arvine111 commited on
Commit
f39d00d
·
verified ·
1 Parent(s): 7dfd409

delete folder

Browse files
checkpoint-5980/config.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-5980/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f377ec25b1b8f10dcf6711265133617779b20f0380da35aaa441672c6c5b86a
3
- size 1359740292
 
 
 
 
checkpoint-5980/onnx/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab15ba3157ce13dfba235edc09959a5f6404ce9a9ed4336e447b1e5d096ed81
3
- size 1360289800
 
 
 
 
checkpoint-5980/onnx/model_quantized.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c8b5623375d22bc0593cc2725abecaff69d3c6cb2a66558d4b8437626259b25
3
- size 341923308
 
 
 
 
checkpoint-5980/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3be0150cc864f8770578ce0f805a6cad0b79c97ddef0b64f49d091a2d950c2d
3
- size 2719715437
 
 
 
 
checkpoint-5980/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:020567ffe4dc055a0c2275fc567b377dbeb1f753bb990a62eba60cb76427d645
3
- size 14244
 
 
 
 
checkpoint-5980/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2eabc779bff69825ce130e50f2b6e3c7a00cc5ee0a306c893c0771962d9bca5
3
- size 1064
 
 
 
 
checkpoint-5980/special_tokens_map.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
checkpoint-5980/tokenizer_config.json DELETED
@@ -1,64 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "clean_up_tokenization_spaces": false,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": false,
47
- "do_subword_tokenize": true,
48
- "do_word_tokenize": true,
49
- "extra_special_tokens": {},
50
- "jumanpp_kwargs": null,
51
- "mask_token": "[MASK]",
52
- "mecab_kwargs": {
53
- "mecab_dic": "unidic_lite"
54
- },
55
- "model_max_length": 512,
56
- "never_split": null,
57
- "pad_token": "[PAD]",
58
- "sep_token": "[SEP]",
59
- "subword_tokenizer_type": "wordpiece",
60
- "sudachi_kwargs": null,
61
- "tokenizer_class": "BertJapaneseTokenizer",
62
- "unk_token": "[UNK]",
63
- "word_tokenizer_type": "mecab"
64
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-5980/trainer_state.json DELETED
@@ -1,982 +0,0 @@
1
- {
2
- "best_metric": 0.839046835899353,
3
- "best_model_checkpoint": "./bert-large-jpn-grammar\\checkpoint-5980",
4
- "epoch": 10.0,
5
- "eval_steps": 500,
6
- "global_step": 5980,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0016722408026755853,
13
- "grad_norm": 4.53647518157959,
14
- "learning_rate": 2.5083612040133778e-08,
15
- "loss": 7.8555,
16
- "step": 1
17
- },
18
- {
19
- "epoch": 0.08361204013377926,
20
- "grad_norm": 4.600866317749023,
21
- "learning_rate": 1.254180602006689e-06,
22
- "loss": 7.8831,
23
- "step": 50
24
- },
25
- {
26
- "epoch": 0.16722408026755853,
27
- "grad_norm": 4.168644428253174,
28
- "learning_rate": 2.508361204013378e-06,
29
- "loss": 7.8681,
30
- "step": 100
31
- },
32
- {
33
- "epoch": 0.2508361204013378,
34
- "grad_norm": 13.43441104888916,
35
- "learning_rate": 3.762541806020067e-06,
36
- "loss": 7.8594,
37
- "step": 150
38
- },
39
- {
40
- "epoch": 0.33444816053511706,
41
- "grad_norm": 3.9283835887908936,
42
- "learning_rate": 5.016722408026756e-06,
43
- "loss": 7.8337,
44
- "step": 200
45
- },
46
- {
47
- "epoch": 0.4180602006688963,
48
- "grad_norm": 3.899462938308716,
49
- "learning_rate": 6.270903010033445e-06,
50
- "loss": 7.8177,
51
- "step": 250
52
- },
53
- {
54
- "epoch": 0.5016722408026756,
55
- "grad_norm": 4.085901737213135,
56
- "learning_rate": 7.525083612040134e-06,
57
- "loss": 7.7797,
58
- "step": 300
59
- },
60
- {
61
- "epoch": 0.5852842809364549,
62
- "grad_norm": 4.916100025177002,
63
- "learning_rate": 8.779264214046824e-06,
64
- "loss": 7.7515,
65
- "step": 350
66
- },
67
- {
68
- "epoch": 0.6688963210702341,
69
- "grad_norm": 5.722199440002441,
70
- "learning_rate": 1.0033444816053512e-05,
71
- "loss": 7.7095,
72
- "step": 400
73
- },
74
- {
75
- "epoch": 0.7525083612040134,
76
- "grad_norm": 6.974526405334473,
77
- "learning_rate": 1.1287625418060201e-05,
78
- "loss": 7.6088,
79
- "step": 450
80
- },
81
- {
82
- "epoch": 0.8361204013377926,
83
- "grad_norm": 7.1739888191223145,
84
- "learning_rate": 1.254180602006689e-05,
85
- "loss": 7.4935,
86
- "step": 500
87
- },
88
- {
89
- "epoch": 0.919732441471572,
90
- "grad_norm": 7.732913494110107,
91
- "learning_rate": 1.379598662207358e-05,
92
- "loss": 7.3773,
93
- "step": 550
94
- },
95
- {
96
- "epoch": 1.0,
97
- "eval_accuracy": 0.1417224109172821,
98
- "eval_f1": 0.1417224109172821,
99
- "eval_loss": 7.010268688201904,
100
- "eval_runtime": 59.6669,
101
- "eval_samples_per_second": 80.178,
102
- "eval_steps_per_second": 1.257,
103
- "step": 598
104
- },
105
- {
106
- "epoch": 1.0033444816053512,
107
- "grad_norm": 7.402344703674316,
108
- "learning_rate": 1.5050167224080267e-05,
109
- "loss": 7.2391,
110
- "step": 600
111
- },
112
- {
113
- "epoch": 1.0869565217391304,
114
- "grad_norm": 7.742281913757324,
115
- "learning_rate": 1.6304347826086955e-05,
116
- "loss": 6.9797,
117
- "step": 650
118
- },
119
- {
120
- "epoch": 1.1705685618729098,
121
- "grad_norm": 7.522943019866943,
122
- "learning_rate": 1.7558528428093648e-05,
123
- "loss": 6.8021,
124
- "step": 700
125
- },
126
- {
127
- "epoch": 1.254180602006689,
128
- "grad_norm": 7.755581378936768,
129
- "learning_rate": 1.8812709030100337e-05,
130
- "loss": 6.6368,
131
- "step": 750
132
- },
133
- {
134
- "epoch": 1.3377926421404682,
135
- "grad_norm": 7.403460502624512,
136
- "learning_rate": 2.0066889632107023e-05,
137
- "loss": 6.4424,
138
- "step": 800
139
- },
140
- {
141
- "epoch": 1.4214046822742474,
142
- "grad_norm": 7.275426864624023,
143
- "learning_rate": 2.1321070234113713e-05,
144
- "loss": 6.2322,
145
- "step": 850
146
- },
147
- {
148
- "epoch": 1.5050167224080266,
149
- "grad_norm": 7.691336631774902,
150
- "learning_rate": 2.2575250836120402e-05,
151
- "loss": 6.0312,
152
- "step": 900
153
- },
154
- {
155
- "epoch": 1.588628762541806,
156
- "grad_norm": 7.337137699127197,
157
- "learning_rate": 2.382943143812709e-05,
158
- "loss": 5.8301,
159
- "step": 950
160
- },
161
- {
162
- "epoch": 1.6722408026755853,
163
- "grad_norm": 7.574013710021973,
164
- "learning_rate": 2.508361204013378e-05,
165
- "loss": 5.6195,
166
- "step": 1000
167
- },
168
- {
169
- "epoch": 1.7558528428093645,
170
- "grad_norm": 7.1535773277282715,
171
- "learning_rate": 2.6337792642140467e-05,
172
- "loss": 5.3459,
173
- "step": 1050
174
- },
175
- {
176
- "epoch": 1.839464882943144,
177
- "grad_norm": 7.483964443206787,
178
- "learning_rate": 2.759197324414716e-05,
179
- "loss": 5.1481,
180
- "step": 1100
181
- },
182
- {
183
- "epoch": 1.9230769230769231,
184
- "grad_norm": 7.383283615112305,
185
- "learning_rate": 2.884615384615385e-05,
186
- "loss": 4.9299,
187
- "step": 1150
188
- },
189
- {
190
- "epoch": 2.0,
191
- "eval_accuracy": 0.6444398164749146,
192
- "eval_f1": 0.6444398164749146,
193
- "eval_loss": 4.192617893218994,
194
- "eval_runtime": 55.4042,
195
- "eval_samples_per_second": 86.347,
196
- "eval_steps_per_second": 1.354,
197
- "step": 1196
198
- },
199
- {
200
- "epoch": 2.0066889632107023,
201
- "grad_norm": 7.1753668785095215,
202
- "learning_rate": 2.9974916387959864e-05,
203
- "loss": 4.6789,
204
- "step": 1200
205
- },
206
- {
207
- "epoch": 2.0903010033444818,
208
- "grad_norm": 7.401775360107422,
209
- "learning_rate": 2.9661371237458197e-05,
210
- "loss": 4.2448,
211
- "step": 1250
212
- },
213
- {
214
- "epoch": 2.1739130434782608,
215
- "grad_norm": 7.254606246948242,
216
- "learning_rate": 2.9347826086956523e-05,
217
- "loss": 4.0163,
218
- "step": 1300
219
- },
220
- {
221
- "epoch": 2.25752508361204,
222
- "grad_norm": 7.533504962921143,
223
- "learning_rate": 2.903428093645485e-05,
224
- "loss": 3.8083,
225
- "step": 1350
226
- },
227
- {
228
- "epoch": 2.3411371237458196,
229
- "grad_norm": 6.658289432525635,
230
- "learning_rate": 2.8720735785953178e-05,
231
- "loss": 3.5772,
232
- "step": 1400
233
- },
234
- {
235
- "epoch": 2.4247491638795986,
236
- "grad_norm": 9.382271766662598,
237
- "learning_rate": 2.8407190635451504e-05,
238
- "loss": 3.4262,
239
- "step": 1450
240
- },
241
- {
242
- "epoch": 2.508361204013378,
243
- "grad_norm": 6.964470863342285,
244
- "learning_rate": 2.8093645484949833e-05,
245
- "loss": 3.2302,
246
- "step": 1500
247
- },
248
- {
249
- "epoch": 2.591973244147157,
250
- "grad_norm": 6.510575294494629,
251
- "learning_rate": 2.7780100334448163e-05,
252
- "loss": 3.0355,
253
- "step": 1550
254
- },
255
- {
256
- "epoch": 2.6755852842809364,
257
- "grad_norm": 6.38152551651001,
258
- "learning_rate": 2.746655518394649e-05,
259
- "loss": 2.8789,
260
- "step": 1600
261
- },
262
- {
263
- "epoch": 2.759197324414716,
264
- "grad_norm": 6.31973934173584,
265
- "learning_rate": 2.7153010033444814e-05,
266
- "loss": 2.6744,
267
- "step": 1650
268
- },
269
- {
270
- "epoch": 2.842809364548495,
271
- "grad_norm": 8.131747245788574,
272
- "learning_rate": 2.6839464882943144e-05,
273
- "loss": 2.5437,
274
- "step": 1700
275
- },
276
- {
277
- "epoch": 2.9264214046822743,
278
- "grad_norm": 6.337752342224121,
279
- "learning_rate": 2.6525919732441473e-05,
280
- "loss": 2.3661,
281
- "step": 1750
282
- },
283
- {
284
- "epoch": 3.0,
285
- "eval_accuracy": 0.735785961151123,
286
- "eval_f1": 0.735785961151123,
287
- "eval_loss": 1.8872631788253784,
288
- "eval_runtime": 58.5991,
289
- "eval_samples_per_second": 81.64,
290
- "eval_steps_per_second": 1.28,
291
- "step": 1794
292
- },
293
- {
294
- "epoch": 3.0100334448160537,
295
- "grad_norm": 6.063199520111084,
296
- "learning_rate": 2.6212374581939803e-05,
297
- "loss": 2.2655,
298
- "step": 1800
299
- },
300
- {
301
- "epoch": 3.0936454849498327,
302
- "grad_norm": 5.415772914886475,
303
- "learning_rate": 2.589882943143813e-05,
304
- "loss": 1.9437,
305
- "step": 1850
306
- },
307
- {
308
- "epoch": 3.177257525083612,
309
- "grad_norm": 5.352977752685547,
310
- "learning_rate": 2.5585284280936454e-05,
311
- "loss": 1.8229,
312
- "step": 1900
313
- },
314
- {
315
- "epoch": 3.260869565217391,
316
- "grad_norm": 6.909513473510742,
317
- "learning_rate": 2.5271739130434784e-05,
318
- "loss": 1.7459,
319
- "step": 1950
320
- },
321
- {
322
- "epoch": 3.3444816053511706,
323
- "grad_norm": 5.768405914306641,
324
- "learning_rate": 2.495819397993311e-05,
325
- "loss": 1.6214,
326
- "step": 2000
327
- },
328
- {
329
- "epoch": 3.42809364548495,
330
- "grad_norm": 4.940030574798584,
331
- "learning_rate": 2.464464882943144e-05,
332
- "loss": 1.5412,
333
- "step": 2050
334
- },
335
- {
336
- "epoch": 3.511705685618729,
337
- "grad_norm": 5.3233323097229,
338
- "learning_rate": 2.433110367892977e-05,
339
- "loss": 1.4467,
340
- "step": 2100
341
- },
342
- {
343
- "epoch": 3.5953177257525084,
344
- "grad_norm": 5.229661464691162,
345
- "learning_rate": 2.4017558528428094e-05,
346
- "loss": 1.3918,
347
- "step": 2150
348
- },
349
- {
350
- "epoch": 3.678929765886288,
351
- "grad_norm": 4.888563632965088,
352
- "learning_rate": 2.370401337792642e-05,
353
- "loss": 1.3623,
354
- "step": 2200
355
- },
356
- {
357
- "epoch": 3.762541806020067,
358
- "grad_norm": 4.426875591278076,
359
- "learning_rate": 2.339046822742475e-05,
360
- "loss": 1.2494,
361
- "step": 2250
362
- },
363
- {
364
- "epoch": 3.8461538461538463,
365
- "grad_norm": 5.58463191986084,
366
- "learning_rate": 2.307692307692308e-05,
367
- "loss": 1.2034,
368
- "step": 2300
369
- },
370
- {
371
- "epoch": 3.9297658862876252,
372
- "grad_norm": 4.331861972808838,
373
- "learning_rate": 2.2763377926421405e-05,
374
- "loss": 1.1543,
375
- "step": 2350
376
- },
377
- {
378
- "epoch": 4.0,
379
- "eval_accuracy": 0.7759197354316711,
380
- "eval_f1": 0.7759197354316711,
381
- "eval_loss": 0.9816091060638428,
382
- "eval_runtime": 56.0644,
383
- "eval_samples_per_second": 85.33,
384
- "eval_steps_per_second": 1.338,
385
- "step": 2392
386
- },
387
- {
388
- "epoch": 4.013377926421405,
389
- "grad_norm": 4.542367935180664,
390
- "learning_rate": 2.2449832775919734e-05,
391
- "loss": 1.0647,
392
- "step": 2400
393
- },
394
- {
395
- "epoch": 4.096989966555184,
396
- "grad_norm": 4.851340293884277,
397
- "learning_rate": 2.213628762541806e-05,
398
- "loss": 0.9377,
399
- "step": 2450
400
- },
401
- {
402
- "epoch": 4.1806020066889635,
403
- "grad_norm": 4.438965797424316,
404
- "learning_rate": 2.1822742474916386e-05,
405
- "loss": 0.9529,
406
- "step": 2500
407
- },
408
- {
409
- "epoch": 4.264214046822742,
410
- "grad_norm": 4.728175163269043,
411
- "learning_rate": 2.150919732441472e-05,
412
- "loss": 0.8806,
413
- "step": 2550
414
- },
415
- {
416
- "epoch": 4.3478260869565215,
417
- "grad_norm": 4.2397284507751465,
418
- "learning_rate": 2.1195652173913045e-05,
419
- "loss": 0.8575,
420
- "step": 2600
421
- },
422
- {
423
- "epoch": 4.431438127090301,
424
- "grad_norm": 3.8949732780456543,
425
- "learning_rate": 2.088210702341137e-05,
426
- "loss": 0.8447,
427
- "step": 2650
428
- },
429
- {
430
- "epoch": 4.51505016722408,
431
- "grad_norm": 4.523480415344238,
432
- "learning_rate": 2.05685618729097e-05,
433
- "loss": 0.8167,
434
- "step": 2700
435
- },
436
- {
437
- "epoch": 4.59866220735786,
438
- "grad_norm": 5.011022090911865,
439
- "learning_rate": 2.0255016722408026e-05,
440
- "loss": 0.7993,
441
- "step": 2750
442
- },
443
- {
444
- "epoch": 4.682274247491639,
445
- "grad_norm": 4.6291399002075195,
446
- "learning_rate": 1.9941471571906352e-05,
447
- "loss": 0.7959,
448
- "step": 2800
449
- },
450
- {
451
- "epoch": 4.765886287625418,
452
- "grad_norm": 4.647440433502197,
453
- "learning_rate": 1.9627926421404685e-05,
454
- "loss": 0.7582,
455
- "step": 2850
456
- },
457
- {
458
- "epoch": 4.849498327759197,
459
- "grad_norm": 3.1524765491485596,
460
- "learning_rate": 1.931438127090301e-05,
461
- "loss": 0.7298,
462
- "step": 2900
463
- },
464
- {
465
- "epoch": 4.933110367892977,
466
- "grad_norm": 5.388834476470947,
467
- "learning_rate": 1.9000836120401337e-05,
468
- "loss": 0.6885,
469
- "step": 2950
470
- },
471
- {
472
- "epoch": 5.0,
473
- "eval_accuracy": 0.8018394708633423,
474
- "eval_f1": 0.8018394708633423,
475
- "eval_loss": 0.6958563327789307,
476
- "eval_runtime": 57.0066,
477
- "eval_samples_per_second": 83.92,
478
- "eval_steps_per_second": 1.316,
479
- "step": 2990
480
- },
481
- {
482
- "epoch": 5.016722408026756,
483
- "grad_norm": 2.930847644805908,
484
- "learning_rate": 1.8687290969899666e-05,
485
- "loss": 0.6759,
486
- "step": 3000
487
- },
488
- {
489
- "epoch": 5.1003344481605355,
490
- "grad_norm": 4.471439361572266,
491
- "learning_rate": 1.8373745819397992e-05,
492
- "loss": 0.6077,
493
- "step": 3050
494
- },
495
- {
496
- "epoch": 5.183946488294314,
497
- "grad_norm": 3.0460543632507324,
498
- "learning_rate": 1.806020066889632e-05,
499
- "loss": 0.6214,
500
- "step": 3100
501
- },
502
- {
503
- "epoch": 5.2675585284280935,
504
- "grad_norm": 3.273836851119995,
505
- "learning_rate": 1.774665551839465e-05,
506
- "loss": 0.6055,
507
- "step": 3150
508
- },
509
- {
510
- "epoch": 5.351170568561873,
511
- "grad_norm": 3.214381456375122,
512
- "learning_rate": 1.7433110367892977e-05,
513
- "loss": 0.5718,
514
- "step": 3200
515
- },
516
- {
517
- "epoch": 5.434782608695652,
518
- "grad_norm": 2.87959361076355,
519
- "learning_rate": 1.7119565217391303e-05,
520
- "loss": 0.565,
521
- "step": 3250
522
- },
523
- {
524
- "epoch": 5.518394648829432,
525
- "grad_norm": 4.1827521324157715,
526
- "learning_rate": 1.6806020066889632e-05,
527
- "loss": 0.5923,
528
- "step": 3300
529
- },
530
- {
531
- "epoch": 5.602006688963211,
532
- "grad_norm": 2.584045886993408,
533
- "learning_rate": 1.649247491638796e-05,
534
- "loss": 0.5553,
535
- "step": 3350
536
- },
537
- {
538
- "epoch": 5.68561872909699,
539
- "grad_norm": 2.441519260406494,
540
- "learning_rate": 1.6178929765886288e-05,
541
- "loss": 0.557,
542
- "step": 3400
543
- },
544
- {
545
- "epoch": 5.769230769230769,
546
- "grad_norm": 3.489903688430786,
547
- "learning_rate": 1.5865384615384617e-05,
548
- "loss": 0.5212,
549
- "step": 3450
550
- },
551
- {
552
- "epoch": 5.852842809364549,
553
- "grad_norm": 3.7490415573120117,
554
- "learning_rate": 1.5551839464882943e-05,
555
- "loss": 0.5246,
556
- "step": 3500
557
- },
558
- {
559
- "epoch": 5.936454849498328,
560
- "grad_norm": 3.0013935565948486,
561
- "learning_rate": 1.523829431438127e-05,
562
- "loss": 0.5341,
563
- "step": 3550
564
- },
565
- {
566
- "epoch": 6.0,
567
- "eval_accuracy": 0.8160535097122192,
568
- "eval_f1": 0.8160535097122192,
569
- "eval_loss": 0.610401451587677,
570
- "eval_runtime": 57.2156,
571
- "eval_samples_per_second": 83.614,
572
- "eval_steps_per_second": 1.311,
573
- "step": 3588
574
- },
575
- {
576
- "epoch": 6.0200668896321075,
577
- "grad_norm": 3.0697216987609863,
578
- "learning_rate": 1.49247491638796e-05,
579
- "loss": 0.5124,
580
- "step": 3600
581
- },
582
- {
583
- "epoch": 6.103678929765886,
584
- "grad_norm": 3.071810722351074,
585
- "learning_rate": 1.4611204013377926e-05,
586
- "loss": 0.4665,
587
- "step": 3650
588
- },
589
- {
590
- "epoch": 6.187290969899665,
591
- "grad_norm": 2.360440969467163,
592
- "learning_rate": 1.4297658862876255e-05,
593
- "loss": 0.4523,
594
- "step": 3700
595
- },
596
- {
597
- "epoch": 6.270903010033445,
598
- "grad_norm": 3.7450270652770996,
599
- "learning_rate": 1.3984113712374583e-05,
600
- "loss": 0.4557,
601
- "step": 3750
602
- },
603
- {
604
- "epoch": 6.354515050167224,
605
- "grad_norm": 2.299044370651245,
606
- "learning_rate": 1.3670568561872909e-05,
607
- "loss": 0.4486,
608
- "step": 3800
609
- },
610
- {
611
- "epoch": 6.438127090301004,
612
- "grad_norm": 3.2113373279571533,
613
- "learning_rate": 1.3357023411371238e-05,
614
- "loss": 0.4441,
615
- "step": 3850
616
- },
617
- {
618
- "epoch": 6.521739130434782,
619
- "grad_norm": 3.265704393386841,
620
- "learning_rate": 1.3043478260869566e-05,
621
- "loss": 0.4476,
622
- "step": 3900
623
- },
624
- {
625
- "epoch": 6.605351170568562,
626
- "grad_norm": 2.365684747695923,
627
- "learning_rate": 1.2729933110367893e-05,
628
- "loss": 0.4326,
629
- "step": 3950
630
- },
631
- {
632
- "epoch": 6.688963210702341,
633
- "grad_norm": 2.623091697692871,
634
- "learning_rate": 1.2416387959866221e-05,
635
- "loss": 0.4493,
636
- "step": 4000
637
- },
638
- {
639
- "epoch": 6.7725752508361206,
640
- "grad_norm": 4.2816362380981445,
641
- "learning_rate": 1.2102842809364549e-05,
642
- "loss": 0.4374,
643
- "step": 4050
644
- },
645
- {
646
- "epoch": 6.8561872909699,
647
- "grad_norm": 2.976745367050171,
648
- "learning_rate": 1.1789297658862876e-05,
649
- "loss": 0.4246,
650
- "step": 4100
651
- },
652
- {
653
- "epoch": 6.9397993311036785,
654
- "grad_norm": 2.723569631576538,
655
- "learning_rate": 1.1475752508361204e-05,
656
- "loss": 0.4104,
657
- "step": 4150
658
- },
659
- {
660
- "epoch": 7.0,
661
- "eval_accuracy": 0.8235785961151123,
662
- "eval_f1": 0.8235785961151123,
663
- "eval_loss": 0.5483660697937012,
664
- "eval_runtime": 56.6001,
665
- "eval_samples_per_second": 84.523,
666
- "eval_steps_per_second": 1.325,
667
- "step": 4186
668
- },
669
- {
670
- "epoch": 7.023411371237458,
671
- "grad_norm": 2.4986026287078857,
672
- "learning_rate": 1.1162207357859532e-05,
673
- "loss": 0.413,
674
- "step": 4200
675
- },
676
- {
677
- "epoch": 7.107023411371237,
678
- "grad_norm": 3.6669883728027344,
679
- "learning_rate": 1.084866220735786e-05,
680
- "loss": 0.3636,
681
- "step": 4250
682
- },
683
- {
684
- "epoch": 7.190635451505017,
685
- "grad_norm": 2.7657742500305176,
686
- "learning_rate": 1.0535117056856187e-05,
687
- "loss": 0.3762,
688
- "step": 4300
689
- },
690
- {
691
- "epoch": 7.274247491638796,
692
- "grad_norm": 2.6917202472686768,
693
- "learning_rate": 1.0221571906354516e-05,
694
- "loss": 0.3688,
695
- "step": 4350
696
- },
697
- {
698
- "epoch": 7.357859531772576,
699
- "grad_norm": 2.6124022006988525,
700
- "learning_rate": 9.908026755852842e-06,
701
- "loss": 0.3534,
702
- "step": 4400
703
- },
704
- {
705
- "epoch": 7.441471571906354,
706
- "grad_norm": 2.3492910861968994,
707
- "learning_rate": 9.59448160535117e-06,
708
- "loss": 0.3648,
709
- "step": 4450
710
- },
711
- {
712
- "epoch": 7.525083612040134,
713
- "grad_norm": 1.842259168624878,
714
- "learning_rate": 9.2809364548495e-06,
715
- "loss": 0.3457,
716
- "step": 4500
717
- },
718
- {
719
- "epoch": 7.608695652173913,
720
- "grad_norm": 2.880143404006958,
721
- "learning_rate": 8.967391304347827e-06,
722
- "loss": 0.3747,
723
- "step": 4550
724
- },
725
- {
726
- "epoch": 7.6923076923076925,
727
- "grad_norm": 2.546765089035034,
728
- "learning_rate": 8.653846153846153e-06,
729
- "loss": 0.349,
730
- "step": 4600
731
- },
732
- {
733
- "epoch": 7.775919732441472,
734
- "grad_norm": 2.572425127029419,
735
- "learning_rate": 8.340301003344482e-06,
736
- "loss": 0.3479,
737
- "step": 4650
738
- },
739
- {
740
- "epoch": 7.8595317725752505,
741
- "grad_norm": 3.774538278579712,
742
- "learning_rate": 8.02675585284281e-06,
743
- "loss": 0.3458,
744
- "step": 4700
745
- },
746
- {
747
- "epoch": 7.94314381270903,
748
- "grad_norm": 2.3983170986175537,
749
- "learning_rate": 7.713210702341138e-06,
750
- "loss": 0.3549,
751
- "step": 4750
752
- },
753
- {
754
- "epoch": 8.0,
755
- "eval_accuracy": 0.8317307829856873,
756
- "eval_f1": 0.8317307829856873,
757
- "eval_loss": 0.5173951983451843,
758
- "eval_runtime": 57.872,
759
- "eval_samples_per_second": 82.665,
760
- "eval_steps_per_second": 1.296,
761
- "step": 4784
762
- },
763
- {
764
- "epoch": 8.02675585284281,
765
- "grad_norm": 2.7807955741882324,
766
- "learning_rate": 7.399665551839465e-06,
767
- "loss": 0.3324,
768
- "step": 4800
769
- },
770
- {
771
- "epoch": 8.110367892976589,
772
- "grad_norm": 3.530358076095581,
773
- "learning_rate": 7.086120401337793e-06,
774
- "loss": 0.3212,
775
- "step": 4850
776
- },
777
- {
778
- "epoch": 8.193979933110368,
779
- "grad_norm": 2.1531357765197754,
780
- "learning_rate": 6.772575250836121e-06,
781
- "loss": 0.3141,
782
- "step": 4900
783
- },
784
- {
785
- "epoch": 8.277591973244148,
786
- "grad_norm": 1.996618628501892,
787
- "learning_rate": 6.459030100334448e-06,
788
- "loss": 0.288,
789
- "step": 4950
790
- },
791
- {
792
- "epoch": 8.361204013377927,
793
- "grad_norm": 2.6897034645080566,
794
- "learning_rate": 6.145484949832776e-06,
795
- "loss": 0.2943,
796
- "step": 5000
797
- },
798
- {
799
- "epoch": 8.444816053511706,
800
- "grad_norm": 2.446686267852783,
801
- "learning_rate": 5.831939799331104e-06,
802
- "loss": 0.308,
803
- "step": 5050
804
- },
805
- {
806
- "epoch": 8.528428093645484,
807
- "grad_norm": 2.7985997200012207,
808
- "learning_rate": 5.518394648829431e-06,
809
- "loss": 0.3014,
810
- "step": 5100
811
- },
812
- {
813
- "epoch": 8.612040133779264,
814
- "grad_norm": 2.4453961849212646,
815
- "learning_rate": 5.204849498327759e-06,
816
- "loss": 0.2996,
817
- "step": 5150
818
- },
819
- {
820
- "epoch": 8.695652173913043,
821
- "grad_norm": 3.4949986934661865,
822
- "learning_rate": 4.891304347826087e-06,
823
- "loss": 0.3024,
824
- "step": 5200
825
- },
826
- {
827
- "epoch": 8.779264214046822,
828
- "grad_norm": 3.0933334827423096,
829
- "learning_rate": 4.577759197324415e-06,
830
- "loss": 0.318,
831
- "step": 5250
832
- },
833
- {
834
- "epoch": 8.862876254180602,
835
- "grad_norm": 2.353951930999756,
836
- "learning_rate": 4.264214046822742e-06,
837
- "loss": 0.3042,
838
- "step": 5300
839
- },
840
- {
841
- "epoch": 8.946488294314381,
842
- "grad_norm": 3.0331270694732666,
843
- "learning_rate": 3.95066889632107e-06,
844
- "loss": 0.299,
845
- "step": 5350
846
- },
847
- {
848
- "epoch": 9.0,
849
- "eval_accuracy": 0.8377926349639893,
850
- "eval_f1": 0.8377926349639893,
851
- "eval_loss": 0.4919103980064392,
852
- "eval_runtime": 57.5334,
853
- "eval_samples_per_second": 83.152,
854
- "eval_steps_per_second": 1.304,
855
- "step": 5382
856
- },
857
- {
858
- "epoch": 9.03010033444816,
859
- "grad_norm": 1.635090947151184,
860
- "learning_rate": 3.637123745819398e-06,
861
- "loss": 0.27,
862
- "step": 5400
863
- },
864
- {
865
- "epoch": 9.11371237458194,
866
- "grad_norm": 2.002584934234619,
867
- "learning_rate": 3.3235785953177257e-06,
868
- "loss": 0.2604,
869
- "step": 5450
870
- },
871
- {
872
- "epoch": 9.19732441471572,
873
- "grad_norm": 2.2020089626312256,
874
- "learning_rate": 3.0100334448160537e-06,
875
- "loss": 0.2643,
876
- "step": 5500
877
- },
878
- {
879
- "epoch": 9.280936454849499,
880
- "grad_norm": 2.3574795722961426,
881
- "learning_rate": 2.6964882943143814e-06,
882
- "loss": 0.2754,
883
- "step": 5550
884
- },
885
- {
886
- "epoch": 9.364548494983278,
887
- "grad_norm": 2.37418794631958,
888
- "learning_rate": 2.382943143812709e-06,
889
- "loss": 0.2833,
890
- "step": 5600
891
- },
892
- {
893
- "epoch": 9.448160535117056,
894
- "grad_norm": 2.4970650672912598,
895
- "learning_rate": 2.0693979933110367e-06,
896
- "loss": 0.2598,
897
- "step": 5650
898
- },
899
- {
900
- "epoch": 9.531772575250836,
901
- "grad_norm": 2.6536877155303955,
902
- "learning_rate": 1.7558528428093646e-06,
903
- "loss": 0.2685,
904
- "step": 5700
905
- },
906
- {
907
- "epoch": 9.615384615384615,
908
- "grad_norm": 2.722958564758301,
909
- "learning_rate": 1.4423076923076924e-06,
910
- "loss": 0.2588,
911
- "step": 5750
912
- },
913
- {
914
- "epoch": 9.698996655518394,
915
- "grad_norm": 2.4485061168670654,
916
- "learning_rate": 1.12876254180602e-06,
917
- "loss": 0.2728,
918
- "step": 5800
919
- },
920
- {
921
- "epoch": 9.782608695652174,
922
- "grad_norm": 2.3278067111968994,
923
- "learning_rate": 8.152173913043479e-07,
924
- "loss": 0.2752,
925
- "step": 5850
926
- },
927
- {
928
- "epoch": 9.866220735785953,
929
- "grad_norm": 1.9324153661727905,
930
- "learning_rate": 5.016722408026756e-07,
931
- "loss": 0.2604,
932
- "step": 5900
933
- },
934
- {
935
- "epoch": 9.949832775919733,
936
- "grad_norm": 1.9075779914855957,
937
- "learning_rate": 1.8812709030100336e-07,
938
- "loss": 0.2599,
939
- "step": 5950
940
- },
941
- {
942
- "epoch": 10.0,
943
- "eval_accuracy": 0.839046835899353,
944
- "eval_f1": 0.839046835899353,
945
- "eval_loss": 0.49083635210990906,
946
- "eval_runtime": 59.1954,
947
- "eval_samples_per_second": 80.817,
948
- "eval_steps_per_second": 1.267,
949
- "step": 5980
950
- }
951
- ],
952
- "logging_steps": 50,
953
- "max_steps": 5980,
954
- "num_input_tokens_seen": 0,
955
- "num_train_epochs": 10,
956
- "save_steps": 500,
957
- "stateful_callbacks": {
958
- "EarlyStoppingCallback": {
959
- "args": {
960
- "early_stopping_patience": 3,
961
- "early_stopping_threshold": 0.0
962
- },
963
- "attributes": {
964
- "early_stopping_patience_counter": 0
965
- }
966
- },
967
- "TrainerControl": {
968
- "args": {
969
- "should_epoch_stop": false,
970
- "should_evaluate": false,
971
- "should_log": false,
972
- "should_save": true,
973
- "should_training_stop": true
974
- },
975
- "attributes": {}
976
- }
977
- },
978
- "total_flos": 1.6022352226511616e+16,
979
- "train_batch_size": 64,
980
- "trial_name": null,
981
- "trial_params": null
982
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-5980/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc9831b3c6c974be5142429c073136e051bbed16cffc7dfd5ae89083b04a29fc
3
- size 5304
 
 
 
 
checkpoint-5980/vocab.txt DELETED
The diff for this file is too large to render. See raw diff