matterai commited on
Commit
48a6843
·
verified ·
1 Parent(s): b8e7607
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 50282,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "LABEL_0"
24
+ },
25
+ "initializer_cutoff_factor": 2.0,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 1152,
28
+ "label2id": {
29
+ "LABEL_0": 0
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "local_attention": 128,
33
+ "local_rope_theta": 10000.0,
34
+ "max_position_embeddings": 8192,
35
+ "mlp_bias": false,
36
+ "mlp_dropout": 0.0,
37
+ "model_type": "modernbert",
38
+ "norm_bias": false,
39
+ "norm_eps": 1e-05,
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 22,
42
+ "pad_token_id": 50283,
43
+ "position_embedding_type": "absolute",
44
+ "problem_type": "multi_label_classification",
45
+ "repad_logits_with_grad": false,
46
+ "sep_token_id": 50282,
47
+ "sparse_pred_ignore_index": -100,
48
+ "sparse_prediction": false,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.51.3",
51
+ "vocab_size": 50368
52
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98eb039ce8a62ff28e48b96d4130dc0501eff6c624c11030b7940b1e88ccb20c
3
+ size 598436708
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab13e0757ee80037fa7b017b3081cf493b30578848a65af80c04246fa0f41aed
3
+ size 1196961547
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad50b1dfc77c5e1d74ed16de3490372bcd2506d88a973c1d586e777a7e6b37e4
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3373f6d8d8368b9bbb72711ae97a4c92128804df2f77229a6e0d4b68fd381be8
3
+ size 1401
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 8192,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizer",
944
+ "unk_token": "[UNK]"
945
+ }
trainer_state.json ADDED
@@ -0,0 +1,828 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1024,
3
+ "best_metric": 0.9530514004567643,
4
+ "best_model_checkpoint": "checkpoints/checkpoint-1024",
5
+ "epoch": 0.37730287398673545,
6
+ "eval_steps": 128,
7
+ "global_step": 1024,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0036845983787767134,
14
+ "grad_norm": 8.914146423339844,
15
+ "learning_rate": 1.3499999999999998e-05,
16
+ "loss": 0.6841,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.007369196757553427,
21
+ "grad_norm": 6.666998386383057,
22
+ "learning_rate": 2.8499999999999998e-05,
23
+ "loss": 0.517,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.01105379513633014,
28
+ "grad_norm": 5.241199016571045,
29
+ "learning_rate": 4.3499999999999993e-05,
30
+ "loss": 0.4514,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.014738393515106854,
35
+ "grad_norm": 5.938083171844482,
36
+ "learning_rate": 5.85e-05,
37
+ "loss": 0.4963,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.018422991893883568,
42
+ "grad_norm": 3.599522590637207,
43
+ "learning_rate": 7.35e-05,
44
+ "loss": 0.4226,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.02210759027266028,
49
+ "grad_norm": 4.397755146026611,
50
+ "learning_rate": 8.849999999999998e-05,
51
+ "loss": 0.4117,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.025792188651436992,
56
+ "grad_norm": 11.364407539367676,
57
+ "learning_rate": 0.00010349999999999998,
58
+ "loss": 0.3636,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.029476787030213707,
63
+ "grad_norm": 3.12703800201416,
64
+ "learning_rate": 0.0001185,
65
+ "loss": 0.3726,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.03316138540899042,
70
+ "grad_norm": 2.9937469959259033,
71
+ "learning_rate": 0.0001335,
72
+ "loss": 0.3421,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.036845983787767135,
77
+ "grad_norm": 2.8763785362243652,
78
+ "learning_rate": 0.00014849999999999998,
79
+ "loss": 0.4045,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.040530582166543844,
84
+ "grad_norm": 4.576082706451416,
85
+ "learning_rate": 0.0001635,
86
+ "loss": 0.3629,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.04421518054532056,
91
+ "grad_norm": 4.948099613189697,
92
+ "learning_rate": 0.00017849999999999997,
93
+ "loss": 0.394,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.04716285924834193,
98
+ "eval_has_safety_issue_roc_auc": 0.918227021974626,
99
+ "eval_loss": 0.40556982159614563,
100
+ "eval_mean_roc_auc": 0.918227021974626,
101
+ "eval_runtime": 489.5112,
102
+ "eval_samples_per_second": 76.035,
103
+ "eval_steps_per_second": 2.378,
104
+ "step": 128
105
+ },
106
+ {
107
+ "epoch": 0.047899778924097275,
108
+ "grad_norm": 2.6524598598480225,
109
+ "learning_rate": 0.0001935,
110
+ "loss": 0.3734,
111
+ "step": 130
112
+ },
113
+ {
114
+ "epoch": 0.051584377302873984,
115
+ "grad_norm": 4.847095966339111,
116
+ "learning_rate": 0.00020849999999999997,
117
+ "loss": 0.3707,
118
+ "step": 140
119
+ },
120
+ {
121
+ "epoch": 0.0552689756816507,
122
+ "grad_norm": 2.1986277103424072,
123
+ "learning_rate": 0.00022349999999999998,
124
+ "loss": 0.3914,
125
+ "step": 150
126
+ },
127
+ {
128
+ "epoch": 0.058953574060427415,
129
+ "grad_norm": 1.9227941036224365,
130
+ "learning_rate": 0.0002385,
131
+ "loss": 0.3834,
132
+ "step": 160
133
+ },
134
+ {
135
+ "epoch": 0.06263817243920412,
136
+ "grad_norm": 1.3873552083969116,
137
+ "learning_rate": 0.0002535,
138
+ "loss": 0.2576,
139
+ "step": 170
140
+ },
141
+ {
142
+ "epoch": 0.06632277081798084,
143
+ "grad_norm": 4.532320022583008,
144
+ "learning_rate": 0.00026849999999999997,
145
+ "loss": 0.4172,
146
+ "step": 180
147
+ },
148
+ {
149
+ "epoch": 0.07000736919675755,
150
+ "grad_norm": 2.5069925785064697,
151
+ "learning_rate": 0.00028349999999999995,
152
+ "loss": 0.4712,
153
+ "step": 190
154
+ },
155
+ {
156
+ "epoch": 0.07369196757553427,
157
+ "grad_norm": 1.9502817392349243,
158
+ "learning_rate": 0.0002985,
159
+ "loss": 0.3573,
160
+ "step": 200
161
+ },
162
+ {
163
+ "epoch": 0.07737656595431099,
164
+ "grad_norm": 6.129453182220459,
165
+ "learning_rate": 0.00029994004614753843,
166
+ "loss": 0.2982,
167
+ "step": 210
168
+ },
169
+ {
170
+ "epoch": 0.08106116433308769,
171
+ "grad_norm": 4.473495006561279,
172
+ "learning_rate": 0.00029973285979173177,
173
+ "loss": 0.4217,
174
+ "step": 220
175
+ },
176
+ {
177
+ "epoch": 0.0847457627118644,
178
+ "grad_norm": 1.3703476190567017,
179
+ "learning_rate": 0.0002993779051807778,
180
+ "loss": 0.3758,
181
+ "step": 230
182
+ },
183
+ {
184
+ "epoch": 0.08843036109064112,
185
+ "grad_norm": 1.4541234970092773,
186
+ "learning_rate": 0.00029887553261202354,
187
+ "loss": 0.3863,
188
+ "step": 240
189
+ },
190
+ {
191
+ "epoch": 0.09211495946941783,
192
+ "grad_norm": 1.872299075126648,
193
+ "learning_rate": 0.00029822623786654207,
194
+ "loss": 0.3525,
195
+ "step": 250
196
+ },
197
+ {
198
+ "epoch": 0.09432571849668386,
199
+ "eval_has_safety_issue_roc_auc": 0.9362037324386603,
200
+ "eval_loss": 0.33471250534057617,
201
+ "eval_mean_roc_auc": 0.9362037324386603,
202
+ "eval_runtime": 487.3367,
203
+ "eval_samples_per_second": 76.374,
204
+ "eval_steps_per_second": 2.388,
205
+ "step": 256
206
+ },
207
+ {
208
+ "epoch": 0.09579955784819455,
209
+ "grad_norm": 2.644226312637329,
210
+ "learning_rate": 0.0002974306617198568,
211
+ "loss": 0.3905,
212
+ "step": 260
213
+ },
214
+ {
215
+ "epoch": 0.09948415622697127,
216
+ "grad_norm": 2.3409223556518555,
217
+ "learning_rate": 0.0002964895893095737,
218
+ "loss": 0.3515,
219
+ "step": 270
220
+ },
221
+ {
222
+ "epoch": 0.10316875460574797,
223
+ "grad_norm": 2.0618879795074463,
224
+ "learning_rate": 0.00029540394936054435,
225
+ "loss": 0.3592,
226
+ "step": 280
227
+ },
228
+ {
229
+ "epoch": 0.10685335298452468,
230
+ "grad_norm": 0.9815084338188171,
231
+ "learning_rate": 0.00029417481326832776,
232
+ "loss": 0.3944,
233
+ "step": 290
234
+ },
235
+ {
236
+ "epoch": 0.1105379513633014,
237
+ "grad_norm": 4.9908013343811035,
238
+ "learning_rate": 0.00029280339404185146,
239
+ "loss": 0.4092,
240
+ "step": 300
241
+ },
242
+ {
243
+ "epoch": 0.11422254974207811,
244
+ "grad_norm": 0.6844871640205383,
245
+ "learning_rate": 0.00029129104510631853,
246
+ "loss": 0.4466,
247
+ "step": 310
248
+ },
249
+ {
250
+ "epoch": 0.11790714812085483,
251
+ "grad_norm": 1.8045854568481445,
252
+ "learning_rate": 0.00028963925896754035,
253
+ "loss": 0.3698,
254
+ "step": 320
255
+ },
256
+ {
257
+ "epoch": 0.12159174649963155,
258
+ "grad_norm": 4.337238788604736,
259
+ "learning_rate": 0.00028784966573901314,
260
+ "loss": 0.3892,
261
+ "step": 330
262
+ },
263
+ {
264
+ "epoch": 0.12527634487840825,
265
+ "grad_norm": 0.8228144645690918,
266
+ "learning_rate": 0.0002859240315331935,
267
+ "loss": 0.417,
268
+ "step": 340
269
+ },
270
+ {
271
+ "epoch": 0.12896094325718496,
272
+ "grad_norm": 1.259918212890625,
273
+ "learning_rate": 0.00028386425671855764,
274
+ "loss": 0.3393,
275
+ "step": 350
276
+ },
277
+ {
278
+ "epoch": 0.13264554163596168,
279
+ "grad_norm": 4.035144805908203,
280
+ "learning_rate": 0.00028167237404416826,
281
+ "loss": 0.2893,
282
+ "step": 360
283
+ },
284
+ {
285
+ "epoch": 0.1363301400147384,
286
+ "grad_norm": 1.1749995946884155,
287
+ "learning_rate": 0.0002793505466335956,
288
+ "loss": 0.4133,
289
+ "step": 370
290
+ },
291
+ {
292
+ "epoch": 0.1400147383935151,
293
+ "grad_norm": 1.3367811441421509,
294
+ "learning_rate": 0.0002769010658501763,
295
+ "loss": 0.3775,
296
+ "step": 380
297
+ },
298
+ {
299
+ "epoch": 0.1414885777450258,
300
+ "eval_has_safety_issue_roc_auc": 0.9363893661137548,
301
+ "eval_loss": 0.3488316535949707,
302
+ "eval_mean_roc_auc": 0.9363893661137548,
303
+ "eval_runtime": 487.0696,
304
+ "eval_samples_per_second": 76.416,
305
+ "eval_steps_per_second": 2.39,
306
+ "step": 384
307
+ },
308
+ {
309
+ "epoch": 0.14369933677229182,
310
+ "grad_norm": 1.7076958417892456,
311
+ "learning_rate": 0.00027432634903571426,
312
+ "loss": 0.4061,
313
+ "step": 390
314
+ },
315
+ {
316
+ "epoch": 0.14738393515106854,
317
+ "grad_norm": 1.1982675790786743,
318
+ "learning_rate": 0.000271628937124856,
319
+ "loss": 0.3591,
320
+ "step": 400
321
+ },
322
+ {
323
+ "epoch": 0.15106853352984526,
324
+ "grad_norm": 0.9970278143882751,
325
+ "learning_rate": 0.000268811492137495,
326
+ "loss": 0.3556,
327
+ "step": 410
328
+ },
329
+ {
330
+ "epoch": 0.15475313190862197,
331
+ "grad_norm": 3.2783939838409424,
332
+ "learning_rate": 0.0002658767945516796,
333
+ "loss": 0.3119,
334
+ "step": 420
335
+ },
336
+ {
337
+ "epoch": 0.1584377302873987,
338
+ "grad_norm": 0.9100527763366699,
339
+ "learning_rate": 0.0002628277405596167,
340
+ "loss": 0.3235,
341
+ "step": 430
342
+ },
343
+ {
344
+ "epoch": 0.16212232866617537,
345
+ "grad_norm": 2.0034751892089844,
346
+ "learning_rate": 0.0002596673392094796,
347
+ "loss": 0.3409,
348
+ "step": 440
349
+ },
350
+ {
351
+ "epoch": 0.1658069270449521,
352
+ "grad_norm": 2.4519588947296143,
353
+ "learning_rate": 0.00025639870943584104,
354
+ "loss": 0.3431,
355
+ "step": 450
356
+ },
357
+ {
358
+ "epoch": 0.1694915254237288,
359
+ "grad_norm": 3.1098690032958984,
360
+ "learning_rate": 0.0002530250769816612,
361
+ "loss": 0.3966,
362
+ "step": 460
363
+ },
364
+ {
365
+ "epoch": 0.17317612380250552,
366
+ "grad_norm": 1.0801705121994019,
367
+ "learning_rate": 0.0002495497712148688,
368
+ "loss": 0.3026,
369
+ "step": 470
370
+ },
371
+ {
372
+ "epoch": 0.17686072218128224,
373
+ "grad_norm": 2.5059814453125,
374
+ "learning_rate": 0.00024597622184267673,
375
+ "loss": 0.3053,
376
+ "step": 480
377
+ },
378
+ {
379
+ "epoch": 0.18054532056005895,
380
+ "grad_norm": 4.749985694885254,
381
+ "learning_rate": 0.00024230795552687568,
382
+ "loss": 0.3585,
383
+ "step": 490
384
+ },
385
+ {
386
+ "epoch": 0.18422991893883567,
387
+ "grad_norm": 2.033231735229492,
388
+ "learning_rate": 0.00023854859240344416,
389
+ "loss": 0.3503,
390
+ "step": 500
391
+ },
392
+ {
393
+ "epoch": 0.18791451731761238,
394
+ "grad_norm": 1.2591739892959595,
395
+ "learning_rate": 0.00023470184250991156,
396
+ "loss": 0.3347,
397
+ "step": 510
398
+ },
399
+ {
400
+ "epoch": 0.18865143699336773,
401
+ "eval_has_safety_issue_roc_auc": 0.941105104803345,
402
+ "eval_loss": 0.3277105987071991,
403
+ "eval_mean_roc_auc": 0.941105104803345,
404
+ "eval_runtime": 487.352,
405
+ "eval_samples_per_second": 76.372,
406
+ "eval_steps_per_second": 2.388,
407
+ "step": 512
408
+ },
409
+ {
410
+ "epoch": 0.1915991156963891,
411
+ "grad_norm": 3.9085240364074707,
412
+ "learning_rate": 0.00023077150212399899,
413
+ "loss": 0.3273,
414
+ "step": 520
415
+ },
416
+ {
417
+ "epoch": 0.19528371407516582,
418
+ "grad_norm": 0.7869892120361328,
419
+ "learning_rate": 0.00022676145001715174,
420
+ "loss": 0.3515,
421
+ "step": 530
422
+ },
423
+ {
424
+ "epoch": 0.19896831245394253,
425
+ "grad_norm": 0.9839105606079102,
426
+ "learning_rate": 0.00022267564362665968,
427
+ "loss": 0.3073,
428
+ "step": 540
429
+ },
430
+ {
431
+ "epoch": 0.20265291083271925,
432
+ "grad_norm": 0.618803083896637,
433
+ "learning_rate": 0.0002185181151501449,
434
+ "loss": 0.3734,
435
+ "step": 550
436
+ },
437
+ {
438
+ "epoch": 0.20633750921149593,
439
+ "grad_norm": 1.2680476903915405,
440
+ "learning_rate": 0.00021429296756626925,
441
+ "loss": 0.3323,
442
+ "step": 560
443
+ },
444
+ {
445
+ "epoch": 0.21002210759027265,
446
+ "grad_norm": 1.8254988193511963,
447
+ "learning_rate": 0.00021000437058558968,
448
+ "loss": 0.35,
449
+ "step": 570
450
+ },
451
+ {
452
+ "epoch": 0.21370670596904937,
453
+ "grad_norm": 1.5576568841934204,
454
+ "learning_rate": 0.00020565655653555763,
455
+ "loss": 0.2629,
456
+ "step": 580
457
+ },
458
+ {
459
+ "epoch": 0.21739130434782608,
460
+ "grad_norm": 0.9699956178665161,
461
+ "learning_rate": 0.0002012538161837225,
462
+ "loss": 0.2764,
463
+ "step": 590
464
+ },
465
+ {
466
+ "epoch": 0.2210759027266028,
467
+ "grad_norm": 0.5201606154441833,
468
+ "learning_rate": 0.00019680049450326222,
469
+ "loss": 0.267,
470
+ "step": 600
471
+ },
472
+ {
473
+ "epoch": 0.2247605011053795,
474
+ "grad_norm": 0.876549243927002,
475
+ "learning_rate": 0.00019230098638501938,
476
+ "loss": 0.3421,
477
+ "step": 610
478
+ },
479
+ {
480
+ "epoch": 0.22844509948415623,
481
+ "grad_norm": 0.6652014255523682,
482
+ "learning_rate": 0.00018775973230027458,
483
+ "loss": 0.3823,
484
+ "step": 620
485
+ },
486
+ {
487
+ "epoch": 0.23212969786293294,
488
+ "grad_norm": 1.2416579723358154,
489
+ "learning_rate": 0.00018318121391853708,
490
+ "loss": 0.2984,
491
+ "step": 630
492
+ },
493
+ {
494
+ "epoch": 0.23581429624170966,
495
+ "grad_norm": 0.8337903618812561,
496
+ "learning_rate": 0.00017856994968467845,
497
+ "loss": 0.2969,
498
+ "step": 640
499
+ },
500
+ {
501
+ "epoch": 0.23581429624170966,
502
+ "eval_has_safety_issue_roc_auc": 0.9458881980708542,
503
+ "eval_loss": 0.31154128909111023,
504
+ "eval_mean_roc_auc": 0.9458881980708542,
505
+ "eval_runtime": 487.6344,
506
+ "eval_samples_per_second": 76.328,
507
+ "eval_steps_per_second": 2.387,
508
+ "step": 640
509
+ },
510
+ {
511
+ "epoch": 0.23949889462048637,
512
+ "grad_norm": 0.8940573930740356,
513
+ "learning_rate": 0.00017393049035977292,
514
+ "loss": 0.3488,
515
+ "step": 650
516
+ },
517
+ {
518
+ "epoch": 0.2431834929992631,
519
+ "grad_norm": 1.5384459495544434,
520
+ "learning_rate": 0.00016926741453004545,
521
+ "loss": 0.3101,
522
+ "step": 660
523
+ },
524
+ {
525
+ "epoch": 0.2468680913780398,
526
+ "grad_norm": 1.3179084062576294,
527
+ "learning_rate": 0.00016458532408835993,
528
+ "loss": 0.2165,
529
+ "step": 670
530
+ },
531
+ {
532
+ "epoch": 0.2505526897568165,
533
+ "grad_norm": 1.6649147272109985,
534
+ "learning_rate": 0.00015988883969270665,
535
+ "loss": 0.2676,
536
+ "step": 680
537
+ },
538
+ {
539
+ "epoch": 0.2542372881355932,
540
+ "grad_norm": 1.43660569190979,
541
+ "learning_rate": 0.00015518259620617085,
542
+ "loss": 0.3425,
543
+ "step": 690
544
+ },
545
+ {
546
+ "epoch": 0.2579218865143699,
547
+ "grad_norm": 1.0876473188400269,
548
+ "learning_rate": 0.00015047123812288193,
549
+ "loss": 0.3139,
550
+ "step": 700
551
+ },
552
+ {
553
+ "epoch": 0.26160648489314664,
554
+ "grad_norm": 1.0270347595214844,
555
+ "learning_rate": 0.000145759414984459,
556
+ "loss": 0.3059,
557
+ "step": 710
558
+ },
559
+ {
560
+ "epoch": 0.26529108327192336,
561
+ "grad_norm": 0.6378604173660278,
562
+ "learning_rate": 0.00014105177679147446,
563
+ "loss": 0.2809,
564
+ "step": 720
565
+ },
566
+ {
567
+ "epoch": 0.26897568165070007,
568
+ "grad_norm": 0.8198941349983215,
569
+ "learning_rate": 0.00013635296941446449,
570
+ "loss": 0.3358,
571
+ "step": 730
572
+ },
573
+ {
574
+ "epoch": 0.2726602800294768,
575
+ "grad_norm": 0.7575820684432983,
576
+ "learning_rate": 0.00013166763000901655,
577
+ "loss": 0.3009,
578
+ "step": 740
579
+ },
580
+ {
581
+ "epoch": 0.2763448784082535,
582
+ "grad_norm": 1.4956635236740112,
583
+ "learning_rate": 0.00012700038243945594,
584
+ "loss": 0.3287,
585
+ "step": 750
586
+ },
587
+ {
588
+ "epoch": 0.2800294767870302,
589
+ "grad_norm": 0.945459246635437,
590
+ "learning_rate": 0.00012235583271565003,
591
+ "loss": 0.3243,
592
+ "step": 760
593
+ },
594
+ {
595
+ "epoch": 0.2829771554900516,
596
+ "eval_has_safety_issue_roc_auc": 0.9507512976389587,
597
+ "eval_loss": 0.2935161590576172,
598
+ "eval_mean_roc_auc": 0.9507512976389587,
599
+ "eval_runtime": 487.4239,
600
+ "eval_samples_per_second": 76.361,
601
+ "eval_steps_per_second": 2.388,
602
+ "step": 768
603
+ },
604
+ {
605
+ "epoch": 0.28371407516580693,
606
+ "grad_norm": 1.6803070306777954,
607
+ "learning_rate": 0.00011773856444743296,
608
+ "loss": 0.2998,
609
+ "step": 770
610
+ },
611
+ {
612
+ "epoch": 0.28739867354458365,
613
+ "grad_norm": 0.8402862548828125,
614
+ "learning_rate": 0.00011315313432113607,
615
+ "loss": 0.2805,
616
+ "step": 780
617
+ },
618
+ {
619
+ "epoch": 0.29108327192336036,
620
+ "grad_norm": 0.950634241104126,
621
+ "learning_rate": 0.00010860406760268816,
622
+ "loss": 0.3111,
623
+ "step": 790
624
+ },
625
+ {
626
+ "epoch": 0.2947678703021371,
627
+ "grad_norm": 0.8810547590255737,
628
+ "learning_rate": 0.00010409585367172489,
629
+ "loss": 0.2858,
630
+ "step": 800
631
+ },
632
+ {
633
+ "epoch": 0.2984524686809138,
634
+ "grad_norm": 0.8042846322059631,
635
+ "learning_rate": 9.96329415911129e-05,
636
+ "loss": 0.3156,
637
+ "step": 810
638
+ },
639
+ {
640
+ "epoch": 0.3021370670596905,
641
+ "grad_norm": 0.6347734332084656,
642
+ "learning_rate": 9.521973571626184e-05,
643
+ "loss": 0.347,
644
+ "step": 820
645
+ },
646
+ {
647
+ "epoch": 0.3058216654384672,
648
+ "grad_norm": 1.017738938331604,
649
+ "learning_rate": 9.086059134855733e-05,
650
+ "loss": 0.2554,
651
+ "step": 830
652
+ },
653
+ {
654
+ "epoch": 0.30950626381724394,
655
+ "grad_norm": 0.5769331455230713,
656
+ "learning_rate": 8.655981043720452e-05,
657
+ "loss": 0.2573,
658
+ "step": 840
659
+ },
660
+ {
661
+ "epoch": 0.31319086219602066,
662
+ "grad_norm": 1.6331214904785156,
663
+ "learning_rate": 8.232163733372322e-05,
664
+ "loss": 0.3412,
665
+ "step": 850
666
+ },
667
+ {
668
+ "epoch": 0.3168754605747974,
669
+ "grad_norm": 1.2017263174057007,
670
+ "learning_rate": 7.815025460328584e-05,
671
+ "loss": 0.245,
672
+ "step": 860
673
+ },
674
+ {
675
+ "epoch": 0.32056005895357403,
676
+ "grad_norm": 0.7730036377906799,
677
+ "learning_rate": 7.404977889703008e-05,
678
+ "loss": 0.3052,
679
+ "step": 870
680
+ },
681
+ {
682
+ "epoch": 0.32424465733235075,
683
+ "grad_norm": 0.643957793712616,
684
+ "learning_rate": 7.00242568894217e-05,
685
+ "loss": 0.2292,
686
+ "step": 880
687
+ },
688
+ {
689
+ "epoch": 0.32792925571112747,
690
+ "grad_norm": 1.9052222967147827,
691
+ "learning_rate": 6.607766128467497e-05,
692
+ "loss": 0.3792,
693
+ "step": 890
694
+ },
695
+ {
696
+ "epoch": 0.3301400147383935,
697
+ "eval_has_safety_issue_roc_auc": 0.9519071421594945,
698
+ "eval_loss": 0.29572874307632446,
699
+ "eval_mean_roc_auc": 0.9519071421594945,
700
+ "eval_runtime": 487.4395,
701
+ "eval_samples_per_second": 76.358,
702
+ "eval_steps_per_second": 2.388,
703
+ "step": 896
704
+ },
705
+ {
706
+ "epoch": 0.3316138540899042,
707
+ "grad_norm": 0.7808663249015808,
708
+ "learning_rate": 6.221388689617348e-05,
709
+ "loss": 0.2955,
710
+ "step": 900
711
+ },
712
+ {
713
+ "epoch": 0.3352984524686809,
714
+ "grad_norm": 0.7185715436935425,
715
+ "learning_rate": 5.843674680275963e-05,
716
+ "loss": 0.2523,
717
+ "step": 910
718
+ },
719
+ {
720
+ "epoch": 0.3389830508474576,
721
+ "grad_norm": 1.606952428817749,
722
+ "learning_rate": 5.474996858568593e-05,
723
+ "loss": 0.3108,
724
+ "step": 920
725
+ },
726
+ {
727
+ "epoch": 0.3426676492262343,
728
+ "grad_norm": 0.7948682308197021,
729
+ "learning_rate": 5.115719064994245e-05,
730
+ "loss": 0.2796,
731
+ "step": 930
732
+ },
733
+ {
734
+ "epoch": 0.34635224760501104,
735
+ "grad_norm": 0.7030922770500183,
736
+ "learning_rate": 4.766195863359054e-05,
737
+ "loss": 0.2397,
738
+ "step": 940
739
+ },
740
+ {
741
+ "epoch": 0.35003684598378776,
742
+ "grad_norm": 1.6789747476577759,
743
+ "learning_rate": 4.426772190864578e-05,
744
+ "loss": 0.2918,
745
+ "step": 950
746
+ },
747
+ {
748
+ "epoch": 0.3537214443625645,
749
+ "grad_norm": 1.2274649143218994,
750
+ "learning_rate": 4.0977830176964584e-05,
751
+ "loss": 0.2523,
752
+ "step": 960
753
+ },
754
+ {
755
+ "epoch": 0.3574060427413412,
756
+ "grad_norm": 0.8976671695709229,
757
+ "learning_rate": 3.77955301644926e-05,
758
+ "loss": 0.2475,
759
+ "step": 970
760
+ },
761
+ {
762
+ "epoch": 0.3610906411201179,
763
+ "grad_norm": 1.8330504894256592,
764
+ "learning_rate": 3.472396241713854e-05,
765
+ "loss": 0.319,
766
+ "step": 980
767
+ },
768
+ {
769
+ "epoch": 0.3647752394988946,
770
+ "grad_norm": 0.5846236944198608,
771
+ "learning_rate": 3.1766158201434e-05,
772
+ "loss": 0.2242,
773
+ "step": 990
774
+ },
775
+ {
776
+ "epoch": 0.36845983787767134,
777
+ "grad_norm": 1.2076009511947632,
778
+ "learning_rate": 2.8925036513039986e-05,
779
+ "loss": 0.306,
780
+ "step": 1000
781
+ },
782
+ {
783
+ "epoch": 0.37214443625644805,
784
+ "grad_norm": 0.7948538064956665,
785
+ "learning_rate": 2.620340119605006e-05,
786
+ "loss": 0.2373,
787
+ "step": 1010
788
+ },
789
+ {
790
+ "epoch": 0.37582903463522477,
791
+ "grad_norm": 2.274285316467285,
792
+ "learning_rate": 2.360393817593514e-05,
793
+ "loss": 0.2993,
794
+ "step": 1020
795
+ },
796
+ {
797
+ "epoch": 0.37730287398673545,
798
+ "eval_has_safety_issue_roc_auc": 0.9530514004567643,
799
+ "eval_loss": 0.2790428400039673,
800
+ "eval_mean_roc_auc": 0.9530514004567643,
801
+ "eval_runtime": 487.3953,
802
+ "eval_samples_per_second": 76.365,
803
+ "eval_steps_per_second": 2.388,
804
+ "step": 1024
805
+ }
806
+ ],
807
+ "logging_steps": 10,
808
+ "max_steps": 3200,
809
+ "num_input_tokens_seen": 0,
810
+ "num_train_epochs": 2,
811
+ "save_steps": 128,
812
+ "stateful_callbacks": {
813
+ "TrainerControl": {
814
+ "args": {
815
+ "should_epoch_stop": false,
816
+ "should_evaluate": false,
817
+ "should_log": false,
818
+ "should_save": true,
819
+ "should_training_stop": false
820
+ },
821
+ "attributes": {}
822
+ }
823
+ },
824
+ "total_flos": 4.466350275271066e+16,
825
+ "train_batch_size": 32,
826
+ "trial_name": null,
827
+ "trial_params": null
828
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f88798c59603bc6e4f0b20367cdf58f88c4554f50f764dfc81f5ac154f49b48
3
+ size 5713