svyas-hf commited on
Commit
0392403
·
verified ·
1 Parent(s): 7c6666e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-classification
6
+ base_model: tasksource/deberta-small-long-nli
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Text Classification
14
+
15
+ ## Validation Metrics
16
+ loss: 1.6780412197113037
17
+
18
+ f1_macro: 0.48698637963343844
19
+
20
+ f1_micro: 0.5510204081632653
21
+
22
+ f1_weighted: 0.5140266479552194
23
+
24
+ precision_macro: 0.49788642729819194
25
+
26
+ precision_micro: 0.5510204081632653
27
+
28
+ precision_weighted: 0.5202149041434755
29
+
30
+ recall_macro: 0.5220588235294118
31
+
32
+ recall_micro: 0.5510204081632653
33
+
34
+ recall_weighted: 0.5510204081632653
35
+
36
+ accuracy: 0.5510204081632653
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-125/config.json ADDED
@@ -0,0 +1,1138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tasksource/deberta-small-long-nli",
3
+ "_num_labels": 17,
4
+ "architectures": [
5
+ "DebertaV2ForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifiers_size": [
9
+ 3,
10
+ 2,
11
+ 2,
12
+ 2,
13
+ 2,
14
+ 2,
15
+ 1,
16
+ 2,
17
+ 3,
18
+ 2,
19
+ 2,
20
+ 2,
21
+ 3,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 1,
26
+ 3,
27
+ 3,
28
+ 2,
29
+ 2,
30
+ 3,
31
+ 2,
32
+ 6,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 3,
43
+ 3,
44
+ 3,
45
+ 3,
46
+ 3,
47
+ 3,
48
+ 3,
49
+ 2,
50
+ 2,
51
+ 2,
52
+ 2,
53
+ 5,
54
+ 3,
55
+ 3,
56
+ 3,
57
+ 3,
58
+ 3,
59
+ 3,
60
+ 3,
61
+ 3,
62
+ 2,
63
+ 2,
64
+ 2,
65
+ 3,
66
+ 3,
67
+ 3,
68
+ 3,
69
+ 3,
70
+ 3,
71
+ 3,
72
+ 2,
73
+ 2,
74
+ 2,
75
+ 2,
76
+ 1,
77
+ 1,
78
+ 1,
79
+ 1,
80
+ 1,
81
+ 1,
82
+ 1,
83
+ 1,
84
+ 1,
85
+ 1,
86
+ 1,
87
+ 1,
88
+ 1,
89
+ 1,
90
+ 1,
91
+ 1,
92
+ 1,
93
+ 1,
94
+ 1,
95
+ 1,
96
+ 1,
97
+ 1,
98
+ 1,
99
+ 1,
100
+ 1,
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 1,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 1,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 1,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 1,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 1,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 1,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 1,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 1,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 1,
137
+ 1,
138
+ 1,
139
+ 1,
140
+ 1,
141
+ 1,
142
+ 1,
143
+ 1,
144
+ 1,
145
+ 1,
146
+ 1,
147
+ 1,
148
+ 1,
149
+ 1,
150
+ 1,
151
+ 1,
152
+ 1,
153
+ 1,
154
+ 1,
155
+ 1,
156
+ 1,
157
+ 1,
158
+ 1,
159
+ 1,
160
+ 1,
161
+ 1,
162
+ 1,
163
+ 1,
164
+ 1,
165
+ 1,
166
+ 1,
167
+ 1,
168
+ 1,
169
+ 1,
170
+ 1,
171
+ 1,
172
+ 1,
173
+ 1,
174
+ 1,
175
+ 1,
176
+ 1,
177
+ 1,
178
+ 1,
179
+ 1,
180
+ 1,
181
+ 1,
182
+ 1,
183
+ 1,
184
+ 1,
185
+ 1,
186
+ 1,
187
+ 1,
188
+ 1,
189
+ 1,
190
+ 1,
191
+ 1,
192
+ 1,
193
+ 1,
194
+ 1,
195
+ 1,
196
+ 1,
197
+ 1,
198
+ 1,
199
+ 1,
200
+ 1,
201
+ 1,
202
+ 1,
203
+ 1,
204
+ 2,
205
+ 2,
206
+ 2,
207
+ 2,
208
+ 2,
209
+ 2,
210
+ 20,
211
+ 50,
212
+ 3,
213
+ 3,
214
+ 4,
215
+ 2,
216
+ 8,
217
+ 2,
218
+ 3,
219
+ 2,
220
+ 2,
221
+ 4,
222
+ 20,
223
+ 3,
224
+ 3,
225
+ 3,
226
+ 3,
227
+ 3,
228
+ 174,
229
+ 2,
230
+ 2,
231
+ 2,
232
+ 2,
233
+ 41,
234
+ 3,
235
+ 51,
236
+ 2,
237
+ 2,
238
+ 2,
239
+ 2,
240
+ 16,
241
+ 17,
242
+ 18,
243
+ 2,
244
+ 2,
245
+ 2,
246
+ 3,
247
+ 8,
248
+ 3,
249
+ 7,
250
+ 7,
251
+ 11,
252
+ 3,
253
+ 3,
254
+ 42,
255
+ 12,
256
+ 4,
257
+ 100,
258
+ 13,
259
+ 100,
260
+ 8,
261
+ 1,
262
+ 20,
263
+ 2,
264
+ 2,
265
+ 4,
266
+ 5,
267
+ 3,
268
+ 4,
269
+ 14,
270
+ 2,
271
+ 6,
272
+ 4,
273
+ 2,
274
+ 1,
275
+ 3,
276
+ 10,
277
+ 3,
278
+ 10,
279
+ 4,
280
+ 2,
281
+ 7,
282
+ 6,
283
+ 28,
284
+ 3,
285
+ 6,
286
+ 5,
287
+ 7,
288
+ 4,
289
+ 6,
290
+ 3,
291
+ 2,
292
+ 2,
293
+ 2,
294
+ 6,
295
+ 2,
296
+ 7,
297
+ 20,
298
+ 2,
299
+ 2,
300
+ 4,
301
+ 2,
302
+ 9,
303
+ 13,
304
+ 4,
305
+ 2,
306
+ 3,
307
+ 2,
308
+ 3,
309
+ 2,
310
+ 2,
311
+ 2,
312
+ 2,
313
+ 4,
314
+ 1,
315
+ 2,
316
+ 1,
317
+ 2,
318
+ 49,
319
+ 40,
320
+ 10,
321
+ 4,
322
+ 1,
323
+ 2,
324
+ 2,
325
+ 1,
326
+ 5,
327
+ 2,
328
+ 3,
329
+ 2,
330
+ 2,
331
+ 12,
332
+ 3,
333
+ 3,
334
+ 2,
335
+ 19,
336
+ 3,
337
+ 1,
338
+ 2,
339
+ 2,
340
+ 2,
341
+ 2,
342
+ 2,
343
+ 1,
344
+ 2,
345
+ 2,
346
+ 1,
347
+ 1,
348
+ 2,
349
+ 3,
350
+ 2,
351
+ 1,
352
+ 4,
353
+ 3,
354
+ 1,
355
+ 1,
356
+ 1,
357
+ 2,
358
+ 3,
359
+ 2,
360
+ 3,
361
+ 1,
362
+ 1,
363
+ 2,
364
+ 1,
365
+ 2,
366
+ 2,
367
+ 2,
368
+ 2,
369
+ 3,
370
+ 2,
371
+ 2,
372
+ 2,
373
+ 1,
374
+ 3,
375
+ 2,
376
+ 2,
377
+ 1,
378
+ 1,
379
+ 1,
380
+ 1,
381
+ 2,
382
+ 1,
383
+ 1,
384
+ 1,
385
+ 1,
386
+ 4,
387
+ 1,
388
+ 1,
389
+ 1,
390
+ 1,
391
+ 3,
392
+ 1,
393
+ 3,
394
+ 1,
395
+ 2,
396
+ 2,
397
+ 1,
398
+ 2,
399
+ 3,
400
+ 3,
401
+ 2,
402
+ 1,
403
+ 3,
404
+ 1,
405
+ 1,
406
+ 3,
407
+ 1,
408
+ 3,
409
+ 2,
410
+ 1,
411
+ 1,
412
+ 1,
413
+ 2,
414
+ 2,
415
+ 1,
416
+ 1,
417
+ 1,
418
+ 1,
419
+ 1,
420
+ 1,
421
+ 1,
422
+ 1,
423
+ 1,
424
+ 1,
425
+ 2,
426
+ 2,
427
+ 2,
428
+ 2,
429
+ 77,
430
+ 3,
431
+ 2,
432
+ 2,
433
+ 1,
434
+ 1,
435
+ 2,
436
+ 3,
437
+ 18,
438
+ 13,
439
+ 2,
440
+ 2,
441
+ 2,
442
+ 2,
443
+ 2,
444
+ 4,
445
+ 2,
446
+ 24,
447
+ 3,
448
+ 2,
449
+ 2,
450
+ 1,
451
+ 2,
452
+ 2,
453
+ 3,
454
+ 1,
455
+ 2,
456
+ 3,
457
+ 2,
458
+ 3,
459
+ 3,
460
+ 2,
461
+ 2,
462
+ 4,
463
+ 1,
464
+ 17,
465
+ 3,
466
+ 3,
467
+ 2,
468
+ 3,
469
+ 2,
470
+ 3,
471
+ 3,
472
+ 2,
473
+ 1,
474
+ 1,
475
+ 3,
476
+ 2,
477
+ 9,
478
+ 2,
479
+ 1,
480
+ 1,
481
+ 1,
482
+ 1,
483
+ 1,
484
+ 2,
485
+ 2,
486
+ 3,
487
+ 2,
488
+ 3,
489
+ 4,
490
+ 3,
491
+ 3,
492
+ 2,
493
+ 1,
494
+ 1,
495
+ 2,
496
+ 1,
497
+ 1,
498
+ 6,
499
+ 2,
500
+ 3,
501
+ 3,
502
+ 1,
503
+ 1,
504
+ 2,
505
+ 2,
506
+ 10,
507
+ 2,
508
+ 2,
509
+ 2,
510
+ 5,
511
+ 5,
512
+ 5,
513
+ 5,
514
+ 5,
515
+ 5,
516
+ 5,
517
+ 5,
518
+ 5,
519
+ 5,
520
+ 4,
521
+ 1,
522
+ 7,
523
+ 6,
524
+ 6,
525
+ 6,
526
+ 6,
527
+ 6,
528
+ 6,
529
+ 3,
530
+ 2,
531
+ 1,
532
+ 2,
533
+ 2,
534
+ 2,
535
+ 3,
536
+ 3,
537
+ 3,
538
+ 1
539
+ ],
540
+ "hidden_act": "gelu",
541
+ "hidden_dropout_prob": 0.1,
542
+ "hidden_size": 768,
543
+ "id2label": {
544
+ "0": "aging-parents",
545
+ "1": "asset-protection",
546
+ "2": "big-purchase",
547
+ "3": "cash-flow-management",
548
+ "4": "emergency-savings",
549
+ "5": "estate-planning",
550
+ "6": "job-change",
551
+ "7": "marriage-divorce",
552
+ "8": "new-child",
553
+ "9": "no-detection",
554
+ "10": "philanthropic-needs",
555
+ "11": "portfolio-performance",
556
+ "12": "retirement-planning",
557
+ "13": "risk-assessment-tolerance",
558
+ "14": "small-business-owner",
559
+ "15": "tax-optimization",
560
+ "16": "windfall-bankruptcy"
561
+ },
562
+ "initializer_range": 0.02,
563
+ "intermediate_size": 3072,
564
+ "label2id": {
565
+ "aging-parents": 0,
566
+ "asset-protection": 1,
567
+ "big-purchase": 2,
568
+ "cash-flow-management": 3,
569
+ "emergency-savings": 4,
570
+ "estate-planning": 5,
571
+ "job-change": 6,
572
+ "marriage-divorce": 7,
573
+ "new-child": 8,
574
+ "no-detection": 9,
575
+ "philanthropic-needs": 10,
576
+ "portfolio-performance": 11,
577
+ "retirement-planning": 12,
578
+ "risk-assessment-tolerance": 13,
579
+ "small-business-owner": 14,
580
+ "tax-optimization": 15,
581
+ "windfall-bankruptcy": 16
582
+ },
583
+ "layer_norm_eps": 1e-07,
584
+ "max_position_embeddings": 1680,
585
+ "max_relative_positions": -1,
586
+ "model_type": "deberta-v2",
587
+ "norm_rel_ebd": "layer_norm",
588
+ "num_attention_heads": 12,
589
+ "num_hidden_layers": 6,
590
+ "pad_token_id": 0,
591
+ "pooler_dropout": 0,
592
+ "pooler_hidden_act": "gelu",
593
+ "pooler_hidden_size": 768,
594
+ "pos_att_type": [
595
+ "p2c",
596
+ "c2p"
597
+ ],
598
+ "position_biased_input": false,
599
+ "position_buckets": 256,
600
+ "relative_attention": true,
601
+ "share_att_key": true,
602
+ "tasks": [
603
+ "glue/mnli",
604
+ "glue/qnli",
605
+ "glue/rte",
606
+ "glue/wnli",
607
+ "glue/mrpc",
608
+ "glue/qqp",
609
+ "glue/stsb",
610
+ "super_glue/boolq",
611
+ "super_glue/cb",
612
+ "super_glue/multirc",
613
+ "super_glue/wic",
614
+ "super_glue/axg",
615
+ "anli/a1",
616
+ "anli/a2",
617
+ "anli/a3",
618
+ "sick/label",
619
+ "sick/relatedness",
620
+ "sick/entailment_AB",
621
+ "snli",
622
+ "scitail/snli_format",
623
+ "hans",
624
+ "WANLI",
625
+ "recast/recast_ner",
626
+ "recast/recast_kg_relations",
627
+ "recast/recast_puns",
628
+ "recast/recast_verbcorner",
629
+ "recast/recast_sentiment",
630
+ "recast/recast_verbnet",
631
+ "recast/recast_factuality",
632
+ "recast/recast_megaveridicality",
633
+ "probability_words_nli/reasoning_2hop",
634
+ "probability_words_nli/reasoning_1hop",
635
+ "probability_words_nli/usnli",
636
+ "nan-nli",
637
+ "nli_fever",
638
+ "breaking_nli",
639
+ "conj_nli",
640
+ "fracas",
641
+ "dialogue_nli",
642
+ "mpe",
643
+ "dnc",
644
+ "recast_white/fnplus",
645
+ "recast_white/sprl",
646
+ "recast_white/dpr",
647
+ "joci",
648
+ "robust_nli/IS_CS",
649
+ "robust_nli/LI_LI",
650
+ "robust_nli/ST_WO",
651
+ "robust_nli/PI_SP",
652
+ "robust_nli/PI_CD",
653
+ "robust_nli/ST_SE",
654
+ "robust_nli/ST_NE",
655
+ "robust_nli/ST_LM",
656
+ "robust_nli_is_sd",
657
+ "robust_nli_li_ts",
658
+ "add_one_rte",
659
+ "imppres/implicature_quantifiers/log",
660
+ "imppres/implicature_numerals_2_3/log",
661
+ "imppres/implicature_gradable_adjective/log",
662
+ "imppres/implicature_connectives/log",
663
+ "imppres/implicature_modals/log",
664
+ "imppres/implicature_numerals_10_100/log",
665
+ "imppres/implicature_gradable_verb/log",
666
+ "hlgd",
667
+ "paws/labeled_final",
668
+ "paws/labeled_swap",
669
+ "medical_questions_pairs",
670
+ "model-written-evals",
671
+ "truthful_qa/multiple_choice",
672
+ "fig-qa",
673
+ "bigbench/bbq_lite_json",
674
+ "bigbench/english_proverbs",
675
+ "bigbench/figure_of_speech_detection",
676
+ "bigbench/emoji_movie",
677
+ "bigbench/date_understanding",
678
+ "bigbench/metaphor_understanding",
679
+ "bigbench/logical_fallacy_detection",
680
+ "bigbench/analogical_similarity",
681
+ "bigbench/mnist_ascii",
682
+ "bigbench/elementary_math_qa",
683
+ "bigbench/snarks",
684
+ "bigbench/social_support",
685
+ "bigbench/logical_deduction",
686
+ "bigbench/emojis_emotion_prediction",
687
+ "bigbench/sports_understanding",
688
+ "bigbench/cifar10_classification",
689
+ "bigbench/tracking_shuffled_objects",
690
+ "bigbench/physics",
691
+ "bigbench/mathematical_induction",
692
+ "bigbench/movie_dialog_same_or_different",
693
+ "bigbench/goal_step_wikihow",
694
+ "bigbench/strategyqa",
695
+ "bigbench/identify_math_theorems",
696
+ "bigbench/gre_reading_comprehension",
697
+ "bigbench/novel_concepts",
698
+ "bigbench/conceptual_combinations",
699
+ "bigbench/hyperbaton",
700
+ "bigbench/strange_stories",
701
+ "bigbench/contextual_parametric_knowledge_conflicts",
702
+ "bigbench/implicatures",
703
+ "bigbench/penguins_in_a_table",
704
+ "bigbench/logical_sequence",
705
+ "bigbench/simple_ethical_questions",
706
+ "bigbench/dyck_languages",
707
+ "bigbench/geometric_shapes",
708
+ "bigbench/irony_identification",
709
+ "bigbench/intent_recognition",
710
+ "bigbench/logical_args",
711
+ "bigbench/known_unknowns",
712
+ "bigbench/formal_fallacies_syllogisms_negation",
713
+ "bigbench/suicide_risk",
714
+ "bigbench/crash_blossom",
715
+ "bigbench/logic_grid_puzzle",
716
+ "bigbench/analytic_entailment",
717
+ "bigbench/dark_humor_detection",
718
+ "bigbench/timedial",
719
+ "bigbench/presuppositions_as_nli",
720
+ "bigbench/arithmetic",
721
+ "bigbench/implicit_relations",
722
+ "bigbench/understanding_fables",
723
+ "bigbench/salient_translation_error_detection",
724
+ "bigbench/anachronisms",
725
+ "bigbench/moral_permissibility",
726
+ "bigbench/abstract_narrative_understanding",
727
+ "bigbench/misconceptions",
728
+ "bigbench/nonsense_words_grammar",
729
+ "bigbench/code_line_description",
730
+ "bigbench/sentence_ambiguity",
731
+ "bigbench/disambiguation_qa",
732
+ "bigbench/crass_ai",
733
+ "bigbench/similarities_abstraction",
734
+ "bigbench/authorship_verification",
735
+ "bigbench/phrase_relatedness",
736
+ "bigbench/color",
737
+ "bigbench/hhh_alignment",
738
+ "bigbench/metaphor_boolean",
739
+ "bigbench/fantasy_reasoning",
740
+ "bigbench/ruin_names",
741
+ "bigbench/cause_and_effect",
742
+ "bigbench/temporal_sequences",
743
+ "bigbench/navigate",
744
+ "bigbench/symbol_interpretation",
745
+ "bigbench/key_value_maps",
746
+ "bigbench/entailed_polarity",
747
+ "bigbench/riddle_sense",
748
+ "bigbench/discourse_marker_prediction",
749
+ "bigbench/reasoning_about_colored_objects",
750
+ "bigbench/empirical_judgments",
751
+ "bigbench/fact_checker",
752
+ "bigbench/movie_recommendation",
753
+ "bigbench/checkmate_in_one",
754
+ "bigbench/epistemic_reasoning",
755
+ "bigbench/vitaminc_fact_verification",
756
+ "bigbench/general_knowledge",
757
+ "bigbench/identify_odd_metaphor",
758
+ "bigbench/physical_intuition",
759
+ "bigbench/winowhy",
760
+ "bigbench/cs_algorithms",
761
+ "bigbench/undo_permutation",
762
+ "bigbench/evaluating_information_essentiality",
763
+ "bigbench/unit_interpretation",
764
+ "bigbench/question_selection",
765
+ "bigbench/international_phonetic_alphabet_nli",
766
+ "bigbench/play_dialog_same_or_different",
767
+ "bigbench/real_or_fake_text",
768
+ "bigbench/human_organs_senses",
769
+ "bigbench/hindu_knowledge",
770
+ "bigbench/social_iqa",
771
+ "bigbench/odd_one_out",
772
+ "bigbench/causal_judgment",
773
+ "cos_e/v1.0",
774
+ "cosmos_qa",
775
+ "dream",
776
+ "openbookqa",
777
+ "qasc",
778
+ "quartz",
779
+ "quail",
780
+ "head_qa/en",
781
+ "sciq",
782
+ "social_i_qa",
783
+ "wiki_hop/original",
784
+ "wiqa",
785
+ "piqa",
786
+ "hellaswag",
787
+ "super_glue/copa",
788
+ "balanced-copa",
789
+ "e-CARE",
790
+ "art",
791
+ "winogrande/winogrande_xl",
792
+ "codah/codah",
793
+ "ai2_arc/ARC-Easy/challenge",
794
+ "ai2_arc/ARC-Challenge/challenge",
795
+ "definite_pronoun_resolution",
796
+ "swag/regular",
797
+ "math_qa",
798
+ "glue/cola",
799
+ "glue/sst2",
800
+ "utilitarianism",
801
+ "amazon_counterfactual/en",
802
+ "insincere-questions",
803
+ "toxic_conversations",
804
+ "TuringBench",
805
+ "trec",
806
+ "vitaminc",
807
+ "hope_edi/english",
808
+ "rumoureval_2019/RumourEval2019",
809
+ "ethos/binary",
810
+ "ethos/multilabel",
811
+ "tweet_eval/offensive",
812
+ "tweet_eval/sentiment",
813
+ "tweet_eval/irony",
814
+ "tweet_eval/hate",
815
+ "tweet_eval/emotion",
816
+ "tweet_eval/emoji",
817
+ "tweet_eval/stance_abortion",
818
+ "tweet_eval/stance_atheism",
819
+ "tweet_eval/stance_climate",
820
+ "tweet_eval/stance_feminist",
821
+ "tweet_eval/stance_hillary",
822
+ "discovery/discovery",
823
+ "pragmeval/squinky-formality",
824
+ "pragmeval/emobank-arousal",
825
+ "pragmeval/squinky-implicature",
826
+ "pragmeval/squinky-informativeness",
827
+ "pragmeval/switchboard",
828
+ "pragmeval/verifiability",
829
+ "pragmeval/mrda",
830
+ "pragmeval/emobank-valence",
831
+ "pragmeval/emobank-dominance",
832
+ "pragmeval/persuasiveness-strength",
833
+ "pragmeval/persuasiveness-relevance",
834
+ "pragmeval/pdtb",
835
+ "pragmeval/gum",
836
+ "pragmeval/stac",
837
+ "pragmeval/persuasiveness-specificity",
838
+ "pragmeval/sarcasm",
839
+ "pragmeval/persuasiveness-eloquence",
840
+ "pragmeval/emergent",
841
+ "pragmeval/persuasiveness-premisetype",
842
+ "pragmeval/persuasiveness-claimtype",
843
+ "silicone/meld_e",
844
+ "silicone/dyda_e",
845
+ "silicone/iemocap",
846
+ "silicone/sem",
847
+ "silicone/meld_s",
848
+ "silicone/oasis",
849
+ "silicone/maptask",
850
+ "silicone/dyda_da",
851
+ "lex_glue/eurlex",
852
+ "lex_glue/scotus",
853
+ "lex_glue/ledgar",
854
+ "lex_glue/unfair_tos",
855
+ "lex_glue/case_hold",
856
+ "language-identification",
857
+ "imdb",
858
+ "rotten_tomatoes",
859
+ "ag_news",
860
+ "yelp_review_full/yelp_review_full",
861
+ "financial_phrasebank/sentences_allagree",
862
+ "poem_sentiment",
863
+ "dbpedia_14/dbpedia_14",
864
+ "amazon_polarity/amazon_polarity",
865
+ "app_reviews",
866
+ "hate_speech18",
867
+ "sms_spam",
868
+ "humicroedit/subtask-1",
869
+ "humicroedit/subtask-2",
870
+ "snips_built_in_intents",
871
+ "hate_speech_offensive",
872
+ "yahoo_answers_topics",
873
+ "stackoverflow-questions",
874
+ "hyperpartisan_news",
875
+ "sciie",
876
+ "citation_intent",
877
+ "go_emotions/simplified",
878
+ "scicite",
879
+ "liar",
880
+ "lexical_relation_classification/CogALexV",
881
+ "lexical_relation_classification/EVALution",
882
+ "lexical_relation_classification/K&H+N",
883
+ "lexical_relation_classification/BLESS",
884
+ "lexical_relation_classification/ROOT09",
885
+ "linguisticprobing/obj_number",
886
+ "linguisticprobing/bigram_shift",
887
+ "linguisticprobing/subj_number",
888
+ "linguisticprobing/sentence_length",
889
+ "linguisticprobing/odd_man_out",
890
+ "linguisticprobing/tree_depth",
891
+ "linguisticprobing/top_constituents",
892
+ "linguisticprobing/coordination_inversion",
893
+ "linguisticprobing/past_present",
894
+ "crowdflower/sentiment_nuclear_power",
895
+ "crowdflower/tweet_global_warming",
896
+ "crowdflower/political-media-message",
897
+ "crowdflower/text_emotion",
898
+ "crowdflower/corporate-messaging",
899
+ "crowdflower/political-media-audience",
900
+ "crowdflower/airline-sentiment",
901
+ "crowdflower/political-media-bias",
902
+ "crowdflower/economic-news",
903
+ "ethics/commonsense",
904
+ "ethics/deontology",
905
+ "ethics/justice",
906
+ "ethics/virtue",
907
+ "emo/emo2019",
908
+ "google_wellformed_query",
909
+ "tweets_hate_speech_detection",
910
+ "has_part",
911
+ "blog_authorship_corpus/gender",
912
+ "blog_authorship_corpus/age",
913
+ "blog_authorship_corpus/job",
914
+ "open_question_type",
915
+ "health_fact",
916
+ "commonsense_qa",
917
+ "mc_taco",
918
+ "ade_corpus_v2/Ade_corpus_v2_classification",
919
+ "discosense",
920
+ "circa",
921
+ "phrase_similarity",
922
+ "scientific-exaggeration-detection",
923
+ "quarel",
924
+ "fever-evidence-related",
925
+ "numer_sense",
926
+ "dynasent/dynabench.dynasent.r1.all/r1",
927
+ "dynasent/dynabench.dynasent.r2.all/r2",
928
+ "Sarcasm_News_Headline",
929
+ "sem_eval_2010_task_8",
930
+ "auditor_review",
931
+ "medmcqa",
932
+ "Dynasent_Disagreement",
933
+ "Politeness_Disagreement",
934
+ "SBIC_Disagreement",
935
+ "SChem_Disagreement",
936
+ "Dilemmas_Disagreement",
937
+ "logiqa",
938
+ "wiki_qa",
939
+ "cycic_classification",
940
+ "cycic_multiplechoice",
941
+ "sts-companion",
942
+ "commonsense_qa_2.0",
943
+ "lingnli",
944
+ "monotonicity-entailment",
945
+ "arct",
946
+ "scinli",
947
+ "naturallogic",
948
+ "onestop_qa",
949
+ "moral_stories/full",
950
+ "prost",
951
+ "dynahate",
952
+ "syntactic-augmentation-nli",
953
+ "autotnli",
954
+ "CONDAQA",
955
+ "webgpt_comparisons",
956
+ "synthetic-instruct-gptj-pairwise",
957
+ "scruples",
958
+ "wouldyourather",
959
+ "defeasible-nli/atomic",
960
+ "defeasible-nli/snli",
961
+ "help-nli",
962
+ "nli-veridicality-transitivity",
963
+ "lonli",
964
+ "dadc-limit-nli",
965
+ "FLUTE",
966
+ "strategy-qa",
967
+ "summarize_from_feedback/comparisons",
968
+ "folio",
969
+ "tomi-nli",
970
+ "avicenna",
971
+ "SHP",
972
+ "MedQA-USMLE-4-options-hf",
973
+ "wikimedqa/medwiki",
974
+ "cicero",
975
+ "CREAK",
976
+ "mutual",
977
+ "NeQA",
978
+ "quote-repetition",
979
+ "redefine-math",
980
+ "puzzte",
981
+ "implicatures",
982
+ "race/middle",
983
+ "race/high",
984
+ "race-c",
985
+ "spartqa-yn",
986
+ "spartqa-mchoice",
987
+ "temporal-nli",
988
+ "riddle_sense",
989
+ "clcd-english",
990
+ "twentyquestions",
991
+ "reclor",
992
+ "counterfactually-augmented-imdb",
993
+ "counterfactually-augmented-snli",
994
+ "cnli",
995
+ "boolq-natural-perturbations",
996
+ "acceptability-prediction",
997
+ "equate",
998
+ "ScienceQA_text_only",
999
+ "ekar_english",
1000
+ "implicit-hate-stg1",
1001
+ "chaos-mnli-ambiguity",
1002
+ "headline_cause/en_simple",
1003
+ "logiqa-2.0-nli",
1004
+ "oasst2_dense_flat/quality",
1005
+ "oasst2_dense_flat/toxicity",
1006
+ "oasst2_dense_flat/helpfulness",
1007
+ "mindgames",
1008
+ "ambient",
1009
+ "path-naturalness-prediction",
1010
+ "civil_comments/toxicity",
1011
+ "civil_comments/severe_toxicity",
1012
+ "civil_comments/obscene",
1013
+ "civil_comments/threat",
1014
+ "civil_comments/insult",
1015
+ "civil_comments/identity_attack",
1016
+ "civil_comments/sexual_explicit",
1017
+ "cloth",
1018
+ "dgen",
1019
+ "I2D2",
1020
+ "args_me",
1021
+ "Touche23-ValueEval",
1022
+ "starcon",
1023
+ "banking77",
1024
+ "ConTRoL-nli",
1025
+ "tracie",
1026
+ "sherliic",
1027
+ "sen-making/1",
1028
+ "sen-making/2",
1029
+ "winowhy",
1030
+ "robustLR",
1031
+ "v1/gen_train234_test2to10",
1032
+ "logical-fallacy",
1033
+ "parade",
1034
+ "cladder",
1035
+ "subjectivity",
1036
+ "MOH",
1037
+ "VUAC",
1038
+ "sharc_modified/mod",
1039
+ "conceptrules_v2",
1040
+ "disrpt/eng.dep.scidtb.rels",
1041
+ "zero-shot-label-nli",
1042
+ "com2sense",
1043
+ "scone",
1044
+ "winodict",
1045
+ "fool-me-twice",
1046
+ "monli",
1047
+ "corr2cause",
1048
+ "lsat_qa/all",
1049
+ "apt",
1050
+ "twitter-financial-news-sentiment",
1051
+ "icl-symbol-tuning-instruct",
1052
+ "SpaceNLI",
1053
+ "propsegment/nli",
1054
+ "HatemojiBuild",
1055
+ "regset",
1056
+ "esci",
1057
+ "chatbot_arena_conversations",
1058
+ "dnd_style_intents",
1059
+ "FLD.v2/default",
1060
+ "FLD.v2/star",
1061
+ "SDOH-NLI",
1062
+ "scifact_entailment",
1063
+ "feasibilityQA",
1064
+ "simple_pair",
1065
+ "AdjectiveScaleProbe-nli",
1066
+ "resnli",
1067
+ "SpaRTUN",
1068
+ "ReSQ",
1069
+ "semantic_fragments_nli",
1070
+ "dataset_train_nli",
1071
+ "stepgame",
1072
+ "nlgraph",
1073
+ "oasst2_pairwise_rlhf_reward",
1074
+ "hh-rlhf/helpful-base",
1075
+ "hh-rlhf/helpful-online",
1076
+ "hh-rlhf/helpful-rejection-sampled",
1077
+ "hh-rlhf/harmless-base",
1078
+ "ruletaker",
1079
+ "PARARULE-Plus",
1080
+ "proofwriter",
1081
+ "logical-entailment",
1082
+ "nope",
1083
+ "LogicNLI",
1084
+ "contract-nli/contractnli_a/seg",
1085
+ "contract-nli/contractnli_b/full",
1086
+ "nli4ct_semeval2024",
1087
+ "lsat-ar",
1088
+ "lsat-rc",
1089
+ "biosift-nli",
1090
+ "brainteasers/WP",
1091
+ "brainteasers/SP",
1092
+ "persuasion",
1093
+ "AmbigNQ-clarifying-question",
1094
+ "SIGA-nli",
1095
+ "FOL-nli",
1096
+ "goal-step-wikihow/order",
1097
+ "PARADISE",
1098
+ "doc-nli",
1099
+ "mctest-nli",
1100
+ "patent-phrase-similarity",
1101
+ "natural-language-satisfiability",
1102
+ "idioms-nli",
1103
+ "lifecycle-entailment",
1104
+ "HelpSteer/helpfulness",
1105
+ "HelpSteer/correctness",
1106
+ "HelpSteer/coherence",
1107
+ "HelpSteer/complexity",
1108
+ "HelpSteer/verbosity",
1109
+ "HelpSteer2/helpfulness",
1110
+ "HelpSteer2/correctness",
1111
+ "HelpSteer2/coherence",
1112
+ "HelpSteer2/complexity",
1113
+ "HelpSteer2/verbosity",
1114
+ "MSciNLI",
1115
+ "UltraFeedback-paired",
1116
+ "AES2-essay-scoring",
1117
+ "english-grading/cohesion",
1118
+ "english-grading/syntax",
1119
+ "english-grading/vocabulary",
1120
+ "english-grading/phraseology",
1121
+ "english-grading/grammar",
1122
+ "english-grading/conventions",
1123
+ "wice",
1124
+ "hover",
1125
+ "tasksource_dpo_pairs",
1126
+ "seahorse_summarization_evaluation",
1127
+ "missing-item-prediction/contrastive",
1128
+ "babi_nli",
1129
+ "gen_debiased_nli",
1130
+ "imppres/presupposition",
1131
+ "/prag",
1132
+ "blimp-2"
1133
+ ],
1134
+ "torch_dtype": "float32",
1135
+ "transformers_version": "4.44.1",
1136
+ "type_vocab_size": 0,
1137
+ "vocab_size": 128100
1138
+ }
checkpoint-125/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f243f21c43e25ef5a91ee9a57e314b5e4ddd47478e562a0dec3ca562962005
3
+ size 567644700
checkpoint-125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6d274c8526b7f87dbb2aceb59d6fbcbbe9934de6f217715386e4a5b8bb04ca
3
+ size 1135352762
checkpoint-125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ea41fa2429f33ae3776e80dce5d6dea9217682b9d1ce87c7be307080c49339
3
+ size 14244
checkpoint-125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0819444978676ac43808e788b0dc5feedc57ea2d09899e2f3d55db5941e919bb
3
+ size 1064
checkpoint-125/trainer_state.json ADDED
@@ -0,0 +1,1007 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.6780412197113037,
3
+ "best_model_checkpoint": "autotrain-dpdvy-2fgj4/checkpoint-125",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 125,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "grad_norm": 14.090579986572266,
14
+ "learning_rate": 3.846153846153847e-06,
15
+ "loss": 3.0673,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.08,
20
+ "grad_norm": 12.678583145141602,
21
+ "learning_rate": 7.692307692307694e-06,
22
+ "loss": 3.1665,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.12,
27
+ "grad_norm": 13.062363624572754,
28
+ "learning_rate": 1.153846153846154e-05,
29
+ "loss": 3.0745,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.16,
34
+ "grad_norm": 12.005086898803711,
35
+ "learning_rate": 1.5384615384615387e-05,
36
+ "loss": 2.9223,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.2,
41
+ "grad_norm": 12.953086853027344,
42
+ "learning_rate": 1.923076923076923e-05,
43
+ "loss": 3.1513,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.24,
48
+ "grad_norm": 13.483661651611328,
49
+ "learning_rate": 2.307692307692308e-05,
50
+ "loss": 3.1013,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.28,
55
+ "grad_norm": 13.102580070495605,
56
+ "learning_rate": 2.6923076923076923e-05,
57
+ "loss": 2.9917,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.32,
62
+ "grad_norm": Infinity,
63
+ "learning_rate": 2.6923076923076923e-05,
64
+ "loss": 3.0553,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.36,
69
+ "grad_norm": 12.6341552734375,
70
+ "learning_rate": 3.0769230769230774e-05,
71
+ "loss": 3.1777,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.4,
76
+ "grad_norm": 10.707420349121094,
77
+ "learning_rate": 3.461538461538462e-05,
78
+ "loss": 2.9388,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.44,
83
+ "grad_norm": 10.78902530670166,
84
+ "learning_rate": 3.846153846153846e-05,
85
+ "loss": 3.0375,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.48,
90
+ "grad_norm": 12.372330665588379,
91
+ "learning_rate": 4.230769230769231e-05,
92
+ "loss": 2.9353,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.52,
97
+ "grad_norm": 11.65170955657959,
98
+ "learning_rate": 4.615384615384616e-05,
99
+ "loss": 2.8238,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.56,
104
+ "grad_norm": 10.07817268371582,
105
+ "learning_rate": 5e-05,
106
+ "loss": 3.1418,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.6,
111
+ "grad_norm": 11.010019302368164,
112
+ "learning_rate": 4.955357142857143e-05,
113
+ "loss": 2.7185,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.64,
118
+ "grad_norm": 11.038318634033203,
119
+ "learning_rate": 4.910714285714286e-05,
120
+ "loss": 2.9647,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.68,
125
+ "grad_norm": 10.025190353393555,
126
+ "learning_rate": 4.866071428571429e-05,
127
+ "loss": 2.7857,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.72,
132
+ "grad_norm": 10.354557991027832,
133
+ "learning_rate": 4.8214285714285716e-05,
134
+ "loss": 2.726,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.76,
139
+ "grad_norm": 9.022831916809082,
140
+ "learning_rate": 4.7767857142857144e-05,
141
+ "loss": 2.7734,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.8,
146
+ "grad_norm": 8.233414649963379,
147
+ "learning_rate": 4.732142857142857e-05,
148
+ "loss": 2.8013,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.84,
153
+ "grad_norm": 9.093657493591309,
154
+ "learning_rate": 4.6875e-05,
155
+ "loss": 2.7761,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.88,
160
+ "grad_norm": 9.356589317321777,
161
+ "learning_rate": 4.642857142857143e-05,
162
+ "loss": 2.7867,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.92,
167
+ "grad_norm": 7.915736198425293,
168
+ "learning_rate": 4.598214285714286e-05,
169
+ "loss": 2.5973,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.96,
174
+ "grad_norm": 9.075019836425781,
175
+ "learning_rate": 4.5535714285714286e-05,
176
+ "loss": 2.7835,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 1.0,
181
+ "grad_norm": 15.833548545837402,
182
+ "learning_rate": 4.5089285714285714e-05,
183
+ "loss": 2.8758,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 1.0,
188
+ "eval_accuracy": 0.1326530612244898,
189
+ "eval_f1_macro": 0.057275273745861985,
190
+ "eval_f1_micro": 0.1326530612244898,
191
+ "eval_f1_weighted": 0.08088347027122537,
192
+ "eval_loss": 2.653775930404663,
193
+ "eval_precision_macro": 0.044651835093011565,
194
+ "eval_precision_micro": 0.1326530612244898,
195
+ "eval_precision_weighted": 0.06580869527298099,
196
+ "eval_recall_macro": 0.09901960784313725,
197
+ "eval_recall_micro": 0.1326530612244898,
198
+ "eval_recall_weighted": 0.1326530612244898,
199
+ "eval_runtime": 0.1203,
200
+ "eval_samples_per_second": 814.945,
201
+ "eval_steps_per_second": 33.263,
202
+ "step": 25
203
+ },
204
+ {
205
+ "epoch": 1.04,
206
+ "grad_norm": 7.568680763244629,
207
+ "learning_rate": 4.464285714285715e-05,
208
+ "loss": 2.5985,
209
+ "step": 26
210
+ },
211
+ {
212
+ "epoch": 1.08,
213
+ "grad_norm": 9.416265487670898,
214
+ "learning_rate": 4.419642857142857e-05,
215
+ "loss": 2.3711,
216
+ "step": 27
217
+ },
218
+ {
219
+ "epoch": 1.12,
220
+ "grad_norm": 8.699418067932129,
221
+ "learning_rate": 4.375e-05,
222
+ "loss": 2.5099,
223
+ "step": 28
224
+ },
225
+ {
226
+ "epoch": 1.16,
227
+ "grad_norm": 9.023210525512695,
228
+ "learning_rate": 4.3303571428571435e-05,
229
+ "loss": 2.4655,
230
+ "step": 29
231
+ },
232
+ {
233
+ "epoch": 1.2,
234
+ "grad_norm": 9.81415843963623,
235
+ "learning_rate": 4.2857142857142856e-05,
236
+ "loss": 2.4712,
237
+ "step": 30
238
+ },
239
+ {
240
+ "epoch": 1.24,
241
+ "grad_norm": 9.26953411102295,
242
+ "learning_rate": 4.2410714285714285e-05,
243
+ "loss": 2.432,
244
+ "step": 31
245
+ },
246
+ {
247
+ "epoch": 1.28,
248
+ "grad_norm": 9.773411750793457,
249
+ "learning_rate": 4.196428571428572e-05,
250
+ "loss": 2.38,
251
+ "step": 32
252
+ },
253
+ {
254
+ "epoch": 1.32,
255
+ "grad_norm": 8.679231643676758,
256
+ "learning_rate": 4.151785714285715e-05,
257
+ "loss": 2.3639,
258
+ "step": 33
259
+ },
260
+ {
261
+ "epoch": 1.3599999999999999,
262
+ "grad_norm": 9.794059753417969,
263
+ "learning_rate": 4.107142857142857e-05,
264
+ "loss": 2.3523,
265
+ "step": 34
266
+ },
267
+ {
268
+ "epoch": 1.4,
269
+ "grad_norm": 10.422601699829102,
270
+ "learning_rate": 4.0625000000000005e-05,
271
+ "loss": 2.3657,
272
+ "step": 35
273
+ },
274
+ {
275
+ "epoch": 1.44,
276
+ "grad_norm": 8.450103759765625,
277
+ "learning_rate": 4.017857142857143e-05,
278
+ "loss": 2.3282,
279
+ "step": 36
280
+ },
281
+ {
282
+ "epoch": 1.48,
283
+ "grad_norm": 9.94312858581543,
284
+ "learning_rate": 3.9732142857142855e-05,
285
+ "loss": 2.36,
286
+ "step": 37
287
+ },
288
+ {
289
+ "epoch": 1.52,
290
+ "grad_norm": 10.141396522521973,
291
+ "learning_rate": 3.928571428571429e-05,
292
+ "loss": 2.4293,
293
+ "step": 38
294
+ },
295
+ {
296
+ "epoch": 1.56,
297
+ "grad_norm": 9.665178298950195,
298
+ "learning_rate": 3.883928571428572e-05,
299
+ "loss": 2.2062,
300
+ "step": 39
301
+ },
302
+ {
303
+ "epoch": 1.6,
304
+ "grad_norm": 11.53431510925293,
305
+ "learning_rate": 3.839285714285715e-05,
306
+ "loss": 2.4555,
307
+ "step": 40
308
+ },
309
+ {
310
+ "epoch": 1.6400000000000001,
311
+ "grad_norm": 10.239005088806152,
312
+ "learning_rate": 3.794642857142857e-05,
313
+ "loss": 2.2474,
314
+ "step": 41
315
+ },
316
+ {
317
+ "epoch": 1.6800000000000002,
318
+ "grad_norm": 11.729203224182129,
319
+ "learning_rate": 3.7500000000000003e-05,
320
+ "loss": 2.4625,
321
+ "step": 42
322
+ },
323
+ {
324
+ "epoch": 1.72,
325
+ "grad_norm": 13.804224014282227,
326
+ "learning_rate": 3.705357142857143e-05,
327
+ "loss": 2.4599,
328
+ "step": 43
329
+ },
330
+ {
331
+ "epoch": 1.76,
332
+ "grad_norm": 10.596861839294434,
333
+ "learning_rate": 3.6607142857142853e-05,
334
+ "loss": 2.3025,
335
+ "step": 44
336
+ },
337
+ {
338
+ "epoch": 1.8,
339
+ "grad_norm": 10.572052955627441,
340
+ "learning_rate": 3.616071428571429e-05,
341
+ "loss": 2.3181,
342
+ "step": 45
343
+ },
344
+ {
345
+ "epoch": 1.8399999999999999,
346
+ "grad_norm": 11.940258026123047,
347
+ "learning_rate": 3.571428571428572e-05,
348
+ "loss": 2.2404,
349
+ "step": 46
350
+ },
351
+ {
352
+ "epoch": 1.88,
353
+ "grad_norm": 11.33704662322998,
354
+ "learning_rate": 3.5267857142857145e-05,
355
+ "loss": 2.5559,
356
+ "step": 47
357
+ },
358
+ {
359
+ "epoch": 1.92,
360
+ "grad_norm": 12.002726554870605,
361
+ "learning_rate": 3.4821428571428574e-05,
362
+ "loss": 2.0579,
363
+ "step": 48
364
+ },
365
+ {
366
+ "epoch": 1.96,
367
+ "grad_norm": 11.418220520019531,
368
+ "learning_rate": 3.4375e-05,
369
+ "loss": 2.1282,
370
+ "step": 49
371
+ },
372
+ {
373
+ "epoch": 2.0,
374
+ "grad_norm": 17.700702667236328,
375
+ "learning_rate": 3.392857142857143e-05,
376
+ "loss": 2.4874,
377
+ "step": 50
378
+ },
379
+ {
380
+ "epoch": 2.0,
381
+ "eval_accuracy": 0.2857142857142857,
382
+ "eval_f1_macro": 0.19056662291956414,
383
+ "eval_f1_micro": 0.2857142857142857,
384
+ "eval_f1_weighted": 0.22140982600166276,
385
+ "eval_loss": 2.349097967147827,
386
+ "eval_precision_macro": 0.21696943483275663,
387
+ "eval_precision_micro": 0.2857142857142857,
388
+ "eval_precision_weighted": 0.23142757102841136,
389
+ "eval_recall_macro": 0.2230392156862745,
390
+ "eval_recall_micro": 0.2857142857142857,
391
+ "eval_recall_weighted": 0.2857142857142857,
392
+ "eval_runtime": 0.116,
393
+ "eval_samples_per_second": 845.135,
394
+ "eval_steps_per_second": 34.495,
395
+ "step": 50
396
+ },
397
+ {
398
+ "epoch": 2.04,
399
+ "grad_norm": 10.884347915649414,
400
+ "learning_rate": 3.348214285714286e-05,
401
+ "loss": 2.0613,
402
+ "step": 51
403
+ },
404
+ {
405
+ "epoch": 2.08,
406
+ "grad_norm": 10.920637130737305,
407
+ "learning_rate": 3.303571428571429e-05,
408
+ "loss": 1.9789,
409
+ "step": 52
410
+ },
411
+ {
412
+ "epoch": 2.12,
413
+ "grad_norm": 10.85609245300293,
414
+ "learning_rate": 3.2589285714285716e-05,
415
+ "loss": 1.8808,
416
+ "step": 53
417
+ },
418
+ {
419
+ "epoch": 2.16,
420
+ "grad_norm": 10.412084579467773,
421
+ "learning_rate": 3.2142857142857144e-05,
422
+ "loss": 1.9346,
423
+ "step": 54
424
+ },
425
+ {
426
+ "epoch": 2.2,
427
+ "grad_norm": 9.992473602294922,
428
+ "learning_rate": 3.169642857142857e-05,
429
+ "loss": 1.5298,
430
+ "step": 55
431
+ },
432
+ {
433
+ "epoch": 2.24,
434
+ "grad_norm": 12.011486053466797,
435
+ "learning_rate": 3.125e-05,
436
+ "loss": 2.1032,
437
+ "step": 56
438
+ },
439
+ {
440
+ "epoch": 2.2800000000000002,
441
+ "grad_norm": 12.152674674987793,
442
+ "learning_rate": 3.080357142857143e-05,
443
+ "loss": 2.0241,
444
+ "step": 57
445
+ },
446
+ {
447
+ "epoch": 2.32,
448
+ "grad_norm": 11.63778305053711,
449
+ "learning_rate": 3.0357142857142857e-05,
450
+ "loss": 2.1084,
451
+ "step": 58
452
+ },
453
+ {
454
+ "epoch": 2.36,
455
+ "grad_norm": 10.898219108581543,
456
+ "learning_rate": 2.9910714285714286e-05,
457
+ "loss": 1.8422,
458
+ "step": 59
459
+ },
460
+ {
461
+ "epoch": 2.4,
462
+ "grad_norm": 10.050783157348633,
463
+ "learning_rate": 2.9464285714285718e-05,
464
+ "loss": 1.6849,
465
+ "step": 60
466
+ },
467
+ {
468
+ "epoch": 2.44,
469
+ "grad_norm": 11.283549308776855,
470
+ "learning_rate": 2.9017857142857146e-05,
471
+ "loss": 1.6371,
472
+ "step": 61
473
+ },
474
+ {
475
+ "epoch": 2.48,
476
+ "grad_norm": 10.182291030883789,
477
+ "learning_rate": 2.857142857142857e-05,
478
+ "loss": 1.8368,
479
+ "step": 62
480
+ },
481
+ {
482
+ "epoch": 2.52,
483
+ "grad_norm": 10.567183494567871,
484
+ "learning_rate": 2.8125000000000003e-05,
485
+ "loss": 1.7345,
486
+ "step": 63
487
+ },
488
+ {
489
+ "epoch": 2.56,
490
+ "grad_norm": 13.132766723632812,
491
+ "learning_rate": 2.767857142857143e-05,
492
+ "loss": 1.9293,
493
+ "step": 64
494
+ },
495
+ {
496
+ "epoch": 2.6,
497
+ "grad_norm": 11.20378589630127,
498
+ "learning_rate": 2.7232142857142856e-05,
499
+ "loss": 1.9088,
500
+ "step": 65
501
+ },
502
+ {
503
+ "epoch": 2.64,
504
+ "grad_norm": 9.244080543518066,
505
+ "learning_rate": 2.6785714285714288e-05,
506
+ "loss": 1.8632,
507
+ "step": 66
508
+ },
509
+ {
510
+ "epoch": 2.68,
511
+ "grad_norm": 14.100431442260742,
512
+ "learning_rate": 2.6339285714285716e-05,
513
+ "loss": 2.0808,
514
+ "step": 67
515
+ },
516
+ {
517
+ "epoch": 2.7199999999999998,
518
+ "grad_norm": 10.50901985168457,
519
+ "learning_rate": 2.5892857142857148e-05,
520
+ "loss": 1.7468,
521
+ "step": 68
522
+ },
523
+ {
524
+ "epoch": 2.76,
525
+ "grad_norm": 10.505558013916016,
526
+ "learning_rate": 2.544642857142857e-05,
527
+ "loss": 1.7015,
528
+ "step": 69
529
+ },
530
+ {
531
+ "epoch": 2.8,
532
+ "grad_norm": 10.95505428314209,
533
+ "learning_rate": 2.5e-05,
534
+ "loss": 1.5555,
535
+ "step": 70
536
+ },
537
+ {
538
+ "epoch": 2.84,
539
+ "grad_norm": 12.247352600097656,
540
+ "learning_rate": 2.455357142857143e-05,
541
+ "loss": 1.8414,
542
+ "step": 71
543
+ },
544
+ {
545
+ "epoch": 2.88,
546
+ "grad_norm": 14.747278213500977,
547
+ "learning_rate": 2.4107142857142858e-05,
548
+ "loss": 1.7425,
549
+ "step": 72
550
+ },
551
+ {
552
+ "epoch": 2.92,
553
+ "grad_norm": 12.440173149108887,
554
+ "learning_rate": 2.3660714285714286e-05,
555
+ "loss": 1.8499,
556
+ "step": 73
557
+ },
558
+ {
559
+ "epoch": 2.96,
560
+ "grad_norm": 9.904756546020508,
561
+ "learning_rate": 2.3214285714285715e-05,
562
+ "loss": 1.523,
563
+ "step": 74
564
+ },
565
+ {
566
+ "epoch": 3.0,
567
+ "grad_norm": 17.330537796020508,
568
+ "learning_rate": 2.2767857142857143e-05,
569
+ "loss": 1.8983,
570
+ "step": 75
571
+ },
572
+ {
573
+ "epoch": 3.0,
574
+ "eval_accuracy": 0.46938775510204084,
575
+ "eval_f1_macro": 0.39296402771634975,
576
+ "eval_f1_micro": 0.46938775510204084,
577
+ "eval_f1_weighted": 0.42382422893969623,
578
+ "eval_loss": 1.962062120437622,
579
+ "eval_precision_macro": 0.4379509379509379,
580
+ "eval_precision_micro": 0.46938775510204084,
581
+ "eval_precision_weighted": 0.4513148982536737,
582
+ "eval_recall_macro": 0.4205882352941176,
583
+ "eval_recall_micro": 0.46938775510204084,
584
+ "eval_recall_weighted": 0.46938775510204084,
585
+ "eval_runtime": 0.1162,
586
+ "eval_samples_per_second": 843.061,
587
+ "eval_steps_per_second": 34.411,
588
+ "step": 75
589
+ },
590
+ {
591
+ "epoch": 3.04,
592
+ "grad_norm": 11.348670959472656,
593
+ "learning_rate": 2.2321428571428575e-05,
594
+ "loss": 1.4333,
595
+ "step": 76
596
+ },
597
+ {
598
+ "epoch": 3.08,
599
+ "grad_norm": 10.445756912231445,
600
+ "learning_rate": 2.1875e-05,
601
+ "loss": 1.6537,
602
+ "step": 77
603
+ },
604
+ {
605
+ "epoch": 3.12,
606
+ "grad_norm": 10.392913818359375,
607
+ "learning_rate": 2.1428571428571428e-05,
608
+ "loss": 1.383,
609
+ "step": 78
610
+ },
611
+ {
612
+ "epoch": 3.16,
613
+ "grad_norm": 9.649495124816895,
614
+ "learning_rate": 2.098214285714286e-05,
615
+ "loss": 1.4573,
616
+ "step": 79
617
+ },
618
+ {
619
+ "epoch": 3.2,
620
+ "grad_norm": 9.06779670715332,
621
+ "learning_rate": 2.0535714285714285e-05,
622
+ "loss": 1.3847,
623
+ "step": 80
624
+ },
625
+ {
626
+ "epoch": 3.24,
627
+ "grad_norm": 11.916837692260742,
628
+ "learning_rate": 2.0089285714285717e-05,
629
+ "loss": 1.4877,
630
+ "step": 81
631
+ },
632
+ {
633
+ "epoch": 3.2800000000000002,
634
+ "grad_norm": 10.652131080627441,
635
+ "learning_rate": 1.9642857142857145e-05,
636
+ "loss": 1.614,
637
+ "step": 82
638
+ },
639
+ {
640
+ "epoch": 3.32,
641
+ "grad_norm": 9.547950744628906,
642
+ "learning_rate": 1.9196428571428573e-05,
643
+ "loss": 1.4662,
644
+ "step": 83
645
+ },
646
+ {
647
+ "epoch": 3.36,
648
+ "grad_norm": 11.057686805725098,
649
+ "learning_rate": 1.8750000000000002e-05,
650
+ "loss": 1.3756,
651
+ "step": 84
652
+ },
653
+ {
654
+ "epoch": 3.4,
655
+ "grad_norm": 11.566869735717773,
656
+ "learning_rate": 1.8303571428571427e-05,
657
+ "loss": 1.5774,
658
+ "step": 85
659
+ },
660
+ {
661
+ "epoch": 3.44,
662
+ "grad_norm": 13.334156036376953,
663
+ "learning_rate": 1.785714285714286e-05,
664
+ "loss": 1.5652,
665
+ "step": 86
666
+ },
667
+ {
668
+ "epoch": 3.48,
669
+ "grad_norm": 12.016660690307617,
670
+ "learning_rate": 1.7410714285714287e-05,
671
+ "loss": 1.5098,
672
+ "step": 87
673
+ },
674
+ {
675
+ "epoch": 3.52,
676
+ "grad_norm": 9.972099304199219,
677
+ "learning_rate": 1.6964285714285715e-05,
678
+ "loss": 1.3357,
679
+ "step": 88
680
+ },
681
+ {
682
+ "epoch": 3.56,
683
+ "grad_norm": 10.04750919342041,
684
+ "learning_rate": 1.6517857142857144e-05,
685
+ "loss": 1.2745,
686
+ "step": 89
687
+ },
688
+ {
689
+ "epoch": 3.6,
690
+ "grad_norm": 10.588435173034668,
691
+ "learning_rate": 1.6071428571428572e-05,
692
+ "loss": 1.0839,
693
+ "step": 90
694
+ },
695
+ {
696
+ "epoch": 3.64,
697
+ "grad_norm": 10.37175178527832,
698
+ "learning_rate": 1.5625e-05,
699
+ "loss": 1.1205,
700
+ "step": 91
701
+ },
702
+ {
703
+ "epoch": 3.68,
704
+ "grad_norm": 10.8080415725708,
705
+ "learning_rate": 1.5178571428571429e-05,
706
+ "loss": 1.4232,
707
+ "step": 92
708
+ },
709
+ {
710
+ "epoch": 3.7199999999999998,
711
+ "grad_norm": 9.315281867980957,
712
+ "learning_rate": 1.4732142857142859e-05,
713
+ "loss": 1.175,
714
+ "step": 93
715
+ },
716
+ {
717
+ "epoch": 3.76,
718
+ "grad_norm": 10.718316078186035,
719
+ "learning_rate": 1.4285714285714285e-05,
720
+ "loss": 1.3465,
721
+ "step": 94
722
+ },
723
+ {
724
+ "epoch": 3.8,
725
+ "grad_norm": 10.400609970092773,
726
+ "learning_rate": 1.3839285714285715e-05,
727
+ "loss": 1.3037,
728
+ "step": 95
729
+ },
730
+ {
731
+ "epoch": 3.84,
732
+ "grad_norm": 10.373046875,
733
+ "learning_rate": 1.3392857142857144e-05,
734
+ "loss": 1.3794,
735
+ "step": 96
736
+ },
737
+ {
738
+ "epoch": 3.88,
739
+ "grad_norm": 12.27895736694336,
740
+ "learning_rate": 1.2946428571428574e-05,
741
+ "loss": 1.5354,
742
+ "step": 97
743
+ },
744
+ {
745
+ "epoch": 3.92,
746
+ "grad_norm": 9.416078567504883,
747
+ "learning_rate": 1.25e-05,
748
+ "loss": 1.1127,
749
+ "step": 98
750
+ },
751
+ {
752
+ "epoch": 3.96,
753
+ "grad_norm": 10.97613525390625,
754
+ "learning_rate": 1.2053571428571429e-05,
755
+ "loss": 1.208,
756
+ "step": 99
757
+ },
758
+ {
759
+ "epoch": 4.0,
760
+ "grad_norm": 19.747652053833008,
761
+ "learning_rate": 1.1607142857142857e-05,
762
+ "loss": 1.3328,
763
+ "step": 100
764
+ },
765
+ {
766
+ "epoch": 4.0,
767
+ "eval_accuracy": 0.5612244897959183,
768
+ "eval_f1_macro": 0.4927701383583736,
769
+ "eval_f1_micro": 0.5612244897959183,
770
+ "eval_f1_weighted": 0.5213652560591336,
771
+ "eval_loss": 1.7371511459350586,
772
+ "eval_precision_macro": 0.5056022408963585,
773
+ "eval_precision_micro": 0.5612244897959183,
774
+ "eval_precision_weighted": 0.5240767735665695,
775
+ "eval_recall_macro": 0.5225490196078431,
776
+ "eval_recall_micro": 0.5612244897959183,
777
+ "eval_recall_weighted": 0.5612244897959183,
778
+ "eval_runtime": 0.1152,
779
+ "eval_samples_per_second": 850.765,
780
+ "eval_steps_per_second": 34.725,
781
+ "step": 100
782
+ },
783
+ {
784
+ "epoch": 4.04,
785
+ "grad_norm": 9.819528579711914,
786
+ "learning_rate": 1.1160714285714287e-05,
787
+ "loss": 1.2081,
788
+ "step": 101
789
+ },
790
+ {
791
+ "epoch": 4.08,
792
+ "grad_norm": 9.64730453491211,
793
+ "learning_rate": 1.0714285714285714e-05,
794
+ "loss": 1.1187,
795
+ "step": 102
796
+ },
797
+ {
798
+ "epoch": 4.12,
799
+ "grad_norm": 10.466198921203613,
800
+ "learning_rate": 1.0267857142857142e-05,
801
+ "loss": 1.3042,
802
+ "step": 103
803
+ },
804
+ {
805
+ "epoch": 4.16,
806
+ "grad_norm": 10.586526870727539,
807
+ "learning_rate": 9.821428571428573e-06,
808
+ "loss": 1.2627,
809
+ "step": 104
810
+ },
811
+ {
812
+ "epoch": 4.2,
813
+ "grad_norm": 11.021370887756348,
814
+ "learning_rate": 9.375000000000001e-06,
815
+ "loss": 1.369,
816
+ "step": 105
817
+ },
818
+ {
819
+ "epoch": 4.24,
820
+ "grad_norm": 9.286604881286621,
821
+ "learning_rate": 8.92857142857143e-06,
822
+ "loss": 1.0915,
823
+ "step": 106
824
+ },
825
+ {
826
+ "epoch": 4.28,
827
+ "grad_norm": 10.715047836303711,
828
+ "learning_rate": 8.482142857142858e-06,
829
+ "loss": 1.28,
830
+ "step": 107
831
+ },
832
+ {
833
+ "epoch": 4.32,
834
+ "grad_norm": 9.866848945617676,
835
+ "learning_rate": 8.035714285714286e-06,
836
+ "loss": 1.0737,
837
+ "step": 108
838
+ },
839
+ {
840
+ "epoch": 4.36,
841
+ "grad_norm": 10.503690719604492,
842
+ "learning_rate": 7.589285714285714e-06,
843
+ "loss": 1.1515,
844
+ "step": 109
845
+ },
846
+ {
847
+ "epoch": 4.4,
848
+ "grad_norm": 9.61823844909668,
849
+ "learning_rate": 7.142857142857143e-06,
850
+ "loss": 1.0827,
851
+ "step": 110
852
+ },
853
+ {
854
+ "epoch": 4.44,
855
+ "grad_norm": 10.555536270141602,
856
+ "learning_rate": 6.696428571428572e-06,
857
+ "loss": 1.1674,
858
+ "step": 111
859
+ },
860
+ {
861
+ "epoch": 4.48,
862
+ "grad_norm": 9.302597999572754,
863
+ "learning_rate": 6.25e-06,
864
+ "loss": 1.0401,
865
+ "step": 112
866
+ },
867
+ {
868
+ "epoch": 4.52,
869
+ "grad_norm": 11.41283130645752,
870
+ "learning_rate": 5.803571428571429e-06,
871
+ "loss": 1.0568,
872
+ "step": 113
873
+ },
874
+ {
875
+ "epoch": 4.5600000000000005,
876
+ "grad_norm": 8.852797508239746,
877
+ "learning_rate": 5.357142857142857e-06,
878
+ "loss": 1.043,
879
+ "step": 114
880
+ },
881
+ {
882
+ "epoch": 4.6,
883
+ "grad_norm": 10.713024139404297,
884
+ "learning_rate": 4.910714285714286e-06,
885
+ "loss": 1.2006,
886
+ "step": 115
887
+ },
888
+ {
889
+ "epoch": 4.64,
890
+ "grad_norm": 11.334012031555176,
891
+ "learning_rate": 4.464285714285715e-06,
892
+ "loss": 1.0098,
893
+ "step": 116
894
+ },
895
+ {
896
+ "epoch": 4.68,
897
+ "grad_norm": 9.988310813903809,
898
+ "learning_rate": 4.017857142857143e-06,
899
+ "loss": 1.1678,
900
+ "step": 117
901
+ },
902
+ {
903
+ "epoch": 4.72,
904
+ "grad_norm": 11.369806289672852,
905
+ "learning_rate": 3.5714285714285714e-06,
906
+ "loss": 1.1006,
907
+ "step": 118
908
+ },
909
+ {
910
+ "epoch": 4.76,
911
+ "grad_norm": 8.683494567871094,
912
+ "learning_rate": 3.125e-06,
913
+ "loss": 0.9208,
914
+ "step": 119
915
+ },
916
+ {
917
+ "epoch": 4.8,
918
+ "grad_norm": 11.041170120239258,
919
+ "learning_rate": 2.6785714285714285e-06,
920
+ "loss": 1.1191,
921
+ "step": 120
922
+ },
923
+ {
924
+ "epoch": 4.84,
925
+ "grad_norm": 11.118208885192871,
926
+ "learning_rate": 2.2321428571428573e-06,
927
+ "loss": 1.2661,
928
+ "step": 121
929
+ },
930
+ {
931
+ "epoch": 4.88,
932
+ "grad_norm": 9.99183177947998,
933
+ "learning_rate": 1.7857142857142857e-06,
934
+ "loss": 1.0169,
935
+ "step": 122
936
+ },
937
+ {
938
+ "epoch": 4.92,
939
+ "grad_norm": 8.416065216064453,
940
+ "learning_rate": 1.3392857142857143e-06,
941
+ "loss": 0.9999,
942
+ "step": 123
943
+ },
944
+ {
945
+ "epoch": 4.96,
946
+ "grad_norm": 10.9324312210083,
947
+ "learning_rate": 8.928571428571428e-07,
948
+ "loss": 1.1752,
949
+ "step": 124
950
+ },
951
+ {
952
+ "epoch": 5.0,
953
+ "grad_norm": 17.929676055908203,
954
+ "learning_rate": 4.464285714285714e-07,
955
+ "loss": 1.3872,
956
+ "step": 125
957
+ },
958
+ {
959
+ "epoch": 5.0,
960
+ "eval_accuracy": 0.5510204081632653,
961
+ "eval_f1_macro": 0.48698637963343844,
962
+ "eval_f1_micro": 0.5510204081632653,
963
+ "eval_f1_weighted": 0.5140266479552194,
964
+ "eval_loss": 1.6780412197113037,
965
+ "eval_precision_macro": 0.49788642729819194,
966
+ "eval_precision_micro": 0.5510204081632653,
967
+ "eval_precision_weighted": 0.5202149041434755,
968
+ "eval_recall_macro": 0.5220588235294118,
969
+ "eval_recall_micro": 0.5510204081632653,
970
+ "eval_recall_weighted": 0.5510204081632653,
971
+ "eval_runtime": 0.1179,
972
+ "eval_samples_per_second": 831.21,
973
+ "eval_steps_per_second": 33.927,
974
+ "step": 125
975
+ }
976
+ ],
977
+ "logging_steps": 1,
978
+ "max_steps": 125,
979
+ "num_input_tokens_seen": 0,
980
+ "num_train_epochs": 5,
981
+ "save_steps": 500,
982
+ "stateful_callbacks": {
983
+ "EarlyStoppingCallback": {
984
+ "args": {
985
+ "early_stopping_patience": 5,
986
+ "early_stopping_threshold": 0.01
987
+ },
988
+ "attributes": {
989
+ "early_stopping_patience_counter": 0
990
+ }
991
+ },
992
+ "TrainerControl": {
993
+ "args": {
994
+ "should_epoch_stop": false,
995
+ "should_evaluate": false,
996
+ "should_log": false,
997
+ "should_save": true,
998
+ "should_training_stop": true
999
+ },
1000
+ "attributes": {}
1001
+ }
1002
+ },
1003
+ "total_flos": 64763066415360.0,
1004
+ "train_batch_size": 16,
1005
+ "trial_name": null,
1006
+ "trial_params": null
1007
+ }
checkpoint-125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649e04f81adcd305e28a0eee6fa502b72847f79907dddedef7dfc69db01eef51
3
+ size 5240
config.json ADDED
@@ -0,0 +1,1138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tasksource/deberta-small-long-nli",
3
+ "_num_labels": 17,
4
+ "architectures": [
5
+ "DebertaV2ForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifiers_size": [
9
+ 3,
10
+ 2,
11
+ 2,
12
+ 2,
13
+ 2,
14
+ 2,
15
+ 1,
16
+ 2,
17
+ 3,
18
+ 2,
19
+ 2,
20
+ 2,
21
+ 3,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 1,
26
+ 3,
27
+ 3,
28
+ 2,
29
+ 2,
30
+ 3,
31
+ 2,
32
+ 6,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 3,
43
+ 3,
44
+ 3,
45
+ 3,
46
+ 3,
47
+ 3,
48
+ 3,
49
+ 2,
50
+ 2,
51
+ 2,
52
+ 2,
53
+ 5,
54
+ 3,
55
+ 3,
56
+ 3,
57
+ 3,
58
+ 3,
59
+ 3,
60
+ 3,
61
+ 3,
62
+ 2,
63
+ 2,
64
+ 2,
65
+ 3,
66
+ 3,
67
+ 3,
68
+ 3,
69
+ 3,
70
+ 3,
71
+ 3,
72
+ 2,
73
+ 2,
74
+ 2,
75
+ 2,
76
+ 1,
77
+ 1,
78
+ 1,
79
+ 1,
80
+ 1,
81
+ 1,
82
+ 1,
83
+ 1,
84
+ 1,
85
+ 1,
86
+ 1,
87
+ 1,
88
+ 1,
89
+ 1,
90
+ 1,
91
+ 1,
92
+ 1,
93
+ 1,
94
+ 1,
95
+ 1,
96
+ 1,
97
+ 1,
98
+ 1,
99
+ 1,
100
+ 1,
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 1,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 1,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 1,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 1,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 1,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 1,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 1,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 1,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 1,
137
+ 1,
138
+ 1,
139
+ 1,
140
+ 1,
141
+ 1,
142
+ 1,
143
+ 1,
144
+ 1,
145
+ 1,
146
+ 1,
147
+ 1,
148
+ 1,
149
+ 1,
150
+ 1,
151
+ 1,
152
+ 1,
153
+ 1,
154
+ 1,
155
+ 1,
156
+ 1,
157
+ 1,
158
+ 1,
159
+ 1,
160
+ 1,
161
+ 1,
162
+ 1,
163
+ 1,
164
+ 1,
165
+ 1,
166
+ 1,
167
+ 1,
168
+ 1,
169
+ 1,
170
+ 1,
171
+ 1,
172
+ 1,
173
+ 1,
174
+ 1,
175
+ 1,
176
+ 1,
177
+ 1,
178
+ 1,
179
+ 1,
180
+ 1,
181
+ 1,
182
+ 1,
183
+ 1,
184
+ 1,
185
+ 1,
186
+ 1,
187
+ 1,
188
+ 1,
189
+ 1,
190
+ 1,
191
+ 1,
192
+ 1,
193
+ 1,
194
+ 1,
195
+ 1,
196
+ 1,
197
+ 1,
198
+ 1,
199
+ 1,
200
+ 1,
201
+ 1,
202
+ 1,
203
+ 1,
204
+ 2,
205
+ 2,
206
+ 2,
207
+ 2,
208
+ 2,
209
+ 2,
210
+ 20,
211
+ 50,
212
+ 3,
213
+ 3,
214
+ 4,
215
+ 2,
216
+ 8,
217
+ 2,
218
+ 3,
219
+ 2,
220
+ 2,
221
+ 4,
222
+ 20,
223
+ 3,
224
+ 3,
225
+ 3,
226
+ 3,
227
+ 3,
228
+ 174,
229
+ 2,
230
+ 2,
231
+ 2,
232
+ 2,
233
+ 41,
234
+ 3,
235
+ 51,
236
+ 2,
237
+ 2,
238
+ 2,
239
+ 2,
240
+ 16,
241
+ 17,
242
+ 18,
243
+ 2,
244
+ 2,
245
+ 2,
246
+ 3,
247
+ 8,
248
+ 3,
249
+ 7,
250
+ 7,
251
+ 11,
252
+ 3,
253
+ 3,
254
+ 42,
255
+ 12,
256
+ 4,
257
+ 100,
258
+ 13,
259
+ 100,
260
+ 8,
261
+ 1,
262
+ 20,
263
+ 2,
264
+ 2,
265
+ 4,
266
+ 5,
267
+ 3,
268
+ 4,
269
+ 14,
270
+ 2,
271
+ 6,
272
+ 4,
273
+ 2,
274
+ 1,
275
+ 3,
276
+ 10,
277
+ 3,
278
+ 10,
279
+ 4,
280
+ 2,
281
+ 7,
282
+ 6,
283
+ 28,
284
+ 3,
285
+ 6,
286
+ 5,
287
+ 7,
288
+ 4,
289
+ 6,
290
+ 3,
291
+ 2,
292
+ 2,
293
+ 2,
294
+ 6,
295
+ 2,
296
+ 7,
297
+ 20,
298
+ 2,
299
+ 2,
300
+ 4,
301
+ 2,
302
+ 9,
303
+ 13,
304
+ 4,
305
+ 2,
306
+ 3,
307
+ 2,
308
+ 3,
309
+ 2,
310
+ 2,
311
+ 2,
312
+ 2,
313
+ 4,
314
+ 1,
315
+ 2,
316
+ 1,
317
+ 2,
318
+ 49,
319
+ 40,
320
+ 10,
321
+ 4,
322
+ 1,
323
+ 2,
324
+ 2,
325
+ 1,
326
+ 5,
327
+ 2,
328
+ 3,
329
+ 2,
330
+ 2,
331
+ 12,
332
+ 3,
333
+ 3,
334
+ 2,
335
+ 19,
336
+ 3,
337
+ 1,
338
+ 2,
339
+ 2,
340
+ 2,
341
+ 2,
342
+ 2,
343
+ 1,
344
+ 2,
345
+ 2,
346
+ 1,
347
+ 1,
348
+ 2,
349
+ 3,
350
+ 2,
351
+ 1,
352
+ 4,
353
+ 3,
354
+ 1,
355
+ 1,
356
+ 1,
357
+ 2,
358
+ 3,
359
+ 2,
360
+ 3,
361
+ 1,
362
+ 1,
363
+ 2,
364
+ 1,
365
+ 2,
366
+ 2,
367
+ 2,
368
+ 2,
369
+ 3,
370
+ 2,
371
+ 2,
372
+ 2,
373
+ 1,
374
+ 3,
375
+ 2,
376
+ 2,
377
+ 1,
378
+ 1,
379
+ 1,
380
+ 1,
381
+ 2,
382
+ 1,
383
+ 1,
384
+ 1,
385
+ 1,
386
+ 4,
387
+ 1,
388
+ 1,
389
+ 1,
390
+ 1,
391
+ 3,
392
+ 1,
393
+ 3,
394
+ 1,
395
+ 2,
396
+ 2,
397
+ 1,
398
+ 2,
399
+ 3,
400
+ 3,
401
+ 2,
402
+ 1,
403
+ 3,
404
+ 1,
405
+ 1,
406
+ 3,
407
+ 1,
408
+ 3,
409
+ 2,
410
+ 1,
411
+ 1,
412
+ 1,
413
+ 2,
414
+ 2,
415
+ 1,
416
+ 1,
417
+ 1,
418
+ 1,
419
+ 1,
420
+ 1,
421
+ 1,
422
+ 1,
423
+ 1,
424
+ 1,
425
+ 2,
426
+ 2,
427
+ 2,
428
+ 2,
429
+ 77,
430
+ 3,
431
+ 2,
432
+ 2,
433
+ 1,
434
+ 1,
435
+ 2,
436
+ 3,
437
+ 18,
438
+ 13,
439
+ 2,
440
+ 2,
441
+ 2,
442
+ 2,
443
+ 2,
444
+ 4,
445
+ 2,
446
+ 24,
447
+ 3,
448
+ 2,
449
+ 2,
450
+ 1,
451
+ 2,
452
+ 2,
453
+ 3,
454
+ 1,
455
+ 2,
456
+ 3,
457
+ 2,
458
+ 3,
459
+ 3,
460
+ 2,
461
+ 2,
462
+ 4,
463
+ 1,
464
+ 17,
465
+ 3,
466
+ 3,
467
+ 2,
468
+ 3,
469
+ 2,
470
+ 3,
471
+ 3,
472
+ 2,
473
+ 1,
474
+ 1,
475
+ 3,
476
+ 2,
477
+ 9,
478
+ 2,
479
+ 1,
480
+ 1,
481
+ 1,
482
+ 1,
483
+ 1,
484
+ 2,
485
+ 2,
486
+ 3,
487
+ 2,
488
+ 3,
489
+ 4,
490
+ 3,
491
+ 3,
492
+ 2,
493
+ 1,
494
+ 1,
495
+ 2,
496
+ 1,
497
+ 1,
498
+ 6,
499
+ 2,
500
+ 3,
501
+ 3,
502
+ 1,
503
+ 1,
504
+ 2,
505
+ 2,
506
+ 10,
507
+ 2,
508
+ 2,
509
+ 2,
510
+ 5,
511
+ 5,
512
+ 5,
513
+ 5,
514
+ 5,
515
+ 5,
516
+ 5,
517
+ 5,
518
+ 5,
519
+ 5,
520
+ 4,
521
+ 1,
522
+ 7,
523
+ 6,
524
+ 6,
525
+ 6,
526
+ 6,
527
+ 6,
528
+ 6,
529
+ 3,
530
+ 2,
531
+ 1,
532
+ 2,
533
+ 2,
534
+ 2,
535
+ 3,
536
+ 3,
537
+ 3,
538
+ 1
539
+ ],
540
+ "hidden_act": "gelu",
541
+ "hidden_dropout_prob": 0.1,
542
+ "hidden_size": 768,
543
+ "id2label": {
544
+ "0": "aging-parents",
545
+ "1": "asset-protection",
546
+ "2": "big-purchase",
547
+ "3": "cash-flow-management",
548
+ "4": "emergency-savings",
549
+ "5": "estate-planning",
550
+ "6": "job-change",
551
+ "7": "marriage-divorce",
552
+ "8": "new-child",
553
+ "9": "no-detection",
554
+ "10": "philanthropic-needs",
555
+ "11": "portfolio-performance",
556
+ "12": "retirement-planning",
557
+ "13": "risk-assessment-tolerance",
558
+ "14": "small-business-owner",
559
+ "15": "tax-optimization",
560
+ "16": "windfall-bankruptcy"
561
+ },
562
+ "initializer_range": 0.02,
563
+ "intermediate_size": 3072,
564
+ "label2id": {
565
+ "aging-parents": 0,
566
+ "asset-protection": 1,
567
+ "big-purchase": 2,
568
+ "cash-flow-management": 3,
569
+ "emergency-savings": 4,
570
+ "estate-planning": 5,
571
+ "job-change": 6,
572
+ "marriage-divorce": 7,
573
+ "new-child": 8,
574
+ "no-detection": 9,
575
+ "philanthropic-needs": 10,
576
+ "portfolio-performance": 11,
577
+ "retirement-planning": 12,
578
+ "risk-assessment-tolerance": 13,
579
+ "small-business-owner": 14,
580
+ "tax-optimization": 15,
581
+ "windfall-bankruptcy": 16
582
+ },
583
+ "layer_norm_eps": 1e-07,
584
+ "max_position_embeddings": 1680,
585
+ "max_relative_positions": -1,
586
+ "model_type": "deberta-v2",
587
+ "norm_rel_ebd": "layer_norm",
588
+ "num_attention_heads": 12,
589
+ "num_hidden_layers": 6,
590
+ "pad_token_id": 0,
591
+ "pooler_dropout": 0,
592
+ "pooler_hidden_act": "gelu",
593
+ "pooler_hidden_size": 768,
594
+ "pos_att_type": [
595
+ "p2c",
596
+ "c2p"
597
+ ],
598
+ "position_biased_input": false,
599
+ "position_buckets": 256,
600
+ "relative_attention": true,
601
+ "share_att_key": true,
602
+ "tasks": [
603
+ "glue/mnli",
604
+ "glue/qnli",
605
+ "glue/rte",
606
+ "glue/wnli",
607
+ "glue/mrpc",
608
+ "glue/qqp",
609
+ "glue/stsb",
610
+ "super_glue/boolq",
611
+ "super_glue/cb",
612
+ "super_glue/multirc",
613
+ "super_glue/wic",
614
+ "super_glue/axg",
615
+ "anli/a1",
616
+ "anli/a2",
617
+ "anli/a3",
618
+ "sick/label",
619
+ "sick/relatedness",
620
+ "sick/entailment_AB",
621
+ "snli",
622
+ "scitail/snli_format",
623
+ "hans",
624
+ "WANLI",
625
+ "recast/recast_ner",
626
+ "recast/recast_kg_relations",
627
+ "recast/recast_puns",
628
+ "recast/recast_verbcorner",
629
+ "recast/recast_sentiment",
630
+ "recast/recast_verbnet",
631
+ "recast/recast_factuality",
632
+ "recast/recast_megaveridicality",
633
+ "probability_words_nli/reasoning_2hop",
634
+ "probability_words_nli/reasoning_1hop",
635
+ "probability_words_nli/usnli",
636
+ "nan-nli",
637
+ "nli_fever",
638
+ "breaking_nli",
639
+ "conj_nli",
640
+ "fracas",
641
+ "dialogue_nli",
642
+ "mpe",
643
+ "dnc",
644
+ "recast_white/fnplus",
645
+ "recast_white/sprl",
646
+ "recast_white/dpr",
647
+ "joci",
648
+ "robust_nli/IS_CS",
649
+ "robust_nli/LI_LI",
650
+ "robust_nli/ST_WO",
651
+ "robust_nli/PI_SP",
652
+ "robust_nli/PI_CD",
653
+ "robust_nli/ST_SE",
654
+ "robust_nli/ST_NE",
655
+ "robust_nli/ST_LM",
656
+ "robust_nli_is_sd",
657
+ "robust_nli_li_ts",
658
+ "add_one_rte",
659
+ "imppres/implicature_quantifiers/log",
660
+ "imppres/implicature_numerals_2_3/log",
661
+ "imppres/implicature_gradable_adjective/log",
662
+ "imppres/implicature_connectives/log",
663
+ "imppres/implicature_modals/log",
664
+ "imppres/implicature_numerals_10_100/log",
665
+ "imppres/implicature_gradable_verb/log",
666
+ "hlgd",
667
+ "paws/labeled_final",
668
+ "paws/labeled_swap",
669
+ "medical_questions_pairs",
670
+ "model-written-evals",
671
+ "truthful_qa/multiple_choice",
672
+ "fig-qa",
673
+ "bigbench/bbq_lite_json",
674
+ "bigbench/english_proverbs",
675
+ "bigbench/figure_of_speech_detection",
676
+ "bigbench/emoji_movie",
677
+ "bigbench/date_understanding",
678
+ "bigbench/metaphor_understanding",
679
+ "bigbench/logical_fallacy_detection",
680
+ "bigbench/analogical_similarity",
681
+ "bigbench/mnist_ascii",
682
+ "bigbench/elementary_math_qa",
683
+ "bigbench/snarks",
684
+ "bigbench/social_support",
685
+ "bigbench/logical_deduction",
686
+ "bigbench/emojis_emotion_prediction",
687
+ "bigbench/sports_understanding",
688
+ "bigbench/cifar10_classification",
689
+ "bigbench/tracking_shuffled_objects",
690
+ "bigbench/physics",
691
+ "bigbench/mathematical_induction",
692
+ "bigbench/movie_dialog_same_or_different",
693
+ "bigbench/goal_step_wikihow",
694
+ "bigbench/strategyqa",
695
+ "bigbench/identify_math_theorems",
696
+ "bigbench/gre_reading_comprehension",
697
+ "bigbench/novel_concepts",
698
+ "bigbench/conceptual_combinations",
699
+ "bigbench/hyperbaton",
700
+ "bigbench/strange_stories",
701
+ "bigbench/contextual_parametric_knowledge_conflicts",
702
+ "bigbench/implicatures",
703
+ "bigbench/penguins_in_a_table",
704
+ "bigbench/logical_sequence",
705
+ "bigbench/simple_ethical_questions",
706
+ "bigbench/dyck_languages",
707
+ "bigbench/geometric_shapes",
708
+ "bigbench/irony_identification",
709
+ "bigbench/intent_recognition",
710
+ "bigbench/logical_args",
711
+ "bigbench/known_unknowns",
712
+ "bigbench/formal_fallacies_syllogisms_negation",
713
+ "bigbench/suicide_risk",
714
+ "bigbench/crash_blossom",
715
+ "bigbench/logic_grid_puzzle",
716
+ "bigbench/analytic_entailment",
717
+ "bigbench/dark_humor_detection",
718
+ "bigbench/timedial",
719
+ "bigbench/presuppositions_as_nli",
720
+ "bigbench/arithmetic",
721
+ "bigbench/implicit_relations",
722
+ "bigbench/understanding_fables",
723
+ "bigbench/salient_translation_error_detection",
724
+ "bigbench/anachronisms",
725
+ "bigbench/moral_permissibility",
726
+ "bigbench/abstract_narrative_understanding",
727
+ "bigbench/misconceptions",
728
+ "bigbench/nonsense_words_grammar",
729
+ "bigbench/code_line_description",
730
+ "bigbench/sentence_ambiguity",
731
+ "bigbench/disambiguation_qa",
732
+ "bigbench/crass_ai",
733
+ "bigbench/similarities_abstraction",
734
+ "bigbench/authorship_verification",
735
+ "bigbench/phrase_relatedness",
736
+ "bigbench/color",
737
+ "bigbench/hhh_alignment",
738
+ "bigbench/metaphor_boolean",
739
+ "bigbench/fantasy_reasoning",
740
+ "bigbench/ruin_names",
741
+ "bigbench/cause_and_effect",
742
+ "bigbench/temporal_sequences",
743
+ "bigbench/navigate",
744
+ "bigbench/symbol_interpretation",
745
+ "bigbench/key_value_maps",
746
+ "bigbench/entailed_polarity",
747
+ "bigbench/riddle_sense",
748
+ "bigbench/discourse_marker_prediction",
749
+ "bigbench/reasoning_about_colored_objects",
750
+ "bigbench/empirical_judgments",
751
+ "bigbench/fact_checker",
752
+ "bigbench/movie_recommendation",
753
+ "bigbench/checkmate_in_one",
754
+ "bigbench/epistemic_reasoning",
755
+ "bigbench/vitaminc_fact_verification",
756
+ "bigbench/general_knowledge",
757
+ "bigbench/identify_odd_metaphor",
758
+ "bigbench/physical_intuition",
759
+ "bigbench/winowhy",
760
+ "bigbench/cs_algorithms",
761
+ "bigbench/undo_permutation",
762
+ "bigbench/evaluating_information_essentiality",
763
+ "bigbench/unit_interpretation",
764
+ "bigbench/question_selection",
765
+ "bigbench/international_phonetic_alphabet_nli",
766
+ "bigbench/play_dialog_same_or_different",
767
+ "bigbench/real_or_fake_text",
768
+ "bigbench/human_organs_senses",
769
+ "bigbench/hindu_knowledge",
770
+ "bigbench/social_iqa",
771
+ "bigbench/odd_one_out",
772
+ "bigbench/causal_judgment",
773
+ "cos_e/v1.0",
774
+ "cosmos_qa",
775
+ "dream",
776
+ "openbookqa",
777
+ "qasc",
778
+ "quartz",
779
+ "quail",
780
+ "head_qa/en",
781
+ "sciq",
782
+ "social_i_qa",
783
+ "wiki_hop/original",
784
+ "wiqa",
785
+ "piqa",
786
+ "hellaswag",
787
+ "super_glue/copa",
788
+ "balanced-copa",
789
+ "e-CARE",
790
+ "art",
791
+ "winogrande/winogrande_xl",
792
+ "codah/codah",
793
+ "ai2_arc/ARC-Easy/challenge",
794
+ "ai2_arc/ARC-Challenge/challenge",
795
+ "definite_pronoun_resolution",
796
+ "swag/regular",
797
+ "math_qa",
798
+ "glue/cola",
799
+ "glue/sst2",
800
+ "utilitarianism",
801
+ "amazon_counterfactual/en",
802
+ "insincere-questions",
803
+ "toxic_conversations",
804
+ "TuringBench",
805
+ "trec",
806
+ "vitaminc",
807
+ "hope_edi/english",
808
+ "rumoureval_2019/RumourEval2019",
809
+ "ethos/binary",
810
+ "ethos/multilabel",
811
+ "tweet_eval/offensive",
812
+ "tweet_eval/sentiment",
813
+ "tweet_eval/irony",
814
+ "tweet_eval/hate",
815
+ "tweet_eval/emotion",
816
+ "tweet_eval/emoji",
817
+ "tweet_eval/stance_abortion",
818
+ "tweet_eval/stance_atheism",
819
+ "tweet_eval/stance_climate",
820
+ "tweet_eval/stance_feminist",
821
+ "tweet_eval/stance_hillary",
822
+ "discovery/discovery",
823
+ "pragmeval/squinky-formality",
824
+ "pragmeval/emobank-arousal",
825
+ "pragmeval/squinky-implicature",
826
+ "pragmeval/squinky-informativeness",
827
+ "pragmeval/switchboard",
828
+ "pragmeval/verifiability",
829
+ "pragmeval/mrda",
830
+ "pragmeval/emobank-valence",
831
+ "pragmeval/emobank-dominance",
832
+ "pragmeval/persuasiveness-strength",
833
+ "pragmeval/persuasiveness-relevance",
834
+ "pragmeval/pdtb",
835
+ "pragmeval/gum",
836
+ "pragmeval/stac",
837
+ "pragmeval/persuasiveness-specificity",
838
+ "pragmeval/sarcasm",
839
+ "pragmeval/persuasiveness-eloquence",
840
+ "pragmeval/emergent",
841
+ "pragmeval/persuasiveness-premisetype",
842
+ "pragmeval/persuasiveness-claimtype",
843
+ "silicone/meld_e",
844
+ "silicone/dyda_e",
845
+ "silicone/iemocap",
846
+ "silicone/sem",
847
+ "silicone/meld_s",
848
+ "silicone/oasis",
849
+ "silicone/maptask",
850
+ "silicone/dyda_da",
851
+ "lex_glue/eurlex",
852
+ "lex_glue/scotus",
853
+ "lex_glue/ledgar",
854
+ "lex_glue/unfair_tos",
855
+ "lex_glue/case_hold",
856
+ "language-identification",
857
+ "imdb",
858
+ "rotten_tomatoes",
859
+ "ag_news",
860
+ "yelp_review_full/yelp_review_full",
861
+ "financial_phrasebank/sentences_allagree",
862
+ "poem_sentiment",
863
+ "dbpedia_14/dbpedia_14",
864
+ "amazon_polarity/amazon_polarity",
865
+ "app_reviews",
866
+ "hate_speech18",
867
+ "sms_spam",
868
+ "humicroedit/subtask-1",
869
+ "humicroedit/subtask-2",
870
+ "snips_built_in_intents",
871
+ "hate_speech_offensive",
872
+ "yahoo_answers_topics",
873
+ "stackoverflow-questions",
874
+ "hyperpartisan_news",
875
+ "sciie",
876
+ "citation_intent",
877
+ "go_emotions/simplified",
878
+ "scicite",
879
+ "liar",
880
+ "lexical_relation_classification/CogALexV",
881
+ "lexical_relation_classification/EVALution",
882
+ "lexical_relation_classification/K&H+N",
883
+ "lexical_relation_classification/BLESS",
884
+ "lexical_relation_classification/ROOT09",
885
+ "linguisticprobing/obj_number",
886
+ "linguisticprobing/bigram_shift",
887
+ "linguisticprobing/subj_number",
888
+ "linguisticprobing/sentence_length",
889
+ "linguisticprobing/odd_man_out",
890
+ "linguisticprobing/tree_depth",
891
+ "linguisticprobing/top_constituents",
892
+ "linguisticprobing/coordination_inversion",
893
+ "linguisticprobing/past_present",
894
+ "crowdflower/sentiment_nuclear_power",
895
+ "crowdflower/tweet_global_warming",
896
+ "crowdflower/political-media-message",
897
+ "crowdflower/text_emotion",
898
+ "crowdflower/corporate-messaging",
899
+ "crowdflower/political-media-audience",
900
+ "crowdflower/airline-sentiment",
901
+ "crowdflower/political-media-bias",
902
+ "crowdflower/economic-news",
903
+ "ethics/commonsense",
904
+ "ethics/deontology",
905
+ "ethics/justice",
906
+ "ethics/virtue",
907
+ "emo/emo2019",
908
+ "google_wellformed_query",
909
+ "tweets_hate_speech_detection",
910
+ "has_part",
911
+ "blog_authorship_corpus/gender",
912
+ "blog_authorship_corpus/age",
913
+ "blog_authorship_corpus/job",
914
+ "open_question_type",
915
+ "health_fact",
916
+ "commonsense_qa",
917
+ "mc_taco",
918
+ "ade_corpus_v2/Ade_corpus_v2_classification",
919
+ "discosense",
920
+ "circa",
921
+ "phrase_similarity",
922
+ "scientific-exaggeration-detection",
923
+ "quarel",
924
+ "fever-evidence-related",
925
+ "numer_sense",
926
+ "dynasent/dynabench.dynasent.r1.all/r1",
927
+ "dynasent/dynabench.dynasent.r2.all/r2",
928
+ "Sarcasm_News_Headline",
929
+ "sem_eval_2010_task_8",
930
+ "auditor_review",
931
+ "medmcqa",
932
+ "Dynasent_Disagreement",
933
+ "Politeness_Disagreement",
934
+ "SBIC_Disagreement",
935
+ "SChem_Disagreement",
936
+ "Dilemmas_Disagreement",
937
+ "logiqa",
938
+ "wiki_qa",
939
+ "cycic_classification",
940
+ "cycic_multiplechoice",
941
+ "sts-companion",
942
+ "commonsense_qa_2.0",
943
+ "lingnli",
944
+ "monotonicity-entailment",
945
+ "arct",
946
+ "scinli",
947
+ "naturallogic",
948
+ "onestop_qa",
949
+ "moral_stories/full",
950
+ "prost",
951
+ "dynahate",
952
+ "syntactic-augmentation-nli",
953
+ "autotnli",
954
+ "CONDAQA",
955
+ "webgpt_comparisons",
956
+ "synthetic-instruct-gptj-pairwise",
957
+ "scruples",
958
+ "wouldyourather",
959
+ "defeasible-nli/atomic",
960
+ "defeasible-nli/snli",
961
+ "help-nli",
962
+ "nli-veridicality-transitivity",
963
+ "lonli",
964
+ "dadc-limit-nli",
965
+ "FLUTE",
966
+ "strategy-qa",
967
+ "summarize_from_feedback/comparisons",
968
+ "folio",
969
+ "tomi-nli",
970
+ "avicenna",
971
+ "SHP",
972
+ "MedQA-USMLE-4-options-hf",
973
+ "wikimedqa/medwiki",
974
+ "cicero",
975
+ "CREAK",
976
+ "mutual",
977
+ "NeQA",
978
+ "quote-repetition",
979
+ "redefine-math",
980
+ "puzzte",
981
+ "implicatures",
982
+ "race/middle",
983
+ "race/high",
984
+ "race-c",
985
+ "spartqa-yn",
986
+ "spartqa-mchoice",
987
+ "temporal-nli",
988
+ "riddle_sense",
989
+ "clcd-english",
990
+ "twentyquestions",
991
+ "reclor",
992
+ "counterfactually-augmented-imdb",
993
+ "counterfactually-augmented-snli",
994
+ "cnli",
995
+ "boolq-natural-perturbations",
996
+ "acceptability-prediction",
997
+ "equate",
998
+ "ScienceQA_text_only",
999
+ "ekar_english",
1000
+ "implicit-hate-stg1",
1001
+ "chaos-mnli-ambiguity",
1002
+ "headline_cause/en_simple",
1003
+ "logiqa-2.0-nli",
1004
+ "oasst2_dense_flat/quality",
1005
+ "oasst2_dense_flat/toxicity",
1006
+ "oasst2_dense_flat/helpfulness",
1007
+ "mindgames",
1008
+ "ambient",
1009
+ "path-naturalness-prediction",
1010
+ "civil_comments/toxicity",
1011
+ "civil_comments/severe_toxicity",
1012
+ "civil_comments/obscene",
1013
+ "civil_comments/threat",
1014
+ "civil_comments/insult",
1015
+ "civil_comments/identity_attack",
1016
+ "civil_comments/sexual_explicit",
1017
+ "cloth",
1018
+ "dgen",
1019
+ "I2D2",
1020
+ "args_me",
1021
+ "Touche23-ValueEval",
1022
+ "starcon",
1023
+ "banking77",
1024
+ "ConTRoL-nli",
1025
+ "tracie",
1026
+ "sherliic",
1027
+ "sen-making/1",
1028
+ "sen-making/2",
1029
+ "winowhy",
1030
+ "robustLR",
1031
+ "v1/gen_train234_test2to10",
1032
+ "logical-fallacy",
1033
+ "parade",
1034
+ "cladder",
1035
+ "subjectivity",
1036
+ "MOH",
1037
+ "VUAC",
1038
+ "sharc_modified/mod",
1039
+ "conceptrules_v2",
1040
+ "disrpt/eng.dep.scidtb.rels",
1041
+ "zero-shot-label-nli",
1042
+ "com2sense",
1043
+ "scone",
1044
+ "winodict",
1045
+ "fool-me-twice",
1046
+ "monli",
1047
+ "corr2cause",
1048
+ "lsat_qa/all",
1049
+ "apt",
1050
+ "twitter-financial-news-sentiment",
1051
+ "icl-symbol-tuning-instruct",
1052
+ "SpaceNLI",
1053
+ "propsegment/nli",
1054
+ "HatemojiBuild",
1055
+ "regset",
1056
+ "esci",
1057
+ "chatbot_arena_conversations",
1058
+ "dnd_style_intents",
1059
+ "FLD.v2/default",
1060
+ "FLD.v2/star",
1061
+ "SDOH-NLI",
1062
+ "scifact_entailment",
1063
+ "feasibilityQA",
1064
+ "simple_pair",
1065
+ "AdjectiveScaleProbe-nli",
1066
+ "resnli",
1067
+ "SpaRTUN",
1068
+ "ReSQ",
1069
+ "semantic_fragments_nli",
1070
+ "dataset_train_nli",
1071
+ "stepgame",
1072
+ "nlgraph",
1073
+ "oasst2_pairwise_rlhf_reward",
1074
+ "hh-rlhf/helpful-base",
1075
+ "hh-rlhf/helpful-online",
1076
+ "hh-rlhf/helpful-rejection-sampled",
1077
+ "hh-rlhf/harmless-base",
1078
+ "ruletaker",
1079
+ "PARARULE-Plus",
1080
+ "proofwriter",
1081
+ "logical-entailment",
1082
+ "nope",
1083
+ "LogicNLI",
1084
+ "contract-nli/contractnli_a/seg",
1085
+ "contract-nli/contractnli_b/full",
1086
+ "nli4ct_semeval2024",
1087
+ "lsat-ar",
1088
+ "lsat-rc",
1089
+ "biosift-nli",
1090
+ "brainteasers/WP",
1091
+ "brainteasers/SP",
1092
+ "persuasion",
1093
+ "AmbigNQ-clarifying-question",
1094
+ "SIGA-nli",
1095
+ "FOL-nli",
1096
+ "goal-step-wikihow/order",
1097
+ "PARADISE",
1098
+ "doc-nli",
1099
+ "mctest-nli",
1100
+ "patent-phrase-similarity",
1101
+ "natural-language-satisfiability",
1102
+ "idioms-nli",
1103
+ "lifecycle-entailment",
1104
+ "HelpSteer/helpfulness",
1105
+ "HelpSteer/correctness",
1106
+ "HelpSteer/coherence",
1107
+ "HelpSteer/complexity",
1108
+ "HelpSteer/verbosity",
1109
+ "HelpSteer2/helpfulness",
1110
+ "HelpSteer2/correctness",
1111
+ "HelpSteer2/coherence",
1112
+ "HelpSteer2/complexity",
1113
+ "HelpSteer2/verbosity",
1114
+ "MSciNLI",
1115
+ "UltraFeedback-paired",
1116
+ "AES2-essay-scoring",
1117
+ "english-grading/cohesion",
1118
+ "english-grading/syntax",
1119
+ "english-grading/vocabulary",
1120
+ "english-grading/phraseology",
1121
+ "english-grading/grammar",
1122
+ "english-grading/conventions",
1123
+ "wice",
1124
+ "hover",
1125
+ "tasksource_dpo_pairs",
1126
+ "seahorse_summarization_evaluation",
1127
+ "missing-item-prediction/contrastive",
1128
+ "babi_nli",
1129
+ "gen_debiased_nli",
1130
+ "imppres/presupposition",
1131
+ "/prag",
1132
+ "blimp-2"
1133
+ ],
1134
+ "torch_dtype": "float32",
1135
+ "transformers_version": "4.44.1",
1136
+ "type_vocab_size": 0,
1137
+ "vocab_size": 128100
1138
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f243f21c43e25ef5a91ee9a57e314b5e4ddd47478e562a0dec3ca562962005
3
+ size 567644700
runs/Aug28_13-19-54_r-svyas-hf-autotrain-classification-p4kbgon6-0fc54-i3uf4/events.out.tfevents.1724851196.r-svyas-hf-autotrain-classification-p4kbgon6-0fc54-i3uf4.97.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a86633ce317aff4449606cf7e63019547e928bb5086db1b1af6b6dbebc14ce4
3
- size 24335
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a5d29177b0c5049457ad42b191a6330c5c852fe8a0e6a811563ab2797c3bda
3
+ size 54648
runs/Aug28_13-19-54_r-svyas-hf-autotrain-classification-p4kbgon6-0fc54-i3uf4/events.out.tfevents.1724851245.r-svyas-hf-autotrain-classification-p4kbgon6-0fc54-i3uf4.97.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ad395141ce5b9bcc24d498d6a2bc4467cb52760b4a9e94bfa06557fd82211bd
3
+ size 906
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "max_length": 1680,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "sp_model_kwargs": {},
58
+ "split_by_punct": false,
59
+ "stride": 0,
60
+ "tokenizer_class": "DebertaV2Tokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]",
64
+ "vocab_type": "spm"
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649e04f81adcd305e28a0eee6fa502b72847f79907dddedef7dfc69db01eef51
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-dpdvy-2fgj4/autotrain-data",
3
+ "model": "tasksource/deberta-small-long-nli",
4
+ "lr": 5e-05,
5
+ "epochs": 5,
6
+ "max_seq_length": 128,
7
+ "batch_size": 16,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "text_column": "autotrain_text",
18
+ "target_column": "autotrain_label",
19
+ "logging_steps": -1,
20
+ "project_name": "autotrain-dpdvy-2fgj4",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "svyas-hf",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }