anoaky commited on
Commit
6b95561
·
verified ·
1 Parent(s): ab727d3

Training in progress, epoch 1, checkpoint

Browse files
checkpoint-555/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-mnli",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForSequenceClassification"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 4096,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 2,
26
+ "forced_eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "init_std": 0.02,
33
+ "is_encoder_decoder": true,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "max_position_embeddings": 1024,
39
+ "model_type": "bart",
40
+ "normalize_before": false,
41
+ "num_hidden_layers": 12,
42
+ "output_past": false,
43
+ "pad_token_id": 1,
44
+ "scale_embedding": false,
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.47.0",
47
+ "use_cache": true,
48
+ "vocab_size": 50265
49
+ }
checkpoint-555/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f74f9f4ff34b668f2cf1ed044080969a05f7c00ad80383c44ef509f68df306
3
+ size 1629432864
checkpoint-555/trainer_state.json ADDED
@@ -0,0 +1,429 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 555,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.018026137899954935,
13
+ "grad_norm": 21.723926544189453,
14
+ "learning_rate": 4.981949458483755e-05,
15
+ "loss": 0.8104,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03605227579990987,
20
+ "grad_norm": 55.4254035949707,
21
+ "learning_rate": 4.963898916967509e-05,
22
+ "loss": 0.5178,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.054078413699864804,
27
+ "grad_norm": 41.4888801574707,
28
+ "learning_rate": 4.945848375451264e-05,
29
+ "loss": 0.5092,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.07210455159981974,
34
+ "grad_norm": 25.77608299255371,
35
+ "learning_rate": 4.927797833935018e-05,
36
+ "loss": 0.5581,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.09013068949977468,
41
+ "grad_norm": 61.5268669128418,
42
+ "learning_rate": 4.909747292418773e-05,
43
+ "loss": 0.5132,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.10815682739972961,
48
+ "grad_norm": 18.218244552612305,
49
+ "learning_rate": 4.891696750902527e-05,
50
+ "loss": 0.4614,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.12618296529968454,
55
+ "grad_norm": 30.51982879638672,
56
+ "learning_rate": 4.873646209386282e-05,
57
+ "loss": 0.4648,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.14420910319963948,
62
+ "grad_norm": 20.707260131835938,
63
+ "learning_rate": 4.855595667870036e-05,
64
+ "loss": 0.4317,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.16223524109959442,
69
+ "grad_norm": 21.699357986450195,
70
+ "learning_rate": 4.837545126353791e-05,
71
+ "loss": 0.4226,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.18026137899954936,
76
+ "grad_norm": 51.80731201171875,
77
+ "learning_rate": 4.819494584837546e-05,
78
+ "loss": 0.5002,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.19828751689950427,
83
+ "grad_norm": 44.694942474365234,
84
+ "learning_rate": 4.8014440433213e-05,
85
+ "loss": 0.4933,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.21631365479945922,
90
+ "grad_norm": 22.704530715942383,
91
+ "learning_rate": 4.783393501805055e-05,
92
+ "loss": 0.4399,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.23433979269941416,
97
+ "grad_norm": 26.04544448852539,
98
+ "learning_rate": 4.765342960288809e-05,
99
+ "loss": 0.438,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.25236593059936907,
104
+ "grad_norm": 14.642335891723633,
105
+ "learning_rate": 4.747292418772563e-05,
106
+ "loss": 0.4591,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.270392068499324,
111
+ "grad_norm": 16.13884162902832,
112
+ "learning_rate": 4.7292418772563177e-05,
113
+ "loss": 0.4546,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.28841820639927895,
118
+ "grad_norm": 29.33772087097168,
119
+ "learning_rate": 4.711191335740072e-05,
120
+ "loss": 0.4665,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.3064443442992339,
125
+ "grad_norm": 15.900433540344238,
126
+ "learning_rate": 4.693140794223827e-05,
127
+ "loss": 0.4703,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.32447048219918884,
132
+ "grad_norm": 17.246356964111328,
133
+ "learning_rate": 4.675090252707581e-05,
134
+ "loss": 0.426,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.3424966200991438,
139
+ "grad_norm": 25.457477569580078,
140
+ "learning_rate": 4.657039711191336e-05,
141
+ "loss": 0.4711,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.3605227579990987,
146
+ "grad_norm": 25.43963050842285,
147
+ "learning_rate": 4.63898916967509e-05,
148
+ "loss": 0.4547,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.3785488958990536,
153
+ "grad_norm": 32.49702072143555,
154
+ "learning_rate": 4.620938628158845e-05,
155
+ "loss": 0.4603,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.39657503379900855,
160
+ "grad_norm": 52.78520965576172,
161
+ "learning_rate": 4.602888086642599e-05,
162
+ "loss": 0.4471,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.4146011716989635,
167
+ "grad_norm": 16.70362663269043,
168
+ "learning_rate": 4.584837545126354e-05,
169
+ "loss": 0.4393,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.43262730959891843,
174
+ "grad_norm": 23.55246353149414,
175
+ "learning_rate": 4.566787003610109e-05,
176
+ "loss": 0.4256,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.45065344749887337,
181
+ "grad_norm": 18.868804931640625,
182
+ "learning_rate": 4.548736462093863e-05,
183
+ "loss": 0.4324,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.4686795853988283,
188
+ "grad_norm": 19.074827194213867,
189
+ "learning_rate": 4.530685920577618e-05,
190
+ "loss": 0.4419,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.48670572329878325,
195
+ "grad_norm": 29.232803344726562,
196
+ "learning_rate": 4.5126353790613716e-05,
197
+ "loss": 0.4179,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5047318611987381,
202
+ "grad_norm": 17.780059814453125,
203
+ "learning_rate": 4.494584837545127e-05,
204
+ "loss": 0.3917,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.5227579990986931,
209
+ "grad_norm": 13.99399471282959,
210
+ "learning_rate": 4.4765342960288806e-05,
211
+ "loss": 0.4321,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.540784136998648,
216
+ "grad_norm": 14.700942039489746,
217
+ "learning_rate": 4.458483754512636e-05,
218
+ "loss": 0.4163,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.558810274898603,
223
+ "grad_norm": 17.43704605102539,
224
+ "learning_rate": 4.44043321299639e-05,
225
+ "loss": 0.4268,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.5768364127985579,
230
+ "grad_norm": 28.500301361083984,
231
+ "learning_rate": 4.422382671480145e-05,
232
+ "loss": 0.4229,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.5948625506985128,
237
+ "grad_norm": 36.14088439941406,
238
+ "learning_rate": 4.404332129963899e-05,
239
+ "loss": 0.4559,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.6128886885984678,
244
+ "grad_norm": 15.279230117797852,
245
+ "learning_rate": 4.386281588447654e-05,
246
+ "loss": 0.4067,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.6309148264984227,
251
+ "grad_norm": 21.569740295410156,
252
+ "learning_rate": 4.368231046931408e-05,
253
+ "loss": 0.4298,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.6489409643983777,
258
+ "grad_norm": 20.630115509033203,
259
+ "learning_rate": 4.350180505415163e-05,
260
+ "loss": 0.4173,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.6669671022983326,
265
+ "grad_norm": 15.515020370483398,
266
+ "learning_rate": 4.332129963898917e-05,
267
+ "loss": 0.4063,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.6849932401982876,
272
+ "grad_norm": 16.33180046081543,
273
+ "learning_rate": 4.314079422382672e-05,
274
+ "loss": 0.3651,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.7030193780982424,
279
+ "grad_norm": 16.77664566040039,
280
+ "learning_rate": 4.296028880866426e-05,
281
+ "loss": 0.3879,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.7210455159981974,
286
+ "grad_norm": 11.113824844360352,
287
+ "learning_rate": 4.277978339350181e-05,
288
+ "loss": 0.4205,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.7390716538981523,
293
+ "grad_norm": 17.835678100585938,
294
+ "learning_rate": 4.259927797833935e-05,
295
+ "loss": 0.4466,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.7570977917981072,
300
+ "grad_norm": 24.48379135131836,
301
+ "learning_rate": 4.24187725631769e-05,
302
+ "loss": 0.4084,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.7751239296980622,
307
+ "grad_norm": 29.183530807495117,
308
+ "learning_rate": 4.223826714801444e-05,
309
+ "loss": 0.3588,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.7931500675980171,
314
+ "grad_norm": 16.398386001586914,
315
+ "learning_rate": 4.205776173285199e-05,
316
+ "loss": 0.4594,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.8111762054979721,
321
+ "grad_norm": 24.11660385131836,
322
+ "learning_rate": 4.187725631768953e-05,
323
+ "loss": 0.376,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.829202343397927,
328
+ "grad_norm": 21.480924606323242,
329
+ "learning_rate": 4.169675090252708e-05,
330
+ "loss": 0.4035,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.847228481297882,
335
+ "grad_norm": 11.91422176361084,
336
+ "learning_rate": 4.151624548736462e-05,
337
+ "loss": 0.4074,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.8652546191978369,
342
+ "grad_norm": 17.17136001586914,
343
+ "learning_rate": 4.1335740072202167e-05,
344
+ "loss": 0.4259,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.8832807570977917,
349
+ "grad_norm": 15.024781227111816,
350
+ "learning_rate": 4.115523465703972e-05,
351
+ "loss": 0.413,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.9013068949977467,
356
+ "grad_norm": 15.877848625183105,
357
+ "learning_rate": 4.0974729241877256e-05,
358
+ "loss": 0.4013,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.9193330328977016,
363
+ "grad_norm": 20.711393356323242,
364
+ "learning_rate": 4.079422382671481e-05,
365
+ "loss": 0.3875,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.9373591707976566,
370
+ "grad_norm": 14.360701560974121,
371
+ "learning_rate": 4.0613718411552346e-05,
372
+ "loss": 0.4025,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.9553853086976115,
377
+ "grad_norm": 16.94271469116211,
378
+ "learning_rate": 4.043321299638989e-05,
379
+ "loss": 0.3971,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.9734114465975665,
384
+ "grad_norm": 23.218050003051758,
385
+ "learning_rate": 4.0252707581227436e-05,
386
+ "loss": 0.4305,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.9914375844975214,
391
+ "grad_norm": 25.439455032348633,
392
+ "learning_rate": 4.007220216606498e-05,
393
+ "loss": 0.3969,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 1.0,
398
+ "eval_f1": 0.8410362694300518,
399
+ "eval_loss": 0.36654186248779297,
400
+ "eval_precision": 0.7994483845547675,
401
+ "eval_recall": 0.8871884564932225,
402
+ "eval_runtime": 77.9824,
403
+ "eval_samples_per_second": 59.924,
404
+ "eval_steps_per_second": 7.502,
405
+ "step": 555
406
+ }
407
+ ],
408
+ "logging_steps": 10,
409
+ "max_steps": 2770,
410
+ "num_input_tokens_seen": 0,
411
+ "num_train_epochs": 5,
412
+ "save_steps": 500,
413
+ "stateful_callbacks": {
414
+ "TrainerControl": {
415
+ "args": {
416
+ "should_epoch_stop": false,
417
+ "should_evaluate": false,
418
+ "should_log": false,
419
+ "should_save": true,
420
+ "should_training_stop": false
421
+ },
422
+ "attributes": {}
423
+ }
424
+ },
425
+ "total_flos": 1.929257128088371e+16,
426
+ "train_batch_size": 8,
427
+ "trial_name": null,
428
+ "trial_params": null
429
+ }
checkpoint-555/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd360ff6566a7421740b08164da56480ee843ecd9962d79899c9150e4be0d68e
3
+ size 5432