Unggi commited on
Commit
03e7408
·
verified ·
1 Parent(s): 61f43f7

Upload folder using huggingface_hub

Browse files
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_eval_accuracy": 0.8580002500729379,
3
+ "best_eval_auc": 0.9118745580382054,
4
+ "best_eval_loss": 0.35949909687042236,
5
+ "epoch": 99.52892561983471,
6
+ "eval_accuracy": 0.85401096163428,
7
+ "eval_auc": 0.9065855978572865,
8
+ "eval_loss": 0.37084951996803284,
9
+ "total_flos": 1.3065819223244145e+18,
10
+ "train_loss": 0.5646095657348633,
11
+ "train_runtime": 38955.3575,
12
+ "train_samples": 3862,
13
+ "train_samples_per_second": 9.914,
14
+ "train_steps_per_second": 0.003
15
+ }
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "answerdotai/ModernBERT-base",
3
+ "architectures": [
4
+ "ModernBertForTokenClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "LABEL_0"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "LABEL_0": 0
31
+ },
32
+ "layer_norm_eps": 1e-05,
33
+ "local_attention": 128,
34
+ "local_rope_theta": 10000.0,
35
+ "max_position_embeddings": 8192,
36
+ "mlp_bias": false,
37
+ "mlp_dropout": 0.0,
38
+ "model_type": "modernbert",
39
+ "norm_bias": false,
40
+ "norm_eps": 1e-05,
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 22,
43
+ "pad_token_id": 50283,
44
+ "position_embedding_type": "absolute",
45
+ "reference_compile": false,
46
+ "repad_logits_with_grad": false,
47
+ "sep_token_id": 50282,
48
+ "sparse_pred_ignore_index": -100,
49
+ "sparse_prediction": false,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.49.0",
52
+ "vocab_size": 50370
53
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a00017564e488e276b45fd753d98fac5b5b847c4d0ffa4511c62981edaf970
3
+ size 598442852
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[CORRECT]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "[INCORRECT]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "cls_token": {
19
+ "content": "[CLS]",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "mask_token": {
26
+ "content": "[MASK]",
27
+ "lstrip": true,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "[PAD]",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "sep_token": {
40
+ "content": "[SEP]",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "[UNK]",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,965 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ },
931
+ "50368": {
932
+ "content": "[CORRECT]",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "50369": {
940
+ "content": "[INCORRECT]",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ }
947
+ },
948
+ "additional_special_tokens": [
949
+ "[CORRECT]",
950
+ "[INCORRECT]"
951
+ ],
952
+ "clean_up_tokenization_spaces": true,
953
+ "cls_token": "[CLS]",
954
+ "extra_special_tokens": {},
955
+ "mask_token": "[MASK]",
956
+ "model_input_names": [
957
+ "input_ids",
958
+ "attention_mask"
959
+ ],
960
+ "model_max_length": 8192,
961
+ "pad_token": "[PAD]",
962
+ "sep_token": "[SEP]",
963
+ "tokenizer_class": "PreTrainedTokenizer",
964
+ "unk_token": "[UNK]"
965
+ }
train_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_eval_accuracy": 0.8580002500729379,
3
+ "best_eval_auc": 0.9118745580382054,
4
+ "best_eval_loss": 0.35949909687042236,
5
+ "epoch": 99.52892561983471,
6
+ "eval_accuracy": 0.85401096163428,
7
+ "eval_auc": 0.9065855978572865,
8
+ "eval_loss": 0.37084951996803284,
9
+ "total_flos": 1.3065819223244145e+18,
10
+ "train_loss": 0.5646095657348633,
11
+ "train_runtime": 38955.3575,
12
+ "train_samples": 3862,
13
+ "train_samples_per_second": 9.914,
14
+ "train_steps_per_second": 0.003
15
+ }
trainer_state.json ADDED
@@ -0,0 +1,1042 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9118745580382054,
3
+ "best_model_checkpoint": "output/lkt/modernbert_encoder_lt_sv_seq_8192_sv-kt-25-v1_fold1/checkpoint-95",
4
+ "epoch": 99.52892561983471,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5289256198347108,
13
+ "eval_accuracy": 0.7331542046265587,
14
+ "eval_auc": 0.5143351499224811,
15
+ "eval_loss": 2.040724992752075,
16
+ "eval_runtime": 87.1763,
17
+ "eval_samples_per_second": 17.929,
18
+ "eval_steps_per_second": 0.562,
19
+ "step": 1
20
+ },
21
+ {
22
+ "epoch": 1.5289256198347108,
23
+ "eval_accuracy": 0.7408476632776871,
24
+ "eval_auc": 0.51197317676667,
25
+ "eval_loss": 1.091392159461975,
26
+ "eval_runtime": 87.925,
27
+ "eval_samples_per_second": 17.777,
28
+ "eval_steps_per_second": 0.557,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 2.5289256198347108,
33
+ "eval_accuracy": 0.73017929535671,
34
+ "eval_auc": 0.5016966206823285,
35
+ "eval_loss": 0.6090491414070129,
36
+ "eval_runtime": 86.9757,
37
+ "eval_samples_per_second": 17.971,
38
+ "eval_steps_per_second": 0.563,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 3.5289256198347108,
43
+ "eval_accuracy": 0.4361599462929551,
44
+ "eval_auc": 0.5311078494767836,
45
+ "eval_loss": 0.7663666605949402,
46
+ "eval_runtime": 87.4181,
47
+ "eval_samples_per_second": 17.88,
48
+ "eval_steps_per_second": 0.561,
49
+ "step": 4
50
+ },
51
+ {
52
+ "epoch": 4.528925619834711,
53
+ "eval_accuracy": 0.46085721447071604,
54
+ "eval_auc": 0.5224822287662265,
55
+ "eval_loss": 0.7409077286720276,
56
+ "eval_runtime": 86.8753,
57
+ "eval_samples_per_second": 17.991,
58
+ "eval_steps_per_second": 0.564,
59
+ "step": 5
60
+ },
61
+ {
62
+ "epoch": 5.528925619834711,
63
+ "eval_accuracy": 0.628442663995994,
64
+ "eval_auc": 0.5120648700750261,
65
+ "eval_loss": 0.6520037651062012,
66
+ "eval_runtime": 86.897,
67
+ "eval_samples_per_second": 17.987,
68
+ "eval_steps_per_second": 0.564,
69
+ "step": 6
70
+ },
71
+ {
72
+ "epoch": 6.528925619834711,
73
+ "eval_accuracy": 0.7313003212214759,
74
+ "eval_auc": 0.5084010161513127,
75
+ "eval_loss": 0.6003755927085876,
76
+ "eval_runtime": 87.1425,
77
+ "eval_samples_per_second": 17.936,
78
+ "eval_steps_per_second": 0.562,
79
+ "step": 7
80
+ },
81
+ {
82
+ "epoch": 7.528925619834711,
83
+ "eval_accuracy": 0.7341205041242725,
84
+ "eval_auc": 0.5183164612818807,
85
+ "eval_loss": 0.5912967324256897,
86
+ "eval_runtime": 86.9548,
87
+ "eval_samples_per_second": 17.975,
88
+ "eval_steps_per_second": 0.564,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 8.52892561983471,
93
+ "eval_accuracy": 0.7300701062088073,
94
+ "eval_auc": 0.52227280547719,
95
+ "eval_loss": 0.5922901630401611,
96
+ "eval_runtime": 87.1144,
97
+ "eval_samples_per_second": 17.942,
98
+ "eval_steps_per_second": 0.562,
99
+ "step": 9
100
+ },
101
+ {
102
+ "epoch": 9.52892561983471,
103
+ "eval_accuracy": 0.7153363526820958,
104
+ "eval_auc": 0.519620938227537,
105
+ "eval_loss": 0.6102342009544373,
106
+ "eval_runtime": 87.0597,
107
+ "eval_samples_per_second": 17.953,
108
+ "eval_steps_per_second": 0.563,
109
+ "step": 10
110
+ },
111
+ {
112
+ "epoch": 10.52892561983471,
113
+ "eval_accuracy": 0.7153826787512588,
114
+ "eval_auc": 0.5197902476971228,
115
+ "eval_loss": 0.6204488277435303,
116
+ "eval_runtime": 87.5573,
117
+ "eval_samples_per_second": 17.851,
118
+ "eval_steps_per_second": 0.56,
119
+ "step": 11
120
+ },
121
+ {
122
+ "epoch": 11.52892561983471,
123
+ "eval_accuracy": 0.7372763628709745,
124
+ "eval_auc": 0.5502068743063773,
125
+ "eval_loss": 0.5996901392936707,
126
+ "eval_runtime": 86.9158,
127
+ "eval_samples_per_second": 17.983,
128
+ "eval_steps_per_second": 0.564,
129
+ "step": 12
130
+ },
131
+ {
132
+ "epoch": 12.52892561983471,
133
+ "eval_accuracy": 0.734802716553477,
134
+ "eval_auc": 0.5574448164030912,
135
+ "eval_loss": 0.5834851861000061,
136
+ "eval_runtime": 87.0333,
137
+ "eval_samples_per_second": 17.959,
138
+ "eval_steps_per_second": 0.563,
139
+ "step": 13
140
+ },
141
+ {
142
+ "epoch": 13.52892561983471,
143
+ "eval_accuracy": 0.7389339804200485,
144
+ "eval_auc": 0.5629247811105401,
145
+ "eval_loss": 0.5793451070785522,
146
+ "eval_runtime": 87.2737,
147
+ "eval_samples_per_second": 17.909,
148
+ "eval_steps_per_second": 0.561,
149
+ "step": 14
150
+ },
151
+ {
152
+ "epoch": 14.52892561983471,
153
+ "eval_accuracy": 0.7359946043923619,
154
+ "eval_auc": 0.5624202321874743,
155
+ "eval_loss": 0.5870313048362732,
156
+ "eval_runtime": 87.0434,
157
+ "eval_samples_per_second": 17.957,
158
+ "eval_steps_per_second": 0.563,
159
+ "step": 15
160
+ },
161
+ {
162
+ "epoch": 15.52892561983471,
163
+ "eval_accuracy": 0.7327740912315847,
164
+ "eval_auc": 0.5694981599851945,
165
+ "eval_loss": 0.591485857963562,
166
+ "eval_runtime": 87.1532,
167
+ "eval_samples_per_second": 17.934,
168
+ "eval_steps_per_second": 0.562,
169
+ "step": 16
170
+ },
171
+ {
172
+ "epoch": 16.52892561983471,
173
+ "eval_accuracy": 0.735887601100642,
174
+ "eval_auc": 0.5814546071072487,
175
+ "eval_loss": 0.5902533531188965,
176
+ "eval_runtime": 87.078,
177
+ "eval_samples_per_second": 17.949,
178
+ "eval_steps_per_second": 0.563,
179
+ "step": 17
180
+ },
181
+ {
182
+ "epoch": 17.52892561983471,
183
+ "eval_accuracy": 0.7314548111041537,
184
+ "eval_auc": 0.5843823384546716,
185
+ "eval_loss": 0.5845540165901184,
186
+ "eval_runtime": 87.3811,
187
+ "eval_samples_per_second": 17.887,
188
+ "eval_steps_per_second": 0.561,
189
+ "step": 18
190
+ },
191
+ {
192
+ "epoch": 18.52892561983471,
193
+ "eval_accuracy": 0.7293128808573229,
194
+ "eval_auc": 0.5920336706070137,
195
+ "eval_loss": 0.5858773589134216,
196
+ "eval_runtime": 87.4438,
197
+ "eval_samples_per_second": 17.874,
198
+ "eval_steps_per_second": 0.56,
199
+ "step": 19
200
+ },
201
+ {
202
+ "epoch": 19.52892561983471,
203
+ "eval_accuracy": 0.7326169930302024,
204
+ "eval_auc": 0.6028381748490906,
205
+ "eval_loss": 0.5842309594154358,
206
+ "eval_runtime": 87.0159,
207
+ "eval_samples_per_second": 17.962,
208
+ "eval_steps_per_second": 0.563,
209
+ "step": 20
210
+ },
211
+ {
212
+ "epoch": 20.52892561983471,
213
+ "eval_accuracy": 0.7325605724567937,
214
+ "eval_auc": 0.6027433860514931,
215
+ "eval_loss": 0.5875126719474792,
216
+ "eval_runtime": 87.2907,
217
+ "eval_samples_per_second": 17.906,
218
+ "eval_steps_per_second": 0.561,
219
+ "step": 21
220
+ },
221
+ {
222
+ "epoch": 21.52892561983471,
223
+ "eval_accuracy": 0.7361993977919037,
224
+ "eval_auc": 0.6182446520940644,
225
+ "eval_loss": 0.5847510695457458,
226
+ "eval_runtime": 87.6614,
227
+ "eval_samples_per_second": 17.83,
228
+ "eval_steps_per_second": 0.559,
229
+ "step": 22
230
+ },
231
+ {
232
+ "epoch": 22.52892561983471,
233
+ "eval_accuracy": 0.7462780457118893,
234
+ "eval_auc": 0.628322667206198,
235
+ "eval_loss": 0.576776385307312,
236
+ "eval_runtime": 87.1263,
237
+ "eval_samples_per_second": 17.939,
238
+ "eval_steps_per_second": 0.562,
239
+ "step": 23
240
+ },
241
+ {
242
+ "epoch": 23.52892561983471,
243
+ "eval_accuracy": 0.7492718648581177,
244
+ "eval_auc": 0.6393962023092061,
245
+ "eval_loss": 0.5682416558265686,
246
+ "eval_runtime": 86.9792,
247
+ "eval_samples_per_second": 17.97,
248
+ "eval_steps_per_second": 0.563,
249
+ "step": 24
250
+ },
251
+ {
252
+ "epoch": 24.52892561983471,
253
+ "eval_accuracy": 0.7504689649422652,
254
+ "eval_auc": 0.6549488864965162,
255
+ "eval_loss": 0.5700637102127075,
256
+ "eval_runtime": 87.1123,
257
+ "eval_samples_per_second": 17.942,
258
+ "eval_steps_per_second": 0.562,
259
+ "step": 25
260
+ },
261
+ {
262
+ "epoch": 25.52892561983471,
263
+ "eval_accuracy": 0.7586950213489201,
264
+ "eval_auc": 0.6535722943146133,
265
+ "eval_loss": 0.5706145763397217,
266
+ "eval_runtime": 87.1536,
267
+ "eval_samples_per_second": 17.934,
268
+ "eval_steps_per_second": 0.562,
269
+ "step": 26
270
+ },
271
+ {
272
+ "epoch": 26.52892561983471,
273
+ "eval_accuracy": 0.758530292942743,
274
+ "eval_auc": 0.6705127145569517,
275
+ "eval_loss": 0.5659807324409485,
276
+ "eval_runtime": 87.1643,
277
+ "eval_samples_per_second": 17.932,
278
+ "eval_steps_per_second": 0.562,
279
+ "step": 27
280
+ },
281
+ {
282
+ "epoch": 27.52892561983471,
283
+ "eval_accuracy": 0.7626077812828601,
284
+ "eval_auc": 0.6836288433471565,
285
+ "eval_loss": 0.5608318448066711,
286
+ "eval_runtime": 87.2631,
287
+ "eval_samples_per_second": 17.911,
288
+ "eval_steps_per_second": 0.562,
289
+ "step": 28
290
+ },
291
+ {
292
+ "epoch": 28.52892561983471,
293
+ "eval_accuracy": 0.7654740908709162,
294
+ "eval_auc": 0.6950791752220067,
295
+ "eval_loss": 0.5519375801086426,
296
+ "eval_runtime": 87.2123,
297
+ "eval_samples_per_second": 17.922,
298
+ "eval_steps_per_second": 0.562,
299
+ "step": 29
300
+ },
301
+ {
302
+ "epoch": 29.52892561983471,
303
+ "eval_accuracy": 0.7769064807899759,
304
+ "eval_auc": 0.7193222407927639,
305
+ "eval_loss": 0.5410986542701721,
306
+ "eval_runtime": 87.2445,
307
+ "eval_samples_per_second": 17.915,
308
+ "eval_steps_per_second": 0.562,
309
+ "step": 30
310
+ },
311
+ {
312
+ "epoch": 30.52892561983471,
313
+ "eval_accuracy": 0.7784772688862599,
314
+ "eval_auc": 0.7328795729349562,
315
+ "eval_loss": 0.5388126373291016,
316
+ "eval_runtime": 87.52,
317
+ "eval_samples_per_second": 17.859,
318
+ "eval_steps_per_second": 0.56,
319
+ "step": 31
320
+ },
321
+ {
322
+ "epoch": 31.52892561983471,
323
+ "eval_accuracy": 0.7844610476830087,
324
+ "eval_auc": 0.745194904815567,
325
+ "eval_loss": 0.5323736071586609,
326
+ "eval_runtime": 87.5061,
327
+ "eval_samples_per_second": 17.862,
328
+ "eval_steps_per_second": 0.56,
329
+ "step": 32
330
+ },
331
+ {
332
+ "epoch": 32.52892561983471,
333
+ "eval_accuracy": 0.7868728464576855,
334
+ "eval_auc": 0.7633782144987803,
335
+ "eval_loss": 0.5242195129394531,
336
+ "eval_runtime": 87.523,
337
+ "eval_samples_per_second": 17.858,
338
+ "eval_steps_per_second": 0.56,
339
+ "step": 33
340
+ },
341
+ {
342
+ "epoch": 33.52892561983471,
343
+ "eval_accuracy": 0.801027654774835,
344
+ "eval_auc": 0.7848154366679554,
345
+ "eval_loss": 0.5102821588516235,
346
+ "eval_runtime": 87.416,
347
+ "eval_samples_per_second": 17.88,
348
+ "eval_steps_per_second": 0.561,
349
+ "step": 34
350
+ },
351
+ {
352
+ "epoch": 34.52892561983471,
353
+ "eval_accuracy": 0.8095675021895984,
354
+ "eval_auc": 0.8044254944777215,
355
+ "eval_loss": 0.49118560552597046,
356
+ "eval_runtime": 87.4291,
357
+ "eval_samples_per_second": 17.877,
358
+ "eval_steps_per_second": 0.56,
359
+ "step": 35
360
+ },
361
+ {
362
+ "epoch": 35.52892561983471,
363
+ "eval_accuracy": 0.808054481251051,
364
+ "eval_auc": 0.8127819702239659,
365
+ "eval_loss": 0.49621692299842834,
366
+ "eval_runtime": 87.3816,
367
+ "eval_samples_per_second": 17.887,
368
+ "eval_steps_per_second": 0.561,
369
+ "step": 36
370
+ },
371
+ {
372
+ "epoch": 36.52892561983471,
373
+ "eval_accuracy": 0.8106980431426545,
374
+ "eval_auc": 0.8177832625735753,
375
+ "eval_loss": 0.47984379529953003,
376
+ "eval_runtime": 87.2654,
377
+ "eval_samples_per_second": 17.911,
378
+ "eval_steps_per_second": 0.562,
379
+ "step": 37
380
+ },
381
+ {
382
+ "epoch": 37.52892561983471,
383
+ "eval_accuracy": 0.8177696435256437,
384
+ "eval_auc": 0.827274967926651,
385
+ "eval_loss": 0.4731045067310333,
386
+ "eval_runtime": 87.7254,
387
+ "eval_samples_per_second": 17.817,
388
+ "eval_steps_per_second": 0.559,
389
+ "step": 38
390
+ },
391
+ {
392
+ "epoch": 38.52892561983471,
393
+ "eval_accuracy": 0.8207282913165266,
394
+ "eval_auc": 0.8375385714074627,
395
+ "eval_loss": 0.47474202513694763,
396
+ "eval_runtime": 87.4041,
397
+ "eval_samples_per_second": 17.882,
398
+ "eval_steps_per_second": 0.561,
399
+ "step": 39
400
+ },
401
+ {
402
+ "epoch": 39.52892561983471,
403
+ "eval_accuracy": 0.8275631934595812,
404
+ "eval_auc": 0.8410336724323663,
405
+ "eval_loss": 0.46342405676841736,
406
+ "eval_runtime": 87.8301,
407
+ "eval_samples_per_second": 17.796,
408
+ "eval_steps_per_second": 0.558,
409
+ "step": 40
410
+ },
411
+ {
412
+ "epoch": 40.52892561983471,
413
+ "eval_accuracy": 0.8293715675177127,
414
+ "eval_auc": 0.8441929782134601,
415
+ "eval_loss": 0.45804405212402344,
416
+ "eval_runtime": 87.7721,
417
+ "eval_samples_per_second": 17.807,
418
+ "eval_steps_per_second": 0.558,
419
+ "step": 41
420
+ },
421
+ {
422
+ "epoch": 41.52892561983471,
423
+ "eval_accuracy": 0.8324868835257083,
424
+ "eval_auc": 0.8559241505799194,
425
+ "eval_loss": 0.45006582140922546,
426
+ "eval_runtime": 87.8021,
427
+ "eval_samples_per_second": 17.801,
428
+ "eval_steps_per_second": 0.558,
429
+ "step": 42
430
+ },
431
+ {
432
+ "epoch": 42.52892561983471,
433
+ "eval_accuracy": 0.8311230485143528,
434
+ "eval_auc": 0.8587163210853371,
435
+ "eval_loss": 0.4452967643737793,
436
+ "eval_runtime": 87.5143,
437
+ "eval_samples_per_second": 17.86,
438
+ "eval_steps_per_second": 0.56,
439
+ "step": 43
440
+ },
441
+ {
442
+ "epoch": 43.52892561983471,
443
+ "eval_accuracy": 0.8340865344380283,
444
+ "eval_auc": 0.857364275353225,
445
+ "eval_loss": 0.4441353678703308,
446
+ "eval_runtime": 87.8752,
447
+ "eval_samples_per_second": 17.787,
448
+ "eval_steps_per_second": 0.558,
449
+ "step": 44
450
+ },
451
+ {
452
+ "epoch": 44.52892561983471,
453
+ "eval_accuracy": 0.831814588274456,
454
+ "eval_auc": 0.8595554642045306,
455
+ "eval_loss": 0.4439769387245178,
456
+ "eval_runtime": 87.3569,
457
+ "eval_samples_per_second": 17.892,
458
+ "eval_steps_per_second": 0.561,
459
+ "step": 45
460
+ },
461
+ {
462
+ "epoch": 45.52892561983471,
463
+ "eval_accuracy": 0.8309363076019959,
464
+ "eval_auc": 0.8652269601426812,
465
+ "eval_loss": 0.44992780685424805,
466
+ "eval_runtime": 87.7423,
467
+ "eval_samples_per_second": 17.814,
468
+ "eval_steps_per_second": 0.558,
469
+ "step": 46
470
+ },
471
+ {
472
+ "epoch": 46.52892561983471,
473
+ "eval_accuracy": 0.8358215231927331,
474
+ "eval_auc": 0.8724579775216834,
475
+ "eval_loss": 0.4382532238960266,
476
+ "eval_runtime": 86.7981,
477
+ "eval_samples_per_second": 18.007,
478
+ "eval_steps_per_second": 0.565,
479
+ "step": 47
480
+ },
481
+ {
482
+ "epoch": 47.52892561983471,
483
+ "eval_accuracy": 0.8303788960766193,
484
+ "eval_auc": 0.8759259059740221,
485
+ "eval_loss": 0.44722461700439453,
486
+ "eval_runtime": 87.2144,
487
+ "eval_samples_per_second": 17.921,
488
+ "eval_steps_per_second": 0.562,
489
+ "step": 48
490
+ },
491
+ {
492
+ "epoch": 48.52892561983471,
493
+ "eval_accuracy": 0.8288733882900021,
494
+ "eval_auc": 0.8755758560284902,
495
+ "eval_loss": 0.4499235153198242,
496
+ "eval_runtime": 87.4863,
497
+ "eval_samples_per_second": 17.866,
498
+ "eval_steps_per_second": 0.56,
499
+ "step": 49
500
+ },
501
+ {
502
+ "epoch": 49.52892561983471,
503
+ "eval_accuracy": 0.8366122740047821,
504
+ "eval_auc": 0.8722859993505708,
505
+ "eval_loss": 0.43037721514701843,
506
+ "eval_runtime": 87.3899,
507
+ "eval_samples_per_second": 17.885,
508
+ "eval_steps_per_second": 0.561,
509
+ "step": 50
510
+ },
511
+ {
512
+ "epoch": 50.52892561983471,
513
+ "eval_accuracy": 0.8408468244084683,
514
+ "eval_auc": 0.8780468282392765,
515
+ "eval_loss": 0.42251306772232056,
516
+ "eval_runtime": 88.0914,
517
+ "eval_samples_per_second": 17.743,
518
+ "eval_steps_per_second": 0.556,
519
+ "step": 51
520
+ },
521
+ {
522
+ "epoch": 51.52892561983471,
523
+ "eval_accuracy": 0.8348957897380096,
524
+ "eval_auc": 0.8806832163850822,
525
+ "eval_loss": 0.4276401400566101,
526
+ "eval_runtime": 87.1252,
527
+ "eval_samples_per_second": 17.94,
528
+ "eval_steps_per_second": 0.562,
529
+ "step": 52
530
+ },
531
+ {
532
+ "epoch": 52.52892561983471,
533
+ "eval_accuracy": 0.8378014959240272,
534
+ "eval_auc": 0.8808032157957699,
535
+ "eval_loss": 0.4195541739463806,
536
+ "eval_runtime": 87.7674,
537
+ "eval_samples_per_second": 17.808,
538
+ "eval_steps_per_second": 0.558,
539
+ "step": 53
540
+ },
541
+ {
542
+ "epoch": 53.52892561983471,
543
+ "eval_accuracy": 0.8377568673783704,
544
+ "eval_auc": 0.8786280513672797,
545
+ "eval_loss": 0.4280298352241516,
546
+ "eval_runtime": 87.7048,
547
+ "eval_samples_per_second": 17.821,
548
+ "eval_steps_per_second": 0.559,
549
+ "step": 54
550
+ },
551
+ {
552
+ "epoch": 54.52892561983471,
553
+ "eval_accuracy": 0.8383378575903111,
554
+ "eval_auc": 0.8820957840849988,
555
+ "eval_loss": 0.42469218373298645,
556
+ "eval_runtime": 87.1863,
557
+ "eval_samples_per_second": 17.927,
558
+ "eval_steps_per_second": 0.562,
559
+ "step": 55
560
+ },
561
+ {
562
+ "epoch": 55.52892561983471,
563
+ "eval_accuracy": 0.842429061689127,
564
+ "eval_auc": 0.8827017786870297,
565
+ "eval_loss": 0.4173997938632965,
566
+ "eval_runtime": 87.6623,
567
+ "eval_samples_per_second": 17.83,
568
+ "eval_steps_per_second": 0.559,
569
+ "step": 56
570
+ },
571
+ {
572
+ "epoch": 56.52892561983471,
573
+ "eval_accuracy": 0.8355014687368862,
574
+ "eval_auc": 0.8882257143168839,
575
+ "eval_loss": 0.4334041178226471,
576
+ "eval_runtime": 87.6362,
577
+ "eval_samples_per_second": 17.835,
578
+ "eval_steps_per_second": 0.559,
579
+ "step": 57
580
+ },
581
+ {
582
+ "epoch": 57.52892561983471,
583
+ "eval_accuracy": 0.8325969153814089,
584
+ "eval_auc": 0.8857916625601976,
585
+ "eval_loss": 0.4321269392967224,
586
+ "eval_runtime": 87.35,
587
+ "eval_samples_per_second": 17.894,
588
+ "eval_steps_per_second": 0.561,
589
+ "step": 58
590
+ },
591
+ {
592
+ "epoch": 58.52892561983471,
593
+ "eval_accuracy": 0.8416129440020225,
594
+ "eval_auc": 0.8910538928083584,
595
+ "eval_loss": 0.40702491998672485,
596
+ "eval_runtime": 87.8845,
597
+ "eval_samples_per_second": 17.785,
598
+ "eval_steps_per_second": 0.558,
599
+ "step": 59
600
+ },
601
+ {
602
+ "epoch": 59.52892561983471,
603
+ "eval_accuracy": 0.8413397048960429,
604
+ "eval_auc": 0.8893585400665207,
605
+ "eval_loss": 0.4055131673812866,
606
+ "eval_runtime": 88.2916,
607
+ "eval_samples_per_second": 17.703,
608
+ "eval_steps_per_second": 0.555,
609
+ "step": 60
610
+ },
611
+ {
612
+ "epoch": 60.52892561983471,
613
+ "eval_accuracy": 0.8392555705604321,
614
+ "eval_auc": 0.8901523827034017,
615
+ "eval_loss": 0.42441731691360474,
616
+ "eval_runtime": 87.7981,
617
+ "eval_samples_per_second": 17.802,
618
+ "eval_steps_per_second": 0.558,
619
+ "step": 61
620
+ },
621
+ {
622
+ "epoch": 61.52892561983471,
623
+ "eval_accuracy": 0.8413905486148832,
624
+ "eval_auc": 0.891842125915449,
625
+ "eval_loss": 0.40616291761398315,
626
+ "eval_runtime": 87.9641,
627
+ "eval_samples_per_second": 17.769,
628
+ "eval_steps_per_second": 0.557,
629
+ "step": 62
630
+ },
631
+ {
632
+ "epoch": 62.52892561983471,
633
+ "eval_accuracy": 0.8435168887771352,
634
+ "eval_auc": 0.8880043881473931,
635
+ "eval_loss": 0.4057115912437439,
636
+ "eval_runtime": 87.4566,
637
+ "eval_samples_per_second": 17.872,
638
+ "eval_steps_per_second": 0.56,
639
+ "step": 63
640
+ },
641
+ {
642
+ "epoch": 63.52892561983471,
643
+ "eval_accuracy": 0.846263703952619,
644
+ "eval_auc": 0.8953799373668658,
645
+ "eval_loss": 0.3976118266582489,
646
+ "eval_runtime": 87.9297,
647
+ "eval_samples_per_second": 17.776,
648
+ "eval_steps_per_second": 0.557,
649
+ "step": 64
650
+ },
651
+ {
652
+ "epoch": 64.52892561983471,
653
+ "eval_accuracy": 0.8499107105776817,
654
+ "eval_auc": 0.8947752373117648,
655
+ "eval_loss": 0.39355602860450745,
656
+ "eval_runtime": 87.5668,
657
+ "eval_samples_per_second": 17.849,
658
+ "eval_steps_per_second": 0.56,
659
+ "step": 65
660
+ },
661
+ {
662
+ "epoch": 65.52892561983471,
663
+ "eval_accuracy": 0.8481150668847235,
664
+ "eval_auc": 0.896237061343548,
665
+ "eval_loss": 0.393976628780365,
666
+ "eval_runtime": 87.8459,
667
+ "eval_samples_per_second": 17.793,
668
+ "eval_steps_per_second": 0.558,
669
+ "step": 66
670
+ },
671
+ {
672
+ "epoch": 66.52892561983471,
673
+ "eval_accuracy": 0.8459397715472482,
674
+ "eval_auc": 0.8930191170596469,
675
+ "eval_loss": 0.3947405219078064,
676
+ "eval_runtime": 86.8892,
677
+ "eval_samples_per_second": 17.988,
678
+ "eval_steps_per_second": 0.564,
679
+ "step": 67
680
+ },
681
+ {
682
+ "epoch": 67.52892561983471,
683
+ "eval_accuracy": 0.8459760453876864,
684
+ "eval_auc": 0.8953554221000491,
685
+ "eval_loss": 0.3895111680030823,
686
+ "eval_runtime": 87.5311,
687
+ "eval_samples_per_second": 17.857,
688
+ "eval_steps_per_second": 0.56,
689
+ "step": 68
690
+ },
691
+ {
692
+ "epoch": 68.52892561983471,
693
+ "eval_accuracy": 0.8494102780117945,
694
+ "eval_auc": 0.8994428285472086,
695
+ "eval_loss": 0.39013946056365967,
696
+ "eval_runtime": 87.6498,
697
+ "eval_samples_per_second": 17.832,
698
+ "eval_steps_per_second": 0.559,
699
+ "step": 69
700
+ },
701
+ {
702
+ "epoch": 69.52892561983471,
703
+ "eval_accuracy": 0.8487719004107637,
704
+ "eval_auc": 0.8975541144199808,
705
+ "eval_loss": 0.3885815143585205,
706
+ "eval_runtime": 87.095,
707
+ "eval_samples_per_second": 17.946,
708
+ "eval_steps_per_second": 0.563,
709
+ "step": 70
710
+ },
711
+ {
712
+ "epoch": 70.52892561983471,
713
+ "eval_accuracy": 0.8476486918482375,
714
+ "eval_auc": 0.8951087258228319,
715
+ "eval_loss": 0.3933103084564209,
716
+ "eval_runtime": 87.43,
717
+ "eval_samples_per_second": 17.877,
718
+ "eval_steps_per_second": 0.56,
719
+ "step": 71
720
+ },
721
+ {
722
+ "epoch": 71.52892561983471,
723
+ "eval_accuracy": 0.8505171838505172,
724
+ "eval_auc": 0.8986224830157784,
725
+ "eval_loss": 0.3884218633174896,
726
+ "eval_runtime": 87.2605,
727
+ "eval_samples_per_second": 17.912,
728
+ "eval_steps_per_second": 0.562,
729
+ "step": 72
730
+ },
731
+ {
732
+ "epoch": 72.52892561983471,
733
+ "eval_accuracy": 0.851218487394958,
734
+ "eval_auc": 0.8991789100147513,
735
+ "eval_loss": 0.3868821859359741,
736
+ "eval_runtime": 87.4057,
737
+ "eval_samples_per_second": 17.882,
738
+ "eval_steps_per_second": 0.561,
739
+ "step": 73
740
+ },
741
+ {
742
+ "epoch": 73.52892561983471,
743
+ "eval_accuracy": 0.8519613558757392,
744
+ "eval_auc": 0.898218220649988,
745
+ "eval_loss": 0.3877873122692108,
746
+ "eval_runtime": 87.3717,
747
+ "eval_samples_per_second": 17.889,
748
+ "eval_steps_per_second": 0.561,
749
+ "step": 74
750
+ },
751
+ {
752
+ "epoch": 74.52892561983471,
753
+ "eval_accuracy": 0.8548414376321353,
754
+ "eval_auc": 0.9043920962719242,
755
+ "eval_loss": 0.3716762959957123,
756
+ "eval_runtime": 87.7248,
757
+ "eval_samples_per_second": 17.817,
758
+ "eval_steps_per_second": 0.559,
759
+ "step": 75
760
+ },
761
+ {
762
+ "epoch": 75.52892561983471,
763
+ "eval_accuracy": 0.8507235338918507,
764
+ "eval_auc": 0.9019998015352945,
765
+ "eval_loss": 0.3796072006225586,
766
+ "eval_runtime": 87.5861,
767
+ "eval_samples_per_second": 17.845,
768
+ "eval_steps_per_second": 0.559,
769
+ "step": 76
770
+ },
771
+ {
772
+ "epoch": 76.52892561983471,
773
+ "eval_accuracy": 0.8552576630752526,
774
+ "eval_auc": 0.9050678522215962,
775
+ "eval_loss": 0.3757629692554474,
776
+ "eval_runtime": 88.0061,
777
+ "eval_samples_per_second": 17.76,
778
+ "eval_steps_per_second": 0.557,
779
+ "step": 77
780
+ },
781
+ {
782
+ "epoch": 77.52892561983471,
783
+ "eval_accuracy": 0.8553914389723419,
784
+ "eval_auc": 0.9055021150936422,
785
+ "eval_loss": 0.37119558453559875,
786
+ "eval_runtime": 87.5028,
787
+ "eval_samples_per_second": 17.862,
788
+ "eval_steps_per_second": 0.56,
789
+ "step": 78
790
+ },
791
+ {
792
+ "epoch": 78.52892561983471,
793
+ "eval_accuracy": 0.8529289225897841,
794
+ "eval_auc": 0.9042613508439051,
795
+ "eval_loss": 0.3714446425437927,
796
+ "eval_runtime": 87.2641,
797
+ "eval_samples_per_second": 17.911,
798
+ "eval_steps_per_second": 0.562,
799
+ "step": 79
800
+ },
801
+ {
802
+ "epoch": 79.52892561983471,
803
+ "eval_accuracy": 0.8507856693903205,
804
+ "eval_auc": 0.9015082574820903,
805
+ "eval_loss": 0.3804471492767334,
806
+ "eval_runtime": 87.3664,
807
+ "eval_samples_per_second": 17.89,
808
+ "eval_steps_per_second": 0.561,
809
+ "step": 80
810
+ },
811
+ {
812
+ "epoch": 80.52892561983471,
813
+ "eval_accuracy": 0.8524967561006237,
814
+ "eval_auc": 0.9033352494220062,
815
+ "eval_loss": 0.3733759820461273,
816
+ "eval_runtime": 87.4052,
817
+ "eval_samples_per_second": 17.882,
818
+ "eval_steps_per_second": 0.561,
819
+ "step": 81
820
+ },
821
+ {
822
+ "epoch": 81.52892561983471,
823
+ "eval_accuracy": 0.8495783157806402,
824
+ "eval_auc": 0.9056206015902386,
825
+ "eval_loss": 0.3749751150608063,
826
+ "eval_runtime": 87.2115,
827
+ "eval_samples_per_second": 17.922,
828
+ "eval_steps_per_second": 0.562,
829
+ "step": 82
830
+ },
831
+ {
832
+ "epoch": 82.52892561983471,
833
+ "eval_accuracy": 0.8469255528152824,
834
+ "eval_auc": 0.9015017576251956,
835
+ "eval_loss": 0.37824445962905884,
836
+ "eval_runtime": 87.3018,
837
+ "eval_samples_per_second": 17.903,
838
+ "eval_steps_per_second": 0.561,
839
+ "step": 83
840
+ },
841
+ {
842
+ "epoch": 83.52892561983471,
843
+ "eval_accuracy": 0.851901323204074,
844
+ "eval_auc": 0.904959278213227,
845
+ "eval_loss": 0.37339141964912415,
846
+ "eval_runtime": 87.5274,
847
+ "eval_samples_per_second": 17.857,
848
+ "eval_steps_per_second": 0.56,
849
+ "step": 84
850
+ },
851
+ {
852
+ "epoch": 84.52892561983471,
853
+ "eval_accuracy": 0.8520324519736012,
854
+ "eval_auc": 0.9043750712310512,
855
+ "eval_loss": 0.37398338317871094,
856
+ "eval_runtime": 87.9354,
857
+ "eval_samples_per_second": 17.774,
858
+ "eval_steps_per_second": 0.557,
859
+ "step": 85
860
+ },
861
+ {
862
+ "epoch": 85.52892561983471,
863
+ "eval_accuracy": 0.8538973264716957,
864
+ "eval_auc": 0.9069493908976312,
865
+ "eval_loss": 0.37228140234947205,
866
+ "eval_runtime": 87.9449,
867
+ "eval_samples_per_second": 17.772,
868
+ "eval_steps_per_second": 0.557,
869
+ "step": 86
870
+ },
871
+ {
872
+ "epoch": 86.52892561983471,
873
+ "eval_accuracy": 0.8509990405873274,
874
+ "eval_auc": 0.9069128627267412,
875
+ "eval_loss": 0.3711836338043213,
876
+ "eval_runtime": 87.5107,
877
+ "eval_samples_per_second": 17.861,
878
+ "eval_steps_per_second": 0.56,
879
+ "step": 87
880
+ },
881
+ {
882
+ "epoch": 87.52892561983471,
883
+ "eval_accuracy": 0.8546714238300697,
884
+ "eval_auc": 0.9058326445962316,
885
+ "eval_loss": 0.3642977178096771,
886
+ "eval_runtime": 87.7755,
887
+ "eval_samples_per_second": 17.807,
888
+ "eval_steps_per_second": 0.558,
889
+ "step": 88
890
+ },
891
+ {
892
+ "epoch": 88.52892561983471,
893
+ "eval_accuracy": 0.8579306280518606,
894
+ "eval_auc": 0.9092894250442615,
895
+ "eval_loss": 0.36133790016174316,
896
+ "eval_runtime": 87.6348,
897
+ "eval_samples_per_second": 17.835,
898
+ "eval_steps_per_second": 0.559,
899
+ "step": 89
900
+ },
901
+ {
902
+ "epoch": 89.52892561983471,
903
+ "eval_accuracy": 0.8563854214503402,
904
+ "eval_auc": 0.9109548936444647,
905
+ "eval_loss": 0.36236608028411865,
906
+ "eval_runtime": 87.4485,
907
+ "eval_samples_per_second": 17.873,
908
+ "eval_steps_per_second": 0.56,
909
+ "step": 90
910
+ },
911
+ {
912
+ "epoch": 90.52892561983471,
913
+ "eval_accuracy": 0.8541448058761805,
914
+ "eval_auc": 0.9055844765532028,
915
+ "eval_loss": 0.364606648683548,
916
+ "eval_runtime": 87.7842,
917
+ "eval_samples_per_second": 17.805,
918
+ "eval_steps_per_second": 0.558,
919
+ "step": 91
920
+ },
921
+ {
922
+ "epoch": 91.52892561983471,
923
+ "eval_accuracy": 0.8555063132368927,
924
+ "eval_auc": 0.9095905111982248,
925
+ "eval_loss": 0.36065495014190674,
926
+ "eval_runtime": 87.8589,
927
+ "eval_samples_per_second": 17.79,
928
+ "eval_steps_per_second": 0.558,
929
+ "step": 92
930
+ },
931
+ {
932
+ "epoch": 92.52892561983471,
933
+ "eval_accuracy": 0.8537793259747345,
934
+ "eval_auc": 0.9075183954759425,
935
+ "eval_loss": 0.3644067347049713,
936
+ "eval_runtime": 87.4575,
937
+ "eval_samples_per_second": 17.872,
938
+ "eval_steps_per_second": 0.56,
939
+ "step": 93
940
+ },
941
+ {
942
+ "epoch": 93.52892561983471,
943
+ "eval_accuracy": 0.8566125290023202,
944
+ "eval_auc": 0.9105956199515519,
945
+ "eval_loss": 0.3642030656337738,
946
+ "eval_runtime": 87.9636,
947
+ "eval_samples_per_second": 17.769,
948
+ "eval_steps_per_second": 0.557,
949
+ "step": 94
950
+ },
951
+ {
952
+ "epoch": 94.52892561983471,
953
+ "eval_accuracy": 0.8580002500729379,
954
+ "eval_auc": 0.9118745580382054,
955
+ "eval_loss": 0.35949909687042236,
956
+ "eval_runtime": 87.3425,
957
+ "eval_samples_per_second": 17.895,
958
+ "eval_steps_per_second": 0.561,
959
+ "step": 95
960
+ },
961
+ {
962
+ "epoch": 95.52892561983471,
963
+ "eval_accuracy": 0.8576235541535226,
964
+ "eval_auc": 0.9098413741505762,
965
+ "eval_loss": 0.3638646602630615,
966
+ "eval_runtime": 87.708,
967
+ "eval_samples_per_second": 17.82,
968
+ "eval_steps_per_second": 0.559,
969
+ "step": 96
970
+ },
971
+ {
972
+ "epoch": 96.52892561983471,
973
+ "eval_accuracy": 0.85633238778575,
974
+ "eval_auc": 0.9106240561108658,
975
+ "eval_loss": 0.3620871901512146,
976
+ "eval_runtime": 87.4841,
977
+ "eval_samples_per_second": 17.866,
978
+ "eval_steps_per_second": 0.56,
979
+ "step": 97
980
+ },
981
+ {
982
+ "epoch": 97.52892561983471,
983
+ "eval_accuracy": 0.8512826919873396,
984
+ "eval_auc": 0.9098123479022083,
985
+ "eval_loss": 0.36590248346328735,
986
+ "eval_runtime": 87.3427,
987
+ "eval_samples_per_second": 17.895,
988
+ "eval_steps_per_second": 0.561,
989
+ "step": 98
990
+ },
991
+ {
992
+ "epoch": 98.52892561983471,
993
+ "eval_accuracy": 0.8521421983734384,
994
+ "eval_auc": 0.9058724695907405,
995
+ "eval_loss": 0.3740386664867401,
996
+ "eval_runtime": 87.6579,
997
+ "eval_samples_per_second": 17.831,
998
+ "eval_steps_per_second": 0.559,
999
+ "step": 99
1000
+ },
1001
+ {
1002
+ "epoch": 99.52892561983471,
1003
+ "eval_accuracy": 0.85401096163428,
1004
+ "eval_auc": 0.9065855978572865,
1005
+ "eval_loss": 0.37084951996803284,
1006
+ "eval_runtime": 87.5494,
1007
+ "eval_samples_per_second": 17.853,
1008
+ "eval_steps_per_second": 0.56,
1009
+ "step": 100
1010
+ },
1011
+ {
1012
+ "epoch": 99.52892561983471,
1013
+ "step": 100,
1014
+ "total_flos": 1.3065819223244145e+18,
1015
+ "train_loss": 0.5646095657348633,
1016
+ "train_runtime": 38955.3575,
1017
+ "train_samples_per_second": 9.914,
1018
+ "train_steps_per_second": 0.003
1019
+ }
1020
+ ],
1021
+ "logging_steps": 500,
1022
+ "max_steps": 100,
1023
+ "num_input_tokens_seen": 0,
1024
+ "num_train_epochs": 100,
1025
+ "save_steps": 500,
1026
+ "stateful_callbacks": {
1027
+ "TrainerControl": {
1028
+ "args": {
1029
+ "should_epoch_stop": false,
1030
+ "should_evaluate": false,
1031
+ "should_log": false,
1032
+ "should_save": false,
1033
+ "should_training_stop": false
1034
+ },
1035
+ "attributes": {}
1036
+ }
1037
+ },
1038
+ "total_flos": 1.3065819223244145e+18,
1039
+ "train_batch_size": 16,
1040
+ "trial_name": null,
1041
+ "trial_params": null
1042
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9e479e775dd2b856178dfe4a166e8ee64e0db9ab84b0caf14e516c499bc6409
3
+ size 5432