anoaky commited on
Commit
376b754
·
verified ·
1 Parent(s): bedbdc8

Training in progress, epoch 2, checkpoint

Browse files
checkpoint-1110/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.47.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
checkpoint-1110/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c949958fa796793924b642bfd8e370e1e15a20e333c3f6eced033461335ba6ba
3
+ size 437958648
checkpoint-1110/trainer_state.json ADDED
@@ -0,0 +1,843 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1110,
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,
13
+ "eval_f1": 0.6562770562770562,
14
+ "eval_loss": 0.7476533651351929,
15
+ "eval_precision": 0.48976954555244456,
16
+ "eval_recall": 0.9943156974202011,
17
+ "eval_runtime": 16.4688,
18
+ "eval_samples_per_second": 283.749,
19
+ "eval_steps_per_second": 35.522,
20
+ "step": 0
21
+ },
22
+ {
23
+ "epoch": 0.018026137899954935,
24
+ "grad_norm": 14.20566463470459,
25
+ "learning_rate": 4.981949458483755e-05,
26
+ "loss": 0.6876,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 0.03605227579990987,
31
+ "grad_norm": 27.79998016357422,
32
+ "learning_rate": 4.963898916967509e-05,
33
+ "loss": 0.5988,
34
+ "step": 20
35
+ },
36
+ {
37
+ "epoch": 0.054078413699864804,
38
+ "grad_norm": 39.63682556152344,
39
+ "learning_rate": 4.945848375451264e-05,
40
+ "loss": 0.5677,
41
+ "step": 30
42
+ },
43
+ {
44
+ "epoch": 0.07210455159981974,
45
+ "grad_norm": 38.49867630004883,
46
+ "learning_rate": 4.927797833935018e-05,
47
+ "loss": 0.5922,
48
+ "step": 40
49
+ },
50
+ {
51
+ "epoch": 0.09013068949977468,
52
+ "grad_norm": 52.28614044189453,
53
+ "learning_rate": 4.909747292418773e-05,
54
+ "loss": 0.5506,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.10815682739972961,
59
+ "grad_norm": 29.180490493774414,
60
+ "learning_rate": 4.891696750902527e-05,
61
+ "loss": 0.5173,
62
+ "step": 60
63
+ },
64
+ {
65
+ "epoch": 0.12618296529968454,
66
+ "grad_norm": 33.55237579345703,
67
+ "learning_rate": 4.873646209386282e-05,
68
+ "loss": 0.4931,
69
+ "step": 70
70
+ },
71
+ {
72
+ "epoch": 0.14420910319963948,
73
+ "grad_norm": 32.063228607177734,
74
+ "learning_rate": 4.855595667870036e-05,
75
+ "loss": 0.483,
76
+ "step": 80
77
+ },
78
+ {
79
+ "epoch": 0.16223524109959442,
80
+ "grad_norm": 24.234926223754883,
81
+ "learning_rate": 4.837545126353791e-05,
82
+ "loss": 0.47,
83
+ "step": 90
84
+ },
85
+ {
86
+ "epoch": 0.18026137899954936,
87
+ "grad_norm": 33.66775894165039,
88
+ "learning_rate": 4.819494584837546e-05,
89
+ "loss": 0.4564,
90
+ "step": 100
91
+ },
92
+ {
93
+ "epoch": 0.19828751689950427,
94
+ "grad_norm": 53.322574615478516,
95
+ "learning_rate": 4.8014440433213e-05,
96
+ "loss": 0.5083,
97
+ "step": 110
98
+ },
99
+ {
100
+ "epoch": 0.21631365479945922,
101
+ "grad_norm": 29.443470001220703,
102
+ "learning_rate": 4.783393501805055e-05,
103
+ "loss": 0.463,
104
+ "step": 120
105
+ },
106
+ {
107
+ "epoch": 0.23433979269941416,
108
+ "grad_norm": 33.13877487182617,
109
+ "learning_rate": 4.765342960288809e-05,
110
+ "loss": 0.4626,
111
+ "step": 130
112
+ },
113
+ {
114
+ "epoch": 0.25236593059936907,
115
+ "grad_norm": 25.509536743164062,
116
+ "learning_rate": 4.747292418772563e-05,
117
+ "loss": 0.5113,
118
+ "step": 140
119
+ },
120
+ {
121
+ "epoch": 0.270392068499324,
122
+ "grad_norm": 21.015031814575195,
123
+ "learning_rate": 4.7292418772563177e-05,
124
+ "loss": 0.4611,
125
+ "step": 150
126
+ },
127
+ {
128
+ "epoch": 0.28841820639927895,
129
+ "grad_norm": 28.079387664794922,
130
+ "learning_rate": 4.711191335740072e-05,
131
+ "loss": 0.4783,
132
+ "step": 160
133
+ },
134
+ {
135
+ "epoch": 0.3064443442992339,
136
+ "grad_norm": 19.978599548339844,
137
+ "learning_rate": 4.693140794223827e-05,
138
+ "loss": 0.5026,
139
+ "step": 170
140
+ },
141
+ {
142
+ "epoch": 0.32447048219918884,
143
+ "grad_norm": 29.316265106201172,
144
+ "learning_rate": 4.675090252707581e-05,
145
+ "loss": 0.4906,
146
+ "step": 180
147
+ },
148
+ {
149
+ "epoch": 0.3424966200991438,
150
+ "grad_norm": 18.79282569885254,
151
+ "learning_rate": 4.657039711191336e-05,
152
+ "loss": 0.5016,
153
+ "step": 190
154
+ },
155
+ {
156
+ "epoch": 0.3605227579990987,
157
+ "grad_norm": 18.66801643371582,
158
+ "learning_rate": 4.63898916967509e-05,
159
+ "loss": 0.4502,
160
+ "step": 200
161
+ },
162
+ {
163
+ "epoch": 0.3785488958990536,
164
+ "grad_norm": 27.929332733154297,
165
+ "learning_rate": 4.620938628158845e-05,
166
+ "loss": 0.4302,
167
+ "step": 210
168
+ },
169
+ {
170
+ "epoch": 0.39657503379900855,
171
+ "grad_norm": 20.541879653930664,
172
+ "learning_rate": 4.602888086642599e-05,
173
+ "loss": 0.4496,
174
+ "step": 220
175
+ },
176
+ {
177
+ "epoch": 0.4146011716989635,
178
+ "grad_norm": 19.034873962402344,
179
+ "learning_rate": 4.584837545126354e-05,
180
+ "loss": 0.4541,
181
+ "step": 230
182
+ },
183
+ {
184
+ "epoch": 0.43262730959891843,
185
+ "grad_norm": 32.077945709228516,
186
+ "learning_rate": 4.566787003610109e-05,
187
+ "loss": 0.4562,
188
+ "step": 240
189
+ },
190
+ {
191
+ "epoch": 0.45065344749887337,
192
+ "grad_norm": 25.475997924804688,
193
+ "learning_rate": 4.548736462093863e-05,
194
+ "loss": 0.4456,
195
+ "step": 250
196
+ },
197
+ {
198
+ "epoch": 0.4686795853988283,
199
+ "grad_norm": 17.132720947265625,
200
+ "learning_rate": 4.530685920577618e-05,
201
+ "loss": 0.4629,
202
+ "step": 260
203
+ },
204
+ {
205
+ "epoch": 0.48670572329878325,
206
+ "grad_norm": 22.313941955566406,
207
+ "learning_rate": 4.5126353790613716e-05,
208
+ "loss": 0.4444,
209
+ "step": 270
210
+ },
211
+ {
212
+ "epoch": 0.5047318611987381,
213
+ "grad_norm": 22.373477935791016,
214
+ "learning_rate": 4.494584837545127e-05,
215
+ "loss": 0.4404,
216
+ "step": 280
217
+ },
218
+ {
219
+ "epoch": 0.5227579990986931,
220
+ "grad_norm": 16.72430992126465,
221
+ "learning_rate": 4.4765342960288806e-05,
222
+ "loss": 0.4611,
223
+ "step": 290
224
+ },
225
+ {
226
+ "epoch": 0.540784136998648,
227
+ "grad_norm": 27.037927627563477,
228
+ "learning_rate": 4.458483754512636e-05,
229
+ "loss": 0.4272,
230
+ "step": 300
231
+ },
232
+ {
233
+ "epoch": 0.558810274898603,
234
+ "grad_norm": 31.637985229492188,
235
+ "learning_rate": 4.44043321299639e-05,
236
+ "loss": 0.448,
237
+ "step": 310
238
+ },
239
+ {
240
+ "epoch": 0.5768364127985579,
241
+ "grad_norm": 35.010459899902344,
242
+ "learning_rate": 4.422382671480145e-05,
243
+ "loss": 0.4215,
244
+ "step": 320
245
+ },
246
+ {
247
+ "epoch": 0.5948625506985128,
248
+ "grad_norm": 26.25156021118164,
249
+ "learning_rate": 4.404332129963899e-05,
250
+ "loss": 0.4396,
251
+ "step": 330
252
+ },
253
+ {
254
+ "epoch": 0.6128886885984678,
255
+ "grad_norm": 19.4619083404541,
256
+ "learning_rate": 4.386281588447654e-05,
257
+ "loss": 0.4378,
258
+ "step": 340
259
+ },
260
+ {
261
+ "epoch": 0.6309148264984227,
262
+ "grad_norm": 19.16460609436035,
263
+ "learning_rate": 4.368231046931408e-05,
264
+ "loss": 0.4366,
265
+ "step": 350
266
+ },
267
+ {
268
+ "epoch": 0.6489409643983777,
269
+ "grad_norm": 30.745384216308594,
270
+ "learning_rate": 4.350180505415163e-05,
271
+ "loss": 0.4062,
272
+ "step": 360
273
+ },
274
+ {
275
+ "epoch": 0.6669671022983326,
276
+ "grad_norm": 16.873245239257812,
277
+ "learning_rate": 4.332129963898917e-05,
278
+ "loss": 0.439,
279
+ "step": 370
280
+ },
281
+ {
282
+ "epoch": 0.6849932401982876,
283
+ "grad_norm": 25.771486282348633,
284
+ "learning_rate": 4.314079422382672e-05,
285
+ "loss": 0.4053,
286
+ "step": 380
287
+ },
288
+ {
289
+ "epoch": 0.7030193780982424,
290
+ "grad_norm": 14.48513412475586,
291
+ "learning_rate": 4.296028880866426e-05,
292
+ "loss": 0.4164,
293
+ "step": 390
294
+ },
295
+ {
296
+ "epoch": 0.7210455159981974,
297
+ "grad_norm": 34.993465423583984,
298
+ "learning_rate": 4.277978339350181e-05,
299
+ "loss": 0.4438,
300
+ "step": 400
301
+ },
302
+ {
303
+ "epoch": 0.7390716538981523,
304
+ "grad_norm": 22.576608657836914,
305
+ "learning_rate": 4.259927797833935e-05,
306
+ "loss": 0.4518,
307
+ "step": 410
308
+ },
309
+ {
310
+ "epoch": 0.7570977917981072,
311
+ "grad_norm": 19.088132858276367,
312
+ "learning_rate": 4.24187725631769e-05,
313
+ "loss": 0.4495,
314
+ "step": 420
315
+ },
316
+ {
317
+ "epoch": 0.7751239296980622,
318
+ "grad_norm": 35.2998046875,
319
+ "learning_rate": 4.223826714801444e-05,
320
+ "loss": 0.3897,
321
+ "step": 430
322
+ },
323
+ {
324
+ "epoch": 0.7931500675980171,
325
+ "grad_norm": 20.395572662353516,
326
+ "learning_rate": 4.205776173285199e-05,
327
+ "loss": 0.4818,
328
+ "step": 440
329
+ },
330
+ {
331
+ "epoch": 0.8111762054979721,
332
+ "grad_norm": 21.174386978149414,
333
+ "learning_rate": 4.187725631768953e-05,
334
+ "loss": 0.4103,
335
+ "step": 450
336
+ },
337
+ {
338
+ "epoch": 0.829202343397927,
339
+ "grad_norm": 32.97265625,
340
+ "learning_rate": 4.169675090252708e-05,
341
+ "loss": 0.4036,
342
+ "step": 460
343
+ },
344
+ {
345
+ "epoch": 0.847228481297882,
346
+ "grad_norm": 23.78690528869629,
347
+ "learning_rate": 4.151624548736462e-05,
348
+ "loss": 0.4079,
349
+ "step": 470
350
+ },
351
+ {
352
+ "epoch": 0.8652546191978369,
353
+ "grad_norm": 17.087247848510742,
354
+ "learning_rate": 4.1335740072202167e-05,
355
+ "loss": 0.4371,
356
+ "step": 480
357
+ },
358
+ {
359
+ "epoch": 0.8832807570977917,
360
+ "grad_norm": 13.810160636901855,
361
+ "learning_rate": 4.115523465703972e-05,
362
+ "loss": 0.4249,
363
+ "step": 490
364
+ },
365
+ {
366
+ "epoch": 0.9013068949977467,
367
+ "grad_norm": 20.197996139526367,
368
+ "learning_rate": 4.0974729241877256e-05,
369
+ "loss": 0.3991,
370
+ "step": 500
371
+ },
372
+ {
373
+ "epoch": 0.9193330328977016,
374
+ "grad_norm": 33.1153564453125,
375
+ "learning_rate": 4.079422382671481e-05,
376
+ "loss": 0.3994,
377
+ "step": 510
378
+ },
379
+ {
380
+ "epoch": 0.9373591707976566,
381
+ "grad_norm": 18.20081901550293,
382
+ "learning_rate": 4.0613718411552346e-05,
383
+ "loss": 0.4176,
384
+ "step": 520
385
+ },
386
+ {
387
+ "epoch": 0.9553853086976115,
388
+ "grad_norm": 20.09193992614746,
389
+ "learning_rate": 4.043321299638989e-05,
390
+ "loss": 0.4297,
391
+ "step": 530
392
+ },
393
+ {
394
+ "epoch": 0.9734114465975665,
395
+ "grad_norm": 15.939692497253418,
396
+ "learning_rate": 4.0252707581227436e-05,
397
+ "loss": 0.4309,
398
+ "step": 540
399
+ },
400
+ {
401
+ "epoch": 0.9914375844975214,
402
+ "grad_norm": 24.811601638793945,
403
+ "learning_rate": 4.007220216606498e-05,
404
+ "loss": 0.3908,
405
+ "step": 550
406
+ },
407
+ {
408
+ "epoch": 1.0,
409
+ "eval_f1": 0.8367177786987153,
410
+ "eval_loss": 0.37827184796333313,
411
+ "eval_precision": 0.7951949586451359,
412
+ "eval_recall": 0.8828159160472234,
413
+ "eval_runtime": 15.9582,
414
+ "eval_samples_per_second": 292.827,
415
+ "eval_steps_per_second": 36.658,
416
+ "step": 555
417
+ },
418
+ {
419
+ "epoch": 1.0090130689499774,
420
+ "grad_norm": 16.960424423217773,
421
+ "learning_rate": 3.989169675090253e-05,
422
+ "loss": 0.3719,
423
+ "step": 560
424
+ },
425
+ {
426
+ "epoch": 1.0270392068499323,
427
+ "grad_norm": 15.816173553466797,
428
+ "learning_rate": 3.971119133574007e-05,
429
+ "loss": 0.3238,
430
+ "step": 570
431
+ },
432
+ {
433
+ "epoch": 1.0450653447498874,
434
+ "grad_norm": 19.375043869018555,
435
+ "learning_rate": 3.953068592057762e-05,
436
+ "loss": 0.3516,
437
+ "step": 580
438
+ },
439
+ {
440
+ "epoch": 1.0630914826498423,
441
+ "grad_norm": 36.740943908691406,
442
+ "learning_rate": 3.935018050541516e-05,
443
+ "loss": 0.3329,
444
+ "step": 590
445
+ },
446
+ {
447
+ "epoch": 1.0811176205497972,
448
+ "grad_norm": 23.23931884765625,
449
+ "learning_rate": 3.916967509025271e-05,
450
+ "loss": 0.345,
451
+ "step": 600
452
+ },
453
+ {
454
+ "epoch": 1.099143758449752,
455
+ "grad_norm": 23.009553909301758,
456
+ "learning_rate": 3.898916967509025e-05,
457
+ "loss": 0.3054,
458
+ "step": 610
459
+ },
460
+ {
461
+ "epoch": 1.117169896349707,
462
+ "grad_norm": 18.865903854370117,
463
+ "learning_rate": 3.88086642599278e-05,
464
+ "loss": 0.3236,
465
+ "step": 620
466
+ },
467
+ {
468
+ "epoch": 1.135196034249662,
469
+ "grad_norm": 21.043642044067383,
470
+ "learning_rate": 3.862815884476535e-05,
471
+ "loss": 0.3092,
472
+ "step": 630
473
+ },
474
+ {
475
+ "epoch": 1.153222172149617,
476
+ "grad_norm": 22.50505256652832,
477
+ "learning_rate": 3.844765342960289e-05,
478
+ "loss": 0.3274,
479
+ "step": 640
480
+ },
481
+ {
482
+ "epoch": 1.1712483100495719,
483
+ "grad_norm": 20.4163818359375,
484
+ "learning_rate": 3.826714801444044e-05,
485
+ "loss": 0.2459,
486
+ "step": 650
487
+ },
488
+ {
489
+ "epoch": 1.1892744479495267,
490
+ "grad_norm": 21.210535049438477,
491
+ "learning_rate": 3.8086642599277976e-05,
492
+ "loss": 0.3365,
493
+ "step": 660
494
+ },
495
+ {
496
+ "epoch": 1.2073005858494819,
497
+ "grad_norm": 21.084487915039062,
498
+ "learning_rate": 3.790613718411553e-05,
499
+ "loss": 0.3242,
500
+ "step": 670
501
+ },
502
+ {
503
+ "epoch": 1.2253267237494367,
504
+ "grad_norm": 22.721454620361328,
505
+ "learning_rate": 3.7725631768953066e-05,
506
+ "loss": 0.2844,
507
+ "step": 680
508
+ },
509
+ {
510
+ "epoch": 1.2433528616493916,
511
+ "grad_norm": 49.28988265991211,
512
+ "learning_rate": 3.754512635379062e-05,
513
+ "loss": 0.3247,
514
+ "step": 690
515
+ },
516
+ {
517
+ "epoch": 1.2613789995493465,
518
+ "grad_norm": 48.35593795776367,
519
+ "learning_rate": 3.7364620938628155e-05,
520
+ "loss": 0.3217,
521
+ "step": 700
522
+ },
523
+ {
524
+ "epoch": 1.2794051374493014,
525
+ "grad_norm": 30.997228622436523,
526
+ "learning_rate": 3.718411552346571e-05,
527
+ "loss": 0.2854,
528
+ "step": 710
529
+ },
530
+ {
531
+ "epoch": 1.2974312753492563,
532
+ "grad_norm": 35.57414627075195,
533
+ "learning_rate": 3.700361010830325e-05,
534
+ "loss": 0.3315,
535
+ "step": 720
536
+ },
537
+ {
538
+ "epoch": 1.3154574132492114,
539
+ "grad_norm": 27.17759895324707,
540
+ "learning_rate": 3.68231046931408e-05,
541
+ "loss": 0.2965,
542
+ "step": 730
543
+ },
544
+ {
545
+ "epoch": 1.3334835511491663,
546
+ "grad_norm": 31.296627044677734,
547
+ "learning_rate": 3.664259927797834e-05,
548
+ "loss": 0.3396,
549
+ "step": 740
550
+ },
551
+ {
552
+ "epoch": 1.3515096890491212,
553
+ "grad_norm": 18.639175415039062,
554
+ "learning_rate": 3.646209386281589e-05,
555
+ "loss": 0.3178,
556
+ "step": 750
557
+ },
558
+ {
559
+ "epoch": 1.3695358269490763,
560
+ "grad_norm": 31.972665786743164,
561
+ "learning_rate": 3.628158844765343e-05,
562
+ "loss": 0.2927,
563
+ "step": 760
564
+ },
565
+ {
566
+ "epoch": 1.3875619648490312,
567
+ "grad_norm": 14.907872200012207,
568
+ "learning_rate": 3.610108303249098e-05,
569
+ "loss": 0.3391,
570
+ "step": 770
571
+ },
572
+ {
573
+ "epoch": 1.405588102748986,
574
+ "grad_norm": 33.58858871459961,
575
+ "learning_rate": 3.592057761732852e-05,
576
+ "loss": 0.3111,
577
+ "step": 780
578
+ },
579
+ {
580
+ "epoch": 1.423614240648941,
581
+ "grad_norm": 17.019819259643555,
582
+ "learning_rate": 3.574007220216607e-05,
583
+ "loss": 0.3401,
584
+ "step": 790
585
+ },
586
+ {
587
+ "epoch": 1.4416403785488958,
588
+ "grad_norm": 27.324296951293945,
589
+ "learning_rate": 3.555956678700361e-05,
590
+ "loss": 0.2917,
591
+ "step": 800
592
+ },
593
+ {
594
+ "epoch": 1.4596665164488507,
595
+ "grad_norm": 30.170120239257812,
596
+ "learning_rate": 3.537906137184116e-05,
597
+ "loss": 0.2871,
598
+ "step": 810
599
+ },
600
+ {
601
+ "epoch": 1.4776926543488058,
602
+ "grad_norm": 44.26614761352539,
603
+ "learning_rate": 3.51985559566787e-05,
604
+ "loss": 0.3307,
605
+ "step": 820
606
+ },
607
+ {
608
+ "epoch": 1.4957187922487607,
609
+ "grad_norm": 28.978620529174805,
610
+ "learning_rate": 3.5018050541516247e-05,
611
+ "loss": 0.3207,
612
+ "step": 830
613
+ },
614
+ {
615
+ "epoch": 1.5137449301487156,
616
+ "grad_norm": 22.961040496826172,
617
+ "learning_rate": 3.483754512635379e-05,
618
+ "loss": 0.3075,
619
+ "step": 840
620
+ },
621
+ {
622
+ "epoch": 1.5317710680486707,
623
+ "grad_norm": 22.511327743530273,
624
+ "learning_rate": 3.4657039711191336e-05,
625
+ "loss": 0.3035,
626
+ "step": 850
627
+ },
628
+ {
629
+ "epoch": 1.5497972059486256,
630
+ "grad_norm": 33.944190979003906,
631
+ "learning_rate": 3.447653429602888e-05,
632
+ "loss": 0.3243,
633
+ "step": 860
634
+ },
635
+ {
636
+ "epoch": 1.5678233438485805,
637
+ "grad_norm": 24.72734832763672,
638
+ "learning_rate": 3.4296028880866426e-05,
639
+ "loss": 0.3403,
640
+ "step": 870
641
+ },
642
+ {
643
+ "epoch": 1.5858494817485354,
644
+ "grad_norm": 31.211387634277344,
645
+ "learning_rate": 3.411552346570397e-05,
646
+ "loss": 0.3142,
647
+ "step": 880
648
+ },
649
+ {
650
+ "epoch": 1.6038756196484902,
651
+ "grad_norm": 23.974918365478516,
652
+ "learning_rate": 3.3935018050541516e-05,
653
+ "loss": 0.3015,
654
+ "step": 890
655
+ },
656
+ {
657
+ "epoch": 1.6219017575484451,
658
+ "grad_norm": 30.705829620361328,
659
+ "learning_rate": 3.375451263537907e-05,
660
+ "loss": 0.3529,
661
+ "step": 900
662
+ },
663
+ {
664
+ "epoch": 1.6399278954484002,
665
+ "grad_norm": 20.697528839111328,
666
+ "learning_rate": 3.3574007220216606e-05,
667
+ "loss": 0.302,
668
+ "step": 910
669
+ },
670
+ {
671
+ "epoch": 1.6579540333483551,
672
+ "grad_norm": 28.308101654052734,
673
+ "learning_rate": 3.339350180505416e-05,
674
+ "loss": 0.2735,
675
+ "step": 920
676
+ },
677
+ {
678
+ "epoch": 1.67598017124831,
679
+ "grad_norm": 22.28900909423828,
680
+ "learning_rate": 3.3212996389891696e-05,
681
+ "loss": 0.3194,
682
+ "step": 930
683
+ },
684
+ {
685
+ "epoch": 1.694006309148265,
686
+ "grad_norm": 29.04107666015625,
687
+ "learning_rate": 3.303249097472924e-05,
688
+ "loss": 0.3265,
689
+ "step": 940
690
+ },
691
+ {
692
+ "epoch": 1.71203244704822,
693
+ "grad_norm": 40.08032989501953,
694
+ "learning_rate": 3.2851985559566786e-05,
695
+ "loss": 0.3331,
696
+ "step": 950
697
+ },
698
+ {
699
+ "epoch": 1.7300585849481749,
700
+ "grad_norm": 29.40334129333496,
701
+ "learning_rate": 3.267148014440433e-05,
702
+ "loss": 0.2664,
703
+ "step": 960
704
+ },
705
+ {
706
+ "epoch": 1.7480847228481298,
707
+ "grad_norm": 33.51088333129883,
708
+ "learning_rate": 3.249097472924188e-05,
709
+ "loss": 0.3031,
710
+ "step": 970
711
+ },
712
+ {
713
+ "epoch": 1.7661108607480847,
714
+ "grad_norm": 27.003469467163086,
715
+ "learning_rate": 3.231046931407942e-05,
716
+ "loss": 0.3195,
717
+ "step": 980
718
+ },
719
+ {
720
+ "epoch": 1.7841369986480395,
721
+ "grad_norm": 26.585309982299805,
722
+ "learning_rate": 3.212996389891697e-05,
723
+ "loss": 0.3385,
724
+ "step": 990
725
+ },
726
+ {
727
+ "epoch": 1.8021631365479944,
728
+ "grad_norm": 36.866294860839844,
729
+ "learning_rate": 3.194945848375451e-05,
730
+ "loss": 0.3029,
731
+ "step": 1000
732
+ },
733
+ {
734
+ "epoch": 1.8201892744479495,
735
+ "grad_norm": 44.910362243652344,
736
+ "learning_rate": 3.176895306859206e-05,
737
+ "loss": 0.3239,
738
+ "step": 1010
739
+ },
740
+ {
741
+ "epoch": 1.8382154123479044,
742
+ "grad_norm": 20.13945198059082,
743
+ "learning_rate": 3.15884476534296e-05,
744
+ "loss": 0.3071,
745
+ "step": 1020
746
+ },
747
+ {
748
+ "epoch": 1.8562415502478595,
749
+ "grad_norm": 42.44215774536133,
750
+ "learning_rate": 3.140794223826715e-05,
751
+ "loss": 0.3246,
752
+ "step": 1030
753
+ },
754
+ {
755
+ "epoch": 1.8742676881478144,
756
+ "grad_norm": 31.791410446166992,
757
+ "learning_rate": 3.12274368231047e-05,
758
+ "loss": 0.3273,
759
+ "step": 1040
760
+ },
761
+ {
762
+ "epoch": 1.8922938260477693,
763
+ "grad_norm": 21.244722366333008,
764
+ "learning_rate": 3.104693140794224e-05,
765
+ "loss": 0.3093,
766
+ "step": 1050
767
+ },
768
+ {
769
+ "epoch": 1.9103199639477242,
770
+ "grad_norm": 27.103349685668945,
771
+ "learning_rate": 3.086642599277979e-05,
772
+ "loss": 0.2694,
773
+ "step": 1060
774
+ },
775
+ {
776
+ "epoch": 1.928346101847679,
777
+ "grad_norm": 35.73145294189453,
778
+ "learning_rate": 3.0685920577617325e-05,
779
+ "loss": 0.2934,
780
+ "step": 1070
781
+ },
782
+ {
783
+ "epoch": 1.946372239747634,
784
+ "grad_norm": 19.97008514404297,
785
+ "learning_rate": 3.0505415162454877e-05,
786
+ "loss": 0.3493,
787
+ "step": 1080
788
+ },
789
+ {
790
+ "epoch": 1.9643983776475888,
791
+ "grad_norm": 23.084754943847656,
792
+ "learning_rate": 3.032490974729242e-05,
793
+ "loss": 0.3243,
794
+ "step": 1090
795
+ },
796
+ {
797
+ "epoch": 1.982424515547544,
798
+ "grad_norm": 29.515155792236328,
799
+ "learning_rate": 3.0144404332129967e-05,
800
+ "loss": 0.3235,
801
+ "step": 1100
802
+ },
803
+ {
804
+ "epoch": 2.0,
805
+ "grad_norm": 24.17915916442871,
806
+ "learning_rate": 2.996389891696751e-05,
807
+ "loss": 0.2751,
808
+ "step": 1110
809
+ },
810
+ {
811
+ "epoch": 2.0,
812
+ "eval_f1": 0.8428896708755951,
813
+ "eval_loss": 0.3940623104572296,
814
+ "eval_precision": 0.800314465408805,
815
+ "eval_recall": 0.890249234805422,
816
+ "eval_runtime": 12.3989,
817
+ "eval_samples_per_second": 376.889,
818
+ "eval_steps_per_second": 47.182,
819
+ "step": 1110
820
+ }
821
+ ],
822
+ "logging_steps": 10,
823
+ "max_steps": 2770,
824
+ "num_input_tokens_seen": 0,
825
+ "num_train_epochs": 5,
826
+ "save_steps": 500,
827
+ "stateful_callbacks": {
828
+ "TrainerControl": {
829
+ "args": {
830
+ "should_epoch_stop": false,
831
+ "should_evaluate": false,
832
+ "should_log": false,
833
+ "should_save": true,
834
+ "should_training_stop": false
835
+ },
836
+ "attributes": {}
837
+ }
838
+ },
839
+ "total_flos": 9341494909501440.0,
840
+ "train_batch_size": 8,
841
+ "trial_name": null,
842
+ "trial_params": null
843
+ }
checkpoint-1110/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92aaf17ba6b51dd0179acd28630a512a049c53024ba01863d7232c815d6018dd
3
+ size 5432