,
1898
+ "learning_rate": 5.81631317098717e-06,
1899
+ "loss": 0.0003,
1900
+ "step": 13500
1901
+ },
1902
+ {
1903
+ "epoch": 2.6610369206598588,
1904
+ "grad_norm": 0.0015114744892343879,
1905
+ "learning_rate": 5.652657763812517e-06,
1906
+ "loss": 0.0002,
1907
+ "step": 13550
1908
+ },
1909
+ {
1910
+ "epoch": 2.670856245090338,
1911
+ "grad_norm": 0.006511743646115065,
1912
+ "learning_rate": 5.489002356637864e-06,
1913
+ "loss": 0.0002,
1914
+ "step": 13600
1915
+ },
1916
+ {
1917
+ "epoch": 2.680675569520817,
1918
+ "grad_norm": 3.6607066249416675e-06,
1919
+ "learning_rate": 5.3253469494632106e-06,
1920
+ "loss": 0.0002,
1921
+ "step": 13650
1922
+ },
1923
+ {
1924
+ "epoch": 2.6904948939512963,
1925
+ "grad_norm": 0.0008585217874497175,
1926
+ "learning_rate": 5.161691542288558e-06,
1927
+ "loss": 0.0003,
1928
+ "step": 13700
1929
+ },
1930
+ {
1931
+ "epoch": 2.7003142183817754,
1932
+ "grad_norm": 0.0005489959730766714,
1933
+ "learning_rate": 4.9980361351139045e-06,
1934
+ "loss": 0.0003,
1935
+ "step": 13750
1936
+ },
1937
+ {
1938
+ "epoch": 2.7101335428122546,
1939
+ "grad_norm": 3.3158432870550314e-06,
1940
+ "learning_rate": 4.834380727939251e-06,
1941
+ "loss": 0.0002,
1942
+ "step": 13800
1943
+ },
1944
+ {
1945
+ "epoch": 2.7199528672427338,
1946
+ "grad_norm": 0.0030354801565408707,
1947
+ "learning_rate": 4.670725320764598e-06,
1948
+ "loss": 0.0003,
1949
+ "step": 13850
1950
+ },
1951
+ {
1952
+ "epoch": 2.729772191673213,
1953
+ "grad_norm": 3.2985217330860905e-06,
1954
+ "learning_rate": 4.507069913589945e-06,
1955
+ "loss": 0.0002,
1956
+ "step": 13900
1957
+ },
1958
+ {
1959
+ "epoch": 2.739591516103692,
1960
+ "grad_norm": 7.288464257726446e-05,
1961
+ "learning_rate": 4.343414506415292e-06,
1962
+ "loss": 0.0002,
1963
+ "step": 13950
1964
+ },
1965
+ {
1966
+ "epoch": 2.7494108405341713,
1967
+ "grad_norm": 0.0043890466913580894,
1968
+ "learning_rate": 4.179759099240639e-06,
1969
+ "loss": 0.0003,
1970
+ "step": 14000
1971
+ },
1972
+ {
1973
+ "epoch": 2.7592301649646505,
1974
+ "grad_norm": 0.0019504046067595482,
1975
+ "learning_rate": 4.016103692065986e-06,
1976
+ "loss": 0.0002,
1977
+ "step": 14050
1978
+ },
1979
+ {
1980
+ "epoch": 2.7690494893951296,
1981
+ "grad_norm": 0.0015608868561685085,
1982
+ "learning_rate": 3.852448284891333e-06,
1983
+ "loss": 0.0003,
1984
+ "step": 14100
1985
+ },
1986
+ {
1987
+ "epoch": 2.778868813825609,
1988
+ "grad_norm": 0.002886673668399453,
1989
+ "learning_rate": 3.6887928777166797e-06,
1990
+ "loss": 0.0002,
1991
+ "step": 14150
1992
+ },
1993
+ {
1994
+ "epoch": 2.788688138256088,
1995
+ "grad_norm": 0.0009562448249198496,
1996
+ "learning_rate": 3.5251374705420267e-06,
1997
+ "loss": 0.0003,
1998
+ "step": 14200
1999
+ },
2000
+ {
2001
+ "epoch": 2.798507462686567,
2002
+ "grad_norm": 2.2277029074757593e-06,
2003
+ "learning_rate": 3.3614820633673736e-06,
2004
+ "loss": 0.0003,
2005
+ "step": 14250
2006
+ },
2007
+ {
2008
+ "epoch": 2.8083267871170463,
2009
+ "grad_norm": 0.0023437589406967163,
2010
+ "learning_rate": 3.1978266561927206e-06,
2011
+ "loss": 0.0002,
2012
+ "step": 14300
2013
+ },
2014
+ {
2015
+ "epoch": 2.8181461115475255,
2016
+ "grad_norm": 1.8503330920793815e-06,
2017
+ "learning_rate": 3.034171249018068e-06,
2018
+ "loss": 0.0002,
2019
+ "step": 14350
2020
+ },
2021
+ {
2022
+ "epoch": 2.8279654359780046,
2023
+ "grad_norm": 4.966601863998221e-06,
2024
+ "learning_rate": 2.870515841843415e-06,
2025
+ "loss": 0.0002,
2026
+ "step": 14400
2027
+ },
2028
+ {
2029
+ "epoch": 2.837784760408484,
2030
+ "grad_norm": 1.3409814982878743e-06,
2031
+ "learning_rate": 2.706860434668762e-06,
2032
+ "loss": 0.0002,
2033
+ "step": 14450
2034
+ },
2035
+ {
2036
+ "epoch": 2.847604084838963,
2037
+ "grad_norm": 6.203641532920301e-05,
2038
+ "learning_rate": 2.543205027494109e-06,
2039
+ "loss": 0.0002,
2040
+ "step": 14500
2041
+ },
2042
+ {
2043
+ "epoch": 2.857423409269442,
2044
+ "grad_norm": 0.0002616413403302431,
2045
+ "learning_rate": 2.3795496203194553e-06,
2046
+ "loss": 0.0003,
2047
+ "step": 14550
2048
+ },
2049
+ {
2050
+ "epoch": 2.8672427336999213,
2051
+ "grad_norm": 6.303464488155441e-07,
2052
+ "learning_rate": 2.2158942131448023e-06,
2053
+ "loss": 0.0002,
2054
+ "step": 14600
2055
+ },
2056
+ {
2057
+ "epoch": 2.8770620581304005,
2058
+ "grad_norm": 0.0017262320034205914,
2059
+ "learning_rate": 2.0522388059701493e-06,
2060
+ "loss": 0.0003,
2061
+ "step": 14650
2062
+ },
2063
+ {
2064
+ "epoch": 2.8868813825608797,
2065
+ "grad_norm": 0.0033360267989337444,
2066
+ "learning_rate": 1.8885833987954962e-06,
2067
+ "loss": 0.0003,
2068
+ "step": 14700
2069
+ },
2070
+ {
2071
+ "epoch": 2.896700706991359,
2072
+ "grad_norm": 2.7147841592523037e-06,
2073
+ "learning_rate": 1.7249279916208432e-06,
2074
+ "loss": 0.0002,
2075
+ "step": 14750
2076
+ },
2077
+ {
2078
+ "epoch": 2.906520031421838,
2079
+ "grad_norm": 0.0019037205493077636,
2080
+ "learning_rate": 1.5612725844461901e-06,
2081
+ "loss": 0.0002,
2082
+ "step": 14800
2083
+ },
2084
+ {
2085
+ "epoch": 2.916339355852317,
2086
+ "grad_norm": 0.00883456040173769,
2087
+ "learning_rate": 1.397617177271537e-06,
2088
+ "loss": 0.0003,
2089
+ "step": 14850
2090
+ },
2091
+ {
2092
+ "epoch": 2.9261586802827964,
2093
+ "grad_norm": 0.000769551086705178,
2094
+ "learning_rate": 1.233961770096884e-06,
2095
+ "loss": 0.0003,
2096
+ "step": 14900
2097
+ },
2098
+ {
2099
+ "epoch": 2.9359780047132755,
2100
+ "grad_norm": 1.074038755177753e-05,
2101
+ "learning_rate": 1.070306362922231e-06,
2102
+ "loss": 0.0002,
2103
+ "step": 14950
2104
+ },
2105
+ {
2106
+ "epoch": 2.9457973291437547,
2107
+ "grad_norm": 0.0046028513461351395,
2108
+ "learning_rate": 9.066509557475779e-07,
2109
+ "loss": 0.0003,
2110
+ "step": 15000
2111
+ }
2112
+ ],
2113
+ "logging_steps": 50,
2114
+ "max_steps": 15276,
2115
+ "num_input_tokens_seen": 0,
2116
+ "num_train_epochs": 3,
2117
+ "save_steps": 500,
2118
+ "stateful_callbacks": {
2119
+ "TrainerControl": {
2120
+ "args": {
2121
+ "should_epoch_stop": false,
2122
+ "should_evaluate": false,
2123
+ "should_log": false,
2124
+ "should_save": true,
2125
+ "should_training_stop": false
2126
+ },
2127
+ "attributes": {}
2128
+ }
2129
+ },
2130
+ "total_flos": 3.653381968625664e+16,
2131
+ "train_batch_size": 4,
2132
+ "trial_name": null,
2133
+ "trial_params": null
2134
+ }
checkpoint-15000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b9fd65cee3abc15d70a7c94fe8a522f4e629ace27426230901f90d3992ccbd
3
+ size 5713
checkpoint-15000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-15276/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "relu",
15
+ "gradient_checkpointing": false,
16
+ "id2label": {
17
+ "0": "LABEL_0"
18
+ },
19
+ "initializer_factor": 1.0,
20
+ "is_encoder_decoder": true,
21
+ "is_gated_act": false,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "layer_norm_epsilon": 1e-06,
26
+ "model_type": "t5",
27
+ "n_positions": 512,
28
+ "num_decoder_layers": 12,
29
+ "num_heads": 12,
30
+ "num_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "relative_attention_max_distance": 128,
34
+ "relative_attention_num_buckets": 32,
35
+ "task_specific_params": {
36
+ "summarization": {
37
+ "early_stopping": true,
38
+ "length_penalty": 2.0,
39
+ "max_length": 200,
40
+ "min_length": 30,
41
+ "no_repeat_ngram_size": 3,
42
+ "num_beams": 4,
43
+ "prefix": "summarize: "
44
+ },
45
+ "translation_en_to_de": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to German: "
50
+ },
51
+ "translation_en_to_fr": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to French: "
56
+ },
57
+ "translation_en_to_ro": {
58
+ "early_stopping": true,
59
+ "max_length": 300,
60
+ "num_beams": 4,
61
+ "prefix": "translate English to Romanian: "
62
+ }
63
+ },
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.55.3",
66
+ "use_cache": true,
67
+ "vocab_size": 32100
68
+ }
checkpoint-15276/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": "4.55.3"
8
+ }
checkpoint-15276/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-15276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d4a857ce818263f64b8eaf40a258d336a29a8112e36e17261e6cf4520ef9f2
3
+ size 891558696
checkpoint-15276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af47c77ede1dfd3de5923d6ad711b754247ba15f1709c46c712c8753064c544
3
+ size 1783276811
checkpoint-15276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de5bbab84b871a5a1bf6d9275c233f2688f88127d4a82ad9080cd9cab89ad2f
3
+ size 14645
checkpoint-15276/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b63d4ef737b703eca4998523a8bc70a377a380d9c28ee27465b53e95359210d
3
+ size 1383
checkpoint-15276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7a999a2ce89f8d86cb231ec289c49164ab92974b766259c7e093c379b68b7c
3
+ size 1465
checkpoint-15276/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
+ }
checkpoint-15276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-15276/tokenizer_config.json ADDED
@@ -0,0 +1,960 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
949
+ "cls_token": "<s>",
950
+ "eos_token": "</s>",
951
+ "errors": "replace",
952
+ "extra_special_tokens": {},
953
+ "mask_token": "<mask>",
954
+ "model_max_length": 512,
955
+ "pad_token": "<pad>",
956
+ "sep_token": "</s>",
957
+ "tokenizer_class": "RobertaTokenizer",
958
+ "trim_offsets": true,
959
+ "unk_token": "<unk>"
960
+ }
checkpoint-15276/trainer_state.json ADDED
@@ -0,0 +1,2169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 15276,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.009819324430479183,
14
+ "grad_norm": 0.24714912474155426,
15
+ "learning_rate": 4.983961770096884e-05,
16
+ "loss": 0.3447,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.019638648860958365,
21
+ "grad_norm": 0.12986360490322113,
22
+ "learning_rate": 4.967596229379419e-05,
23
+ "loss": 0.0057,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.02945797329143755,
28
+ "grad_norm": 0.13787369430065155,
29
+ "learning_rate": 4.9512306886619534e-05,
30
+ "loss": 0.0041,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.03927729772191673,
35
+ "grad_norm": 0.032512035220861435,
36
+ "learning_rate": 4.9348651479444883e-05,
37
+ "loss": 0.0031,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.049096622152395915,
42
+ "grad_norm": 0.04660605266690254,
43
+ "learning_rate": 4.9184996072270227e-05,
44
+ "loss": 0.0017,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.0589159465828751,
49
+ "grad_norm": 0.12520131468772888,
50
+ "learning_rate": 4.9021340665095576e-05,
51
+ "loss": 0.0023,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.06873527101335428,
56
+ "grad_norm": 0.03921537473797798,
57
+ "learning_rate": 4.8857685257920926e-05,
58
+ "loss": 0.0016,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.07855459544383346,
63
+ "grad_norm": 0.019508639350533485,
64
+ "learning_rate": 4.869402985074627e-05,
65
+ "loss": 0.0015,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.08837391987431265,
70
+ "grad_norm": 0.03215921297669411,
71
+ "learning_rate": 4.853037444357162e-05,
72
+ "loss": 0.0018,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.09819324430479183,
77
+ "grad_norm": 0.01678670570254326,
78
+ "learning_rate": 4.836671903639696e-05,
79
+ "loss": 0.0012,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.10801256873527101,
84
+ "grad_norm": 0.04076138511300087,
85
+ "learning_rate": 4.820306362922231e-05,
86
+ "loss": 0.0013,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.1178318931657502,
91
+ "grad_norm": 0.028516946360468864,
92
+ "learning_rate": 4.803940822204766e-05,
93
+ "loss": 0.001,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.12765121759622938,
98
+ "grad_norm": 0.0024934338871389627,
99
+ "learning_rate": 4.7875752814873006e-05,
100
+ "loss": 0.0013,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.13747054202670855,
105
+ "grad_norm": 0.009505635127425194,
106
+ "learning_rate": 4.7712097407698356e-05,
107
+ "loss": 0.0006,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.14728986645718775,
112
+ "grad_norm": 0.004126217681914568,
113
+ "learning_rate": 4.75484420005237e-05,
114
+ "loss": 0.0009,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.15710919088766692,
119
+ "grad_norm": 0.001864357735030353,
120
+ "learning_rate": 4.738478659334905e-05,
121
+ "loss": 0.0006,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.16692851531814612,
126
+ "grad_norm": 0.05715826526284218,
127
+ "learning_rate": 4.722113118617439e-05,
128
+ "loss": 0.0009,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.1767478397486253,
133
+ "grad_norm": 0.01866191253066063,
134
+ "learning_rate": 4.7057475778999735e-05,
135
+ "loss": 0.0008,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.1865671641791045,
140
+ "grad_norm": 0.02309831976890564,
141
+ "learning_rate": 4.6893820371825085e-05,
142
+ "loss": 0.0009,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.19638648860958366,
147
+ "grad_norm": 0.008644412271678448,
148
+ "learning_rate": 4.6730164964650435e-05,
149
+ "loss": 0.0008,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.20620581304006286,
154
+ "grad_norm": 0.0034850463271141052,
155
+ "learning_rate": 4.656650955747578e-05,
156
+ "loss": 0.0008,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.21602513747054203,
161
+ "grad_norm": 0.015649326145648956,
162
+ "learning_rate": 4.640285415030113e-05,
163
+ "loss": 0.0005,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.2258444619010212,
168
+ "grad_norm": 0.017577216029167175,
169
+ "learning_rate": 4.623919874312648e-05,
170
+ "loss": 0.0005,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.2356637863315004,
175
+ "grad_norm": 0.001943176961503923,
176
+ "learning_rate": 4.607554333595182e-05,
177
+ "loss": 0.0006,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.24548311076197957,
182
+ "grad_norm": 0.013552217744290829,
183
+ "learning_rate": 4.591188792877717e-05,
184
+ "loss": 0.0007,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.25530243519245877,
189
+ "grad_norm": 0.0009095704299397767,
190
+ "learning_rate": 4.574823252160252e-05,
191
+ "loss": 0.0006,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.26512175962293794,
196
+ "grad_norm": 0.12323999404907227,
197
+ "learning_rate": 4.5584577114427864e-05,
198
+ "loss": 0.001,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.2749410840534171,
203
+ "grad_norm": 0.0046529932878911495,
204
+ "learning_rate": 4.5420921707253214e-05,
205
+ "loss": 0.0006,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.28476040848389633,
210
+ "grad_norm": 0.0006078369333408773,
211
+ "learning_rate": 4.525726630007856e-05,
212
+ "loss": 0.0005,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.2945797329143755,
217
+ "grad_norm": 0.0011770805576816201,
218
+ "learning_rate": 4.509361089290391e-05,
219
+ "loss": 0.0003,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.3043990573448547,
224
+ "grad_norm": 0.004274972248822451,
225
+ "learning_rate": 4.492995548572925e-05,
226
+ "loss": 0.0005,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.31421838177533384,
231
+ "grad_norm": 0.0007647090242244303,
232
+ "learning_rate": 4.476630007855459e-05,
233
+ "loss": 0.0007,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.324037706205813,
238
+ "grad_norm": 0.013916688971221447,
239
+ "learning_rate": 4.460264467137994e-05,
240
+ "loss": 0.0005,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.33385703063629224,
245
+ "grad_norm": 0.001363221788778901,
246
+ "learning_rate": 4.443898926420529e-05,
247
+ "loss": 0.0004,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.3436763550667714,
252
+ "grad_norm": 0.00033090286888182163,
253
+ "learning_rate": 4.4275333857030636e-05,
254
+ "loss": 0.0004,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.3534956794972506,
259
+ "grad_norm": 0.000668744498398155,
260
+ "learning_rate": 4.4111678449855986e-05,
261
+ "loss": 0.0006,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.36331500392772975,
266
+ "grad_norm": 0.0539139024913311,
267
+ "learning_rate": 4.394802304268133e-05,
268
+ "loss": 0.0005,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.373134328358209,
273
+ "grad_norm": 0.0008487588493153453,
274
+ "learning_rate": 4.378436763550668e-05,
275
+ "loss": 0.0004,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.38295365278868815,
280
+ "grad_norm": 0.0008443322731181979,
281
+ "learning_rate": 4.362071222833203e-05,
282
+ "loss": 0.0006,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.3927729772191673,
287
+ "grad_norm": 0.00504659116268158,
288
+ "learning_rate": 4.345705682115737e-05,
289
+ "loss": 0.0006,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.4025923016496465,
294
+ "grad_norm": 0.19237877428531647,
295
+ "learning_rate": 4.329340141398272e-05,
296
+ "loss": 0.0003,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.4124116260801257,
301
+ "grad_norm": 0.052810050547122955,
302
+ "learning_rate": 4.312974600680807e-05,
303
+ "loss": 0.0007,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.4222309505106049,
308
+ "grad_norm": 0.0010182256810367107,
309
+ "learning_rate": 4.2966090599633415e-05,
310
+ "loss": 0.0006,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.43205027494108406,
315
+ "grad_norm": 0.008011899888515472,
316
+ "learning_rate": 4.2802435192458765e-05,
317
+ "loss": 0.0004,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.4418695993715632,
322
+ "grad_norm": 0.004001118242740631,
323
+ "learning_rate": 4.263877978528411e-05,
324
+ "loss": 0.0003,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.4516889238020424,
329
+ "grad_norm": 0.0005824828986078501,
330
+ "learning_rate": 4.247512437810945e-05,
331
+ "loss": 0.0004,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.4615082482325216,
336
+ "grad_norm": 0.00035399169428274035,
337
+ "learning_rate": 4.23114689709348e-05,
338
+ "loss": 0.0006,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.4713275726630008,
343
+ "grad_norm": 0.0008132366347126663,
344
+ "learning_rate": 4.2147813563760144e-05,
345
+ "loss": 0.0004,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.48114689709347996,
350
+ "grad_norm": 0.00029086056747473776,
351
+ "learning_rate": 4.1984158156585494e-05,
352
+ "loss": 0.0004,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.49096622152395913,
357
+ "grad_norm": 0.009674192406237125,
358
+ "learning_rate": 4.1820502749410844e-05,
359
+ "loss": 0.0003,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.5007855459544384,
364
+ "grad_norm": 0.0002215866988990456,
365
+ "learning_rate": 4.165684734223619e-05,
366
+ "loss": 0.0003,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.5106048703849175,
371
+ "grad_norm": 0.0003756559453904629,
372
+ "learning_rate": 4.149319193506154e-05,
373
+ "loss": 0.0003,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.5204241948153967,
378
+ "grad_norm": 3.785878652706742e-05,
379
+ "learning_rate": 4.132953652788688e-05,
380
+ "loss": 0.0002,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.5302435192458759,
385
+ "grad_norm": 0.007607210893183947,
386
+ "learning_rate": 4.116588112071223e-05,
387
+ "loss": 0.0003,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.540062843676355,
392
+ "grad_norm": 0.02198871783912182,
393
+ "learning_rate": 4.100222571353758e-05,
394
+ "loss": 0.0002,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.5498821681068342,
399
+ "grad_norm": 0.00041103907278738916,
400
+ "learning_rate": 4.0838570306362923e-05,
401
+ "loss": 0.0002,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.5597014925373134,
406
+ "grad_norm": 0.01565481722354889,
407
+ "learning_rate": 4.067491489918827e-05,
408
+ "loss": 0.0003,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.5695208169677927,
413
+ "grad_norm": 0.0117128761485219,
414
+ "learning_rate": 4.051125949201362e-05,
415
+ "loss": 0.0004,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.5793401413982718,
420
+ "grad_norm": 0.004789320752024651,
421
+ "learning_rate": 4.0347604084838966e-05,
422
+ "loss": 0.0004,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.589159465828751,
427
+ "grad_norm": 0.0011219610460102558,
428
+ "learning_rate": 4.018394867766431e-05,
429
+ "loss": 0.0004,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.5989787902592302,
434
+ "grad_norm": 0.0518529899418354,
435
+ "learning_rate": 4.002029327048966e-05,
436
+ "loss": 0.0004,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.6087981146897093,
441
+ "grad_norm": 0.01609092392027378,
442
+ "learning_rate": 3.9856637863315e-05,
443
+ "loss": 0.0003,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.6186174391201885,
448
+ "grad_norm": 0.002343968488276005,
449
+ "learning_rate": 3.969298245614035e-05,
450
+ "loss": 0.0003,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.6284367635506677,
455
+ "grad_norm": 0.010258428752422333,
456
+ "learning_rate": 3.9529327048965696e-05,
457
+ "loss": 0.0003,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.6382560879811469,
462
+ "grad_norm": 0.0007253732765093446,
463
+ "learning_rate": 3.9365671641791046e-05,
464
+ "loss": 0.0004,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.648075412411626,
469
+ "grad_norm": 0.01221112348139286,
470
+ "learning_rate": 3.9202016234616395e-05,
471
+ "loss": 0.0003,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.6578947368421053,
476
+ "grad_norm": 0.007547037675976753,
477
+ "learning_rate": 3.903836082744174e-05,
478
+ "loss": 0.0004,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.6677140612725845,
483
+ "grad_norm": 0.0037480357568711042,
484
+ "learning_rate": 3.887470542026709e-05,
485
+ "loss": 0.0003,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.6775333857030637,
490
+ "grad_norm": 9.382007556268945e-05,
491
+ "learning_rate": 3.871105001309244e-05,
492
+ "loss": 0.0005,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.6873527101335428,
497
+ "grad_norm": 0.0019377778517082334,
498
+ "learning_rate": 3.854739460591778e-05,
499
+ "loss": 0.0003,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.697172034564022,
504
+ "grad_norm": 0.00031467623193748295,
505
+ "learning_rate": 3.838373919874313e-05,
506
+ "loss": 0.0003,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.7069913589945012,
511
+ "grad_norm": 0.012330332770943642,
512
+ "learning_rate": 3.8220083791568475e-05,
513
+ "loss": 0.0004,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.7168106834249803,
518
+ "grad_norm": 0.43893539905548096,
519
+ "learning_rate": 3.8056428384393825e-05,
520
+ "loss": 0.002,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.7266300078554595,
525
+ "grad_norm": 0.010738670825958252,
526
+ "learning_rate": 3.789277297721917e-05,
527
+ "loss": 0.0008,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.7364493322859387,
532
+ "grad_norm": 0.0009258920326828957,
533
+ "learning_rate": 3.772911757004452e-05,
534
+ "loss": 0.0005,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.746268656716418,
539
+ "grad_norm": 0.002003765432164073,
540
+ "learning_rate": 3.756546216286986e-05,
541
+ "loss": 0.0004,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.7560879811468971,
546
+ "grad_norm": 0.0003309960593469441,
547
+ "learning_rate": 3.740180675569521e-05,
548
+ "loss": 0.0004,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.7659073055773763,
553
+ "grad_norm": 0.014759145677089691,
554
+ "learning_rate": 3.7238151348520554e-05,
555
+ "loss": 0.0004,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.7757266300078555,
560
+ "grad_norm": 0.00703453179448843,
561
+ "learning_rate": 3.7074495941345904e-05,
562
+ "loss": 0.0005,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.7855459544383346,
567
+ "grad_norm": 0.0093814292922616,
568
+ "learning_rate": 3.691084053417125e-05,
569
+ "loss": 0.0004,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.7953652788688138,
574
+ "grad_norm": 0.00033789846929721534,
575
+ "learning_rate": 3.67471851269966e-05,
576
+ "loss": 0.0003,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.805184603299293,
581
+ "grad_norm": 0.004072342533618212,
582
+ "learning_rate": 3.658352971982195e-05,
583
+ "loss": 0.0004,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.8150039277297721,
588
+ "grad_norm": 0.005905472207814455,
589
+ "learning_rate": 3.641987431264729e-05,
590
+ "loss": 0.0004,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.8248232521602514,
595
+ "grad_norm": 0.008759435266256332,
596
+ "learning_rate": 3.625621890547264e-05,
597
+ "loss": 0.0004,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.8346425765907306,
602
+ "grad_norm": 0.01638154312968254,
603
+ "learning_rate": 3.609256349829799e-05,
604
+ "loss": 0.0003,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.8444619010212098,
609
+ "grad_norm": 0.003001204691827297,
610
+ "learning_rate": 3.592890809112333e-05,
611
+ "loss": 0.0004,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.8542812254516889,
616
+ "grad_norm": 0.0006073117256164551,
617
+ "learning_rate": 3.576525268394868e-05,
618
+ "loss": 0.0003,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.8641005498821681,
623
+ "grad_norm": 0.003654340049251914,
624
+ "learning_rate": 3.5601597276774026e-05,
625
+ "loss": 0.0005,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.8739198743126473,
630
+ "grad_norm": 0.2316829115152359,
631
+ "learning_rate": 3.5437941869599376e-05,
632
+ "loss": 0.0005,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.8837391987431265,
637
+ "grad_norm": 0.027139848098158836,
638
+ "learning_rate": 3.527428646242472e-05,
639
+ "loss": 0.0005,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.8935585231736056,
644
+ "grad_norm": 0.004498090595006943,
645
+ "learning_rate": 3.511063105525006e-05,
646
+ "loss": 0.0004,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.9033778476040848,
651
+ "grad_norm": 0.010397707112133503,
652
+ "learning_rate": 3.494697564807541e-05,
653
+ "loss": 0.0003,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.9131971720345641,
658
+ "grad_norm": 0.00014255594578571618,
659
+ "learning_rate": 3.478332024090076e-05,
660
+ "loss": 0.0003,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.9230164964650432,
665
+ "grad_norm": 0.0028459234163165092,
666
+ "learning_rate": 3.4619664833726105e-05,
667
+ "loss": 0.0003,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.9328358208955224,
672
+ "grad_norm": 0.0030736555345356464,
673
+ "learning_rate": 3.4456009426551455e-05,
674
+ "loss": 0.0002,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.9426551453260016,
679
+ "grad_norm": 0.0026709907688200474,
680
+ "learning_rate": 3.4292354019376805e-05,
681
+ "loss": 0.0003,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.9524744697564808,
686
+ "grad_norm": 0.00022516479657497257,
687
+ "learning_rate": 3.412869861220215e-05,
688
+ "loss": 0.0003,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.9622937941869599,
693
+ "grad_norm": 2.6079122108058073e-05,
694
+ "learning_rate": 3.39650432050275e-05,
695
+ "loss": 0.0002,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.9721131186174391,
700
+ "grad_norm": 0.0010724954772740602,
701
+ "learning_rate": 3.380138779785284e-05,
702
+ "loss": 0.0003,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 0.9819324430479183,
707
+ "grad_norm": 0.00028140624635852873,
708
+ "learning_rate": 3.363773239067819e-05,
709
+ "loss": 0.0004,
710
+ "step": 5000
711
+ },
712
+ {
713
+ "epoch": 0.9917517674783974,
714
+ "grad_norm": 0.002564377384260297,
715
+ "learning_rate": 3.347407698350354e-05,
716
+ "loss": 0.0003,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 1.0015710919088767,
721
+ "grad_norm": 0.0027151070535182953,
722
+ "learning_rate": 3.3310421576328884e-05,
723
+ "loss": 0.0002,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 1.011390416339356,
728
+ "grad_norm": 0.0002080993290292099,
729
+ "learning_rate": 3.3146766169154234e-05,
730
+ "loss": 0.0003,
731
+ "step": 5150
732
+ },
733
+ {
734
+ "epoch": 1.021209740769835,
735
+ "grad_norm": 3.149580516037531e-05,
736
+ "learning_rate": 3.298311076197958e-05,
737
+ "loss": 0.0003,
738
+ "step": 5200
739
+ },
740
+ {
741
+ "epoch": 1.0310290652003142,
742
+ "grad_norm": 0.005241520702838898,
743
+ "learning_rate": 3.281945535480492e-05,
744
+ "loss": 0.0003,
745
+ "step": 5250
746
+ },
747
+ {
748
+ "epoch": 1.0408483896307934,
749
+ "grad_norm": 0.005873743910342455,
750
+ "learning_rate": 3.265579994763027e-05,
751
+ "loss": 0.0002,
752
+ "step": 5300
753
+ },
754
+ {
755
+ "epoch": 1.0506677140612726,
756
+ "grad_norm": 0.006296052597463131,
757
+ "learning_rate": 3.2492144540455613e-05,
758
+ "loss": 0.0003,
759
+ "step": 5350
760
+ },
761
+ {
762
+ "epoch": 1.0604870384917517,
763
+ "grad_norm": 0.00039794211625121534,
764
+ "learning_rate": 3.232848913328096e-05,
765
+ "loss": 0.0004,
766
+ "step": 5400
767
+ },
768
+ {
769
+ "epoch": 1.070306362922231,
770
+ "grad_norm": 0.0039017247036099434,
771
+ "learning_rate": 3.216483372610631e-05,
772
+ "loss": 0.0003,
773
+ "step": 5450
774
+ },
775
+ {
776
+ "epoch": 1.08012568735271,
777
+ "grad_norm": 0.002064199186861515,
778
+ "learning_rate": 3.2001178318931656e-05,
779
+ "loss": 0.0003,
780
+ "step": 5500
781
+ },
782
+ {
783
+ "epoch": 1.0899450117831893,
784
+ "grad_norm": 0.0002229887613793835,
785
+ "learning_rate": 3.1837522911757006e-05,
786
+ "loss": 0.0003,
787
+ "step": 5550
788
+ },
789
+ {
790
+ "epoch": 1.0997643362136684,
791
+ "grad_norm": 3.4759577829390764e-05,
792
+ "learning_rate": 3.1673867504582356e-05,
793
+ "loss": 0.0004,
794
+ "step": 5600
795
+ },
796
+ {
797
+ "epoch": 1.1095836606441476,
798
+ "grad_norm": 2.991587643919047e-05,
799
+ "learning_rate": 3.15102120974077e-05,
800
+ "loss": 0.0002,
801
+ "step": 5650
802
+ },
803
+ {
804
+ "epoch": 1.1194029850746268,
805
+ "grad_norm": 0.0017788242548704147,
806
+ "learning_rate": 3.134655669023305e-05,
807
+ "loss": 0.0003,
808
+ "step": 5700
809
+ },
810
+ {
811
+ "epoch": 1.129222309505106,
812
+ "grad_norm": 0.008592754602432251,
813
+ "learning_rate": 3.118290128305839e-05,
814
+ "loss": 0.0003,
815
+ "step": 5750
816
+ },
817
+ {
818
+ "epoch": 1.139041633935585,
819
+ "grad_norm": 0.0017567313043400645,
820
+ "learning_rate": 3.101924587588374e-05,
821
+ "loss": 0.0003,
822
+ "step": 5800
823
+ },
824
+ {
825
+ "epoch": 1.1488609583660645,
826
+ "grad_norm": 8.339332271134481e-05,
827
+ "learning_rate": 3.085559046870909e-05,
828
+ "loss": 0.0002,
829
+ "step": 5850
830
+ },
831
+ {
832
+ "epoch": 1.1586802827965437,
833
+ "grad_norm": 0.00681919464841485,
834
+ "learning_rate": 3.0691935061534435e-05,
835
+ "loss": 0.0003,
836
+ "step": 5900
837
+ },
838
+ {
839
+ "epoch": 1.1684996072270228,
840
+ "grad_norm": 1.7358417608193122e-05,
841
+ "learning_rate": 3.052827965435978e-05,
842
+ "loss": 0.0002,
843
+ "step": 5950
844
+ },
845
+ {
846
+ "epoch": 1.178318931657502,
847
+ "grad_norm": 0.005276073236018419,
848
+ "learning_rate": 3.0364624247185132e-05,
849
+ "loss": 0.0003,
850
+ "step": 6000
851
+ },
852
+ {
853
+ "epoch": 1.1881382560879812,
854
+ "grad_norm": 1.6649060853524134e-05,
855
+ "learning_rate": 3.0200968840010475e-05,
856
+ "loss": 0.0003,
857
+ "step": 6050
858
+ },
859
+ {
860
+ "epoch": 1.1979575805184604,
861
+ "grad_norm": 1.6310365026583895e-05,
862
+ "learning_rate": 3.003731343283582e-05,
863
+ "loss": 0.0001,
864
+ "step": 6100
865
+ },
866
+ {
867
+ "epoch": 1.2077769049489395,
868
+ "grad_norm": 8.225607598433271e-05,
869
+ "learning_rate": 2.987365802566117e-05,
870
+ "loss": 0.0003,
871
+ "step": 6150
872
+ },
873
+ {
874
+ "epoch": 1.2175962293794187,
875
+ "grad_norm": 0.06942308694124222,
876
+ "learning_rate": 2.9710002618486515e-05,
877
+ "loss": 0.0006,
878
+ "step": 6200
879
+ },
880
+ {
881
+ "epoch": 1.2274155538098979,
882
+ "grad_norm": 0.0003915784473065287,
883
+ "learning_rate": 2.9546347211311865e-05,
884
+ "loss": 0.0008,
885
+ "step": 6250
886
+ },
887
+ {
888
+ "epoch": 1.237234878240377,
889
+ "grad_norm": 5.1170645747333765e-05,
890
+ "learning_rate": 2.9382691804137208e-05,
891
+ "loss": 0.0004,
892
+ "step": 6300
893
+ },
894
+ {
895
+ "epoch": 1.2470542026708562,
896
+ "grad_norm": 0.005075642839074135,
897
+ "learning_rate": 2.9219036396962558e-05,
898
+ "loss": 0.0006,
899
+ "step": 6350
900
+ },
901
+ {
902
+ "epoch": 1.2568735271013354,
903
+ "grad_norm": 0.013923396356403828,
904
+ "learning_rate": 2.9055380989787908e-05,
905
+ "loss": 0.0003,
906
+ "step": 6400
907
+ },
908
+ {
909
+ "epoch": 1.2666928515318145,
910
+ "grad_norm": 0.010688439942896366,
911
+ "learning_rate": 2.889172558261325e-05,
912
+ "loss": 0.0004,
913
+ "step": 6450
914
+ },
915
+ {
916
+ "epoch": 1.2765121759622937,
917
+ "grad_norm": 0.005004653707146645,
918
+ "learning_rate": 2.8728070175438597e-05,
919
+ "loss": 0.0002,
920
+ "step": 6500
921
+ },
922
+ {
923
+ "epoch": 1.286331500392773,
924
+ "grad_norm": 0.015412525273859501,
925
+ "learning_rate": 2.8564414768263947e-05,
926
+ "loss": 0.0003,
927
+ "step": 6550
928
+ },
929
+ {
930
+ "epoch": 1.2961508248232523,
931
+ "grad_norm": 0.002696032403036952,
932
+ "learning_rate": 2.840075936108929e-05,
933
+ "loss": 0.0002,
934
+ "step": 6600
935
+ },
936
+ {
937
+ "epoch": 1.3059701492537314,
938
+ "grad_norm": 0.0005274811992421746,
939
+ "learning_rate": 2.823710395391464e-05,
940
+ "loss": 0.0003,
941
+ "step": 6650
942
+ },
943
+ {
944
+ "epoch": 1.3157894736842106,
945
+ "grad_norm": 2.0785410015378147e-05,
946
+ "learning_rate": 2.8073448546739983e-05,
947
+ "loss": 0.0003,
948
+ "step": 6700
949
+ },
950
+ {
951
+ "epoch": 1.3256087981146898,
952
+ "grad_norm": 0.0011626353953033686,
953
+ "learning_rate": 2.7909793139565333e-05,
954
+ "loss": 0.0001,
955
+ "step": 6750
956
+ },
957
+ {
958
+ "epoch": 1.335428122545169,
959
+ "grad_norm": 0.0003097439184784889,
960
+ "learning_rate": 2.774613773239068e-05,
961
+ "loss": 0.0002,
962
+ "step": 6800
963
+ },
964
+ {
965
+ "epoch": 1.3452474469756481,
966
+ "grad_norm": 5.218560909270309e-05,
967
+ "learning_rate": 2.7582482325216026e-05,
968
+ "loss": 0.0002,
969
+ "step": 6850
970
+ },
971
+ {
972
+ "epoch": 1.3550667714061273,
973
+ "grad_norm": 4.878486288362183e-05,
974
+ "learning_rate": 2.7418826918041373e-05,
975
+ "loss": 0.0002,
976
+ "step": 6900
977
+ },
978
+ {
979
+ "epoch": 1.3648860958366065,
980
+ "grad_norm": 1.3592688446806278e-05,
981
+ "learning_rate": 2.7255171510866723e-05,
982
+ "loss": 0.0003,
983
+ "step": 6950
984
+ },
985
+ {
986
+ "epoch": 1.3747054202670856,
987
+ "grad_norm": 0.0010299599962309003,
988
+ "learning_rate": 2.7091516103692066e-05,
989
+ "loss": 0.0003,
990
+ "step": 7000
991
+ },
992
+ {
993
+ "epoch": 1.3845247446975648,
994
+ "grad_norm": 0.005047979764640331,
995
+ "learning_rate": 2.6927860696517416e-05,
996
+ "loss": 0.0003,
997
+ "step": 7050
998
+ },
999
+ {
1000
+ "epoch": 1.394344069128044,
1001
+ "grad_norm": 0.00903361290693283,
1002
+ "learning_rate": 2.676420528934276e-05,
1003
+ "loss": 0.0005,
1004
+ "step": 7100
1005
+ },
1006
+ {
1007
+ "epoch": 1.4041633935585232,
1008
+ "grad_norm": 0.00216244556941092,
1009
+ "learning_rate": 2.660054988216811e-05,
1010
+ "loss": 0.0004,
1011
+ "step": 7150
1012
+ },
1013
+ {
1014
+ "epoch": 1.4139827179890023,
1015
+ "grad_norm": 0.008215115405619144,
1016
+ "learning_rate": 2.6436894474993455e-05,
1017
+ "loss": 0.0003,
1018
+ "step": 7200
1019
+ },
1020
+ {
1021
+ "epoch": 1.4238020424194815,
1022
+ "grad_norm": 0.00024291670706588775,
1023
+ "learning_rate": 2.62732390678188e-05,
1024
+ "loss": 0.0003,
1025
+ "step": 7250
1026
+ },
1027
+ {
1028
+ "epoch": 1.4336213668499607,
1029
+ "grad_norm": 0.004875461105257273,
1030
+ "learning_rate": 2.610958366064415e-05,
1031
+ "loss": 0.0003,
1032
+ "step": 7300
1033
+ },
1034
+ {
1035
+ "epoch": 1.4434406912804398,
1036
+ "grad_norm": 0.000312354473862797,
1037
+ "learning_rate": 2.59459282534695e-05,
1038
+ "loss": 0.0003,
1039
+ "step": 7350
1040
+ },
1041
+ {
1042
+ "epoch": 1.453260015710919,
1043
+ "grad_norm": 8.923052519094199e-05,
1044
+ "learning_rate": 2.578227284629484e-05,
1045
+ "loss": 0.0004,
1046
+ "step": 7400
1047
+ },
1048
+ {
1049
+ "epoch": 1.4630793401413982,
1050
+ "grad_norm": 0.008472305722534657,
1051
+ "learning_rate": 2.561861743912019e-05,
1052
+ "loss": 0.0003,
1053
+ "step": 7450
1054
+ },
1055
+ {
1056
+ "epoch": 1.4728986645718773,
1057
+ "grad_norm": 4.937009362038225e-05,
1058
+ "learning_rate": 2.5454962031945535e-05,
1059
+ "loss": 0.0002,
1060
+ "step": 7500
1061
+ },
1062
+ {
1063
+ "epoch": 1.4827179890023565,
1064
+ "grad_norm": 0.0038520190864801407,
1065
+ "learning_rate": 2.5291306624770885e-05,
1066
+ "loss": 0.0003,
1067
+ "step": 7550
1068
+ },
1069
+ {
1070
+ "epoch": 1.4925373134328357,
1071
+ "grad_norm": 0.002998525742441416,
1072
+ "learning_rate": 2.512765121759623e-05,
1073
+ "loss": 0.0003,
1074
+ "step": 7600
1075
+ },
1076
+ {
1077
+ "epoch": 1.5023566378633149,
1078
+ "grad_norm": 0.0005952705978415906,
1079
+ "learning_rate": 2.4963995810421578e-05,
1080
+ "loss": 0.0003,
1081
+ "step": 7650
1082
+ },
1083
+ {
1084
+ "epoch": 1.512175962293794,
1085
+ "grad_norm": 2.007077455346007e-05,
1086
+ "learning_rate": 2.4800340403246924e-05,
1087
+ "loss": 0.0002,
1088
+ "step": 7700
1089
+ },
1090
+ {
1091
+ "epoch": 1.5219952867242734,
1092
+ "grad_norm": 0.002962449798360467,
1093
+ "learning_rate": 2.463668499607227e-05,
1094
+ "loss": 0.0003,
1095
+ "step": 7750
1096
+ },
1097
+ {
1098
+ "epoch": 1.5318146111547526,
1099
+ "grad_norm": 3.4512224374338984e-05,
1100
+ "learning_rate": 2.447302958889762e-05,
1101
+ "loss": 0.0002,
1102
+ "step": 7800
1103
+ },
1104
+ {
1105
+ "epoch": 1.5416339355852318,
1106
+ "grad_norm": 5.3643165301764384e-05,
1107
+ "learning_rate": 2.4309374181722967e-05,
1108
+ "loss": 0.0002,
1109
+ "step": 7850
1110
+ },
1111
+ {
1112
+ "epoch": 1.551453260015711,
1113
+ "grad_norm": 4.536865890258923e-05,
1114
+ "learning_rate": 2.4145718774548314e-05,
1115
+ "loss": 0.0003,
1116
+ "step": 7900
1117
+ },
1118
+ {
1119
+ "epoch": 1.56127258444619,
1120
+ "grad_norm": 0.0017064092680811882,
1121
+ "learning_rate": 2.3982063367373657e-05,
1122
+ "loss": 0.0003,
1123
+ "step": 7950
1124
+ },
1125
+ {
1126
+ "epoch": 1.5710919088766693,
1127
+ "grad_norm": 0.0028170356526970863,
1128
+ "learning_rate": 2.3818407960199007e-05,
1129
+ "loss": 0.0003,
1130
+ "step": 8000
1131
+ },
1132
+ {
1133
+ "epoch": 1.5809112333071484,
1134
+ "grad_norm": 6.762581324437633e-05,
1135
+ "learning_rate": 2.3654752553024353e-05,
1136
+ "loss": 0.0003,
1137
+ "step": 8050
1138
+ },
1139
+ {
1140
+ "epoch": 1.5907305577376276,
1141
+ "grad_norm": 5.572327063418925e-05,
1142
+ "learning_rate": 2.34910971458497e-05,
1143
+ "loss": 0.0001,
1144
+ "step": 8100
1145
+ },
1146
+ {
1147
+ "epoch": 1.6005498821681068,
1148
+ "grad_norm": 4.8497397074243054e-05,
1149
+ "learning_rate": 2.3327441738675046e-05,
1150
+ "loss": 0.0003,
1151
+ "step": 8150
1152
+ },
1153
+ {
1154
+ "epoch": 1.6103692065985862,
1155
+ "grad_norm": 0.000499077548738569,
1156
+ "learning_rate": 2.3163786331500396e-05,
1157
+ "loss": 0.0003,
1158
+ "step": 8200
1159
+ },
1160
+ {
1161
+ "epoch": 1.6201885310290653,
1162
+ "grad_norm": 0.0007215180085040629,
1163
+ "learning_rate": 2.3000130924325743e-05,
1164
+ "loss": 0.0003,
1165
+ "step": 8250
1166
+ },
1167
+ {
1168
+ "epoch": 1.6300078554595445,
1169
+ "grad_norm": 0.00015634812007192522,
1170
+ "learning_rate": 2.2836475517151086e-05,
1171
+ "loss": 0.0002,
1172
+ "step": 8300
1173
+ },
1174
+ {
1175
+ "epoch": 1.6398271798900237,
1176
+ "grad_norm": 0.010850101709365845,
1177
+ "learning_rate": 2.2672820109976432e-05,
1178
+ "loss": 0.0002,
1179
+ "step": 8350
1180
+ },
1181
+ {
1182
+ "epoch": 1.6496465043205029,
1183
+ "grad_norm": 0.0009706264827400446,
1184
+ "learning_rate": 2.2509164702801782e-05,
1185
+ "loss": 0.0004,
1186
+ "step": 8400
1187
+ },
1188
+ {
1189
+ "epoch": 1.659465828750982,
1190
+ "grad_norm": 3.204784661647864e-05,
1191
+ "learning_rate": 2.234550929562713e-05,
1192
+ "loss": 0.0003,
1193
+ "step": 8450
1194
+ },
1195
+ {
1196
+ "epoch": 1.6692851531814612,
1197
+ "grad_norm": 0.009143730625510216,
1198
+ "learning_rate": 2.2181853888452475e-05,
1199
+ "loss": 0.0003,
1200
+ "step": 8500
1201
+ },
1202
+ {
1203
+ "epoch": 1.6791044776119404,
1204
+ "grad_norm": 0.005089063663035631,
1205
+ "learning_rate": 2.2018198481277822e-05,
1206
+ "loss": 0.0004,
1207
+ "step": 8550
1208
+ },
1209
+ {
1210
+ "epoch": 1.6889238020424195,
1211
+ "grad_norm": 0.0249613169580698,
1212
+ "learning_rate": 2.1854543074103172e-05,
1213
+ "loss": 0.0003,
1214
+ "step": 8600
1215
+ },
1216
+ {
1217
+ "epoch": 1.6987431264728987,
1218
+ "grad_norm": 0.000527512573171407,
1219
+ "learning_rate": 2.1690887666928515e-05,
1220
+ "loss": 0.0003,
1221
+ "step": 8650
1222
+ },
1223
+ {
1224
+ "epoch": 1.7085624509033779,
1225
+ "grad_norm": 0.0011643558973446488,
1226
+ "learning_rate": 2.152723225975386e-05,
1227
+ "loss": 0.0001,
1228
+ "step": 8700
1229
+ },
1230
+ {
1231
+ "epoch": 1.718381775333857,
1232
+ "grad_norm": 0.0030941637232899666,
1233
+ "learning_rate": 2.1363576852579208e-05,
1234
+ "loss": 0.0002,
1235
+ "step": 8750
1236
+ },
1237
+ {
1238
+ "epoch": 1.7282010997643362,
1239
+ "grad_norm": 2.4613122150185518e-05,
1240
+ "learning_rate": 2.1199921445404558e-05,
1241
+ "loss": 0.0002,
1242
+ "step": 8800
1243
+ },
1244
+ {
1245
+ "epoch": 1.7380204241948154,
1246
+ "grad_norm": 0.009969648905098438,
1247
+ "learning_rate": 2.1036266038229905e-05,
1248
+ "loss": 0.0003,
1249
+ "step": 8850
1250
+ },
1251
+ {
1252
+ "epoch": 1.7478397486252946,
1253
+ "grad_norm": 0.0028629146981984377,
1254
+ "learning_rate": 2.087261063105525e-05,
1255
+ "loss": 0.0003,
1256
+ "step": 8900
1257
+ },
1258
+ {
1259
+ "epoch": 1.7576590730557737,
1260
+ "grad_norm": 0.005532170180231333,
1261
+ "learning_rate": 2.0708955223880598e-05,
1262
+ "loss": 0.0002,
1263
+ "step": 8950
1264
+ },
1265
+ {
1266
+ "epoch": 1.767478397486253,
1267
+ "grad_norm": 0.0001023332224576734,
1268
+ "learning_rate": 2.0545299816705944e-05,
1269
+ "loss": 0.0004,
1270
+ "step": 9000
1271
+ },
1272
+ {
1273
+ "epoch": 1.777297721916732,
1274
+ "grad_norm": 0.0016099640633910894,
1275
+ "learning_rate": 2.038164440953129e-05,
1276
+ "loss": 0.0002,
1277
+ "step": 9050
1278
+ },
1279
+ {
1280
+ "epoch": 1.7871170463472112,
1281
+ "grad_norm": 0.00755878584459424,
1282
+ "learning_rate": 2.0217989002356637e-05,
1283
+ "loss": 0.0003,
1284
+ "step": 9100
1285
+ },
1286
+ {
1287
+ "epoch": 1.7969363707776904,
1288
+ "grad_norm": 0.00131377880461514,
1289
+ "learning_rate": 2.0054333595181984e-05,
1290
+ "loss": 0.0003,
1291
+ "step": 9150
1292
+ },
1293
+ {
1294
+ "epoch": 1.8067556952081696,
1295
+ "grad_norm": 0.0066925594583153725,
1296
+ "learning_rate": 1.9890678188007334e-05,
1297
+ "loss": 0.0003,
1298
+ "step": 9200
1299
+ },
1300
+ {
1301
+ "epoch": 1.8165750196386488,
1302
+ "grad_norm": 0.0016435191500931978,
1303
+ "learning_rate": 1.972702278083268e-05,
1304
+ "loss": 0.0004,
1305
+ "step": 9250
1306
+ },
1307
+ {
1308
+ "epoch": 1.826394344069128,
1309
+ "grad_norm": 0.0049284519627690315,
1310
+ "learning_rate": 1.9563367373658027e-05,
1311
+ "loss": 0.0003,
1312
+ "step": 9300
1313
+ },
1314
+ {
1315
+ "epoch": 1.836213668499607,
1316
+ "grad_norm": 0.007083178497850895,
1317
+ "learning_rate": 1.9399711966483373e-05,
1318
+ "loss": 0.0002,
1319
+ "step": 9350
1320
+ },
1321
+ {
1322
+ "epoch": 1.8460329929300863,
1323
+ "grad_norm": 0.003799445927143097,
1324
+ "learning_rate": 1.923605655930872e-05,
1325
+ "loss": 0.0002,
1326
+ "step": 9400
1327
+ },
1328
+ {
1329
+ "epoch": 1.8558523173605654,
1330
+ "grad_norm": 8.943451575760264e-06,
1331
+ "learning_rate": 1.9072401152134066e-05,
1332
+ "loss": 0.0002,
1333
+ "step": 9450
1334
+ },
1335
+ {
1336
+ "epoch": 1.8656716417910446,
1337
+ "grad_norm": 4.004701168014435e-06,
1338
+ "learning_rate": 1.8908745744959413e-05,
1339
+ "loss": 0.0001,
1340
+ "step": 9500
1341
+ },
1342
+ {
1343
+ "epoch": 1.875490966221524,
1344
+ "grad_norm": 0.0016747256740927696,
1345
+ "learning_rate": 1.8745090337784763e-05,
1346
+ "loss": 0.0003,
1347
+ "step": 9550
1348
+ },
1349
+ {
1350
+ "epoch": 1.8853102906520032,
1351
+ "grad_norm": 0.00582944555208087,
1352
+ "learning_rate": 1.858143493061011e-05,
1353
+ "loss": 0.0003,
1354
+ "step": 9600
1355
+ },
1356
+ {
1357
+ "epoch": 1.8951296150824823,
1358
+ "grad_norm": 5.8452515077078715e-06,
1359
+ "learning_rate": 1.8417779523435456e-05,
1360
+ "loss": 0.0002,
1361
+ "step": 9650
1362
+ },
1363
+ {
1364
+ "epoch": 1.9049489395129615,
1365
+ "grad_norm": 2.22074459088617e-06,
1366
+ "learning_rate": 1.8254124116260802e-05,
1367
+ "loss": 0.0003,
1368
+ "step": 9700
1369
+ },
1370
+ {
1371
+ "epoch": 1.9147682639434407,
1372
+ "grad_norm": 0.0001783396874088794,
1373
+ "learning_rate": 1.809046870908615e-05,
1374
+ "loss": 0.0002,
1375
+ "step": 9750
1376
+ },
1377
+ {
1378
+ "epoch": 1.9245875883739199,
1379
+ "grad_norm": 9.459259308641776e-05,
1380
+ "learning_rate": 1.7926813301911495e-05,
1381
+ "loss": 0.0003,
1382
+ "step": 9800
1383
+ },
1384
+ {
1385
+ "epoch": 1.934406912804399,
1386
+ "grad_norm": 0.001501628546975553,
1387
+ "learning_rate": 1.7763157894736842e-05,
1388
+ "loss": 0.0002,
1389
+ "step": 9850
1390
+ },
1391
+ {
1392
+ "epoch": 1.9442262372348782,
1393
+ "grad_norm": 0.008209704421460629,
1394
+ "learning_rate": 1.759950248756219e-05,
1395
+ "loss": 0.0002,
1396
+ "step": 9900
1397
+ },
1398
+ {
1399
+ "epoch": 1.9540455616653576,
1400
+ "grad_norm": 2.8594949981197715e-05,
1401
+ "learning_rate": 1.743584708038754e-05,
1402
+ "loss": 0.0003,
1403
+ "step": 9950
1404
+ },
1405
+ {
1406
+ "epoch": 1.9638648860958368,
1407
+ "grad_norm": 0.0010227253660559654,
1408
+ "learning_rate": 1.7272191673212885e-05,
1409
+ "loss": 0.0002,
1410
+ "step": 10000
1411
+ },
1412
+ {
1413
+ "epoch": 1.973684210526316,
1414
+ "grad_norm": 1.06588067865232e-05,
1415
+ "learning_rate": 1.710853626603823e-05,
1416
+ "loss": 0.0003,
1417
+ "step": 10050
1418
+ },
1419
+ {
1420
+ "epoch": 1.983503534956795,
1421
+ "grad_norm": 0.0035111424513161182,
1422
+ "learning_rate": 1.6944880858863578e-05,
1423
+ "loss": 0.0003,
1424
+ "step": 10100
1425
+ },
1426
+ {
1427
+ "epoch": 1.9933228593872743,
1428
+ "grad_norm": 7.919372001197189e-05,
1429
+ "learning_rate": 1.6781225451688925e-05,
1430
+ "loss": 0.0002,
1431
+ "step": 10150
1432
+ },
1433
+ {
1434
+ "epoch": 2.0031421838177534,
1435
+ "grad_norm": 0.00608315784484148,
1436
+ "learning_rate": 1.661757004451427e-05,
1437
+ "loss": 0.0002,
1438
+ "step": 10200
1439
+ },
1440
+ {
1441
+ "epoch": 2.0129615082482326,
1442
+ "grad_norm": 6.566229330928763e-06,
1443
+ "learning_rate": 1.6453914637339618e-05,
1444
+ "loss": 0.0002,
1445
+ "step": 10250
1446
+ },
1447
+ {
1448
+ "epoch": 2.022780832678712,
1449
+ "grad_norm": 2.852589432222885e-06,
1450
+ "learning_rate": 1.6290259230164964e-05,
1451
+ "loss": 0.0001,
1452
+ "step": 10300
1453
+ },
1454
+ {
1455
+ "epoch": 2.032600157109191,
1456
+ "grad_norm": 2.3466156562790275e-05,
1457
+ "learning_rate": 1.6126603822990314e-05,
1458
+ "loss": 0.0002,
1459
+ "step": 10350
1460
+ },
1461
+ {
1462
+ "epoch": 2.04241948153967,
1463
+ "grad_norm": 0.006443875841796398,
1464
+ "learning_rate": 1.596294841581566e-05,
1465
+ "loss": 0.0004,
1466
+ "step": 10400
1467
+ },
1468
+ {
1469
+ "epoch": 2.0522388059701493,
1470
+ "grad_norm": 0.0006049483199603856,
1471
+ "learning_rate": 1.5799293008641007e-05,
1472
+ "loss": 0.0002,
1473
+ "step": 10450
1474
+ },
1475
+ {
1476
+ "epoch": 2.0620581304006285,
1477
+ "grad_norm": 0.0022505486849695444,
1478
+ "learning_rate": 1.563563760146635e-05,
1479
+ "loss": 0.0002,
1480
+ "step": 10500
1481
+ },
1482
+ {
1483
+ "epoch": 2.0718774548311076,
1484
+ "grad_norm": 4.880329652223736e-05,
1485
+ "learning_rate": 1.54719821942917e-05,
1486
+ "loss": 0.0002,
1487
+ "step": 10550
1488
+ },
1489
+ {
1490
+ "epoch": 2.081696779261587,
1491
+ "grad_norm": 0.006252319552004337,
1492
+ "learning_rate": 1.5308326787117047e-05,
1493
+ "loss": 0.0003,
1494
+ "step": 10600
1495
+ },
1496
+ {
1497
+ "epoch": 2.091516103692066,
1498
+ "grad_norm": 0.0014218160649761558,
1499
+ "learning_rate": 1.5144671379942393e-05,
1500
+ "loss": 0.0004,
1501
+ "step": 10650
1502
+ },
1503
+ {
1504
+ "epoch": 2.101335428122545,
1505
+ "grad_norm": 1.5717498172307387e-05,
1506
+ "learning_rate": 1.498101597276774e-05,
1507
+ "loss": 0.0003,
1508
+ "step": 10700
1509
+ },
1510
+ {
1511
+ "epoch": 2.1111547525530243,
1512
+ "grad_norm": 2.7057717488787603e-06,
1513
+ "learning_rate": 1.4817360565593088e-05,
1514
+ "loss": 0.0003,
1515
+ "step": 10750
1516
+ },
1517
+ {
1518
+ "epoch": 2.1209740769835035,
1519
+ "grad_norm": 0.003399658016860485,
1520
+ "learning_rate": 1.4653705158418435e-05,
1521
+ "loss": 0.0002,
1522
+ "step": 10800
1523
+ },
1524
+ {
1525
+ "epoch": 2.1307934014139827,
1526
+ "grad_norm": 0.0001567010476719588,
1527
+ "learning_rate": 1.4490049751243781e-05,
1528
+ "loss": 0.0002,
1529
+ "step": 10850
1530
+ },
1531
+ {
1532
+ "epoch": 2.140612725844462,
1533
+ "grad_norm": 1.0206712431681808e-05,
1534
+ "learning_rate": 1.432639434406913e-05,
1535
+ "loss": 0.0002,
1536
+ "step": 10900
1537
+ },
1538
+ {
1539
+ "epoch": 2.150432050274941,
1540
+ "grad_norm": 0.0023415617179125547,
1541
+ "learning_rate": 1.4162738936894476e-05,
1542
+ "loss": 0.0003,
1543
+ "step": 10950
1544
+ },
1545
+ {
1546
+ "epoch": 2.16025137470542,
1547
+ "grad_norm": 9.877283446257934e-05,
1548
+ "learning_rate": 1.3999083529719822e-05,
1549
+ "loss": 0.0002,
1550
+ "step": 11000
1551
+ },
1552
+ {
1553
+ "epoch": 2.1700706991358993,
1554
+ "grad_norm": 0.0009852441726252437,
1555
+ "learning_rate": 1.3835428122545169e-05,
1556
+ "loss": 0.0001,
1557
+ "step": 11050
1558
+ },
1559
+ {
1560
+ "epoch": 2.1798900235663785,
1561
+ "grad_norm": 2.5751623979886062e-05,
1562
+ "learning_rate": 1.3671772715370517e-05,
1563
+ "loss": 0.0002,
1564
+ "step": 11100
1565
+ },
1566
+ {
1567
+ "epoch": 2.1897093479968577,
1568
+ "grad_norm": 0.00046911800745874643,
1569
+ "learning_rate": 1.3508117308195864e-05,
1570
+ "loss": 0.0003,
1571
+ "step": 11150
1572
+ },
1573
+ {
1574
+ "epoch": 2.199528672427337,
1575
+ "grad_norm": 2.548624252085574e-05,
1576
+ "learning_rate": 1.334446190102121e-05,
1577
+ "loss": 0.0003,
1578
+ "step": 11200
1579
+ },
1580
+ {
1581
+ "epoch": 2.209347996857816,
1582
+ "grad_norm": 0.00012927035277243704,
1583
+ "learning_rate": 1.3180806493846557e-05,
1584
+ "loss": 0.0002,
1585
+ "step": 11250
1586
+ },
1587
+ {
1588
+ "epoch": 2.219167321288295,
1589
+ "grad_norm": 5.643380973197054e-06,
1590
+ "learning_rate": 1.3017151086671905e-05,
1591
+ "loss": 0.0002,
1592
+ "step": 11300
1593
+ },
1594
+ {
1595
+ "epoch": 2.2289866457187744,
1596
+ "grad_norm": 0.00517466152086854,
1597
+ "learning_rate": 1.2853495679497251e-05,
1598
+ "loss": 0.0003,
1599
+ "step": 11350
1600
+ },
1601
+ {
1602
+ "epoch": 2.2388059701492535,
1603
+ "grad_norm": 0.0007839313475415111,
1604
+ "learning_rate": 1.2689840272322598e-05,
1605
+ "loss": 0.0002,
1606
+ "step": 11400
1607
+ },
1608
+ {
1609
+ "epoch": 2.2486252945797327,
1610
+ "grad_norm": 0.003385524032637477,
1611
+ "learning_rate": 1.2526184865147945e-05,
1612
+ "loss": 0.0002,
1613
+ "step": 11450
1614
+ },
1615
+ {
1616
+ "epoch": 2.258444619010212,
1617
+ "grad_norm": 0.006902114022523165,
1618
+ "learning_rate": 1.2362529457973291e-05,
1619
+ "loss": 0.0002,
1620
+ "step": 11500
1621
+ },
1622
+ {
1623
+ "epoch": 2.268263943440691,
1624
+ "grad_norm": 0.002237598644569516,
1625
+ "learning_rate": 1.219887405079864e-05,
1626
+ "loss": 0.0002,
1627
+ "step": 11550
1628
+ },
1629
+ {
1630
+ "epoch": 2.27808326787117,
1631
+ "grad_norm": 2.9005691430938896e-06,
1632
+ "learning_rate": 1.2035218643623986e-05,
1633
+ "loss": 0.0002,
1634
+ "step": 11600
1635
+ },
1636
+ {
1637
+ "epoch": 2.28790259230165,
1638
+ "grad_norm": 0.0008452658075839281,
1639
+ "learning_rate": 1.1871563236449332e-05,
1640
+ "loss": 0.0002,
1641
+ "step": 11650
1642
+ },
1643
+ {
1644
+ "epoch": 2.297721916732129,
1645
+ "grad_norm": 0.0014033624902367592,
1646
+ "learning_rate": 1.1707907829274679e-05,
1647
+ "loss": 0.0002,
1648
+ "step": 11700
1649
+ },
1650
+ {
1651
+ "epoch": 2.307541241162608,
1652
+ "grad_norm": 0.001146289287135005,
1653
+ "learning_rate": 1.1544252422100027e-05,
1654
+ "loss": 0.0002,
1655
+ "step": 11750
1656
+ },
1657
+ {
1658
+ "epoch": 2.3173605655930873,
1659
+ "grad_norm": 6.133544957265258e-06,
1660
+ "learning_rate": 1.1380597014925374e-05,
1661
+ "loss": 0.0001,
1662
+ "step": 11800
1663
+ },
1664
+ {
1665
+ "epoch": 2.3271798900235665,
1666
+ "grad_norm": 0.0015589894028380513,
1667
+ "learning_rate": 1.121694160775072e-05,
1668
+ "loss": 0.0004,
1669
+ "step": 11850
1670
+ },
1671
+ {
1672
+ "epoch": 2.3369992144540457,
1673
+ "grad_norm": 0.00035342929186299443,
1674
+ "learning_rate": 1.1053286200576067e-05,
1675
+ "loss": 0.0002,
1676
+ "step": 11900
1677
+ },
1678
+ {
1679
+ "epoch": 2.346818538884525,
1680
+ "grad_norm": 1.368164703308139e-05,
1681
+ "learning_rate": 1.0889630793401415e-05,
1682
+ "loss": 0.0003,
1683
+ "step": 11950
1684
+ },
1685
+ {
1686
+ "epoch": 2.356637863315004,
1687
+ "grad_norm": 0.0021006593015044928,
1688
+ "learning_rate": 1.0725975386226761e-05,
1689
+ "loss": 0.0002,
1690
+ "step": 12000
1691
+ },
1692
+ {
1693
+ "epoch": 2.366457187745483,
1694
+ "grad_norm": 7.3638998401293065e-06,
1695
+ "learning_rate": 1.0562319979052108e-05,
1696
+ "loss": 0.0002,
1697
+ "step": 12050
1698
+ },
1699
+ {
1700
+ "epoch": 2.3762765121759624,
1701
+ "grad_norm": 0.006797213107347488,
1702
+ "learning_rate": 1.0398664571877455e-05,
1703
+ "loss": 0.0002,
1704
+ "step": 12100
1705
+ },
1706
+ {
1707
+ "epoch": 2.3860958366064415,
1708
+ "grad_norm": 0.002575602615252137,
1709
+ "learning_rate": 1.0235009164702803e-05,
1710
+ "loss": 0.0004,
1711
+ "step": 12150
1712
+ },
1713
+ {
1714
+ "epoch": 2.3959151610369207,
1715
+ "grad_norm": 0.0026493787299841642,
1716
+ "learning_rate": 1.007135375752815e-05,
1717
+ "loss": 0.0003,
1718
+ "step": 12200
1719
+ },
1720
+ {
1721
+ "epoch": 2.4057344854674,
1722
+ "grad_norm": 5.164716185390716e-06,
1723
+ "learning_rate": 9.907698350353496e-06,
1724
+ "loss": 0.0003,
1725
+ "step": 12250
1726
+ },
1727
+ {
1728
+ "epoch": 2.415553809897879,
1729
+ "grad_norm": 0.0033771705348044634,
1730
+ "learning_rate": 9.744042943178842e-06,
1731
+ "loss": 0.0003,
1732
+ "step": 12300
1733
+ },
1734
+ {
1735
+ "epoch": 2.425373134328358,
1736
+ "grad_norm": 3.062731593672652e-06,
1737
+ "learning_rate": 9.58038753600419e-06,
1738
+ "loss": 0.0003,
1739
+ "step": 12350
1740
+ },
1741
+ {
1742
+ "epoch": 2.4351924587588374,
1743
+ "grad_norm": 0.002900635125115514,
1744
+ "learning_rate": 9.416732128829537e-06,
1745
+ "loss": 0.0002,
1746
+ "step": 12400
1747
+ },
1748
+ {
1749
+ "epoch": 2.4450117831893166,
1750
+ "grad_norm": 0.005432957783341408,
1751
+ "learning_rate": 9.253076721654884e-06,
1752
+ "loss": 0.0003,
1753
+ "step": 12450
1754
+ },
1755
+ {
1756
+ "epoch": 2.4548311076197957,
1757
+ "grad_norm": 0.0060834819450974464,
1758
+ "learning_rate": 9.089421314480232e-06,
1759
+ "loss": 0.0002,
1760
+ "step": 12500
1761
+ },
1762
+ {
1763
+ "epoch": 2.464650432050275,
1764
+ "grad_norm": 0.0003888920182362199,
1765
+ "learning_rate": 8.925765907305578e-06,
1766
+ "loss": 0.0002,
1767
+ "step": 12550
1768
+ },
1769
+ {
1770
+ "epoch": 2.474469756480754,
1771
+ "grad_norm": 0.0008291418780572712,
1772
+ "learning_rate": 8.762110500130925e-06,
1773
+ "loss": 0.0002,
1774
+ "step": 12600
1775
+ },
1776
+ {
1777
+ "epoch": 2.4842890809112332,
1778
+ "grad_norm": 4.13081716033048e-06,
1779
+ "learning_rate": 8.598455092956271e-06,
1780
+ "loss": 0.0002,
1781
+ "step": 12650
1782
+ },
1783
+ {
1784
+ "epoch": 2.4941084053417124,
1785
+ "grad_norm": 0.0027352613396942616,
1786
+ "learning_rate": 8.43479968578162e-06,
1787
+ "loss": 0.0002,
1788
+ "step": 12700
1789
+ },
1790
+ {
1791
+ "epoch": 2.5039277297721916,
1792
+ "grad_norm": 0.004523648414760828,
1793
+ "learning_rate": 8.271144278606966e-06,
1794
+ "loss": 0.0003,
1795
+ "step": 12750
1796
+ },
1797
+ {
1798
+ "epoch": 2.5137470542026707,
1799
+ "grad_norm": 0.0014511903282254934,
1800
+ "learning_rate": 8.107488871432313e-06,
1801
+ "loss": 0.0002,
1802
+ "step": 12800
1803
+ },
1804
+ {
1805
+ "epoch": 2.52356637863315,
1806
+ "grad_norm": 0.001870101667009294,
1807
+ "learning_rate": 7.94383346425766e-06,
1808
+ "loss": 0.0003,
1809
+ "step": 12850
1810
+ },
1811
+ {
1812
+ "epoch": 2.533385703063629,
1813
+ "grad_norm": 1.8049751133730751e-06,
1814
+ "learning_rate": 7.780178057083008e-06,
1815
+ "loss": 0.0002,
1816
+ "step": 12900
1817
+ },
1818
+ {
1819
+ "epoch": 2.5432050274941083,
1820
+ "grad_norm": 2.639750891830772e-05,
1821
+ "learning_rate": 7.616522649908353e-06,
1822
+ "loss": 0.0002,
1823
+ "step": 12950
1824
+ },
1825
+ {
1826
+ "epoch": 2.5530243519245874,
1827
+ "grad_norm": 0.004915285389870405,
1828
+ "learning_rate": 7.452867242733701e-06,
1829
+ "loss": 0.0003,
1830
+ "step": 13000
1831
+ },
1832
+ {
1833
+ "epoch": 2.562843676355067,
1834
+ "grad_norm": 0.0013427536468952894,
1835
+ "learning_rate": 7.289211835559047e-06,
1836
+ "loss": 0.0002,
1837
+ "step": 13050
1838
+ },
1839
+ {
1840
+ "epoch": 2.572663000785546,
1841
+ "grad_norm": 0.006909032352268696,
1842
+ "learning_rate": 7.1255564283843945e-06,
1843
+ "loss": 0.0002,
1844
+ "step": 13100
1845
+ },
1846
+ {
1847
+ "epoch": 2.5824823252160254,
1848
+ "grad_norm": 0.004452712833881378,
1849
+ "learning_rate": 6.961901021209741e-06,
1850
+ "loss": 0.0002,
1851
+ "step": 13150
1852
+ },
1853
+ {
1854
+ "epoch": 2.5923016496465046,
1855
+ "grad_norm": 1.5004067108748131e-06,
1856
+ "learning_rate": 6.798245614035088e-06,
1857
+ "loss": 0.0002,
1858
+ "step": 13200
1859
+ },
1860
+ {
1861
+ "epoch": 2.6021209740769837,
1862
+ "grad_norm": 9.272382158087566e-06,
1863
+ "learning_rate": 6.634590206860435e-06,
1864
+ "loss": 0.0002,
1865
+ "step": 13250
1866
+ },
1867
+ {
1868
+ "epoch": 2.611940298507463,
1869
+ "grad_norm": 0.004868045449256897,
1870
+ "learning_rate": 6.470934799685782e-06,
1871
+ "loss": 0.0002,
1872
+ "step": 13300
1873
+ },
1874
+ {
1875
+ "epoch": 2.621759622937942,
1876
+ "grad_norm": 6.646020665357355e-06,
1877
+ "learning_rate": 6.307279392511129e-06,
1878
+ "loss": 0.0002,
1879
+ "step": 13350
1880
+ },
1881
+ {
1882
+ "epoch": 2.6315789473684212,
1883
+ "grad_norm": 0.0015008870977908373,
1884
+ "learning_rate": 6.143623985336476e-06,
1885
+ "loss": 0.0003,
1886
+ "step": 13400
1887
+ },
1888
+ {
1889
+ "epoch": 2.6413982717989004,
1890
+ "grad_norm": 0.0031040972098708153,
1891
+ "learning_rate": 5.979968578161823e-06,
1892
+ "loss": 0.0003,
1893
+ "step": 13450
1894
+ },
1895
+ {
1896
+ "epoch": 2.6512175962293796,
1897
+ "grad_norm": 0.0015553946141153574,
1898
+ "learning_rate": 5.81631317098717e-06,
1899
+ "loss": 0.0003,
1900
+ "step": 13500
1901
+ },
1902
+ {
1903
+ "epoch": 2.6610369206598588,
1904
+ "grad_norm": 0.0015114744892343879,
1905
+ "learning_rate": 5.652657763812517e-06,
1906
+ "loss": 0.0002,
1907
+ "step": 13550
1908
+ },
1909
+ {
1910
+ "epoch": 2.670856245090338,
1911
+ "grad_norm": 0.006511743646115065,
1912
+ "learning_rate": 5.489002356637864e-06,
1913
+ "loss": 0.0002,
1914
+ "step": 13600
1915
+ },
1916
+ {
1917
+ "epoch": 2.680675569520817,
1918
+ "grad_norm": 3.6607066249416675e-06,
1919
+ "learning_rate": 5.3253469494632106e-06,
1920
+ "loss": 0.0002,
1921
+ "step": 13650
1922
+ },
1923
+ {
1924
+ "epoch": 2.6904948939512963,
1925
+ "grad_norm": 0.0008585217874497175,
1926
+ "learning_rate": 5.161691542288558e-06,
1927
+ "loss": 0.0003,
1928
+ "step": 13700
1929
+ },
1930
+ {
1931
+ "epoch": 2.7003142183817754,
1932
+ "grad_norm": 0.0005489959730766714,
1933
+ "learning_rate": 4.9980361351139045e-06,
1934
+ "loss": 0.0003,
1935
+ "step": 13750
1936
+ },
1937
+ {
1938
+ "epoch": 2.7101335428122546,
1939
+ "grad_norm": 3.3158432870550314e-06,
1940
+ "learning_rate": 4.834380727939251e-06,
1941
+ "loss": 0.0002,
1942
+ "step": 13800
1943
+ },
1944
+ {
1945
+ "epoch": 2.7199528672427338,
1946
+ "grad_norm": 0.0030354801565408707,
1947
+ "learning_rate": 4.670725320764598e-06,
1948
+ "loss": 0.0003,
1949
+ "step": 13850
1950
+ },
1951
+ {
1952
+ "epoch": 2.729772191673213,
1953
+ "grad_norm": 3.2985217330860905e-06,
1954
+ "learning_rate": 4.507069913589945e-06,
1955
+ "loss": 0.0002,
1956
+ "step": 13900
1957
+ },
1958
+ {
1959
+ "epoch": 2.739591516103692,
1960
+ "grad_norm": 7.288464257726446e-05,
1961
+ "learning_rate": 4.343414506415292e-06,
1962
+ "loss": 0.0002,
1963
+ "step": 13950
1964
+ },
1965
+ {
1966
+ "epoch": 2.7494108405341713,
1967
+ "grad_norm": 0.0043890466913580894,
1968
+ "learning_rate": 4.179759099240639e-06,
1969
+ "loss": 0.0003,
1970
+ "step": 14000
1971
+ },
1972
+ {
1973
+ "epoch": 2.7592301649646505,
1974
+ "grad_norm": 0.0019504046067595482,
1975
+ "learning_rate": 4.016103692065986e-06,
1976
+ "loss": 0.0002,
1977
+ "step": 14050
1978
+ },
1979
+ {
1980
+ "epoch": 2.7690494893951296,
1981
+ "grad_norm": 0.0015608868561685085,
1982
+ "learning_rate": 3.852448284891333e-06,
1983
+ "loss": 0.0003,
1984
+ "step": 14100
1985
+ },
1986
+ {
1987
+ "epoch": 2.778868813825609,
1988
+ "grad_norm": 0.002886673668399453,
1989
+ "learning_rate": 3.6887928777166797e-06,
1990
+ "loss": 0.0002,
1991
+ "step": 14150
1992
+ },
1993
+ {
1994
+ "epoch": 2.788688138256088,
1995
+ "grad_norm": 0.0009562448249198496,
1996
+ "learning_rate": 3.5251374705420267e-06,
1997
+ "loss": 0.0003,
1998
+ "step": 14200
1999
+ },
2000
+ {
2001
+ "epoch": 2.798507462686567,
2002
+ "grad_norm": 2.2277029074757593e-06,
2003
+ "learning_rate": 3.3614820633673736e-06,
2004
+ "loss": 0.0003,
2005
+ "step": 14250
2006
+ },
2007
+ {
2008
+ "epoch": 2.8083267871170463,
2009
+ "grad_norm": 0.0023437589406967163,
2010
+ "learning_rate": 3.1978266561927206e-06,
2011
+ "loss": 0.0002,
2012
+ "step": 14300
2013
+ },
2014
+ {
2015
+ "epoch": 2.8181461115475255,
2016
+ "grad_norm": 1.8503330920793815e-06,
2017
+ "learning_rate": 3.034171249018068e-06,
2018
+ "loss": 0.0002,
2019
+ "step": 14350
2020
+ },
2021
+ {
2022
+ "epoch": 2.8279654359780046,
2023
+ "grad_norm": 4.966601863998221e-06,
2024
+ "learning_rate": 2.870515841843415e-06,
2025
+ "loss": 0.0002,
2026
+ "step": 14400
2027
+ },
2028
+ {
2029
+ "epoch": 2.837784760408484,
2030
+ "grad_norm": 1.3409814982878743e-06,
2031
+ "learning_rate": 2.706860434668762e-06,
2032
+ "loss": 0.0002,
2033
+ "step": 14450
2034
+ },
2035
+ {
2036
+ "epoch": 2.847604084838963,
2037
+ "grad_norm": 6.203641532920301e-05,
2038
+ "learning_rate": 2.543205027494109e-06,
2039
+ "loss": 0.0002,
2040
+ "step": 14500
2041
+ },
2042
+ {
2043
+ "epoch": 2.857423409269442,
2044
+ "grad_norm": 0.0002616413403302431,
2045
+ "learning_rate": 2.3795496203194553e-06,
2046
+ "loss": 0.0003,
2047
+ "step": 14550
2048
+ },
2049
+ {
2050
+ "epoch": 2.8672427336999213,
2051
+ "grad_norm": 6.303464488155441e-07,
2052
+ "learning_rate": 2.2158942131448023e-06,
2053
+ "loss": 0.0002,
2054
+ "step": 14600
2055
+ },
2056
+ {
2057
+ "epoch": 2.8770620581304005,
2058
+ "grad_norm": 0.0017262320034205914,
2059
+ "learning_rate": 2.0522388059701493e-06,
2060
+ "loss": 0.0003,
2061
+ "step": 14650
2062
+ },
2063
+ {
2064
+ "epoch": 2.8868813825608797,
2065
+ "grad_norm": 0.0033360267989337444,
2066
+ "learning_rate": 1.8885833987954962e-06,
2067
+ "loss": 0.0003,
2068
+ "step": 14700
2069
+ },
2070
+ {
2071
+ "epoch": 2.896700706991359,
2072
+ "grad_norm": 2.7147841592523037e-06,
2073
+ "learning_rate": 1.7249279916208432e-06,
2074
+ "loss": 0.0002,
2075
+ "step": 14750
2076
+ },
2077
+ {
2078
+ "epoch": 2.906520031421838,
2079
+ "grad_norm": 0.0019037205493077636,
2080
+ "learning_rate": 1.5612725844461901e-06,
2081
+ "loss": 0.0002,
2082
+ "step": 14800
2083
+ },
2084
+ {
2085
+ "epoch": 2.916339355852317,
2086
+ "grad_norm": 0.00883456040173769,
2087
+ "learning_rate": 1.397617177271537e-06,
2088
+ "loss": 0.0003,
2089
+ "step": 14850
2090
+ },
2091
+ {
2092
+ "epoch": 2.9261586802827964,
2093
+ "grad_norm": 0.000769551086705178,
2094
+ "learning_rate": 1.233961770096884e-06,
2095
+ "loss": 0.0003,
2096
+ "step": 14900
2097
+ },
2098
+ {
2099
+ "epoch": 2.9359780047132755,
2100
+ "grad_norm": 1.074038755177753e-05,
2101
+ "learning_rate": 1.070306362922231e-06,
2102
+ "loss": 0.0002,
2103
+ "step": 14950
2104
+ },
2105
+ {
2106
+ "epoch": 2.9457973291437547,
2107
+ "grad_norm": 0.0046028513461351395,
2108
+ "learning_rate": 9.066509557475779e-07,
2109
+ "loss": 0.0003,
2110
+ "step": 15000
2111
+ },
2112
+ {
2113
+ "epoch": 2.955616653574234,
2114
+ "grad_norm": 0.0024120802991092205,
2115
+ "learning_rate": 7.429955485729249e-07,
2116
+ "loss": 0.0002,
2117
+ "step": 15050
2118
+ },
2119
+ {
2120
+ "epoch": 2.965435978004713,
2121
+ "grad_norm": 0.0019912375137209892,
2122
+ "learning_rate": 5.793401413982719e-07,
2123
+ "loss": 0.0003,
2124
+ "step": 15100
2125
+ },
2126
+ {
2127
+ "epoch": 2.975255302435192,
2128
+ "grad_norm": 0.0013518768828362226,
2129
+ "learning_rate": 4.1568473422361876e-07,
2130
+ "loss": 0.0003,
2131
+ "step": 15150
2132
+ },
2133
+ {
2134
+ "epoch": 2.9850746268656714,
2135
+ "grad_norm": 5.804280954180285e-05,
2136
+ "learning_rate": 2.520293270489657e-07,
2137
+ "loss": 0.0003,
2138
+ "step": 15200
2139
+ },
2140
+ {
2141
+ "epoch": 2.994893951296151,
2142
+ "grad_norm": 0.0008266063523478806,
2143
+ "learning_rate": 8.837391987431265e-08,
2144
+ "loss": 0.0002,
2145
+ "step": 15250
2146
+ }
2147
+ ],
2148
+ "logging_steps": 50,
2149
+ "max_steps": 15276,
2150
+ "num_input_tokens_seen": 0,
2151
+ "num_train_epochs": 3,
2152
+ "save_steps": 500,
2153
+ "stateful_callbacks": {
2154
+ "TrainerControl": {
2155
+ "args": {
2156
+ "should_epoch_stop": false,
2157
+ "should_evaluate": false,
2158
+ "should_log": false,
2159
+ "should_save": true,
2160
+ "should_training_stop": true
2161
+ },
2162
+ "attributes": {}
2163
+ }
2164
+ },
2165
+ "total_flos": 3.72042823237632e+16,
2166
+ "train_batch_size": 4,
2167
+ "trial_name": null,
2168
+ "trial_params": null
2169
+ }
checkpoint-15276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b9fd65cee3abc15d70a7c94fe8a522f4e629ace27426230901f90d3992ccbd
3
+ size 5713
checkpoint-15276/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "relu",
15
+ "gradient_checkpointing": false,
16
+ "id2label": {
17
+ "0": "LABEL_0"
18
+ },
19
+ "initializer_factor": 1.0,
20
+ "is_encoder_decoder": true,
21
+ "is_gated_act": false,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "layer_norm_epsilon": 1e-06,
26
+ "model_type": "t5",
27
+ "n_positions": 512,
28
+ "num_decoder_layers": 12,
29
+ "num_heads": 12,
30
+ "num_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "relative_attention_max_distance": 128,
34
+ "relative_attention_num_buckets": 32,
35
+ "task_specific_params": {
36
+ "summarization": {
37
+ "early_stopping": true,
38
+ "length_penalty": 2.0,
39
+ "max_length": 200,
40
+ "min_length": 30,
41
+ "no_repeat_ngram_size": 3,
42
+ "num_beams": 4,
43
+ "prefix": "summarize: "
44
+ },
45
+ "translation_en_to_de": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to German: "
50
+ },
51
+ "translation_en_to_fr": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to French: "
56
+ },
57
+ "translation_en_to_ro": {
58
+ "early_stopping": true,
59
+ "max_length": 300,
60
+ "num_beams": 4,
61
+ "prefix": "translate English to Romanian: "
62
+ }
63
+ },
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.55.3",
66
+ "use_cache": true,
67
+ "vocab_size": 32100
68
+ }
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": "4.55.3"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d4a857ce818263f64b8eaf40a258d336a29a8112e36e17261e6cf4520ef9f2
3
+ size 891558696
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,960 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
949
+ "cls_token": "<s>",
950
+ "eos_token": "</s>",
951
+ "errors": "replace",
952
+ "extra_special_tokens": {},
953
+ "mask_token": "<mask>",
954
+ "model_max_length": 512,
955
+ "pad_token": "<pad>",
956
+ "sep_token": "</s>",
957
+ "tokenizer_class": "RobertaTokenizer",
958
+ "trim_offsets": true,
959
+ "unk_token": "<unk>"
960
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff