Hugging Face's logo

PedramR
/
ASR_Post-processing

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
PedramR commited on
Commit
7305bb0
·
verified ·
1 Parent(s): 054ef54

checkpoint-4000

Browse files
Files changed (14) hide show
  1. qwen3.5-2b-50pct-masked-weighted/checkpoint-1000/trainer_state.json +0 -734
  2. qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/README.md +0 -0
  3. qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/adapter_config.json +0 -0
  4. qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/adapter_model.safetensors +1 -1
  5. qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/optimizer.pt +1 -1
  6. qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/rng_state.pth +1 -1
  7. qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/scheduler.pt +1 -1
  8. qwen3.5-2b-50pct-masked-weighted/checkpoint-4000/trainer_state.json +2939 -0
  9. qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/training_args.bin +0 -0
  10. qwen3.5-2b-50pct-masked-weighted/tb/events.out.tfevents.1790426135.b0aacb224392.4711.0 +2 -2
  11. qwen3.5-2b-50pct-masked-weighted/test_eval_entity/metrics.json +11 -11
  12. qwen3.5-2b-50pct-masked-weighted/test_eval_entity/predictions.jsonl +0 -0
  13. qwen3.5-2b-50pct-masked-weighted/test_eval_typo/metrics.json +11 -11
  14. qwen3.5-2b-50pct-masked-weighted/test_eval_typo/predictions.jsonl +0 -0
qwen3.5-2b-50pct-masked-weighted/checkpoint-1000/trainer_state.json DELETED
@@ -1,734 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.17946474639388024,
6
- "eval_steps": 500,
7
- "global_step": 1000,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.0017946474639388024,
14
- "grad_norm": 3.4698801040649414,
15
- "learning_rate": 1.6129032258064516e-06,
16
- "loss": 1.4609528541564942,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.003589294927877605,
21
- "grad_norm": 2.894972085952759,
22
- "learning_rate": 3.405017921146954e-06,
23
- "loss": 1.5060235977172851,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.0053839423918164075,
28
- "grad_norm": 2.3209266662597656,
29
- "learning_rate": 5.197132616487455e-06,
30
- "loss": 1.4531757354736328,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.00717858985575521,
35
- "grad_norm": 2.2354202270507812,
36
- "learning_rate": 6.989247311827957e-06,
37
- "loss": 1.5934924125671386,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.008973237319694013,
42
- "grad_norm": 6.718564033508301,
43
- "learning_rate": 8.781362007168458e-06,
44
- "loss": 1.6818513870239258,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.010767884783632815,
49
- "grad_norm": 1.1820789575576782,
50
- "learning_rate": 1.0573476702508961e-05,
51
- "loss": 1.2959606170654296,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.012562532247571617,
56
- "grad_norm": 1.3072574138641357,
57
- "learning_rate": 1.2365591397849464e-05,
58
- "loss": 1.1890168190002441,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.01435717971151042,
63
- "grad_norm": 1.6472913026809692,
64
- "learning_rate": 1.4157706093189965e-05,
65
- "loss": 1.2888777732849122,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.01615182717544922,
70
- "grad_norm": 2.2778408527374268,
71
- "learning_rate": 1.5949820788530468e-05,
72
- "loss": 1.382105255126953,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.017946474639388026,
77
- "grad_norm": 6.462679386138916,
78
- "learning_rate": 1.774193548387097e-05,
79
- "loss": 1.3651474952697753,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.019741122103326826,
84
- "grad_norm": 1.3327974081039429,
85
- "learning_rate": 1.9534050179211473e-05,
86
- "loss": 1.2019264221191406,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.02153576956726563,
91
- "grad_norm": 1.625113606452942,
92
- "learning_rate": 2.132616487455197e-05,
93
- "loss": 1.1140929222106934,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.023330417031204434,
98
- "grad_norm": 2.114356279373169,
99
- "learning_rate": 2.3118279569892472e-05,
100
- "loss": 1.194014072418213,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.025125064495143234,
105
- "grad_norm": 2.738748073577881,
106
- "learning_rate": 2.4910394265232977e-05,
107
- "loss": 1.310903263092041,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.02691971195908204,
112
- "grad_norm": 7.28310489654541,
113
- "learning_rate": 2.670250896057348e-05,
114
- "loss": 1.341808032989502,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.02871435942302084,
119
- "grad_norm": 1.4109766483306885,
120
- "learning_rate": 2.8494623655913982e-05,
121
- "loss": 1.0624680519104004,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.030509006886959643,
126
- "grad_norm": 1.8665562868118286,
127
- "learning_rate": 3.0286738351254483e-05,
128
- "loss": 1.1256374359130858,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.03230365435089844,
133
- "grad_norm": 2.103581190109253,
134
- "learning_rate": 3.207885304659498e-05,
135
- "loss": 1.1144988059997558,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.03409830181483725,
140
- "grad_norm": 2.7976624965667725,
141
- "learning_rate": 3.387096774193548e-05,
142
- "loss": 1.2549245834350586,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 0.03589294927877605,
147
- "grad_norm": 6.750956058502197,
148
- "learning_rate": 3.566308243727599e-05,
149
- "loss": 1.2815749168395996,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 0.03768759674271485,
154
- "grad_norm": 1.6264805793762207,
155
- "learning_rate": 3.7455197132616484e-05,
156
- "loss": 1.0297048568725586,
157
- "step": 210
158
- },
159
- {
160
- "epoch": 0.03948224420665365,
161
- "grad_norm": 1.6889760494232178,
162
- "learning_rate": 3.924731182795699e-05,
163
- "loss": 1.0584090232849122,
164
- "step": 220
165
- },
166
- {
167
- "epoch": 0.04127689167059246,
168
- "grad_norm": 2.0039634704589844,
169
- "learning_rate": 4.1039426523297493e-05,
170
- "loss": 1.085252571105957,
171
- "step": 230
172
- },
173
- {
174
- "epoch": 0.04307153913453126,
175
- "grad_norm": 2.6522042751312256,
176
- "learning_rate": 4.283154121863799e-05,
177
- "loss": 1.2651546478271485,
178
- "step": 240
179
- },
180
- {
181
- "epoch": 0.04486618659847006,
182
- "grad_norm": 8.020312309265137,
183
- "learning_rate": 4.4623655913978496e-05,
184
- "loss": 1.324000644683838,
185
- "step": 250
186
- },
187
- {
188
- "epoch": 0.04666083406240887,
189
- "grad_norm": 1.7270288467407227,
190
- "learning_rate": 4.6415770609319e-05,
191
- "loss": 1.0575682640075683,
192
- "step": 260
193
- },
194
- {
195
- "epoch": 0.04845548152634767,
196
- "grad_norm": 1.5692397356033325,
197
- "learning_rate": 4.82078853046595e-05,
198
- "loss": 1.0243738174438477,
199
- "step": 270
200
- },
201
- {
202
- "epoch": 0.05025012899028647,
203
- "grad_norm": 2.029719591140747,
204
- "learning_rate": 5e-05,
205
- "loss": 1.0656013488769531,
206
- "step": 280
207
- },
208
- {
209
- "epoch": 0.052044776454225276,
210
- "grad_norm": 2.4044599533081055,
211
- "learning_rate": 5.17921146953405e-05,
212
- "loss": 1.1308915138244628,
213
- "step": 290
214
- },
215
- {
216
- "epoch": 0.05383942391816408,
217
- "grad_norm": 7.324768543243408,
218
- "learning_rate": 5.3584229390681005e-05,
219
- "loss": 1.2482977867126466,
220
- "step": 300
221
- },
222
- {
223
- "epoch": 0.05563407138210288,
224
- "grad_norm": 1.4643646478652954,
225
- "learning_rate": 5.53763440860215e-05,
226
- "loss": 0.984095287322998,
227
- "step": 310
228
- },
229
- {
230
- "epoch": 0.05742871884604168,
231
- "grad_norm": 1.6681671142578125,
232
- "learning_rate": 5.7168458781362014e-05,
233
- "loss": 1.011151123046875,
234
- "step": 320
235
- },
236
- {
237
- "epoch": 0.059223366309980485,
238
- "grad_norm": 1.8012951612472534,
239
- "learning_rate": 5.8960573476702505e-05,
240
- "loss": 1.0619875907897949,
241
- "step": 330
242
- },
243
- {
244
- "epoch": 0.061018013773919286,
245
- "grad_norm": 2.7174854278564453,
246
- "learning_rate": 6.0752688172043016e-05,
247
- "loss": 1.1800737380981445,
248
- "step": 340
249
- },
250
- {
251
- "epoch": 0.06281266123785809,
252
- "grad_norm": 7.283389568328857,
253
- "learning_rate": 6.254480286738351e-05,
254
- "loss": 1.2749577522277833,
255
- "step": 350
256
- },
257
- {
258
- "epoch": 0.06460730870179689,
259
- "grad_norm": 1.4635604619979858,
260
- "learning_rate": 6.433691756272402e-05,
261
- "loss": 1.0051876068115235,
262
- "step": 360
263
- },
264
- {
265
- "epoch": 0.06640195616573569,
266
- "grad_norm": 1.4372541904449463,
267
- "learning_rate": 6.612903225806452e-05,
268
- "loss": 1.0501286506652832,
269
- "step": 370
270
- },
271
- {
272
- "epoch": 0.0681966036296745,
273
- "grad_norm": 1.5717954635620117,
274
- "learning_rate": 6.792114695340503e-05,
275
- "loss": 1.0269421577453612,
276
- "step": 380
277
- },
278
- {
279
- "epoch": 0.0699912510936133,
280
- "grad_norm": 2.4193785190582275,
281
- "learning_rate": 6.971326164874552e-05,
282
- "loss": 1.018425464630127,
283
- "step": 390
284
- },
285
- {
286
- "epoch": 0.0717858985575521,
287
- "grad_norm": 5.167453289031982,
288
- "learning_rate": 7.150537634408602e-05,
289
- "loss": 1.2043580055236816,
290
- "step": 400
291
- },
292
- {
293
- "epoch": 0.0735805460214909,
294
- "grad_norm": 1.1322799921035767,
295
- "learning_rate": 7.329749103942653e-05,
296
- "loss": 0.954345417022705,
297
- "step": 410
298
- },
299
- {
300
- "epoch": 0.0753751934854297,
301
- "grad_norm": 1.3257076740264893,
302
- "learning_rate": 7.508960573476703e-05,
303
- "loss": 0.9895898818969726,
304
- "step": 420
305
- },
306
- {
307
- "epoch": 0.0771698409493685,
308
- "grad_norm": 1.317622184753418,
309
- "learning_rate": 7.688172043010752e-05,
310
- "loss": 0.9647544860839844,
311
- "step": 430
312
- },
313
- {
314
- "epoch": 0.0789644884133073,
315
- "grad_norm": 1.8667112588882446,
316
- "learning_rate": 7.867383512544804e-05,
317
- "loss": 1.139955997467041,
318
- "step": 440
319
- },
320
- {
321
- "epoch": 0.08075913587724612,
322
- "grad_norm": 5.289592266082764,
323
- "learning_rate": 8.046594982078853e-05,
324
- "loss": 1.1954397201538085,
325
- "step": 450
326
- },
327
- {
328
- "epoch": 0.08255378334118492,
329
- "grad_norm": 1.0380669832229614,
330
- "learning_rate": 8.225806451612904e-05,
331
- "loss": 0.9445084571838379,
332
- "step": 460
333
- },
334
- {
335
- "epoch": 0.08434843080512372,
336
- "grad_norm": 1.3310823440551758,
337
- "learning_rate": 8.405017921146954e-05,
338
- "loss": 0.9562747955322266,
339
- "step": 470
340
- },
341
- {
342
- "epoch": 0.08614307826906252,
343
- "grad_norm": 1.417316198348999,
344
- "learning_rate": 8.584229390681004e-05,
345
- "loss": 0.9948525428771973,
346
- "step": 480
347
- },
348
- {
349
- "epoch": 0.08793772573300132,
350
- "grad_norm": 1.8197181224822998,
351
- "learning_rate": 8.763440860215054e-05,
352
- "loss": 1.0975610733032226,
353
- "step": 490
354
- },
355
- {
356
- "epoch": 0.08973237319694012,
357
- "grad_norm": 4.941095352172852,
358
- "learning_rate": 8.942652329749104e-05,
359
- "loss": 1.2107452392578124,
360
- "step": 500
361
- },
362
- {
363
- "epoch": 0.09152702066087894,
364
- "grad_norm": 0.9819939732551575,
365
- "learning_rate": 9.121863799283154e-05,
366
- "loss": 0.9593785285949707,
367
- "step": 510
368
- },
369
- {
370
- "epoch": 0.09332166812481774,
371
- "grad_norm": 1.1892472505569458,
372
- "learning_rate": 9.301075268817204e-05,
373
- "loss": 0.9651047706604003,
374
- "step": 520
375
- },
376
- {
377
- "epoch": 0.09511631558875654,
378
- "grad_norm": 1.4324865341186523,
379
- "learning_rate": 9.480286738351255e-05,
380
- "loss": 0.9062895774841309,
381
- "step": 530
382
- },
383
- {
384
- "epoch": 0.09691096305269534,
385
- "grad_norm": 1.6410809755325317,
386
- "learning_rate": 9.659498207885304e-05,
387
- "loss": 1.0246500968933105,
388
- "step": 540
389
- },
390
- {
391
- "epoch": 0.09870561051663414,
392
- "grad_norm": 5.0956501960754395,
393
- "learning_rate": 9.838709677419355e-05,
394
- "loss": 1.1241219520568848,
395
- "step": 550
396
- },
397
- {
398
- "epoch": 0.10050025798057294,
399
- "grad_norm": 0.951851487159729,
400
- "learning_rate": 9.999055534567435e-05,
401
- "loss": 0.9464516639709473,
402
- "step": 560
403
- },
404
- {
405
- "epoch": 0.10229490544451174,
406
- "grad_norm": 1.1737598180770874,
407
- "learning_rate": 9.989610880241783e-05,
408
- "loss": 0.907046890258789,
409
- "step": 570
410
- },
411
- {
412
- "epoch": 0.10408955290845055,
413
- "grad_norm": 1.3924814462661743,
414
- "learning_rate": 9.980166225916132e-05,
415
- "loss": 0.9977164268493652,
416
- "step": 580
417
- },
418
- {
419
- "epoch": 0.10588420037238935,
420
- "grad_norm": 1.6580984592437744,
421
- "learning_rate": 9.97072157159048e-05,
422
- "loss": 1.0950872421264648,
423
- "step": 590
424
- },
425
- {
426
- "epoch": 0.10767884783632815,
427
- "grad_norm": 4.493084907531738,
428
- "learning_rate": 9.961276917264828e-05,
429
- "loss": 1.211144256591797,
430
- "step": 600
431
- },
432
- {
433
- "epoch": 0.10947349530026695,
434
- "grad_norm": 0.8613011240959167,
435
- "learning_rate": 9.951832262939177e-05,
436
- "loss": 0.9501323699951172,
437
- "step": 610
438
- },
439
- {
440
- "epoch": 0.11126814276420575,
441
- "grad_norm": 1.1255444288253784,
442
- "learning_rate": 9.942387608613525e-05,
443
- "loss": 0.903736686706543,
444
- "step": 620
445
- },
446
- {
447
- "epoch": 0.11306279022814456,
448
- "grad_norm": 1.4082947969436646,
449
- "learning_rate": 9.932942954287873e-05,
450
- "loss": 1.0084752082824706,
451
- "step": 630
452
- },
453
- {
454
- "epoch": 0.11485743769208336,
455
- "grad_norm": 1.652286171913147,
456
- "learning_rate": 9.923498299962222e-05,
457
- "loss": 0.930430793762207,
458
- "step": 640
459
- },
460
- {
461
- "epoch": 0.11665208515602217,
462
- "grad_norm": 5.117873668670654,
463
- "learning_rate": 9.91405364563657e-05,
464
- "loss": 1.091403865814209,
465
- "step": 650
466
- },
467
- {
468
- "epoch": 0.11844673261996097,
469
- "grad_norm": 1.0188069343566895,
470
- "learning_rate": 9.904608991310918e-05,
471
- "loss": 0.883120059967041,
472
- "step": 660
473
- },
474
- {
475
- "epoch": 0.12024138008389977,
476
- "grad_norm": 1.1442457437515259,
477
- "learning_rate": 9.895164336985267e-05,
478
- "loss": 0.9172245979309082,
479
- "step": 670
480
- },
481
- {
482
- "epoch": 0.12203602754783857,
483
- "grad_norm": 1.3536146879196167,
484
- "learning_rate": 9.885719682659615e-05,
485
- "loss": 0.9197479248046875,
486
- "step": 680
487
- },
488
- {
489
- "epoch": 0.12383067501177737,
490
- "grad_norm": 1.8869231939315796,
491
- "learning_rate": 9.876275028333963e-05,
492
- "loss": 1.0764457702636718,
493
- "step": 690
494
- },
495
- {
496
- "epoch": 0.12562532247571617,
497
- "grad_norm": 3.6568493843078613,
498
- "learning_rate": 9.866830374008312e-05,
499
- "loss": 1.0616437911987304,
500
- "step": 700
501
- },
502
- {
503
- "epoch": 0.127419969939655,
504
- "grad_norm": 0.8427063822746277,
505
- "learning_rate": 9.85738571968266e-05,
506
- "loss": 0.8856773376464844,
507
- "step": 710
508
- },
509
- {
510
- "epoch": 0.12921461740359377,
511
- "grad_norm": 1.0265027284622192,
512
- "learning_rate": 9.847941065357009e-05,
513
- "loss": 0.907376766204834,
514
- "step": 720
515
- },
516
- {
517
- "epoch": 0.1310092648675326,
518
- "grad_norm": 1.3209590911865234,
519
- "learning_rate": 9.838496411031357e-05,
520
- "loss": 1.0000056266784667,
521
- "step": 730
522
- },
523
- {
524
- "epoch": 0.13280391233147137,
525
- "grad_norm": 1.7275080680847168,
526
- "learning_rate": 9.829051756705705e-05,
527
- "loss": 1.1050853729248047,
528
- "step": 740
529
- },
530
- {
531
- "epoch": 0.1345985597954102,
532
- "grad_norm": 4.58080530166626,
533
- "learning_rate": 9.819607102380054e-05,
534
- "loss": 1.1597484588623046,
535
- "step": 750
536
- },
537
- {
538
- "epoch": 0.136393207259349,
539
- "grad_norm": 0.8872320055961609,
540
- "learning_rate": 9.810162448054402e-05,
541
- "loss": 0.917822265625,
542
- "step": 760
543
- },
544
- {
545
- "epoch": 0.1381878547232878,
546
- "grad_norm": 0.9287213087081909,
547
- "learning_rate": 9.80071779372875e-05,
548
- "loss": 0.8946282386779785,
549
- "step": 770
550
- },
551
- {
552
- "epoch": 0.1399825021872266,
553
- "grad_norm": 1.183867335319519,
554
- "learning_rate": 9.791273139403099e-05,
555
- "loss": 0.9173077583312989,
556
- "step": 780
557
- },
558
- {
559
- "epoch": 0.1417771496511654,
560
- "grad_norm": 1.6546437740325928,
561
- "learning_rate": 9.781828485077447e-05,
562
- "loss": 0.962445068359375,
563
- "step": 790
564
- },
565
- {
566
- "epoch": 0.1435717971151042,
567
- "grad_norm": 4.307088375091553,
568
- "learning_rate": 9.772383830751794e-05,
569
- "loss": 1.1235834121704102,
570
- "step": 800
571
- },
572
- {
573
- "epoch": 0.145366444579043,
574
- "grad_norm": 0.8552832007408142,
575
- "learning_rate": 9.762939176426144e-05,
576
- "loss": 0.8700121879577637,
577
- "step": 810
578
- },
579
- {
580
- "epoch": 0.1471610920429818,
581
- "grad_norm": 0.9782463908195496,
582
- "learning_rate": 9.753494522100492e-05,
583
- "loss": 0.8827217102050782,
584
- "step": 820
585
- },
586
- {
587
- "epoch": 0.14895573950692062,
588
- "grad_norm": 1.2572635412216187,
589
- "learning_rate": 9.74404986777484e-05,
590
- "loss": 0.9147042274475098,
591
- "step": 830
592
- },
593
- {
594
- "epoch": 0.1507503869708594,
595
- "grad_norm": 1.6980787515640259,
596
- "learning_rate": 9.734605213449189e-05,
597
- "loss": 1.0121471405029296,
598
- "step": 840
599
- },
600
- {
601
- "epoch": 0.15254503443479822,
602
- "grad_norm": 4.741994380950928,
603
- "learning_rate": 9.725160559123536e-05,
604
- "loss": 1.070129680633545,
605
- "step": 850
606
- },
607
- {
608
- "epoch": 0.154339681898737,
609
- "grad_norm": 0.7885052561759949,
610
- "learning_rate": 9.715715904797885e-05,
611
- "loss": 0.9009537696838379,
612
- "step": 860
613
- },
614
- {
615
- "epoch": 0.15613432936267582,
616
- "grad_norm": 0.9653502106666565,
617
- "learning_rate": 9.706271250472234e-05,
618
- "loss": 0.8701554298400879,
619
- "step": 870
620
- },
621
- {
622
- "epoch": 0.1579289768266146,
623
- "grad_norm": 1.2959074974060059,
624
- "learning_rate": 9.69682659614658e-05,
625
- "loss": 0.9180045127868652,
626
- "step": 880
627
- },
628
- {
629
- "epoch": 0.15972362429055342,
630
- "grad_norm": 1.5041567087173462,
631
- "learning_rate": 9.68738194182093e-05,
632
- "loss": 0.9027626037597656,
633
- "step": 890
634
- },
635
- {
636
- "epoch": 0.16151827175449224,
637
- "grad_norm": 5.474041938781738,
638
- "learning_rate": 9.677937287495277e-05,
639
- "loss": 1.0739646911621095,
640
- "step": 900
641
- },
642
- {
643
- "epoch": 0.16331291921843102,
644
- "grad_norm": 0.933229923248291,
645
- "learning_rate": 9.668492633169627e-05,
646
- "loss": 0.881598949432373,
647
- "step": 910
648
- },
649
- {
650
- "epoch": 0.16510756668236984,
651
- "grad_norm": 0.997329592704773,
652
- "learning_rate": 9.659047978843975e-05,
653
- "loss": 0.8712461471557618,
654
- "step": 920
655
- },
656
- {
657
- "epoch": 0.16690221414630863,
658
- "grad_norm": 1.319835901260376,
659
- "learning_rate": 9.649603324518322e-05,
660
- "loss": 0.8690865516662598,
661
- "step": 930
662
- },
663
- {
664
- "epoch": 0.16869686161024744,
665
- "grad_norm": 1.8019057512283325,
666
- "learning_rate": 9.640158670192672e-05,
667
- "loss": 1.1501221656799316,
668
- "step": 940
669
- },
670
- {
671
- "epoch": 0.17049150907418623,
672
- "grad_norm": 3.8484811782836914,
673
- "learning_rate": 9.630714015867019e-05,
674
- "loss": 1.1916112899780273,
675
- "step": 950
676
- },
677
- {
678
- "epoch": 0.17228615653812504,
679
- "grad_norm": 0.8143914937973022,
680
- "learning_rate": 9.621269361541369e-05,
681
- "loss": 0.91885404586792,
682
- "step": 960
683
- },
684
- {
685
- "epoch": 0.17408080400206385,
686
- "grad_norm": 1.0034821033477783,
687
- "learning_rate": 9.611824707215716e-05,
688
- "loss": 0.8618650436401367,
689
- "step": 970
690
- },
691
- {
692
- "epoch": 0.17587545146600264,
693
- "grad_norm": 1.3009910583496094,
694
- "learning_rate": 9.602380052890064e-05,
695
- "loss": 0.8944579124450683,
696
- "step": 980
697
- },
698
- {
699
- "epoch": 0.17767009892994146,
700
- "grad_norm": 1.4715969562530518,
701
- "learning_rate": 9.592935398564414e-05,
702
- "loss": 1.0547027587890625,
703
- "step": 990
704
- },
705
- {
706
- "epoch": 0.17946474639388024,
707
- "grad_norm": 4.630854606628418,
708
- "learning_rate": 9.583490744238761e-05,
709
- "loss": 1.1706391334533692,
710
- "step": 1000
711
- }
712
- ],
713
- "logging_steps": 10,
714
- "max_steps": 11146,
715
- "num_input_tokens_seen": 0,
716
- "num_train_epochs": 2,
717
- "save_steps": 1000,
718
- "stateful_callbacks": {
719
- "TrainerControl": {
720
- "args": {
721
- "should_epoch_stop": false,
722
- "should_evaluate": false,
723
- "should_log": false,
724
- "should_save": true,
725
- "should_training_stop": false
726
- },
727
- "attributes": {}
728
- }
729
- },
730
- "total_flos": 1.014956564093929e+17,
731
- "train_batch_size": 2,
732
- "trial_name": null,
733
- "trial_params": null
734
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/README.md RENAMED
File without changes
qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/adapter_config.json RENAMED
File without changes
qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c355b9758d25da25cd198145fefdcbabf96c8381dc3e00789d628ff12d935b2
3
  size 134604152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f904b313d5c2981f31c044ee85504f6260e2383e7c7d7aa71d3b56bcf35e40f
3
  size 134604152
qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a42ad7610cdce89a745a148c3b9f478ca80c2d6be4bbec707af20112091abe
3
  size 269426431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5c87598d2eca94da2bca4f6d519ed5a4f7931685bc8365d7524134695366a7
3
  size 269426431
qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8372e63a426c4c2855a22732d06e8275ff2b5b5b4accbf12ba6a522510c9ee7d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc615d798f2f311eb38f6fdf2234e527695d1ebb07c5e74a461dfeee8f9e7b0d
3
  size 14645
qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34532159d3083a204b1ddf71a34daca30b5d985bb7d15860a5e34b3afa0bfec2
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa6782e635b7496f9addb48f851412afbec0afa48ef63eb9b8c3a28f2d7c7309
3
  size 1465
qwen3.5-2b-50pct-masked-weighted/checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,2939 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.717858985575521,
6
+ "eval_steps": 500,
7
+ "global_step": 4000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0017946474639388024,
14
+ "grad_norm": 3.4698801040649414,
15
+ "learning_rate": 1.6129032258064516e-06,
16
+ "loss": 1.4609528541564942,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.003589294927877605,
21
+ "grad_norm": 2.894972085952759,
22
+ "learning_rate": 3.405017921146954e-06,
23
+ "loss": 1.5060235977172851,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0053839423918164075,
28
+ "grad_norm": 2.3209266662597656,
29
+ "learning_rate": 5.197132616487455e-06,
30
+ "loss": 1.4531757354736328,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.00717858985575521,
35
+ "grad_norm": 2.2354202270507812,
36
+ "learning_rate": 6.989247311827957e-06,
37
+ "loss": 1.5934924125671386,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.008973237319694013,
42
+ "grad_norm": 6.718564033508301,
43
+ "learning_rate": 8.781362007168458e-06,
44
+ "loss": 1.6818513870239258,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.010767884783632815,
49
+ "grad_norm": 1.1820789575576782,
50
+ "learning_rate": 1.0573476702508961e-05,
51
+ "loss": 1.2959606170654296,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.012562532247571617,
56
+ "grad_norm": 1.3072574138641357,
57
+ "learning_rate": 1.2365591397849464e-05,
58
+ "loss": 1.1890168190002441,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.01435717971151042,
63
+ "grad_norm": 1.6472913026809692,
64
+ "learning_rate": 1.4157706093189965e-05,
65
+ "loss": 1.2888777732849122,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.01615182717544922,
70
+ "grad_norm": 2.2778408527374268,
71
+ "learning_rate": 1.5949820788530468e-05,
72
+ "loss": 1.382105255126953,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.017946474639388026,
77
+ "grad_norm": 6.462679386138916,
78
+ "learning_rate": 1.774193548387097e-05,
79
+ "loss": 1.3651474952697753,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.019741122103326826,
84
+ "grad_norm": 1.3327974081039429,
85
+ "learning_rate": 1.9534050179211473e-05,
86
+ "loss": 1.2019264221191406,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.02153576956726563,
91
+ "grad_norm": 1.625113606452942,
92
+ "learning_rate": 2.132616487455197e-05,
93
+ "loss": 1.1140929222106934,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.023330417031204434,
98
+ "grad_norm": 2.114356279373169,
99
+ "learning_rate": 2.3118279569892472e-05,
100
+ "loss": 1.194014072418213,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.025125064495143234,
105
+ "grad_norm": 2.738748073577881,
106
+ "learning_rate": 2.4910394265232977e-05,
107
+ "loss": 1.310903263092041,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.02691971195908204,
112
+ "grad_norm": 7.28310489654541,
113
+ "learning_rate": 2.670250896057348e-05,
114
+ "loss": 1.341808032989502,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.02871435942302084,
119
+ "grad_norm": 1.4109766483306885,
120
+ "learning_rate": 2.8494623655913982e-05,
121
+ "loss": 1.0624680519104004,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.030509006886959643,
126
+ "grad_norm": 1.8665562868118286,
127
+ "learning_rate": 3.0286738351254483e-05,
128
+ "loss": 1.1256374359130858,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.03230365435089844,
133
+ "grad_norm": 2.103581190109253,
134
+ "learning_rate": 3.207885304659498e-05,
135
+ "loss": 1.1144988059997558,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.03409830181483725,
140
+ "grad_norm": 2.7976624965667725,
141
+ "learning_rate": 3.387096774193548e-05,
142
+ "loss": 1.2549245834350586,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.03589294927877605,
147
+ "grad_norm": 6.750956058502197,
148
+ "learning_rate": 3.566308243727599e-05,
149
+ "loss": 1.2815749168395996,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.03768759674271485,
154
+ "grad_norm": 1.6264805793762207,
155
+ "learning_rate": 3.7455197132616484e-05,
156
+ "loss": 1.0297048568725586,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.03948224420665365,
161
+ "grad_norm": 1.6889760494232178,
162
+ "learning_rate": 3.924731182795699e-05,
163
+ "loss": 1.0584090232849122,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.04127689167059246,
168
+ "grad_norm": 2.0039634704589844,
169
+ "learning_rate": 4.1039426523297493e-05,
170
+ "loss": 1.085252571105957,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.04307153913453126,
175
+ "grad_norm": 2.6522042751312256,
176
+ "learning_rate": 4.283154121863799e-05,
177
+ "loss": 1.2651546478271485,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.04486618659847006,
182
+ "grad_norm": 8.020312309265137,
183
+ "learning_rate": 4.4623655913978496e-05,
184
+ "loss": 1.324000644683838,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.04666083406240887,
189
+ "grad_norm": 1.7270288467407227,
190
+ "learning_rate": 4.6415770609319e-05,
191
+ "loss": 1.0575682640075683,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.04845548152634767,
196
+ "grad_norm": 1.5692397356033325,
197
+ "learning_rate": 4.82078853046595e-05,
198
+ "loss": 1.0243738174438477,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.05025012899028647,
203
+ "grad_norm": 2.029719591140747,
204
+ "learning_rate": 5e-05,
205
+ "loss": 1.0656013488769531,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.052044776454225276,
210
+ "grad_norm": 2.4044599533081055,
211
+ "learning_rate": 5.17921146953405e-05,
212
+ "loss": 1.1308915138244628,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.05383942391816408,
217
+ "grad_norm": 7.324768543243408,
218
+ "learning_rate": 5.3584229390681005e-05,
219
+ "loss": 1.2482977867126466,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.05563407138210288,
224
+ "grad_norm": 1.4643646478652954,
225
+ "learning_rate": 5.53763440860215e-05,
226
+ "loss": 0.984095287322998,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.05742871884604168,
231
+ "grad_norm": 1.6681671142578125,
232
+ "learning_rate": 5.7168458781362014e-05,
233
+ "loss": 1.011151123046875,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.059223366309980485,
238
+ "grad_norm": 1.8012951612472534,
239
+ "learning_rate": 5.8960573476702505e-05,
240
+ "loss": 1.0619875907897949,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.061018013773919286,
245
+ "grad_norm": 2.7174854278564453,
246
+ "learning_rate": 6.0752688172043016e-05,
247
+ "loss": 1.1800737380981445,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.06281266123785809,
252
+ "grad_norm": 7.283389568328857,
253
+ "learning_rate": 6.254480286738351e-05,
254
+ "loss": 1.2749577522277833,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.06460730870179689,
259
+ "grad_norm": 1.4635604619979858,
260
+ "learning_rate": 6.433691756272402e-05,
261
+ "loss": 1.0051876068115235,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.06640195616573569,
266
+ "grad_norm": 1.4372541904449463,
267
+ "learning_rate": 6.612903225806452e-05,
268
+ "loss": 1.0501286506652832,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0681966036296745,
273
+ "grad_norm": 1.5717954635620117,
274
+ "learning_rate": 6.792114695340503e-05,
275
+ "loss": 1.0269421577453612,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.0699912510936133,
280
+ "grad_norm": 2.4193785190582275,
281
+ "learning_rate": 6.971326164874552e-05,
282
+ "loss": 1.018425464630127,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.0717858985575521,
287
+ "grad_norm": 5.167453289031982,
288
+ "learning_rate": 7.150537634408602e-05,
289
+ "loss": 1.2043580055236816,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.0735805460214909,
294
+ "grad_norm": 1.1322799921035767,
295
+ "learning_rate": 7.329749103942653e-05,
296
+ "loss": 0.954345417022705,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.0753751934854297,
301
+ "grad_norm": 1.3257076740264893,
302
+ "learning_rate": 7.508960573476703e-05,
303
+ "loss": 0.9895898818969726,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.0771698409493685,
308
+ "grad_norm": 1.317622184753418,
309
+ "learning_rate": 7.688172043010752e-05,
310
+ "loss": 0.9647544860839844,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.0789644884133073,
315
+ "grad_norm": 1.8667112588882446,
316
+ "learning_rate": 7.867383512544804e-05,
317
+ "loss": 1.139955997467041,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.08075913587724612,
322
+ "grad_norm": 5.289592266082764,
323
+ "learning_rate": 8.046594982078853e-05,
324
+ "loss": 1.1954397201538085,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.08255378334118492,
329
+ "grad_norm": 1.0380669832229614,
330
+ "learning_rate": 8.225806451612904e-05,
331
+ "loss": 0.9445084571838379,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.08434843080512372,
336
+ "grad_norm": 1.3310823440551758,
337
+ "learning_rate": 8.405017921146954e-05,
338
+ "loss": 0.9562747955322266,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.08614307826906252,
343
+ "grad_norm": 1.417316198348999,
344
+ "learning_rate": 8.584229390681004e-05,
345
+ "loss": 0.9948525428771973,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.08793772573300132,
350
+ "grad_norm": 1.8197181224822998,
351
+ "learning_rate": 8.763440860215054e-05,
352
+ "loss": 1.0975610733032226,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.08973237319694012,
357
+ "grad_norm": 4.941095352172852,
358
+ "learning_rate": 8.942652329749104e-05,
359
+ "loss": 1.2107452392578124,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.09152702066087894,
364
+ "grad_norm": 0.9819939732551575,
365
+ "learning_rate": 9.121863799283154e-05,
366
+ "loss": 0.9593785285949707,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.09332166812481774,
371
+ "grad_norm": 1.1892472505569458,
372
+ "learning_rate": 9.301075268817204e-05,
373
+ "loss": 0.9651047706604003,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.09511631558875654,
378
+ "grad_norm": 1.4324865341186523,
379
+ "learning_rate": 9.480286738351255e-05,
380
+ "loss": 0.9062895774841309,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.09691096305269534,
385
+ "grad_norm": 1.6410809755325317,
386
+ "learning_rate": 9.659498207885304e-05,
387
+ "loss": 1.0246500968933105,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.09870561051663414,
392
+ "grad_norm": 5.0956501960754395,
393
+ "learning_rate": 9.838709677419355e-05,
394
+ "loss": 1.1241219520568848,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.10050025798057294,
399
+ "grad_norm": 0.951851487159729,
400
+ "learning_rate": 9.999055534567435e-05,
401
+ "loss": 0.9464516639709473,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.10229490544451174,
406
+ "grad_norm": 1.1737598180770874,
407
+ "learning_rate": 9.989610880241783e-05,
408
+ "loss": 0.907046890258789,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.10408955290845055,
413
+ "grad_norm": 1.3924814462661743,
414
+ "learning_rate": 9.980166225916132e-05,
415
+ "loss": 0.9977164268493652,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.10588420037238935,
420
+ "grad_norm": 1.6580984592437744,
421
+ "learning_rate": 9.97072157159048e-05,
422
+ "loss": 1.0950872421264648,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.10767884783632815,
427
+ "grad_norm": 4.493084907531738,
428
+ "learning_rate": 9.961276917264828e-05,
429
+ "loss": 1.211144256591797,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.10947349530026695,
434
+ "grad_norm": 0.8613011240959167,
435
+ "learning_rate": 9.951832262939177e-05,
436
+ "loss": 0.9501323699951172,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.11126814276420575,
441
+ "grad_norm": 1.1255444288253784,
442
+ "learning_rate": 9.942387608613525e-05,
443
+ "loss": 0.903736686706543,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.11306279022814456,
448
+ "grad_norm": 1.4082947969436646,
449
+ "learning_rate": 9.932942954287873e-05,
450
+ "loss": 1.0084752082824706,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.11485743769208336,
455
+ "grad_norm": 1.652286171913147,
456
+ "learning_rate": 9.923498299962222e-05,
457
+ "loss": 0.930430793762207,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.11665208515602217,
462
+ "grad_norm": 5.117873668670654,
463
+ "learning_rate": 9.91405364563657e-05,
464
+ "loss": 1.091403865814209,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.11844673261996097,
469
+ "grad_norm": 1.0188069343566895,
470
+ "learning_rate": 9.904608991310918e-05,
471
+ "loss": 0.883120059967041,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.12024138008389977,
476
+ "grad_norm": 1.1442457437515259,
477
+ "learning_rate": 9.895164336985267e-05,
478
+ "loss": 0.9172245979309082,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.12203602754783857,
483
+ "grad_norm": 1.3536146879196167,
484
+ "learning_rate": 9.885719682659615e-05,
485
+ "loss": 0.9197479248046875,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.12383067501177737,
490
+ "grad_norm": 1.8869231939315796,
491
+ "learning_rate": 9.876275028333963e-05,
492
+ "loss": 1.0764457702636718,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.12562532247571617,
497
+ "grad_norm": 3.6568493843078613,
498
+ "learning_rate": 9.866830374008312e-05,
499
+ "loss": 1.0616437911987304,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.127419969939655,
504
+ "grad_norm": 0.8427063822746277,
505
+ "learning_rate": 9.85738571968266e-05,
506
+ "loss": 0.8856773376464844,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.12921461740359377,
511
+ "grad_norm": 1.0265027284622192,
512
+ "learning_rate": 9.847941065357009e-05,
513
+ "loss": 0.907376766204834,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.1310092648675326,
518
+ "grad_norm": 1.3209590911865234,
519
+ "learning_rate": 9.838496411031357e-05,
520
+ "loss": 1.0000056266784667,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.13280391233147137,
525
+ "grad_norm": 1.7275080680847168,
526
+ "learning_rate": 9.829051756705705e-05,
527
+ "loss": 1.1050853729248047,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.1345985597954102,
532
+ "grad_norm": 4.58080530166626,
533
+ "learning_rate": 9.819607102380054e-05,
534
+ "loss": 1.1597484588623046,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.136393207259349,
539
+ "grad_norm": 0.8872320055961609,
540
+ "learning_rate": 9.810162448054402e-05,
541
+ "loss": 0.917822265625,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.1381878547232878,
546
+ "grad_norm": 0.9287213087081909,
547
+ "learning_rate": 9.80071779372875e-05,
548
+ "loss": 0.8946282386779785,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.1399825021872266,
553
+ "grad_norm": 1.183867335319519,
554
+ "learning_rate": 9.791273139403099e-05,
555
+ "loss": 0.9173077583312989,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.1417771496511654,
560
+ "grad_norm": 1.6546437740325928,
561
+ "learning_rate": 9.781828485077447e-05,
562
+ "loss": 0.962445068359375,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.1435717971151042,
567
+ "grad_norm": 4.307088375091553,
568
+ "learning_rate": 9.772383830751794e-05,
569
+ "loss": 1.1235834121704102,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.145366444579043,
574
+ "grad_norm": 0.8552832007408142,
575
+ "learning_rate": 9.762939176426144e-05,
576
+ "loss": 0.8700121879577637,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.1471610920429818,
581
+ "grad_norm": 0.9782463908195496,
582
+ "learning_rate": 9.753494522100492e-05,
583
+ "loss": 0.8827217102050782,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.14895573950692062,
588
+ "grad_norm": 1.2572635412216187,
589
+ "learning_rate": 9.74404986777484e-05,
590
+ "loss": 0.9147042274475098,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.1507503869708594,
595
+ "grad_norm": 1.6980787515640259,
596
+ "learning_rate": 9.734605213449189e-05,
597
+ "loss": 1.0121471405029296,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.15254503443479822,
602
+ "grad_norm": 4.741994380950928,
603
+ "learning_rate": 9.725160559123536e-05,
604
+ "loss": 1.070129680633545,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.154339681898737,
609
+ "grad_norm": 0.7885052561759949,
610
+ "learning_rate": 9.715715904797885e-05,
611
+ "loss": 0.9009537696838379,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.15613432936267582,
616
+ "grad_norm": 0.9653502106666565,
617
+ "learning_rate": 9.706271250472234e-05,
618
+ "loss": 0.8701554298400879,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.1579289768266146,
623
+ "grad_norm": 1.2959074974060059,
624
+ "learning_rate": 9.69682659614658e-05,
625
+ "loss": 0.9180045127868652,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.15972362429055342,
630
+ "grad_norm": 1.5041567087173462,
631
+ "learning_rate": 9.68738194182093e-05,
632
+ "loss": 0.9027626037597656,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.16151827175449224,
637
+ "grad_norm": 5.474041938781738,
638
+ "learning_rate": 9.677937287495277e-05,
639
+ "loss": 1.0739646911621095,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.16331291921843102,
644
+ "grad_norm": 0.933229923248291,
645
+ "learning_rate": 9.668492633169627e-05,
646
+ "loss": 0.881598949432373,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.16510756668236984,
651
+ "grad_norm": 0.997329592704773,
652
+ "learning_rate": 9.659047978843975e-05,
653
+ "loss": 0.8712461471557618,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.16690221414630863,
658
+ "grad_norm": 1.319835901260376,
659
+ "learning_rate": 9.649603324518322e-05,
660
+ "loss": 0.8690865516662598,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.16869686161024744,
665
+ "grad_norm": 1.8019057512283325,
666
+ "learning_rate": 9.640158670192672e-05,
667
+ "loss": 1.1501221656799316,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.17049150907418623,
672
+ "grad_norm": 3.8484811782836914,
673
+ "learning_rate": 9.630714015867019e-05,
674
+ "loss": 1.1916112899780273,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.17228615653812504,
679
+ "grad_norm": 0.8143914937973022,
680
+ "learning_rate": 9.621269361541369e-05,
681
+ "loss": 0.91885404586792,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.17408080400206385,
686
+ "grad_norm": 1.0034821033477783,
687
+ "learning_rate": 9.611824707215716e-05,
688
+ "loss": 0.8618650436401367,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.17587545146600264,
693
+ "grad_norm": 1.3009910583496094,
694
+ "learning_rate": 9.602380052890064e-05,
695
+ "loss": 0.8944579124450683,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.17767009892994146,
700
+ "grad_norm": 1.4715969562530518,
701
+ "learning_rate": 9.592935398564414e-05,
702
+ "loss": 1.0547027587890625,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.17946474639388024,
707
+ "grad_norm": 4.630854606628418,
708
+ "learning_rate": 9.583490744238761e-05,
709
+ "loss": 1.1706391334533692,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.17946474639388024,
714
+ "step": 1000,
715
+ "test_entity_exact_match": 0.0019801980198019802,
716
+ "test_entity_fix_rate": 0.09490559539092588,
717
+ "test_entity_fix_rate_lenient": 0.09133004926108375,
718
+ "test_entity_fix_rate_recoverable": 0.09265880308751295,
719
+ "test_entity_hallucination_rate": 0.00891089108910891,
720
+ "test_entity_preservation_rate": 0.34338748592568763,
721
+ "test_entity_preservation_rate_lenient": 0.3451304158166866,
722
+ "test_entity_targeted_score": 0.21914654065830674,
723
+ "test_entity_targeted_score_lenient": 0.21823023253888515,
724
+ "test_entity_wer": 0.7114996637525218,
725
+ "test_entity_wer_zwnj_normalized": 0.7087723230964657
726
+ },
727
+ {
728
+ "epoch": 0.17946474639388024,
729
+ "step": 1000,
730
+ "test_typo_exact_match": 0.00558659217877095,
731
+ "test_typo_fix_rate": 0.15878247382706476,
732
+ "test_typo_fix_rate_lenient": 0.1542123783895674,
733
+ "test_typo_fix_rate_recoverable": 0.15657839428331233,
734
+ "test_typo_hallucination_rate": 0.00558659217877095,
735
+ "test_typo_preservation_rate": 0.459294975450563,
736
+ "test_typo_preservation_rate_lenient": 0.46072255266781914,
737
+ "test_typo_targeted_score": 0.3090387246388139,
738
+ "test_typo_targeted_score_lenient": 0.30746746552869325,
739
+ "test_typo_wer": 0.5876286027928825,
740
+ "test_typo_wer_zwnj_normalized": 0.5829312501595568
741
+ },
742
+ {
743
+ "epoch": 0.17946474639388024,
744
+ "step": 1000,
745
+ "test_best_wer": 0.6495641332727022
746
+ },
747
+ {
748
+ "epoch": 0.18125939385781906,
749
+ "grad_norm": 0.845633864402771,
750
+ "learning_rate": 9.57404608991311e-05,
751
+ "loss": 0.8403111457824707,
752
+ "step": 1010
753
+ },
754
+ {
755
+ "epoch": 0.18305404132175787,
756
+ "grad_norm": 1.0008710622787476,
757
+ "learning_rate": 9.564601435587457e-05,
758
+ "loss": 0.8566953659057617,
759
+ "step": 1020
760
+ },
761
+ {
762
+ "epoch": 0.18484868878569666,
763
+ "grad_norm": 1.3020329475402832,
764
+ "learning_rate": 9.555156781261806e-05,
765
+ "loss": 0.8532472610473633,
766
+ "step": 1030
767
+ },
768
+ {
769
+ "epoch": 0.18664333624963547,
770
+ "grad_norm": 1.4005179405212402,
771
+ "learning_rate": 9.545712126936155e-05,
772
+ "loss": 0.8881989479064941,
773
+ "step": 1040
774
+ },
775
+ {
776
+ "epoch": 0.18843798371357426,
777
+ "grad_norm": 4.764884948730469,
778
+ "learning_rate": 9.536267472610502e-05,
779
+ "loss": 1.096081829071045,
780
+ "step": 1050
781
+ },
782
+ {
783
+ "epoch": 0.19023263117751307,
784
+ "grad_norm": 0.8018057346343994,
785
+ "learning_rate": 9.526822818284851e-05,
786
+ "loss": 0.8475461006164551,
787
+ "step": 1060
788
+ },
789
+ {
790
+ "epoch": 0.19202727864145186,
791
+ "grad_norm": 0.9145928621292114,
792
+ "learning_rate": 9.517378163959199e-05,
793
+ "loss": 0.8785548210144043,
794
+ "step": 1070
795
+ },
796
+ {
797
+ "epoch": 0.19382192610539067,
798
+ "grad_norm": 1.1015050411224365,
799
+ "learning_rate": 9.507933509633547e-05,
800
+ "loss": 0.8983614921569825,
801
+ "step": 1080
802
+ },
803
+ {
804
+ "epoch": 0.1956165735693295,
805
+ "grad_norm": 1.5052039623260498,
806
+ "learning_rate": 9.498488855307897e-05,
807
+ "loss": 0.991839599609375,
808
+ "step": 1090
809
+ },
810
+ {
811
+ "epoch": 0.19741122103326827,
812
+ "grad_norm": 4.894501686096191,
813
+ "learning_rate": 9.489044200982244e-05,
814
+ "loss": 1.215499210357666,
815
+ "step": 1100
816
+ },
817
+ {
818
+ "epoch": 0.1992058684972071,
819
+ "grad_norm": 0.8113166689872742,
820
+ "learning_rate": 9.479599546656593e-05,
821
+ "loss": 0.9022952079772949,
822
+ "step": 1110
823
+ },
824
+ {
825
+ "epoch": 0.20100051596114588,
826
+ "grad_norm": 0.9681263566017151,
827
+ "learning_rate": 9.470154892330941e-05,
828
+ "loss": 0.8785144805908203,
829
+ "step": 1120
830
+ },
831
+ {
832
+ "epoch": 0.2027951634250847,
833
+ "grad_norm": 1.053642988204956,
834
+ "learning_rate": 9.460710238005289e-05,
835
+ "loss": 0.8290045738220215,
836
+ "step": 1130
837
+ },
838
+ {
839
+ "epoch": 0.20458981088902348,
840
+ "grad_norm": 1.5265758037567139,
841
+ "learning_rate": 9.451265583679639e-05,
842
+ "loss": 0.9883374214172364,
843
+ "step": 1140
844
+ },
845
+ {
846
+ "epoch": 0.2063844583529623,
847
+ "grad_norm": 3.2777318954467773,
848
+ "learning_rate": 9.441820929353986e-05,
849
+ "loss": 1.108902931213379,
850
+ "step": 1150
851
+ },
852
+ {
853
+ "epoch": 0.2081791058169011,
854
+ "grad_norm": 0.7957113981246948,
855
+ "learning_rate": 9.432376275028334e-05,
856
+ "loss": 0.8370280265808105,
857
+ "step": 1160
858
+ },
859
+ {
860
+ "epoch": 0.2099737532808399,
861
+ "grad_norm": 0.9634260535240173,
862
+ "learning_rate": 9.422931620702683e-05,
863
+ "loss": 0.828273868560791,
864
+ "step": 1170
865
+ },
866
+ {
867
+ "epoch": 0.2117684007447787,
868
+ "grad_norm": 1.2643507719039917,
869
+ "learning_rate": 9.413486966377031e-05,
870
+ "loss": 0.9653972625732422,
871
+ "step": 1180
872
+ },
873
+ {
874
+ "epoch": 0.2135630482087175,
875
+ "grad_norm": 1.4930179119110107,
876
+ "learning_rate": 9.404042312051379e-05,
877
+ "loss": 1.0028544425964356,
878
+ "step": 1190
879
+ },
880
+ {
881
+ "epoch": 0.2153576956726563,
882
+ "grad_norm": 4.001398086547852,
883
+ "learning_rate": 9.394597657725728e-05,
884
+ "loss": 1.049579906463623,
885
+ "step": 1200
886
+ },
887
+ {
888
+ "epoch": 0.2171523431365951,
889
+ "grad_norm": 0.7326865792274475,
890
+ "learning_rate": 9.385153003400076e-05,
891
+ "loss": 0.8290506362915039,
892
+ "step": 1210
893
+ },
894
+ {
895
+ "epoch": 0.2189469906005339,
896
+ "grad_norm": 0.9118326902389526,
897
+ "learning_rate": 9.375708349074424e-05,
898
+ "loss": 0.7963441371917724,
899
+ "step": 1220
900
+ },
901
+ {
902
+ "epoch": 0.22074163806447272,
903
+ "grad_norm": 1.1683183908462524,
904
+ "learning_rate": 9.366263694748773e-05,
905
+ "loss": 0.8069793701171875,
906
+ "step": 1230
907
+ },
908
+ {
909
+ "epoch": 0.2225362855284115,
910
+ "grad_norm": 1.5301281213760376,
911
+ "learning_rate": 9.356819040423121e-05,
912
+ "loss": 0.9929439544677734,
913
+ "step": 1240
914
+ },
915
+ {
916
+ "epoch": 0.22433093299235032,
917
+ "grad_norm": 3.8319618701934814,
918
+ "learning_rate": 9.347374386097469e-05,
919
+ "loss": 1.085425853729248,
920
+ "step": 1250
921
+ },
922
+ {
923
+ "epoch": 0.2261255804562891,
924
+ "grad_norm": 0.8658831119537354,
925
+ "learning_rate": 9.337929731771818e-05,
926
+ "loss": 0.8651467323303222,
927
+ "step": 1260
928
+ },
929
+ {
930
+ "epoch": 0.22792022792022792,
931
+ "grad_norm": 0.9741929769515991,
932
+ "learning_rate": 9.328485077446166e-05,
933
+ "loss": 0.7978952884674072,
934
+ "step": 1270
935
+ },
936
+ {
937
+ "epoch": 0.2297148753841667,
938
+ "grad_norm": 0.9907529354095459,
939
+ "learning_rate": 9.319040423120514e-05,
940
+ "loss": 0.8779685974121094,
941
+ "step": 1280
942
+ },
943
+ {
944
+ "epoch": 0.23150952284810553,
945
+ "grad_norm": 1.577710747718811,
946
+ "learning_rate": 9.309595768794863e-05,
947
+ "loss": 0.9846627235412597,
948
+ "step": 1290
949
+ },
950
+ {
951
+ "epoch": 0.23330417031204434,
952
+ "grad_norm": 4.1397552490234375,
953
+ "learning_rate": 9.300151114469211e-05,
954
+ "loss": 1.1263571739196778,
955
+ "step": 1300
956
+ },
957
+ {
958
+ "epoch": 0.23509881777598313,
959
+ "grad_norm": 0.898070752620697,
960
+ "learning_rate": 9.29070646014356e-05,
961
+ "loss": 0.8741483688354492,
962
+ "step": 1310
963
+ },
964
+ {
965
+ "epoch": 0.23689346523992194,
966
+ "grad_norm": 0.951369047164917,
967
+ "learning_rate": 9.281261805817908e-05,
968
+ "loss": 0.9030444145202636,
969
+ "step": 1320
970
+ },
971
+ {
972
+ "epoch": 0.23868811270386073,
973
+ "grad_norm": 1.1681045293807983,
974
+ "learning_rate": 9.271817151492256e-05,
975
+ "loss": 0.8972801208496094,
976
+ "step": 1330
977
+ },
978
+ {
979
+ "epoch": 0.24048276016779954,
980
+ "grad_norm": 1.5000301599502563,
981
+ "learning_rate": 9.262372497166604e-05,
982
+ "loss": 0.9021479606628418,
983
+ "step": 1340
984
+ },
985
+ {
986
+ "epoch": 0.24227740763173833,
987
+ "grad_norm": 4.603233337402344,
988
+ "learning_rate": 9.252927842840953e-05,
989
+ "loss": 0.9616855621337891,
990
+ "step": 1350
991
+ },
992
+ {
993
+ "epoch": 0.24407205509567714,
994
+ "grad_norm": 0.7789506912231445,
995
+ "learning_rate": 9.243483188515301e-05,
996
+ "loss": 0.8278372764587403,
997
+ "step": 1360
998
+ },
999
+ {
1000
+ "epoch": 0.24586670255961596,
1001
+ "grad_norm": 0.9593271017074585,
1002
+ "learning_rate": 9.23403853418965e-05,
1003
+ "loss": 0.8673165321350098,
1004
+ "step": 1370
1005
+ },
1006
+ {
1007
+ "epoch": 0.24766135002355474,
1008
+ "grad_norm": 1.2493950128555298,
1009
+ "learning_rate": 9.224593879863998e-05,
1010
+ "loss": 0.8802228927612304,
1011
+ "step": 1380
1012
+ },
1013
+ {
1014
+ "epoch": 0.24945599748749356,
1015
+ "grad_norm": 1.4462804794311523,
1016
+ "learning_rate": 9.215149225538345e-05,
1017
+ "loss": 0.925480842590332,
1018
+ "step": 1390
1019
+ },
1020
+ {
1021
+ "epoch": 0.25125064495143234,
1022
+ "grad_norm": 3.787916660308838,
1023
+ "learning_rate": 9.205704571212694e-05,
1024
+ "loss": 1.1019389152526855,
1025
+ "step": 1400
1026
+ },
1027
+ {
1028
+ "epoch": 0.25304529241537116,
1029
+ "grad_norm": 0.8386228084564209,
1030
+ "learning_rate": 9.196259916887043e-05,
1031
+ "loss": 0.8958368301391602,
1032
+ "step": 1410
1033
+ },
1034
+ {
1035
+ "epoch": 0.25483993987931,
1036
+ "grad_norm": 0.9733511805534363,
1037
+ "learning_rate": 9.186815262561391e-05,
1038
+ "loss": 0.7509948253631592,
1039
+ "step": 1420
1040
+ },
1041
+ {
1042
+ "epoch": 0.2566345873432488,
1043
+ "grad_norm": 1.0639692544937134,
1044
+ "learning_rate": 9.17737060823574e-05,
1045
+ "loss": 0.8474295616149903,
1046
+ "step": 1430
1047
+ },
1048
+ {
1049
+ "epoch": 0.25842923480718755,
1050
+ "grad_norm": 1.7223182916641235,
1051
+ "learning_rate": 9.167925953910086e-05,
1052
+ "loss": 0.9051410675048828,
1053
+ "step": 1440
1054
+ },
1055
+ {
1056
+ "epoch": 0.26022388227112636,
1057
+ "grad_norm": 3.473262310028076,
1058
+ "learning_rate": 9.158481299584436e-05,
1059
+ "loss": 0.9940505027770996,
1060
+ "step": 1450
1061
+ },
1062
+ {
1063
+ "epoch": 0.2620185297350652,
1064
+ "grad_norm": 0.8055341243743896,
1065
+ "learning_rate": 9.149036645258784e-05,
1066
+ "loss": 0.8780458450317383,
1067
+ "step": 1460
1068
+ },
1069
+ {
1070
+ "epoch": 0.263813177199004,
1071
+ "grad_norm": 1.0771476030349731,
1072
+ "learning_rate": 9.139591990933131e-05,
1073
+ "loss": 0.8636789321899414,
1074
+ "step": 1470
1075
+ },
1076
+ {
1077
+ "epoch": 0.26560782466294275,
1078
+ "grad_norm": 1.1147541999816895,
1079
+ "learning_rate": 9.130147336607481e-05,
1080
+ "loss": 0.8464085578918457,
1081
+ "step": 1480
1082
+ },
1083
+ {
1084
+ "epoch": 0.26740247212688156,
1085
+ "grad_norm": 1.4540315866470337,
1086
+ "learning_rate": 9.120702682281828e-05,
1087
+ "loss": 0.8976149559020996,
1088
+ "step": 1490
1089
+ },
1090
+ {
1091
+ "epoch": 0.2691971195908204,
1092
+ "grad_norm": 4.394834995269775,
1093
+ "learning_rate": 9.111258027956178e-05,
1094
+ "loss": 1.1389759063720704,
1095
+ "step": 1500
1096
+ },
1097
+ {
1098
+ "epoch": 0.2709917670547592,
1099
+ "grad_norm": 0.8100571036338806,
1100
+ "learning_rate": 9.101813373630526e-05,
1101
+ "loss": 0.7912180900573731,
1102
+ "step": 1510
1103
+ },
1104
+ {
1105
+ "epoch": 0.272786414518698,
1106
+ "grad_norm": 0.9471364617347717,
1107
+ "learning_rate": 9.092368719304873e-05,
1108
+ "loss": 0.8603667259216309,
1109
+ "step": 1520
1110
+ },
1111
+ {
1112
+ "epoch": 0.27458106198263676,
1113
+ "grad_norm": 1.1160653829574585,
1114
+ "learning_rate": 9.082924064979223e-05,
1115
+ "loss": 0.8775869369506836,
1116
+ "step": 1530
1117
+ },
1118
+ {
1119
+ "epoch": 0.2763757094465756,
1120
+ "grad_norm": 1.5980632305145264,
1121
+ "learning_rate": 9.07347941065357e-05,
1122
+ "loss": 0.9348011970520019,
1123
+ "step": 1540
1124
+ },
1125
+ {
1126
+ "epoch": 0.2781703569105144,
1127
+ "grad_norm": 4.296586036682129,
1128
+ "learning_rate": 9.06403475632792e-05,
1129
+ "loss": 1.0446084976196288,
1130
+ "step": 1550
1131
+ },
1132
+ {
1133
+ "epoch": 0.2799650043744532,
1134
+ "grad_norm": 0.8044270873069763,
1135
+ "learning_rate": 9.054590102002267e-05,
1136
+ "loss": 0.8284408569335937,
1137
+ "step": 1560
1138
+ },
1139
+ {
1140
+ "epoch": 0.281759651838392,
1141
+ "grad_norm": 0.9065347909927368,
1142
+ "learning_rate": 9.045145447676615e-05,
1143
+ "loss": 0.8259025573730469,
1144
+ "step": 1570
1145
+ },
1146
+ {
1147
+ "epoch": 0.2835542993023308,
1148
+ "grad_norm": 1.1605452299118042,
1149
+ "learning_rate": 9.035700793350965e-05,
1150
+ "loss": 0.8801176071166992,
1151
+ "step": 1580
1152
+ },
1153
+ {
1154
+ "epoch": 0.2853489467662696,
1155
+ "grad_norm": 1.5614631175994873,
1156
+ "learning_rate": 9.026256139025312e-05,
1157
+ "loss": 0.9447234153747559,
1158
+ "step": 1590
1159
+ },
1160
+ {
1161
+ "epoch": 0.2871435942302084,
1162
+ "grad_norm": 3.539119005203247,
1163
+ "learning_rate": 9.016811484699661e-05,
1164
+ "loss": 1.0134998321533204,
1165
+ "step": 1600
1166
+ },
1167
+ {
1168
+ "epoch": 0.2889382416941472,
1169
+ "grad_norm": 0.8091688752174377,
1170
+ "learning_rate": 9.007366830374008e-05,
1171
+ "loss": 0.8058991432189941,
1172
+ "step": 1610
1173
+ },
1174
+ {
1175
+ "epoch": 0.290732889158086,
1176
+ "grad_norm": 0.9974891543388367,
1177
+ "learning_rate": 8.997922176048357e-05,
1178
+ "loss": 0.7382112979888916,
1179
+ "step": 1620
1180
+ },
1181
+ {
1182
+ "epoch": 0.2925275366220248,
1183
+ "grad_norm": 1.2397563457489014,
1184
+ "learning_rate": 8.988477521722706e-05,
1185
+ "loss": 0.8194489479064941,
1186
+ "step": 1630
1187
+ },
1188
+ {
1189
+ "epoch": 0.2943221840859636,
1190
+ "grad_norm": 1.3829917907714844,
1191
+ "learning_rate": 8.979032867397053e-05,
1192
+ "loss": 0.9316317558288574,
1193
+ "step": 1640
1194
+ },
1195
+ {
1196
+ "epoch": 0.2961168315499024,
1197
+ "grad_norm": 4.598084926605225,
1198
+ "learning_rate": 8.969588213071402e-05,
1199
+ "loss": 1.0294858932495117,
1200
+ "step": 1650
1201
+ },
1202
+ {
1203
+ "epoch": 0.29791147901384124,
1204
+ "grad_norm": 0.8185928463935852,
1205
+ "learning_rate": 8.96014355874575e-05,
1206
+ "loss": 0.8526276588439942,
1207
+ "step": 1660
1208
+ },
1209
+ {
1210
+ "epoch": 0.29970612647778,
1211
+ "grad_norm": 0.8803004622459412,
1212
+ "learning_rate": 8.950698904420098e-05,
1213
+ "loss": 0.8622500419616699,
1214
+ "step": 1670
1215
+ },
1216
+ {
1217
+ "epoch": 0.3015007739417188,
1218
+ "grad_norm": 1.0694444179534912,
1219
+ "learning_rate": 8.941254250094448e-05,
1220
+ "loss": 0.7721203327178955,
1221
+ "step": 1680
1222
+ },
1223
+ {
1224
+ "epoch": 0.30329542140565763,
1225
+ "grad_norm": 1.434861421585083,
1226
+ "learning_rate": 8.931809595768795e-05,
1227
+ "loss": 0.9630851745605469,
1228
+ "step": 1690
1229
+ },
1230
+ {
1231
+ "epoch": 0.30509006886959644,
1232
+ "grad_norm": 4.44917106628418,
1233
+ "learning_rate": 8.922364941443143e-05,
1234
+ "loss": 1.0820582389831543,
1235
+ "step": 1700
1236
+ },
1237
+ {
1238
+ "epoch": 0.30688471633353526,
1239
+ "grad_norm": 0.8227750658988953,
1240
+ "learning_rate": 8.912920287117492e-05,
1241
+ "loss": 0.8339776992797852,
1242
+ "step": 1710
1243
+ },
1244
+ {
1245
+ "epoch": 0.308679363797474,
1246
+ "grad_norm": 0.9008784294128418,
1247
+ "learning_rate": 8.90347563279184e-05,
1248
+ "loss": 0.7638604164123535,
1249
+ "step": 1720
1250
+ },
1251
+ {
1252
+ "epoch": 0.31047401126141283,
1253
+ "grad_norm": 1.1473792791366577,
1254
+ "learning_rate": 8.894030978466188e-05,
1255
+ "loss": 0.9122580528259278,
1256
+ "step": 1730
1257
+ },
1258
+ {
1259
+ "epoch": 0.31226865872535164,
1260
+ "grad_norm": 1.4027907848358154,
1261
+ "learning_rate": 8.884586324140537e-05,
1262
+ "loss": 0.9376218795776368,
1263
+ "step": 1740
1264
+ },
1265
+ {
1266
+ "epoch": 0.31406330618929046,
1267
+ "grad_norm": 3.44396710395813,
1268
+ "learning_rate": 8.875141669814885e-05,
1269
+ "loss": 0.9627013206481934,
1270
+ "step": 1750
1271
+ },
1272
+ {
1273
+ "epoch": 0.3158579536532292,
1274
+ "grad_norm": 0.761950671672821,
1275
+ "learning_rate": 8.865697015489233e-05,
1276
+ "loss": 0.850135612487793,
1277
+ "step": 1760
1278
+ },
1279
+ {
1280
+ "epoch": 0.31765260111716803,
1281
+ "grad_norm": 0.9319304823875427,
1282
+ "learning_rate": 8.856252361163582e-05,
1283
+ "loss": 0.7397173881530762,
1284
+ "step": 1770
1285
+ },
1286
+ {
1287
+ "epoch": 0.31944724858110685,
1288
+ "grad_norm": 1.1564598083496094,
1289
+ "learning_rate": 8.84680770683793e-05,
1290
+ "loss": 0.8239191055297852,
1291
+ "step": 1780
1292
+ },
1293
+ {
1294
+ "epoch": 0.32124189604504566,
1295
+ "grad_norm": 1.4574592113494873,
1296
+ "learning_rate": 8.837363052512278e-05,
1297
+ "loss": 0.9266434669494629,
1298
+ "step": 1790
1299
+ },
1300
+ {
1301
+ "epoch": 0.3230365435089845,
1302
+ "grad_norm": 4.408364295959473,
1303
+ "learning_rate": 8.827918398186627e-05,
1304
+ "loss": 1.0574697494506835,
1305
+ "step": 1800
1306
+ },
1307
+ {
1308
+ "epoch": 0.32483119097292323,
1309
+ "grad_norm": 0.808427095413208,
1310
+ "learning_rate": 8.818473743860975e-05,
1311
+ "loss": 0.8238012313842773,
1312
+ "step": 1810
1313
+ },
1314
+ {
1315
+ "epoch": 0.32662583843686205,
1316
+ "grad_norm": 0.8963003754615784,
1317
+ "learning_rate": 8.809029089535323e-05,
1318
+ "loss": 0.8102021217346191,
1319
+ "step": 1820
1320
+ },
1321
+ {
1322
+ "epoch": 0.32842048590080086,
1323
+ "grad_norm": 1.1847169399261475,
1324
+ "learning_rate": 8.799584435209672e-05,
1325
+ "loss": 0.847196388244629,
1326
+ "step": 1830
1327
+ },
1328
+ {
1329
+ "epoch": 0.3302151333647397,
1330
+ "grad_norm": 1.355234980583191,
1331
+ "learning_rate": 8.79013978088402e-05,
1332
+ "loss": 0.9291248321533203,
1333
+ "step": 1840
1334
+ },
1335
+ {
1336
+ "epoch": 0.3320097808286785,
1337
+ "grad_norm": 4.019794464111328,
1338
+ "learning_rate": 8.780695126558368e-05,
1339
+ "loss": 0.9507856369018555,
1340
+ "step": 1850
1341
+ },
1342
+ {
1343
+ "epoch": 0.33380442829261725,
1344
+ "grad_norm": 0.8047809600830078,
1345
+ "learning_rate": 8.771250472232717e-05,
1346
+ "loss": 0.8097662925720215,
1347
+ "step": 1860
1348
+ },
1349
+ {
1350
+ "epoch": 0.33559907575655606,
1351
+ "grad_norm": 0.9057943820953369,
1352
+ "learning_rate": 8.761805817907065e-05,
1353
+ "loss": 0.8277406692504883,
1354
+ "step": 1870
1355
+ },
1356
+ {
1357
+ "epoch": 0.3373937232204949,
1358
+ "grad_norm": 1.1131069660186768,
1359
+ "learning_rate": 8.752361163581414e-05,
1360
+ "loss": 0.875433349609375,
1361
+ "step": 1880
1362
+ },
1363
+ {
1364
+ "epoch": 0.3391883706844337,
1365
+ "grad_norm": 1.5567286014556885,
1366
+ "learning_rate": 8.742916509255762e-05,
1367
+ "loss": 0.9548139572143555,
1368
+ "step": 1890
1369
+ },
1370
+ {
1371
+ "epoch": 0.34098301814837245,
1372
+ "grad_norm": 3.943831205368042,
1373
+ "learning_rate": 8.73347185493011e-05,
1374
+ "loss": 1.0330249786376953,
1375
+ "step": 1900
1376
+ },
1377
+ {
1378
+ "epoch": 0.34277766561231127,
1379
+ "grad_norm": 0.7638143301010132,
1380
+ "learning_rate": 8.724027200604459e-05,
1381
+ "loss": 0.804904842376709,
1382
+ "step": 1910
1383
+ },
1384
+ {
1385
+ "epoch": 0.3445723130762501,
1386
+ "grad_norm": 0.9346854090690613,
1387
+ "learning_rate": 8.714582546278807e-05,
1388
+ "loss": 0.7564315795898438,
1389
+ "step": 1920
1390
+ },
1391
+ {
1392
+ "epoch": 0.3463669605401889,
1393
+ "grad_norm": 1.1116750240325928,
1394
+ "learning_rate": 8.705137891953155e-05,
1395
+ "loss": 0.7835733413696289,
1396
+ "step": 1930
1397
+ },
1398
+ {
1399
+ "epoch": 0.3481616080041277,
1400
+ "grad_norm": 1.437160611152649,
1401
+ "learning_rate": 8.695693237627504e-05,
1402
+ "loss": 0.9441628456115723,
1403
+ "step": 1940
1404
+ },
1405
+ {
1406
+ "epoch": 0.34995625546806647,
1407
+ "grad_norm": 2.9362335205078125,
1408
+ "learning_rate": 8.686248583301852e-05,
1409
+ "loss": 1.0385236740112305,
1410
+ "step": 1950
1411
+ },
1412
+ {
1413
+ "epoch": 0.3517509029320053,
1414
+ "grad_norm": 0.7919660210609436,
1415
+ "learning_rate": 8.6768039289762e-05,
1416
+ "loss": 0.7995383739471436,
1417
+ "step": 1960
1418
+ },
1419
+ {
1420
+ "epoch": 0.3535455503959441,
1421
+ "grad_norm": 0.8578867316246033,
1422
+ "learning_rate": 8.667359274650549e-05,
1423
+ "loss": 0.7939890384674072,
1424
+ "step": 1970
1425
+ },
1426
+ {
1427
+ "epoch": 0.3553401978598829,
1428
+ "grad_norm": 1.1968882083892822,
1429
+ "learning_rate": 8.657914620324896e-05,
1430
+ "loss": 0.817835807800293,
1431
+ "step": 1980
1432
+ },
1433
+ {
1434
+ "epoch": 0.3571348453238217,
1435
+ "grad_norm": 1.4205067157745361,
1436
+ "learning_rate": 8.648469965999245e-05,
1437
+ "loss": 0.9530954360961914,
1438
+ "step": 1990
1439
+ },
1440
+ {
1441
+ "epoch": 0.3589294927877605,
1442
+ "grad_norm": 4.1284332275390625,
1443
+ "learning_rate": 8.639025311673594e-05,
1444
+ "loss": 1.0853967666625977,
1445
+ "step": 2000
1446
+ },
1447
+ {
1448
+ "epoch": 0.3589294927877605,
1449
+ "step": 2000,
1450
+ "test_entity_exact_match": 0.0049504950495049506,
1451
+ "test_entity_fix_rate": 0.27269311456930834,
1452
+ "test_entity_fix_rate_lenient": 0.26022988505747124,
1453
+ "test_entity_fix_rate_recoverable": 0.26397567414040835,
1454
+ "test_entity_hallucination_rate": 0.006930693069306931,
1455
+ "test_entity_preservation_rate": 0.8482998230657873,
1456
+ "test_entity_preservation_rate_lenient": 0.8518981820047984,
1457
+ "test_entity_targeted_score": 0.5604964688175478,
1458
+ "test_entity_targeted_score_lenient": 0.5560640335311349,
1459
+ "test_entity_wer": 0.27376415708628216,
1460
+ "test_entity_wer_zwnj_normalized": 0.2673380941706429
1461
+ },
1462
+ {
1463
+ "epoch": 0.3589294927877605,
1464
+ "step": 2000,
1465
+ "test_typo_exact_match": 0.008379888268156424,
1466
+ "test_typo_fix_rate": 0.3557580457541683,
1467
+ "test_typo_fix_rate_lenient": 0.3446491409646036,
1468
+ "test_typo_fix_rate_recoverable": 0.3495166036149643,
1469
+ "test_typo_hallucination_rate": 0.008379888268156424,
1470
+ "test_typo_preservation_rate": 0.9167083174080498,
1471
+ "test_typo_preservation_rate_lenient": 0.919745670837118,
1472
+ "test_typo_targeted_score": 0.6362331815811091,
1473
+ "test_typo_targeted_score_lenient": 0.6321974059008608,
1474
+ "test_typo_wer": 0.172500063822726,
1475
+ "test_typo_wer_zwnj_normalized": 0.16473922034157923
1476
+ },
1477
+ {
1478
+ "epoch": 0.3589294927877605,
1479
+ "step": 2000,
1480
+ "test_best_wer": 0.2231321104545041
1481
+ },
1482
+ {
1483
+ "epoch": 0.3607241402516993,
1484
+ "grad_norm": 0.7390958666801453,
1485
+ "learning_rate": 8.62958065734794e-05,
1486
+ "loss": 0.7684628009796143,
1487
+ "step": 2010
1488
+ },
1489
+ {
1490
+ "epoch": 0.3625187877156381,
1491
+ "grad_norm": 0.8893972039222717,
1492
+ "learning_rate": 8.62013600302229e-05,
1493
+ "loss": 0.7752983570098877,
1494
+ "step": 2020
1495
+ },
1496
+ {
1497
+ "epoch": 0.3643134351795769,
1498
+ "grad_norm": 1.067131757736206,
1499
+ "learning_rate": 8.610691348696637e-05,
1500
+ "loss": 0.8518107414245606,
1501
+ "step": 2030
1502
+ },
1503
+ {
1504
+ "epoch": 0.36610808264351574,
1505
+ "grad_norm": 1.5757921934127808,
1506
+ "learning_rate": 8.601246694370987e-05,
1507
+ "loss": 0.8482656478881836,
1508
+ "step": 2040
1509
+ },
1510
+ {
1511
+ "epoch": 0.3679027301074545,
1512
+ "grad_norm": 3.651500701904297,
1513
+ "learning_rate": 8.591802040045335e-05,
1514
+ "loss": 1.0244155883789063,
1515
+ "step": 2050
1516
+ },
1517
+ {
1518
+ "epoch": 0.3696973775713933,
1519
+ "grad_norm": 0.8204668760299683,
1520
+ "learning_rate": 8.582357385719682e-05,
1521
+ "loss": 0.8487360000610351,
1522
+ "step": 2060
1523
+ },
1524
+ {
1525
+ "epoch": 0.37149202503533213,
1526
+ "grad_norm": 0.9089038372039795,
1527
+ "learning_rate": 8.572912731394032e-05,
1528
+ "loss": 0.8046296119689942,
1529
+ "step": 2070
1530
+ },
1531
+ {
1532
+ "epoch": 0.37328667249927094,
1533
+ "grad_norm": 1.0486875772476196,
1534
+ "learning_rate": 8.563468077068379e-05,
1535
+ "loss": 0.7622116088867188,
1536
+ "step": 2080
1537
+ },
1538
+ {
1539
+ "epoch": 0.3750813199632097,
1540
+ "grad_norm": 1.5056663751602173,
1541
+ "learning_rate": 8.554023422742729e-05,
1542
+ "loss": 0.8422880172729492,
1543
+ "step": 2090
1544
+ },
1545
+ {
1546
+ "epoch": 0.3768759674271485,
1547
+ "grad_norm": 4.078341960906982,
1548
+ "learning_rate": 8.544578768417077e-05,
1549
+ "loss": 1.0107419967651368,
1550
+ "step": 2100
1551
+ },
1552
+ {
1553
+ "epoch": 0.37867061489108733,
1554
+ "grad_norm": 0.8763484358787537,
1555
+ "learning_rate": 8.535134114091424e-05,
1556
+ "loss": 0.8312085151672364,
1557
+ "step": 2110
1558
+ },
1559
+ {
1560
+ "epoch": 0.38046526235502615,
1561
+ "grad_norm": 0.982690155506134,
1562
+ "learning_rate": 8.525689459765774e-05,
1563
+ "loss": 0.7727385997772217,
1564
+ "step": 2120
1565
+ },
1566
+ {
1567
+ "epoch": 0.38225990981896496,
1568
+ "grad_norm": 1.123055100440979,
1569
+ "learning_rate": 8.516244805440121e-05,
1570
+ "loss": 0.8653607368469238,
1571
+ "step": 2130
1572
+ },
1573
+ {
1574
+ "epoch": 0.3840545572829037,
1575
+ "grad_norm": 1.557551622390747,
1576
+ "learning_rate": 8.50680015111447e-05,
1577
+ "loss": 0.934599781036377,
1578
+ "step": 2140
1579
+ },
1580
+ {
1581
+ "epoch": 0.38584920474684253,
1582
+ "grad_norm": 3.7444405555725098,
1583
+ "learning_rate": 8.497355496788817e-05,
1584
+ "loss": 0.98599853515625,
1585
+ "step": 2150
1586
+ },
1587
+ {
1588
+ "epoch": 0.38764385221078135,
1589
+ "grad_norm": 0.7720208168029785,
1590
+ "learning_rate": 8.487910842463166e-05,
1591
+ "loss": 0.7521912574768066,
1592
+ "step": 2160
1593
+ },
1594
+ {
1595
+ "epoch": 0.38943849967472016,
1596
+ "grad_norm": 0.9204645752906799,
1597
+ "learning_rate": 8.478466188137515e-05,
1598
+ "loss": 0.8045943260192872,
1599
+ "step": 2170
1600
+ },
1601
+ {
1602
+ "epoch": 0.391233147138659,
1603
+ "grad_norm": 1.1036076545715332,
1604
+ "learning_rate": 8.469021533811862e-05,
1605
+ "loss": 0.7903369426727295,
1606
+ "step": 2180
1607
+ },
1608
+ {
1609
+ "epoch": 0.39302779460259774,
1610
+ "grad_norm": 1.4786419868469238,
1611
+ "learning_rate": 8.459576879486211e-05,
1612
+ "loss": 0.9231284141540528,
1613
+ "step": 2190
1614
+ },
1615
+ {
1616
+ "epoch": 0.39482244206653655,
1617
+ "grad_norm": 3.327639579772949,
1618
+ "learning_rate": 8.450132225160559e-05,
1619
+ "loss": 0.9885027885437012,
1620
+ "step": 2200
1621
+ },
1622
+ {
1623
+ "epoch": 0.39661708953047536,
1624
+ "grad_norm": 0.7114759683609009,
1625
+ "learning_rate": 8.440687570834907e-05,
1626
+ "loss": 0.7236516952514649,
1627
+ "step": 2210
1628
+ },
1629
+ {
1630
+ "epoch": 0.3984117369944142,
1631
+ "grad_norm": 0.9788351058959961,
1632
+ "learning_rate": 8.431242916509257e-05,
1633
+ "loss": 0.8003618240356445,
1634
+ "step": 2220
1635
+ },
1636
+ {
1637
+ "epoch": 0.40020638445835294,
1638
+ "grad_norm": 1.124056339263916,
1639
+ "learning_rate": 8.421798262183604e-05,
1640
+ "loss": 0.830434513092041,
1641
+ "step": 2230
1642
+ },
1643
+ {
1644
+ "epoch": 0.40200103192229175,
1645
+ "grad_norm": 1.548984169960022,
1646
+ "learning_rate": 8.412353607857952e-05,
1647
+ "loss": 0.9224008560180664,
1648
+ "step": 2240
1649
+ },
1650
+ {
1651
+ "epoch": 0.40379567938623057,
1652
+ "grad_norm": 3.2998907566070557,
1653
+ "learning_rate": 8.402908953532301e-05,
1654
+ "loss": 1.0086255073547363,
1655
+ "step": 2250
1656
+ },
1657
+ {
1658
+ "epoch": 0.4055903268501694,
1659
+ "grad_norm": 0.8208487629890442,
1660
+ "learning_rate": 8.393464299206649e-05,
1661
+ "loss": 0.7369195938110351,
1662
+ "step": 2260
1663
+ },
1664
+ {
1665
+ "epoch": 0.4073849743141082,
1666
+ "grad_norm": 0.8723757266998291,
1667
+ "learning_rate": 8.384019644880999e-05,
1668
+ "loss": 0.7349898338317871,
1669
+ "step": 2270
1670
+ },
1671
+ {
1672
+ "epoch": 0.40917962177804695,
1673
+ "grad_norm": 1.0648058652877808,
1674
+ "learning_rate": 8.374574990555346e-05,
1675
+ "loss": 0.7378031253814697,
1676
+ "step": 2280
1677
+ },
1678
+ {
1679
+ "epoch": 0.41097426924198577,
1680
+ "grad_norm": 1.4518014192581177,
1681
+ "learning_rate": 8.365130336229694e-05,
1682
+ "loss": 0.8286027908325195,
1683
+ "step": 2290
1684
+ },
1685
+ {
1686
+ "epoch": 0.4127689167059246,
1687
+ "grad_norm": 3.4065778255462646,
1688
+ "learning_rate": 8.355685681904043e-05,
1689
+ "loss": 0.9797749519348145,
1690
+ "step": 2300
1691
+ },
1692
+ {
1693
+ "epoch": 0.4145635641698634,
1694
+ "grad_norm": 0.7722201347351074,
1695
+ "learning_rate": 8.346241027578391e-05,
1696
+ "loss": 0.8020071029663086,
1697
+ "step": 2310
1698
+ },
1699
+ {
1700
+ "epoch": 0.4163582116338022,
1701
+ "grad_norm": 0.963054358959198,
1702
+ "learning_rate": 8.336796373252739e-05,
1703
+ "loss": 0.7832077980041504,
1704
+ "step": 2320
1705
+ },
1706
+ {
1707
+ "epoch": 0.41815285909774097,
1708
+ "grad_norm": 1.2207591533660889,
1709
+ "learning_rate": 8.327351718927088e-05,
1710
+ "loss": 0.8532069206237793,
1711
+ "step": 2330
1712
+ },
1713
+ {
1714
+ "epoch": 0.4199475065616798,
1715
+ "grad_norm": 1.279175877571106,
1716
+ "learning_rate": 8.317907064601436e-05,
1717
+ "loss": 0.8882369041442871,
1718
+ "step": 2340
1719
+ },
1720
+ {
1721
+ "epoch": 0.4217421540256186,
1722
+ "grad_norm": 3.7435832023620605,
1723
+ "learning_rate": 8.308462410275784e-05,
1724
+ "loss": 0.9548303604125976,
1725
+ "step": 2350
1726
+ },
1727
+ {
1728
+ "epoch": 0.4235368014895574,
1729
+ "grad_norm": 0.8402184844017029,
1730
+ "learning_rate": 8.299017755950133e-05,
1731
+ "loss": 0.80802001953125,
1732
+ "step": 2360
1733
+ },
1734
+ {
1735
+ "epoch": 0.42533144895349617,
1736
+ "grad_norm": 0.9928398728370667,
1737
+ "learning_rate": 8.289573101624481e-05,
1738
+ "loss": 0.7461267948150635,
1739
+ "step": 2370
1740
+ },
1741
+ {
1742
+ "epoch": 0.427126096417435,
1743
+ "grad_norm": 1.029775857925415,
1744
+ "learning_rate": 8.280128447298829e-05,
1745
+ "loss": 0.7816200733184815,
1746
+ "step": 2380
1747
+ },
1748
+ {
1749
+ "epoch": 0.4289207438813738,
1750
+ "grad_norm": 1.676102638244629,
1751
+ "learning_rate": 8.270683792973178e-05,
1752
+ "loss": 0.8625323295593261,
1753
+ "step": 2390
1754
+ },
1755
+ {
1756
+ "epoch": 0.4307153913453126,
1757
+ "grad_norm": 4.379483699798584,
1758
+ "learning_rate": 8.261239138647526e-05,
1759
+ "loss": 1.0918493270874023,
1760
+ "step": 2400
1761
+ },
1762
+ {
1763
+ "epoch": 0.43251003880925143,
1764
+ "grad_norm": 0.801175057888031,
1765
+ "learning_rate": 8.251794484321874e-05,
1766
+ "loss": 0.7958838462829589,
1767
+ "step": 2410
1768
+ },
1769
+ {
1770
+ "epoch": 0.4343046862731902,
1771
+ "grad_norm": 0.9804407954216003,
1772
+ "learning_rate": 8.242349829996223e-05,
1773
+ "loss": 0.7912225723266602,
1774
+ "step": 2420
1775
+ },
1776
+ {
1777
+ "epoch": 0.436099333737129,
1778
+ "grad_norm": 1.0723820924758911,
1779
+ "learning_rate": 8.232905175670571e-05,
1780
+ "loss": 0.7362414360046386,
1781
+ "step": 2430
1782
+ },
1783
+ {
1784
+ "epoch": 0.4378939812010678,
1785
+ "grad_norm": 1.4297014474868774,
1786
+ "learning_rate": 8.223460521344919e-05,
1787
+ "loss": 0.8591861724853516,
1788
+ "step": 2440
1789
+ },
1790
+ {
1791
+ "epoch": 0.43968862866500663,
1792
+ "grad_norm": 3.624446392059326,
1793
+ "learning_rate": 8.214015867019268e-05,
1794
+ "loss": 0.9524138450622559,
1795
+ "step": 2450
1796
+ },
1797
+ {
1798
+ "epoch": 0.44148327612894545,
1799
+ "grad_norm": 0.805458664894104,
1800
+ "learning_rate": 8.204571212693616e-05,
1801
+ "loss": 0.7998561382293701,
1802
+ "step": 2460
1803
+ },
1804
+ {
1805
+ "epoch": 0.4432779235928842,
1806
+ "grad_norm": 1.0265886783599854,
1807
+ "learning_rate": 8.195126558367964e-05,
1808
+ "loss": 0.7871425151824951,
1809
+ "step": 2470
1810
+ },
1811
+ {
1812
+ "epoch": 0.445072571056823,
1813
+ "grad_norm": 1.1441900730133057,
1814
+ "learning_rate": 8.185681904042313e-05,
1815
+ "loss": 0.8011743545532226,
1816
+ "step": 2480
1817
+ },
1818
+ {
1819
+ "epoch": 0.44686721852076183,
1820
+ "grad_norm": 1.324745774269104,
1821
+ "learning_rate": 8.176237249716661e-05,
1822
+ "loss": 0.8792869567871093,
1823
+ "step": 2490
1824
+ },
1825
+ {
1826
+ "epoch": 0.44866186598470065,
1827
+ "grad_norm": 3.6218490600585938,
1828
+ "learning_rate": 8.16679259539101e-05,
1829
+ "loss": 1.0584125518798828,
1830
+ "step": 2500
1831
+ },
1832
+ {
1833
+ "epoch": 0.4504565134486394,
1834
+ "grad_norm": 0.8318199515342712,
1835
+ "learning_rate": 8.157347941065358e-05,
1836
+ "loss": 0.8112331390380859,
1837
+ "step": 2510
1838
+ },
1839
+ {
1840
+ "epoch": 0.4522511609125782,
1841
+ "grad_norm": 0.8700211644172668,
1842
+ "learning_rate": 8.147903286739706e-05,
1843
+ "loss": 0.7301114082336426,
1844
+ "step": 2520
1845
+ },
1846
+ {
1847
+ "epoch": 0.45404580837651703,
1848
+ "grad_norm": 1.0621533393859863,
1849
+ "learning_rate": 8.138458632414054e-05,
1850
+ "loss": 0.7812650203704834,
1851
+ "step": 2530
1852
+ },
1853
+ {
1854
+ "epoch": 0.45584045584045585,
1855
+ "grad_norm": 1.5809693336486816,
1856
+ "learning_rate": 8.129013978088403e-05,
1857
+ "loss": 0.9069185256958008,
1858
+ "step": 2540
1859
+ },
1860
+ {
1861
+ "epoch": 0.45763510330439466,
1862
+ "grad_norm": 4.058928966522217,
1863
+ "learning_rate": 8.11956932376275e-05,
1864
+ "loss": 0.9913713455200195,
1865
+ "step": 2550
1866
+ },
1867
+ {
1868
+ "epoch": 0.4594297507683334,
1869
+ "grad_norm": 0.8730033040046692,
1870
+ "learning_rate": 8.1101246694371e-05,
1871
+ "loss": 0.830630874633789,
1872
+ "step": 2560
1873
+ },
1874
+ {
1875
+ "epoch": 0.46122439823227224,
1876
+ "grad_norm": 0.9506435990333557,
1877
+ "learning_rate": 8.100680015111446e-05,
1878
+ "loss": 0.7877472400665283,
1879
+ "step": 2570
1880
+ },
1881
+ {
1882
+ "epoch": 0.46301904569621105,
1883
+ "grad_norm": 1.205980896949768,
1884
+ "learning_rate": 8.091235360785796e-05,
1885
+ "loss": 0.7747097015380859,
1886
+ "step": 2580
1887
+ },
1888
+ {
1889
+ "epoch": 0.46481369316014987,
1890
+ "grad_norm": 1.4989122152328491,
1891
+ "learning_rate": 8.081790706460144e-05,
1892
+ "loss": 0.8825558662414551,
1893
+ "step": 2590
1894
+ },
1895
+ {
1896
+ "epoch": 0.4666083406240887,
1897
+ "grad_norm": 3.2947559356689453,
1898
+ "learning_rate": 8.072346052134491e-05,
1899
+ "loss": 0.9716864585876465,
1900
+ "step": 2600
1901
+ },
1902
+ {
1903
+ "epoch": 0.46840298808802744,
1904
+ "grad_norm": 0.8623685836791992,
1905
+ "learning_rate": 8.062901397808841e-05,
1906
+ "loss": 0.7903079032897949,
1907
+ "step": 2610
1908
+ },
1909
+ {
1910
+ "epoch": 0.47019763555196625,
1911
+ "grad_norm": 0.8465585112571716,
1912
+ "learning_rate": 8.053456743483188e-05,
1913
+ "loss": 0.7284007549285889,
1914
+ "step": 2620
1915
+ },
1916
+ {
1917
+ "epoch": 0.47199228301590507,
1918
+ "grad_norm": 1.1626179218292236,
1919
+ "learning_rate": 8.044012089157538e-05,
1920
+ "loss": 0.7963805198669434,
1921
+ "step": 2630
1922
+ },
1923
+ {
1924
+ "epoch": 0.4737869304798439,
1925
+ "grad_norm": 1.5383787155151367,
1926
+ "learning_rate": 8.034567434831886e-05,
1927
+ "loss": 0.910552978515625,
1928
+ "step": 2640
1929
+ },
1930
+ {
1931
+ "epoch": 0.47558157794378264,
1932
+ "grad_norm": 3.7534942626953125,
1933
+ "learning_rate": 8.025122780506233e-05,
1934
+ "loss": 1.0089344024658202,
1935
+ "step": 2650
1936
+ },
1937
+ {
1938
+ "epoch": 0.47737622540772146,
1939
+ "grad_norm": 0.8134721517562866,
1940
+ "learning_rate": 8.015678126180583e-05,
1941
+ "loss": 0.8045218467712403,
1942
+ "step": 2660
1943
+ },
1944
+ {
1945
+ "epoch": 0.47917087287166027,
1946
+ "grad_norm": 0.9830255508422852,
1947
+ "learning_rate": 8.00623347185493e-05,
1948
+ "loss": 0.8016125679016113,
1949
+ "step": 2670
1950
+ },
1951
+ {
1952
+ "epoch": 0.4809655203355991,
1953
+ "grad_norm": 1.0700372457504272,
1954
+ "learning_rate": 7.99678881752928e-05,
1955
+ "loss": 0.9045357704162598,
1956
+ "step": 2680
1957
+ },
1958
+ {
1959
+ "epoch": 0.4827601677995379,
1960
+ "grad_norm": 1.521283745765686,
1961
+ "learning_rate": 7.987344163203628e-05,
1962
+ "loss": 0.8992018699645996,
1963
+ "step": 2690
1964
+ },
1965
+ {
1966
+ "epoch": 0.48455481526347666,
1967
+ "grad_norm": 3.5036544799804688,
1968
+ "learning_rate": 7.977899508877975e-05,
1969
+ "loss": 0.9581445693969727,
1970
+ "step": 2700
1971
+ },
1972
+ {
1973
+ "epoch": 0.48634946272741547,
1974
+ "grad_norm": 0.8462426066398621,
1975
+ "learning_rate": 7.968454854552325e-05,
1976
+ "loss": 0.8029226303100586,
1977
+ "step": 2710
1978
+ },
1979
+ {
1980
+ "epoch": 0.4881441101913543,
1981
+ "grad_norm": 1.0023834705352783,
1982
+ "learning_rate": 7.959010200226672e-05,
1983
+ "loss": 0.7849497318267822,
1984
+ "step": 2720
1985
+ },
1986
+ {
1987
+ "epoch": 0.4899387576552931,
1988
+ "grad_norm": 1.1512731313705444,
1989
+ "learning_rate": 7.94956554590102e-05,
1990
+ "loss": 0.7798937320709228,
1991
+ "step": 2730
1992
+ },
1993
+ {
1994
+ "epoch": 0.4917334051192319,
1995
+ "grad_norm": 1.4260687828063965,
1996
+ "learning_rate": 7.940120891575368e-05,
1997
+ "loss": 0.795078706741333,
1998
+ "step": 2740
1999
+ },
2000
+ {
2001
+ "epoch": 0.4935280525831707,
2002
+ "grad_norm": 3.980698585510254,
2003
+ "learning_rate": 7.930676237249717e-05,
2004
+ "loss": 0.937680435180664,
2005
+ "step": 2750
2006
+ },
2007
+ {
2008
+ "epoch": 0.4953227000471095,
2009
+ "grad_norm": 0.85591059923172,
2010
+ "learning_rate": 7.921231582924066e-05,
2011
+ "loss": 0.7800557136535644,
2012
+ "step": 2760
2013
+ },
2014
+ {
2015
+ "epoch": 0.4971173475110483,
2016
+ "grad_norm": 0.8919742703437805,
2017
+ "learning_rate": 7.911786928598413e-05,
2018
+ "loss": 0.8073655128479004,
2019
+ "step": 2770
2020
+ },
2021
+ {
2022
+ "epoch": 0.4989119949749871,
2023
+ "grad_norm": 1.1961230039596558,
2024
+ "learning_rate": 7.902342274272762e-05,
2025
+ "loss": 0.7749494075775146,
2026
+ "step": 2780
2027
+ },
2028
+ {
2029
+ "epoch": 0.5007066424389259,
2030
+ "grad_norm": 1.384748101234436,
2031
+ "learning_rate": 7.89289761994711e-05,
2032
+ "loss": 0.8329132080078125,
2033
+ "step": 2790
2034
+ },
2035
+ {
2036
+ "epoch": 0.5025012899028647,
2037
+ "grad_norm": 4.502509593963623,
2038
+ "learning_rate": 7.883452965621458e-05,
2039
+ "loss": 1.0134794235229492,
2040
+ "step": 2800
2041
+ },
2042
+ {
2043
+ "epoch": 0.5042959373668036,
2044
+ "grad_norm": 0.7542349100112915,
2045
+ "learning_rate": 7.874008311295808e-05,
2046
+ "loss": 0.7716650009155274,
2047
+ "step": 2810
2048
+ },
2049
+ {
2050
+ "epoch": 0.5060905848307423,
2051
+ "grad_norm": 0.8581972718238831,
2052
+ "learning_rate": 7.864563656970155e-05,
2053
+ "loss": 0.7554300785064697,
2054
+ "step": 2820
2055
+ },
2056
+ {
2057
+ "epoch": 0.5078852322946811,
2058
+ "grad_norm": 1.0908201932907104,
2059
+ "learning_rate": 7.855119002644503e-05,
2060
+ "loss": 0.7669723033905029,
2061
+ "step": 2830
2062
+ },
2063
+ {
2064
+ "epoch": 0.50967987975862,
2065
+ "grad_norm": 1.4047800302505493,
2066
+ "learning_rate": 7.845674348318852e-05,
2067
+ "loss": 0.8453067779541016,
2068
+ "step": 2840
2069
+ },
2070
+ {
2071
+ "epoch": 0.5114745272225587,
2072
+ "grad_norm": 3.700296401977539,
2073
+ "learning_rate": 7.8362296939932e-05,
2074
+ "loss": 1.0116771697998046,
2075
+ "step": 2850
2076
+ },
2077
+ {
2078
+ "epoch": 0.5132691746864976,
2079
+ "grad_norm": 0.8191012740135193,
2080
+ "learning_rate": 7.82678503966755e-05,
2081
+ "loss": 0.7772826671600341,
2082
+ "step": 2860
2083
+ },
2084
+ {
2085
+ "epoch": 0.5150638221504363,
2086
+ "grad_norm": 0.855146050453186,
2087
+ "learning_rate": 7.817340385341897e-05,
2088
+ "loss": 0.7753990650177002,
2089
+ "step": 2870
2090
+ },
2091
+ {
2092
+ "epoch": 0.5168584696143751,
2093
+ "grad_norm": 1.1639156341552734,
2094
+ "learning_rate": 7.807895731016245e-05,
2095
+ "loss": 0.7668899059295654,
2096
+ "step": 2880
2097
+ },
2098
+ {
2099
+ "epoch": 0.518653117078314,
2100
+ "grad_norm": 1.4478026628494263,
2101
+ "learning_rate": 7.798451076690593e-05,
2102
+ "loss": 0.843500804901123,
2103
+ "step": 2890
2104
+ },
2105
+ {
2106
+ "epoch": 0.5204477645422527,
2107
+ "grad_norm": 3.984922170639038,
2108
+ "learning_rate": 7.789006422364942e-05,
2109
+ "loss": 0.971616268157959,
2110
+ "step": 2900
2111
+ },
2112
+ {
2113
+ "epoch": 0.5222424120061915,
2114
+ "grad_norm": 0.8589176535606384,
2115
+ "learning_rate": 7.77956176803929e-05,
2116
+ "loss": 0.7315890789031982,
2117
+ "step": 2910
2118
+ },
2119
+ {
2120
+ "epoch": 0.5240370594701304,
2121
+ "grad_norm": 0.9845552444458008,
2122
+ "learning_rate": 7.770117113713638e-05,
2123
+ "loss": 0.7463840007781982,
2124
+ "step": 2920
2125
+ },
2126
+ {
2127
+ "epoch": 0.5258317069340691,
2128
+ "grad_norm": 1.0363562107086182,
2129
+ "learning_rate": 7.760672459387987e-05,
2130
+ "loss": 0.8146579742431641,
2131
+ "step": 2930
2132
+ },
2133
+ {
2134
+ "epoch": 0.527626354398008,
2135
+ "grad_norm": 1.4898813962936401,
2136
+ "learning_rate": 7.751227805062335e-05,
2137
+ "loss": 0.8084490776062012,
2138
+ "step": 2940
2139
+ },
2140
+ {
2141
+ "epoch": 0.5294210018619467,
2142
+ "grad_norm": 3.68038272857666,
2143
+ "learning_rate": 7.741783150736683e-05,
2144
+ "loss": 0.912483024597168,
2145
+ "step": 2950
2146
+ },
2147
+ {
2148
+ "epoch": 0.5312156493258855,
2149
+ "grad_norm": 0.76303631067276,
2150
+ "learning_rate": 7.732338496411032e-05,
2151
+ "loss": 0.694810438156128,
2152
+ "step": 2960
2153
+ },
2154
+ {
2155
+ "epoch": 0.5330102967898244,
2156
+ "grad_norm": 0.9913522005081177,
2157
+ "learning_rate": 7.72289384208538e-05,
2158
+ "loss": 0.7986444473266602,
2159
+ "step": 2970
2160
+ },
2161
+ {
2162
+ "epoch": 0.5348049442537631,
2163
+ "grad_norm": 1.2463011741638184,
2164
+ "learning_rate": 7.713449187759728e-05,
2165
+ "loss": 0.8069249153137207,
2166
+ "step": 2980
2167
+ },
2168
+ {
2169
+ "epoch": 0.536599591717702,
2170
+ "grad_norm": 1.4866461753845215,
2171
+ "learning_rate": 7.704004533434077e-05,
2172
+ "loss": 0.8331960678100586,
2173
+ "step": 2990
2174
+ },
2175
+ {
2176
+ "epoch": 0.5383942391816408,
2177
+ "grad_norm": 4.406412124633789,
2178
+ "learning_rate": 7.694559879108425e-05,
2179
+ "loss": 0.9865753173828125,
2180
+ "step": 3000
2181
+ },
2182
+ {
2183
+ "epoch": 0.5383942391816408,
2184
+ "step": 3000,
2185
+ "test_entity_exact_match": 0.0009900990099009901,
2186
+ "test_entity_fix_rate": 0.2468610076087297,
2187
+ "test_entity_fix_rate_lenient": 0.24013136288998357,
2188
+ "test_entity_fix_rate_recoverable": 0.2436261569819895,
2189
+ "test_entity_hallucination_rate": 0.12772277227722773,
2190
+ "test_entity_preservation_rate": 0.6939617178703554,
2191
+ "test_entity_preservation_rate_lenient": 0.6974968887520367,
2192
+ "test_entity_targeted_score": 0.47041136273954254,
2193
+ "test_entity_targeted_score_lenient": 0.4688141258210102,
2194
+ "test_entity_wer": 0.5446355184082151,
2195
+ "test_entity_wer_zwnj_normalized": 0.5383588988161954
2196
+ },
2197
+ {
2198
+ "epoch": 0.5383942391816408,
2199
+ "step": 3000,
2200
+ "test_typo_exact_match": 0.002793296089385475,
2201
+ "test_typo_fix_rate": 0.33365645599069405,
2202
+ "test_typo_fix_rate_lenient": 0.32995239080935623,
2203
+ "test_typo_fix_rate_recoverable": 0.3343841950399327,
2204
+ "test_typo_hallucination_rate": 0.18156424581005587,
2205
+ "test_typo_preservation_rate": 0.7954311586746244,
2206
+ "test_typo_preservation_rate_lenient": 0.799349526795394,
2207
+ "test_typo_targeted_score": 0.5645438073326592,
2208
+ "test_typo_targeted_score_lenient": 0.5646509588023751,
2209
+ "test_typo_wer": 0.5629164432871256,
2210
+ "test_typo_wer_zwnj_normalized": 0.5535472671108729
2211
+ },
2212
+ {
2213
+ "epoch": 0.5383942391816408,
2214
+ "step": 3000,
2215
+ "test_best_wer": 0.2231321104545041
2216
+ },
2217
+ {
2218
+ "epoch": 0.5401888866455795,
2219
+ "grad_norm": 0.7907835245132446,
2220
+ "learning_rate": 7.685115224782773e-05,
2221
+ "loss": 0.7664157390594483,
2222
+ "step": 3010
2223
+ },
2224
+ {
2225
+ "epoch": 0.5419835341095184,
2226
+ "grad_norm": 0.9218222498893738,
2227
+ "learning_rate": 7.675670570457122e-05,
2228
+ "loss": 0.6932620525360107,
2229
+ "step": 3020
2230
+ },
2231
+ {
2232
+ "epoch": 0.5437781815734571,
2233
+ "grad_norm": 1.0903208255767822,
2234
+ "learning_rate": 7.66622591613147e-05,
2235
+ "loss": 0.714443302154541,
2236
+ "step": 3030
2237
+ },
2238
+ {
2239
+ "epoch": 0.545572829037396,
2240
+ "grad_norm": 1.5942481756210327,
2241
+ "learning_rate": 7.656781261805818e-05,
2242
+ "loss": 0.8341629981994629,
2243
+ "step": 3040
2244
+ },
2245
+ {
2246
+ "epoch": 0.5473674765013348,
2247
+ "grad_norm": 4.375911712646484,
2248
+ "learning_rate": 7.647336607480167e-05,
2249
+ "loss": 1.0025527954101563,
2250
+ "step": 3050
2251
+ },
2252
+ {
2253
+ "epoch": 0.5491621239652735,
2254
+ "grad_norm": 0.8018923401832581,
2255
+ "learning_rate": 7.637891953154515e-05,
2256
+ "loss": 0.7377686977386475,
2257
+ "step": 3060
2258
+ },
2259
+ {
2260
+ "epoch": 0.5509567714292124,
2261
+ "grad_norm": 0.8786219358444214,
2262
+ "learning_rate": 7.628447298828864e-05,
2263
+ "loss": 0.7309036254882812,
2264
+ "step": 3070
2265
+ },
2266
+ {
2267
+ "epoch": 0.5527514188931512,
2268
+ "grad_norm": 1.1047521829605103,
2269
+ "learning_rate": 7.619002644503212e-05,
2270
+ "loss": 0.8081924438476562,
2271
+ "step": 3080
2272
+ },
2273
+ {
2274
+ "epoch": 0.55454606635709,
2275
+ "grad_norm": 1.7077223062515259,
2276
+ "learning_rate": 7.609557990177559e-05,
2277
+ "loss": 0.8322297096252441,
2278
+ "step": 3090
2279
+ },
2280
+ {
2281
+ "epoch": 0.5563407138210288,
2282
+ "grad_norm": 2.7238352298736572,
2283
+ "learning_rate": 7.600113335851909e-05,
2284
+ "loss": 0.9799996376037597,
2285
+ "step": 3100
2286
+ },
2287
+ {
2288
+ "epoch": 0.5581353612849675,
2289
+ "grad_norm": 0.867943286895752,
2290
+ "learning_rate": 7.590668681526257e-05,
2291
+ "loss": 0.7850025177001954,
2292
+ "step": 3110
2293
+ },
2294
+ {
2295
+ "epoch": 0.5599300087489064,
2296
+ "grad_norm": 1.0038567781448364,
2297
+ "learning_rate": 7.581224027200605e-05,
2298
+ "loss": 0.7511962890625,
2299
+ "step": 3120
2300
+ },
2301
+ {
2302
+ "epoch": 0.5617246562128452,
2303
+ "grad_norm": 1.1457417011260986,
2304
+ "learning_rate": 7.571779372874954e-05,
2305
+ "loss": 0.7605049133300781,
2306
+ "step": 3130
2307
+ },
2308
+ {
2309
+ "epoch": 0.563519303676784,
2310
+ "grad_norm": 1.5344796180725098,
2311
+ "learning_rate": 7.5623347185493e-05,
2312
+ "loss": 0.8576217651367187,
2313
+ "step": 3140
2314
+ },
2315
+ {
2316
+ "epoch": 0.5653139511407228,
2317
+ "grad_norm": 4.3801422119140625,
2318
+ "learning_rate": 7.55289006422365e-05,
2319
+ "loss": 1.025908851623535,
2320
+ "step": 3150
2321
+ },
2322
+ {
2323
+ "epoch": 0.5671085986046616,
2324
+ "grad_norm": 0.8065171241760254,
2325
+ "learning_rate": 7.543445409897997e-05,
2326
+ "loss": 0.7597884178161621,
2327
+ "step": 3160
2328
+ },
2329
+ {
2330
+ "epoch": 0.5689032460686004,
2331
+ "grad_norm": 0.8725234866142273,
2332
+ "learning_rate": 7.534000755572347e-05,
2333
+ "loss": 0.7571310520172119,
2334
+ "step": 3170
2335
+ },
2336
+ {
2337
+ "epoch": 0.5706978935325392,
2338
+ "grad_norm": 1.1811846494674683,
2339
+ "learning_rate": 7.524556101246695e-05,
2340
+ "loss": 0.8152105331420898,
2341
+ "step": 3180
2342
+ },
2343
+ {
2344
+ "epoch": 0.572492540996478,
2345
+ "grad_norm": 1.403980016708374,
2346
+ "learning_rate": 7.515111446921042e-05,
2347
+ "loss": 0.7652612209320069,
2348
+ "step": 3190
2349
+ },
2350
+ {
2351
+ "epoch": 0.5742871884604168,
2352
+ "grad_norm": 4.157504081726074,
2353
+ "learning_rate": 7.505666792595392e-05,
2354
+ "loss": 1.0274846076965332,
2355
+ "step": 3200
2356
+ },
2357
+ {
2358
+ "epoch": 0.5760818359243556,
2359
+ "grad_norm": 0.945754885673523,
2360
+ "learning_rate": 7.496222138269739e-05,
2361
+ "loss": 0.776948881149292,
2362
+ "step": 3210
2363
+ },
2364
+ {
2365
+ "epoch": 0.5778764833882944,
2366
+ "grad_norm": 0.9533429741859436,
2367
+ "learning_rate": 7.486777483944089e-05,
2368
+ "loss": 0.7675546646118164,
2369
+ "step": 3220
2370
+ },
2371
+ {
2372
+ "epoch": 0.5796711308522332,
2373
+ "grad_norm": 1.1486726999282837,
2374
+ "learning_rate": 7.477332829618437e-05,
2375
+ "loss": 0.7956206798553467,
2376
+ "step": 3230
2377
+ },
2378
+ {
2379
+ "epoch": 0.581465778316172,
2380
+ "grad_norm": 1.6006696224212646,
2381
+ "learning_rate": 7.467888175292784e-05,
2382
+ "loss": 0.7861947536468505,
2383
+ "step": 3240
2384
+ },
2385
+ {
2386
+ "epoch": 0.5832604257801108,
2387
+ "grad_norm": 3.8867952823638916,
2388
+ "learning_rate": 7.458443520967134e-05,
2389
+ "loss": 0.9292440414428711,
2390
+ "step": 3250
2391
+ },
2392
+ {
2393
+ "epoch": 0.5850550732440496,
2394
+ "grad_norm": 0.738664984703064,
2395
+ "learning_rate": 7.44899886664148e-05,
2396
+ "loss": 0.7322124004364013,
2397
+ "step": 3260
2398
+ },
2399
+ {
2400
+ "epoch": 0.5868497207079885,
2401
+ "grad_norm": 0.9238191843032837,
2402
+ "learning_rate": 7.439554212315829e-05,
2403
+ "loss": 0.7845471858978271,
2404
+ "step": 3270
2405
+ },
2406
+ {
2407
+ "epoch": 0.5886443681719272,
2408
+ "grad_norm": 1.1484863758087158,
2409
+ "learning_rate": 7.430109557990179e-05,
2410
+ "loss": 0.7382680892944335,
2411
+ "step": 3280
2412
+ },
2413
+ {
2414
+ "epoch": 0.590439015635866,
2415
+ "grad_norm": 1.4992003440856934,
2416
+ "learning_rate": 7.420664903664526e-05,
2417
+ "loss": 0.8386685371398925,
2418
+ "step": 3290
2419
+ },
2420
+ {
2421
+ "epoch": 0.5922336630998049,
2422
+ "grad_norm": 3.009324550628662,
2423
+ "learning_rate": 7.411220249338875e-05,
2424
+ "loss": 0.7852167606353759,
2425
+ "step": 3300
2426
+ },
2427
+ {
2428
+ "epoch": 0.5940283105637436,
2429
+ "grad_norm": 0.7642790675163269,
2430
+ "learning_rate": 7.401775595013222e-05,
2431
+ "loss": 0.7435347080230713,
2432
+ "step": 3310
2433
+ },
2434
+ {
2435
+ "epoch": 0.5958229580276825,
2436
+ "grad_norm": 0.9375689029693604,
2437
+ "learning_rate": 7.392330940687571e-05,
2438
+ "loss": 0.7808713436126709,
2439
+ "step": 3320
2440
+ },
2441
+ {
2442
+ "epoch": 0.5976176054916212,
2443
+ "grad_norm": 1.0263559818267822,
2444
+ "learning_rate": 7.382886286361919e-05,
2445
+ "loss": 0.7671473979949951,
2446
+ "step": 3330
2447
+ },
2448
+ {
2449
+ "epoch": 0.59941225295556,
2450
+ "grad_norm": 1.5290082693099976,
2451
+ "learning_rate": 7.373441632036267e-05,
2452
+ "loss": 0.8393860816955566,
2453
+ "step": 3340
2454
+ },
2455
+ {
2456
+ "epoch": 0.6012069004194989,
2457
+ "grad_norm": 3.64926815032959,
2458
+ "learning_rate": 7.363996977710617e-05,
2459
+ "loss": 1.0867633819580078,
2460
+ "step": 3350
2461
+ },
2462
+ {
2463
+ "epoch": 0.6030015478834376,
2464
+ "grad_norm": 0.808864176273346,
2465
+ "learning_rate": 7.354552323384964e-05,
2466
+ "loss": 0.7091707706451416,
2467
+ "step": 3360
2468
+ },
2469
+ {
2470
+ "epoch": 0.6047961953473765,
2471
+ "grad_norm": 0.9375695586204529,
2472
+ "learning_rate": 7.345107669059312e-05,
2473
+ "loss": 0.7503323554992676,
2474
+ "step": 3370
2475
+ },
2476
+ {
2477
+ "epoch": 0.6065908428113153,
2478
+ "grad_norm": 1.1794304847717285,
2479
+ "learning_rate": 7.335663014733661e-05,
2480
+ "loss": 0.7147882461547852,
2481
+ "step": 3380
2482
+ },
2483
+ {
2484
+ "epoch": 0.608385490275254,
2485
+ "grad_norm": 1.5392098426818848,
2486
+ "learning_rate": 7.326218360408009e-05,
2487
+ "loss": 0.7968433380126954,
2488
+ "step": 3390
2489
+ },
2490
+ {
2491
+ "epoch": 0.6101801377391929,
2492
+ "grad_norm": 4.211322784423828,
2493
+ "learning_rate": 7.316773706082359e-05,
2494
+ "loss": 1.0250563621520996,
2495
+ "step": 3400
2496
+ },
2497
+ {
2498
+ "epoch": 0.6119747852031316,
2499
+ "grad_norm": 0.8506379127502441,
2500
+ "learning_rate": 7.307329051756706e-05,
2501
+ "loss": 0.7442142009735108,
2502
+ "step": 3410
2503
+ },
2504
+ {
2505
+ "epoch": 0.6137694326670705,
2506
+ "grad_norm": 0.8980507254600525,
2507
+ "learning_rate": 7.297884397431054e-05,
2508
+ "loss": 0.7057757377624512,
2509
+ "step": 3420
2510
+ },
2511
+ {
2512
+ "epoch": 0.6155640801310093,
2513
+ "grad_norm": 1.1606661081314087,
2514
+ "learning_rate": 7.288439743105402e-05,
2515
+ "loss": 0.7168849468231201,
2516
+ "step": 3430
2517
+ },
2518
+ {
2519
+ "epoch": 0.617358727594948,
2520
+ "grad_norm": 1.7294520139694214,
2521
+ "learning_rate": 7.278995088779751e-05,
2522
+ "loss": 0.829401969909668,
2523
+ "step": 3440
2524
+ },
2525
+ {
2526
+ "epoch": 0.6191533750588869,
2527
+ "grad_norm": 4.571506500244141,
2528
+ "learning_rate": 7.269550434454099e-05,
2529
+ "loss": 0.8971552848815918,
2530
+ "step": 3450
2531
+ },
2532
+ {
2533
+ "epoch": 0.6209480225228257,
2534
+ "grad_norm": 0.8465120792388916,
2535
+ "learning_rate": 7.260105780128448e-05,
2536
+ "loss": 0.7918114185333252,
2537
+ "step": 3460
2538
+ },
2539
+ {
2540
+ "epoch": 0.6227426699867645,
2541
+ "grad_norm": 0.9524924755096436,
2542
+ "learning_rate": 7.250661125802796e-05,
2543
+ "loss": 0.7100203990936279,
2544
+ "step": 3470
2545
+ },
2546
+ {
2547
+ "epoch": 0.6245373174507033,
2548
+ "grad_norm": 1.2286087274551392,
2549
+ "learning_rate": 7.241216471477144e-05,
2550
+ "loss": 0.7934963703155518,
2551
+ "step": 3480
2552
+ },
2553
+ {
2554
+ "epoch": 0.626331964914642,
2555
+ "grad_norm": 1.525288701057434,
2556
+ "learning_rate": 7.231771817151493e-05,
2557
+ "loss": 0.8523421287536621,
2558
+ "step": 3490
2559
+ },
2560
+ {
2561
+ "epoch": 0.6281266123785809,
2562
+ "grad_norm": 3.8124051094055176,
2563
+ "learning_rate": 7.222327162825841e-05,
2564
+ "loss": 0.8778561592102051,
2565
+ "step": 3500
2566
+ },
2567
+ {
2568
+ "epoch": 0.6299212598425197,
2569
+ "grad_norm": 0.784967303276062,
2570
+ "learning_rate": 7.212882508500189e-05,
2571
+ "loss": 0.7515722751617432,
2572
+ "step": 3510
2573
+ },
2574
+ {
2575
+ "epoch": 0.6317159073064584,
2576
+ "grad_norm": 0.9887149333953857,
2577
+ "learning_rate": 7.203437854174538e-05,
2578
+ "loss": 0.7394243240356445,
2579
+ "step": 3520
2580
+ },
2581
+ {
2582
+ "epoch": 0.6335105547703973,
2583
+ "grad_norm": 1.0454784631729126,
2584
+ "learning_rate": 7.193993199848886e-05,
2585
+ "loss": 0.7185003757476807,
2586
+ "step": 3530
2587
+ },
2588
+ {
2589
+ "epoch": 0.6353052022343361,
2590
+ "grad_norm": 1.3647416830062866,
2591
+ "learning_rate": 7.184548545523234e-05,
2592
+ "loss": 0.8064111709594727,
2593
+ "step": 3540
2594
+ },
2595
+ {
2596
+ "epoch": 0.6370998496982749,
2597
+ "grad_norm": 4.639543533325195,
2598
+ "learning_rate": 7.175103891197583e-05,
2599
+ "loss": 1.0075956344604493,
2600
+ "step": 3550
2601
+ },
2602
+ {
2603
+ "epoch": 0.6388944971622137,
2604
+ "grad_norm": 0.7738682627677917,
2605
+ "learning_rate": 7.165659236871931e-05,
2606
+ "loss": 0.7540982246398926,
2607
+ "step": 3560
2608
+ },
2609
+ {
2610
+ "epoch": 0.6406891446261525,
2611
+ "grad_norm": 0.8665961623191833,
2612
+ "learning_rate": 7.156214582546279e-05,
2613
+ "loss": 0.729641342163086,
2614
+ "step": 3570
2615
+ },
2616
+ {
2617
+ "epoch": 0.6424837920900913,
2618
+ "grad_norm": 1.299155831336975,
2619
+ "learning_rate": 7.146769928220628e-05,
2620
+ "loss": 0.829476261138916,
2621
+ "step": 3580
2622
+ },
2623
+ {
2624
+ "epoch": 0.6442784395540301,
2625
+ "grad_norm": 1.4906305074691772,
2626
+ "learning_rate": 7.137325273894976e-05,
2627
+ "loss": 0.8294624328613281,
2628
+ "step": 3590
2629
+ },
2630
+ {
2631
+ "epoch": 0.646073087017969,
2632
+ "grad_norm": 4.132716178894043,
2633
+ "learning_rate": 7.127880619569324e-05,
2634
+ "loss": 0.9922947883605957,
2635
+ "step": 3600
2636
+ },
2637
+ {
2638
+ "epoch": 0.6478677344819077,
2639
+ "grad_norm": 0.7767786979675293,
2640
+ "learning_rate": 7.118435965243673e-05,
2641
+ "loss": 0.8112610816955567,
2642
+ "step": 3610
2643
+ },
2644
+ {
2645
+ "epoch": 0.6496623819458465,
2646
+ "grad_norm": 0.9437559843063354,
2647
+ "learning_rate": 7.108991310918021e-05,
2648
+ "loss": 0.7408264636993408,
2649
+ "step": 3620
2650
+ },
2651
+ {
2652
+ "epoch": 0.6514570294097853,
2653
+ "grad_norm": 1.0995409488677979,
2654
+ "learning_rate": 7.099546656592368e-05,
2655
+ "loss": 0.6897705554962158,
2656
+ "step": 3630
2657
+ },
2658
+ {
2659
+ "epoch": 0.6532516768737241,
2660
+ "grad_norm": 1.4682518243789673,
2661
+ "learning_rate": 7.090102002266718e-05,
2662
+ "loss": 0.8766571998596191,
2663
+ "step": 3640
2664
+ },
2665
+ {
2666
+ "epoch": 0.655046324337663,
2667
+ "grad_norm": 3.8546547889709473,
2668
+ "learning_rate": 7.080657347941066e-05,
2669
+ "loss": 1.0745360374450683,
2670
+ "step": 3650
2671
+ },
2672
+ {
2673
+ "epoch": 0.6568409718016017,
2674
+ "grad_norm": 0.8107970356941223,
2675
+ "learning_rate": 7.071212693615414e-05,
2676
+ "loss": 0.7250616073608398,
2677
+ "step": 3660
2678
+ },
2679
+ {
2680
+ "epoch": 0.6586356192655405,
2681
+ "grad_norm": 1.0033174753189087,
2682
+ "learning_rate": 7.061768039289763e-05,
2683
+ "loss": 0.7318480491638184,
2684
+ "step": 3670
2685
+ },
2686
+ {
2687
+ "epoch": 0.6604302667294794,
2688
+ "grad_norm": 1.1052309274673462,
2689
+ "learning_rate": 7.05232338496411e-05,
2690
+ "loss": 0.6873965263366699,
2691
+ "step": 3680
2692
+ },
2693
+ {
2694
+ "epoch": 0.6622249141934181,
2695
+ "grad_norm": 1.4791178703308105,
2696
+ "learning_rate": 7.04287873063846e-05,
2697
+ "loss": 0.825076675415039,
2698
+ "step": 3690
2699
+ },
2700
+ {
2701
+ "epoch": 0.664019561657357,
2702
+ "grad_norm": 3.5650668144226074,
2703
+ "learning_rate": 7.033434076312806e-05,
2704
+ "loss": 0.946928882598877,
2705
+ "step": 3700
2706
+ },
2707
+ {
2708
+ "epoch": 0.6658142091212957,
2709
+ "grad_norm": 0.8390607237815857,
2710
+ "learning_rate": 7.023989421987156e-05,
2711
+ "loss": 0.7335081577301026,
2712
+ "step": 3710
2713
+ },
2714
+ {
2715
+ "epoch": 0.6676088565852345,
2716
+ "grad_norm": 1.0318807363510132,
2717
+ "learning_rate": 7.014544767661504e-05,
2718
+ "loss": 0.7376636028289795,
2719
+ "step": 3720
2720
+ },
2721
+ {
2722
+ "epoch": 0.6694035040491734,
2723
+ "grad_norm": 1.2701818943023682,
2724
+ "learning_rate": 7.005100113335851e-05,
2725
+ "loss": 0.741237735748291,
2726
+ "step": 3730
2727
+ },
2728
+ {
2729
+ "epoch": 0.6711981515131121,
2730
+ "grad_norm": 1.5756694078445435,
2731
+ "learning_rate": 6.995655459010201e-05,
2732
+ "loss": 0.8473384857177735,
2733
+ "step": 3740
2734
+ },
2735
+ {
2736
+ "epoch": 0.672992798977051,
2737
+ "grad_norm": 3.7947230339050293,
2738
+ "learning_rate": 6.986210804684548e-05,
2739
+ "loss": 0.8996176719665527,
2740
+ "step": 3750
2741
+ },
2742
+ {
2743
+ "epoch": 0.6747874464409898,
2744
+ "grad_norm": 0.7768403887748718,
2745
+ "learning_rate": 6.976766150358898e-05,
2746
+ "loss": 0.7349163055419922,
2747
+ "step": 3760
2748
+ },
2749
+ {
2750
+ "epoch": 0.6765820939049285,
2751
+ "grad_norm": 1.0075407028198242,
2752
+ "learning_rate": 6.967321496033246e-05,
2753
+ "loss": 0.7181667804718017,
2754
+ "step": 3770
2755
+ },
2756
+ {
2757
+ "epoch": 0.6783767413688674,
2758
+ "grad_norm": 1.1049768924713135,
2759
+ "learning_rate": 6.957876841707593e-05,
2760
+ "loss": 0.7353485107421875,
2761
+ "step": 3780
2762
+ },
2763
+ {
2764
+ "epoch": 0.6801713888328061,
2765
+ "grad_norm": 1.455216407775879,
2766
+ "learning_rate": 6.948432187381943e-05,
2767
+ "loss": 0.8581386566162109,
2768
+ "step": 3790
2769
+ },
2770
+ {
2771
+ "epoch": 0.6819660362967449,
2772
+ "grad_norm": 3.471524953842163,
2773
+ "learning_rate": 6.93898753305629e-05,
2774
+ "loss": 0.8986720085144043,
2775
+ "step": 3800
2776
+ },
2777
+ {
2778
+ "epoch": 0.6837606837606838,
2779
+ "grad_norm": 0.788811445236206,
2780
+ "learning_rate": 6.92954287873064e-05,
2781
+ "loss": 0.7062864303588867,
2782
+ "step": 3810
2783
+ },
2784
+ {
2785
+ "epoch": 0.6855553312246225,
2786
+ "grad_norm": 1.0214735269546509,
2787
+ "learning_rate": 6.920098224404988e-05,
2788
+ "loss": 0.7787455081939697,
2789
+ "step": 3820
2790
+ },
2791
+ {
2792
+ "epoch": 0.6873499786885614,
2793
+ "grad_norm": 1.1044228076934814,
2794
+ "learning_rate": 6.910653570079335e-05,
2795
+ "loss": 0.7103426933288575,
2796
+ "step": 3830
2797
+ },
2798
+ {
2799
+ "epoch": 0.6891446261525002,
2800
+ "grad_norm": 1.486441731452942,
2801
+ "learning_rate": 6.901208915753685e-05,
2802
+ "loss": 0.8558782577514649,
2803
+ "step": 3840
2804
+ },
2805
+ {
2806
+ "epoch": 0.6909392736164389,
2807
+ "grad_norm": 4.211693286895752,
2808
+ "learning_rate": 6.891764261428031e-05,
2809
+ "loss": 0.9754589080810547,
2810
+ "step": 3850
2811
+ },
2812
+ {
2813
+ "epoch": 0.6927339210803778,
2814
+ "grad_norm": 0.7651219964027405,
2815
+ "learning_rate": 6.88231960710238e-05,
2816
+ "loss": 0.673793363571167,
2817
+ "step": 3860
2818
+ },
2819
+ {
2820
+ "epoch": 0.6945285685443165,
2821
+ "grad_norm": 0.9120017886161804,
2822
+ "learning_rate": 6.87287495277673e-05,
2823
+ "loss": 0.6949755191802979,
2824
+ "step": 3870
2825
+ },
2826
+ {
2827
+ "epoch": 0.6963232160082554,
2828
+ "grad_norm": 1.1558499336242676,
2829
+ "learning_rate": 6.863430298451077e-05,
2830
+ "loss": 0.7398390769958496,
2831
+ "step": 3880
2832
+ },
2833
+ {
2834
+ "epoch": 0.6981178634721942,
2835
+ "grad_norm": 1.3961721658706665,
2836
+ "learning_rate": 6.853985644125426e-05,
2837
+ "loss": 0.8797501564025879,
2838
+ "step": 3890
2839
+ },
2840
+ {
2841
+ "epoch": 0.6999125109361329,
2842
+ "grad_norm": 4.877803325653076,
2843
+ "learning_rate": 6.844540989799773e-05,
2844
+ "loss": 0.9983924865722656,
2845
+ "step": 3900
2846
+ },
2847
+ {
2848
+ "epoch": 0.7017071584000718,
2849
+ "grad_norm": 0.7820862531661987,
2850
+ "learning_rate": 6.835096335474122e-05,
2851
+ "loss": 0.7368104934692383,
2852
+ "step": 3910
2853
+ },
2854
+ {
2855
+ "epoch": 0.7035018058640106,
2856
+ "grad_norm": 0.8871352076530457,
2857
+ "learning_rate": 6.82565168114847e-05,
2858
+ "loss": 0.6663483142852783,
2859
+ "step": 3920
2860
+ },
2861
+ {
2862
+ "epoch": 0.7052964533279494,
2863
+ "grad_norm": 1.1577374935150146,
2864
+ "learning_rate": 6.816207026822818e-05,
2865
+ "loss": 0.7413091659545898,
2866
+ "step": 3930
2867
+ },
2868
+ {
2869
+ "epoch": 0.7070911007918882,
2870
+ "grad_norm": 1.3942395448684692,
2871
+ "learning_rate": 6.806762372497168e-05,
2872
+ "loss": 0.84088134765625,
2873
+ "step": 3940
2874
+ },
2875
+ {
2876
+ "epoch": 0.708885748255827,
2877
+ "grad_norm": 3.1324944496154785,
2878
+ "learning_rate": 6.797317718171515e-05,
2879
+ "loss": 0.8465492248535156,
2880
+ "step": 3950
2881
+ },
2882
+ {
2883
+ "epoch": 0.7106803957197658,
2884
+ "grad_norm": 0.7963802814483643,
2885
+ "learning_rate": 6.787873063845863e-05,
2886
+ "loss": 0.7199924468994141,
2887
+ "step": 3960
2888
+ },
2889
+ {
2890
+ "epoch": 0.7124750431837046,
2891
+ "grad_norm": 0.9776906967163086,
2892
+ "learning_rate": 6.778428409520212e-05,
2893
+ "loss": 0.6692405700683594,
2894
+ "step": 3970
2895
+ },
2896
+ {
2897
+ "epoch": 0.7142696906476435,
2898
+ "grad_norm": 1.1714221239089966,
2899
+ "learning_rate": 6.76898375519456e-05,
2900
+ "loss": 0.7462035179138183,
2901
+ "step": 3980
2902
+ },
2903
+ {
2904
+ "epoch": 0.7160643381115822,
2905
+ "grad_norm": 1.5628330707550049,
2906
+ "learning_rate": 6.75953910086891e-05,
2907
+ "loss": 0.8628827095031738,
2908
+ "step": 3990
2909
+ },
2910
+ {
2911
+ "epoch": 0.717858985575521,
2912
+ "grad_norm": 3.96386456489563,
2913
+ "learning_rate": 6.750094446543257e-05,
2914
+ "loss": 0.9594356536865234,
2915
+ "step": 4000
2916
+ }
2917
+ ],
2918
+ "logging_steps": 10,
2919
+ "max_steps": 11146,
2920
+ "num_input_tokens_seen": 0,
2921
+ "num_train_epochs": 2,
2922
+ "save_steps": 1000,
2923
+ "stateful_callbacks": {
2924
+ "TrainerControl": {
2925
+ "args": {
2926
+ "should_epoch_stop": false,
2927
+ "should_evaluate": false,
2928
+ "should_log": false,
2929
+ "should_save": true,
2930
+ "should_training_stop": false
2931
+ },
2932
+ "attributes": {}
2933
+ }
2934
+ },
2935
+ "total_flos": 4.069196406696691e+17,
2936
+ "train_batch_size": 2,
2937
+ "trial_name": null,
2938
+ "trial_params": null
2939
+ }
qwen3.5-2b-50pct-masked-weighted/{checkpoint-1000 → checkpoint-4000}/training_args.bin RENAMED
File without changes
qwen3.5-2b-50pct-masked-weighted/tb/events.out.tfevents.1790426135.b0aacb224392.4711.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca83396f2c9c3d6e50c8317c6f4f2698091829f0ca98b657c09deee820a7d347
3
- size 75799
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57798f99534e88c7e2d822d14a0858ac3d6d0a48b6204d86b151751c80a42915
3
+ size 98547
qwen3.5-2b-50pct-masked-weighted/test_eval_entity/metrics.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "wer": 0.5446355184082151,
3
- "wer_zwnj_normalized": 0.5383588988161954,
4
- "exact_match": 0.0009900990099009901,
5
- "fix_rate": 0.2468610076087297,
6
- "preservation_rate": 0.6939617178703554,
7
- "targeted_score": 0.47041136273954254,
8
- "fix_rate_lenient": 0.24013136288998357,
9
- "preservation_rate_lenient": 0.6974968887520367,
10
- "targeted_score_lenient": 0.4688141258210102,
11
- "fix_rate_recoverable": 0.2436261569819895,
12
  "unrecoverable_targets": 523,
13
- "hallucination_rate": 0.12772277227722773,
14
  "n_examples": 1010
15
  }
 
1
  {
2
+ "wer": 0.5756076472283601,
3
+ "wer_zwnj_normalized": 0.5715032930903812,
4
+ "exact_match": 0.0,
5
+ "fix_rate": 0.23646554153489682,
6
+ "preservation_rate": 0.6708058549139456,
7
+ "targeted_score": 0.45363569822442124,
8
+ "fix_rate_lenient": 0.22922824302134648,
9
+ "preservation_rate_lenient": 0.6731650051961049,
10
+ "targeted_score_lenient": 0.4511966241087257,
11
+ "fix_rate_recoverable": 0.23269956895111438,
12
  "unrecoverable_targets": 523,
13
+ "hallucination_rate": 0.13267326732673268,
14
  "n_examples": 1010
15
  }
qwen3.5-2b-50pct-masked-weighted/test_eval_entity/predictions.jsonl CHANGED
The diff for this file is too large to render. See raw diff
 
qwen3.5-2b-50pct-masked-weighted/test_eval_typo/metrics.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "wer": 0.5629164432871256,
3
- "wer_zwnj_normalized": 0.5535472671108729,
4
- "exact_match": 0.002793296089385475,
5
- "fix_rate": 0.33365645599069405,
6
- "preservation_rate": 0.7954311586746244,
7
- "targeted_score": 0.5645438073326592,
8
- "fix_rate_lenient": 0.32995239080935623,
9
- "preservation_rate_lenient": 0.799349526795394,
10
- "targeted_score_lenient": 0.5646509588023751,
11
- "fix_rate_recoverable": 0.3343841950399327,
12
  "unrecoverable_targets": 73,
13
- "hallucination_rate": 0.18156424581005587,
14
  "n_examples": 358
15
  }
 
1
  {
2
+ "wer": 0.5879860100584616,
3
+ "wer_zwnj_normalized": 0.5820122029052105,
4
+ "exact_match": 0.0,
5
+ "fix_rate": 0.31737107405971304,
6
+ "preservation_rate": 0.786258195395878,
7
+ "targeted_score": 0.5518146347277956,
8
+ "fix_rate_lenient": 0.31215069343821156,
9
+ "preservation_rate_lenient": 0.7890943186146678,
10
+ "targeted_score_lenient": 0.5506225060264397,
11
+ "fix_rate_recoverable": 0.316099201345103,
12
  "unrecoverable_targets": 73,
13
+ "hallucination_rate": 0.17039106145251395,
14
  "n_examples": 358
15
  }
qwen3.5-2b-50pct-masked-weighted/test_eval_typo/predictions.jsonl CHANGED
The diff for this file is too large to render. See raw diff