Theoreticallyhugo commited on
Commit
2a57c1b
1 Parent(s): 3539209

Training in progress, epoch 12, checkpoint

Browse files
checkpoint-492/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f68f549d3574ddc833a1bf0e5882e856c15052aa9fd527f955a2646cb3225ed
3
  size 592324828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6196e4ea61870f43126a6769d53a20551c226fff9c3b82c6c1b2f1e42d270778
3
  size 592324828
checkpoint-492/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3facc874d5ca280780eb6392396af2afb55fab003abdca8ae572d7e97cfc1329
3
  size 1014657786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e11cb045821a3d25c10f6c62443440986d45e50175ff61f4590568813b0e76
3
  size 1014657786
checkpoint-492/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e53e706c63ba0c275c9b6332ceadb76c337b40858f3ddadb0ab10622a334eb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c189466643703424c77db24cb1c70bb1b76b65752ddeeaa3d7bb424b6ea3dcb
3
  size 14244
checkpoint-492/trainer_state.json CHANGED
@@ -11,540 +11,540 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
- "f1-score": 0.4643135219309629,
15
- "precision": 0.5337112171837709,
16
- "recall": 0.4108865411116215,
17
- "support": 4354.0
18
  },
19
  "eval_MajorClaim": {
20
- "f1-score": 0.7490950657268052,
21
- "precision": 0.6779310344827586,
22
- "recall": 0.8369518944231588,
23
- "support": 2349.0
24
  },
25
  "eval_O": {
26
- "f1-score": 0.9980494407069782,
27
- "precision": 0.9961064759634486,
28
- "recall": 1.0,
29
- "support": 12536.0
30
  },
31
  "eval_Premise": {
32
- "f1-score": 0.8811786372007365,
33
- "precision": 0.868321718931475,
34
- "recall": 0.8944220128607746,
35
- "support": 13374.0
36
  },
37
- "eval_accuracy": 0.8663109802839358,
38
- "eval_loss": 0.32735684514045715,
39
  "eval_macro avg": {
40
- "f1-score": 0.7731591663913707,
41
- "precision": 0.7690176116403633,
42
- "recall": 0.7855651120988888,
43
- "support": 32613.0
44
- },
45
- "eval_runtime": 1.4205,
46
- "eval_samples_per_second": 57.022,
47
- "eval_steps_per_second": 7.744,
48
  "eval_weighted avg": {
49
- "f1-score": 0.8609350954068932,
50
- "precision": 0.8590551035257559,
51
- "recall": 0.8663109802839358,
52
- "support": 32613.0
53
  },
54
  "step": 41
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
- "f1-score": 0.5737245829782053,
60
- "precision": 0.6105208603265094,
61
- "recall": 0.5411116214974736,
62
- "support": 4354.0
63
  },
64
  "eval_MajorClaim": {
65
- "f1-score": 0.8465994421797898,
66
- "precision": 0.8533737024221453,
67
- "recall": 0.8399318859088974,
68
- "support": 2349.0
69
  },
70
  "eval_O": {
71
- "f1-score": 0.9996808425756004,
72
- "precision": 0.9999201915403033,
73
- "recall": 0.9994416081684748,
74
- "support": 12536.0
75
  },
76
  "eval_Premise": {
77
- "f1-score": 0.8958440225756799,
78
- "precision": 0.8785221391604371,
79
- "recall": 0.9138627187079408,
80
- "support": 13374.0
81
  },
82
- "eval_accuracy": 0.8916689663631068,
83
- "eval_loss": 0.24866953492164612,
84
  "eval_macro avg": {
85
- "f1-score": 0.8289622225773189,
86
- "precision": 0.8355842233623487,
87
- "recall": 0.8235869585706966,
88
- "support": 32613.0
89
- },
90
- "eval_runtime": 1.4275,
91
- "eval_samples_per_second": 56.744,
92
- "eval_steps_per_second": 7.706,
93
  "eval_weighted avg": {
94
- "f1-score": 0.8892060198210008,
95
- "precision": 0.8875950468565349,
96
- "recall": 0.8916689663631068,
97
- "support": 32613.0
98
  },
99
  "step": 82
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
- "f1-score": 0.6284023668639053,
105
- "precision": 0.648193359375,
106
- "recall": 0.6097841065686724,
107
- "support": 4354.0
108
  },
109
  "eval_MajorClaim": {
110
- "f1-score": 0.8758085381630012,
111
- "precision": 0.8872870249017037,
112
- "recall": 0.8646232439335888,
113
- "support": 2349.0
114
  },
115
  "eval_O": {
116
- "f1-score": 0.9998803589232302,
117
- "precision": 0.9997607464710104,
118
- "recall": 1.0,
119
- "support": 12536.0
120
  },
121
  "eval_Premise": {
122
- "f1-score": 0.9024128884454791,
123
- "precision": 0.8920300971583023,
124
- "recall": 0.9130402273067145,
125
- "support": 13374.0
126
  },
127
- "eval_accuracy": 0.9024928709410358,
128
- "eval_loss": 0.2409481257200241,
129
  "eval_macro avg": {
130
- "f1-score": 0.8516260380989039,
131
- "precision": 0.8568178069765041,
132
- "recall": 0.8468618944522439,
133
- "support": 32613.0
134
- },
135
- "eval_runtime": 1.419,
136
- "eval_samples_per_second": 57.082,
137
- "eval_steps_per_second": 7.752,
138
  "eval_weighted avg": {
139
- "f1-score": 0.9013800727011249,
140
- "precision": 0.900545253284536,
141
- "recall": 0.9024928709410358,
142
- "support": 32613.0
143
  },
144
  "step": 123
145
  },
146
  {
147
  "epoch": 4.0,
148
  "eval_Claim": {
149
- "f1-score": 0.6302973542495903,
150
- "precision": 0.6427889207258835,
151
- "recall": 0.6182820395039045,
152
- "support": 4354.0
153
  },
154
  "eval_MajorClaim": {
155
- "f1-score": 0.8868001634654679,
156
- "precision": 0.8526522593320236,
157
- "recall": 0.9237973605789698,
158
- "support": 2349.0
159
  },
160
  "eval_O": {
161
- "f1-score": 0.999680893498205,
162
- "precision": 0.9997606510292005,
163
- "recall": 0.9996011486917677,
164
- "support": 12536.0
165
  },
166
  "eval_Premise": {
167
- "f1-score": 0.8995508982035928,
168
- "precision": 0.9004945301963135,
169
- "recall": 0.8986092418124719,
170
- "support": 13374.0
171
  },
172
- "eval_accuracy": 0.9018182933186153,
173
- "eval_loss": 0.23009340465068817,
174
  "eval_macro avg": {
175
- "f1-score": 0.854082327354214,
176
- "precision": 0.8489240903208553,
177
- "recall": 0.8600724476467785,
178
- "support": 32613.0
179
- },
180
- "eval_runtime": 1.4216,
181
- "eval_samples_per_second": 56.979,
182
- "eval_steps_per_second": 7.738,
183
  "eval_weighted avg": {
184
- "f1-score": 0.9011744291494633,
185
- "precision": 0.9008001866175751,
186
- "recall": 0.9018182933186153,
187
- "support": 32613.0
188
  },
189
  "step": 164
190
  },
191
  {
192
  "epoch": 5.0,
193
  "eval_Claim": {
194
- "f1-score": 0.6072607260726073,
195
- "precision": 0.6787741203178207,
196
- "recall": 0.5493798805695912,
197
- "support": 4354.0
198
  },
199
  "eval_MajorClaim": {
200
- "f1-score": 0.875,
201
- "precision": 0.9056947608200455,
202
- "recall": 0.8463175819497658,
203
- "support": 2349.0
204
  },
205
  "eval_O": {
206
- "f1-score": 0.9998404722022812,
207
- "precision": 0.9997607273887382,
208
- "recall": 0.9999202297383536,
209
- "support": 12536.0
210
  },
211
  "eval_Premise": {
212
- "f1-score": 0.9058781103498017,
213
- "precision": 0.8748955140707718,
214
- "recall": 0.9391356363092568,
215
- "support": 13374.0
216
  },
217
- "eval_accuracy": 0.903780700947475,
218
- "eval_loss": 0.263094037771225,
219
  "eval_macro avg": {
220
- "f1-score": 0.8469948271561726,
221
- "precision": 0.864781280649344,
222
- "recall": 0.8336883321417418,
223
- "support": 32613.0
224
- },
225
- "eval_runtime": 1.4217,
226
- "eval_samples_per_second": 56.974,
227
- "eval_steps_per_second": 7.737,
228
  "eval_weighted avg": {
229
- "f1-score": 0.899905013603967,
230
- "precision": 0.8989271945775551,
231
- "recall": 0.903780700947475,
232
- "support": 32613.0
233
  },
234
  "step": 205
235
  },
236
  {
237
  "epoch": 6.0,
238
  "eval_Claim": {
239
- "f1-score": 0.57247396566282,
240
- "precision": 0.7390988372093024,
241
- "recall": 0.467156637574644,
242
- "support": 4354.0
243
  },
244
  "eval_MajorClaim": {
245
- "f1-score": 0.8933023452355799,
246
- "precision": 0.886744966442953,
247
- "recall": 0.8999574286930608,
248
- "support": 2349.0
249
  },
250
  "eval_O": {
251
- "f1-score": 0.9998005982053838,
252
- "precision": 0.9996809952946806,
253
- "recall": 0.9999202297383536,
254
- "support": 12536.0
255
  },
256
  "eval_Premise": {
257
- "f1-score": 0.9065413958745407,
258
- "precision": 0.8590842147543178,
259
- "recall": 0.9595483774487812,
260
- "support": 13374.0
261
  },
262
- "eval_accuracy": 0.9050378683347131,
263
- "eval_loss": 0.28428906202316284,
264
  "eval_macro avg": {
265
- "f1-score": 0.8430295762445812,
266
- "precision": 0.8711522534253133,
267
- "recall": 0.8316456683637099,
268
- "support": 32613.0
269
- },
270
- "eval_runtime": 1.4177,
271
- "eval_samples_per_second": 57.135,
272
- "eval_steps_per_second": 7.759,
273
  "eval_weighted avg": {
274
- "f1-score": 0.896835733694634,
275
- "precision": 0.8991013862116997,
276
- "recall": 0.9050378683347131,
277
- "support": 32613.0
278
  },
279
  "step": 246
280
  },
281
  {
282
  "epoch": 7.0,
283
  "eval_Claim": {
284
- "f1-score": 0.6294631710362047,
285
- "precision": 0.6895514223194749,
286
- "recall": 0.5790078089113458,
287
- "support": 4354.0
288
  },
289
  "eval_MajorClaim": {
290
- "f1-score": 0.8833069620253163,
291
- "precision": 0.8248984115256742,
292
- "recall": 0.9506172839506173,
293
- "support": 2349.0
294
  },
295
  "eval_O": {
296
- "f1-score": 0.9995215311004785,
297
- "precision": 0.9992028061224489,
298
- "recall": 0.9998404594767071,
299
- "support": 12536.0
300
  },
301
  "eval_Premise": {
302
- "f1-score": 0.9074593796159526,
303
- "precision": 0.8964686998394864,
304
- "recall": 0.9187228951697323,
305
- "support": 13374.0
306
  },
307
- "eval_accuracy": 0.9068469628675682,
308
- "eval_loss": 0.2983298599720001,
309
  "eval_macro avg": {
310
- "f1-score": 0.854937760944488,
311
- "precision": 0.8525303349517711,
312
- "recall": 0.8620471118771007,
313
- "support": 32613.0
314
- },
315
- "eval_runtime": 1.4145,
316
- "eval_samples_per_second": 57.265,
317
- "eval_steps_per_second": 7.777,
318
  "eval_weighted avg": {
319
- "f1-score": 0.9039933265062536,
320
- "precision": 0.9031788559978264,
321
- "recall": 0.9068469628675682,
322
- "support": 32613.0
323
  },
324
  "step": 287
325
  },
326
  {
327
  "epoch": 8.0,
328
  "eval_Claim": {
329
- "f1-score": 0.6635588402501421,
330
- "precision": 0.6570592208961945,
331
- "recall": 0.6701883325677538,
332
- "support": 4354.0
333
  },
334
  "eval_MajorClaim": {
335
- "f1-score": 0.9037098791162985,
336
- "precision": 0.8852592895059208,
337
- "recall": 0.9229459344401874,
338
- "support": 2349.0
339
  },
340
  "eval_O": {
341
- "f1-score": 0.9997208374875374,
342
- "precision": 0.9996012441183507,
343
- "recall": 0.9998404594767071,
344
- "support": 12536.0
345
  },
346
  "eval_Premise": {
347
- "f1-score": 0.9033812787107464,
348
- "precision": 0.9098907766990292,
349
- "recall": 0.8969642590100194,
350
- "support": 13374.0
351
  },
352
- "eval_accuracy": 0.9081041302548064,
353
- "eval_loss": 0.3042994737625122,
354
  "eval_macro avg": {
355
- "f1-score": 0.8675927088911811,
356
- "precision": 0.8629526328048738,
357
- "recall": 0.8724847463736669,
358
- "support": 32613.0
359
- },
360
- "eval_runtime": 1.4198,
361
- "eval_samples_per_second": 57.05,
362
- "eval_steps_per_second": 7.747,
363
  "eval_weighted avg": {
364
- "f1-score": 0.9084190763411705,
365
- "precision": 0.9088458701337473,
366
- "recall": 0.9081041302548064,
367
- "support": 32613.0
368
  },
369
  "step": 328
370
  },
371
  {
372
  "epoch": 9.0,
373
  "eval_Claim": {
374
- "f1-score": 0.6706725213773977,
375
- "precision": 0.6748837209302325,
376
- "recall": 0.6665135507579237,
377
- "support": 4354.0
378
  },
379
  "eval_MajorClaim": {
380
- "f1-score": 0.9129511677282377,
381
- "precision": 0.9106310885218127,
382
- "recall": 0.9152830991911451,
383
- "support": 2349.0
384
  },
385
  "eval_O": {
386
- "f1-score": 0.9996809444045626,
387
- "precision": 0.9996012123145638,
388
- "recall": 0.9997606892150607,
389
- "support": 12536.0
390
  },
391
  "eval_Premise": {
392
- "f1-score": 0.9052560848140958,
393
- "precision": 0.9039063664827792,
394
- "recall": 0.9066098399880365,
395
- "support": 13374.0
396
  },
397
- "eval_accuracy": 0.910986416459694,
398
- "eval_loss": 0.3104316294193268,
399
  "eval_macro avg": {
400
- "f1-score": 0.8721401795810735,
401
- "precision": 0.8722555970623471,
402
- "recall": 0.8720417947880416,
403
- "support": 32613.0
404
- },
405
- "eval_runtime": 1.4235,
406
- "eval_samples_per_second": 56.901,
407
- "eval_steps_per_second": 7.727,
408
  "eval_weighted avg": {
409
- "f1-score": 0.9107878958829343,
410
- "precision": 0.9105988621342419,
411
- "recall": 0.910986416459694,
412
- "support": 32613.0
413
  },
414
  "step": 369
415
  },
416
  {
417
  "epoch": 10.0,
418
  "eval_Claim": {
419
- "f1-score": 0.6484411354118194,
420
- "precision": 0.657001414427157,
421
- "recall": 0.6401010564997703,
422
- "support": 4354.0
423
  },
424
  "eval_MajorClaim": {
425
- "f1-score": 0.8997963340122199,
426
- "precision": 0.8625536899648575,
427
- "recall": 0.9404001702852277,
428
- "support": 2349.0
429
  },
430
  "eval_O": {
431
- "f1-score": 0.9997607083034219,
432
- "precision": 0.999680969851651,
433
- "recall": 0.9998404594767071,
434
- "support": 12536.0
435
  },
436
  "eval_Premise": {
437
- "f1-score": 0.9021992043833972,
438
- "precision": 0.905666063893912,
439
- "recall": 0.898758785703604,
440
- "support": 13374.0
441
  },
442
- "eval_accuracy": 0.9060803973875449,
443
- "eval_loss": 0.3316749632358551,
444
  "eval_macro avg": {
445
- "f1-score": 0.8625493455277146,
446
- "precision": 0.8562255345343944,
447
- "recall": 0.8697751179913272,
448
- "support": 32613.0
449
- },
450
- "eval_runtime": 1.4233,
451
- "eval_samples_per_second": 56.909,
452
- "eval_steps_per_second": 7.728,
453
  "eval_weighted avg": {
454
- "f1-score": 0.9056494861218845,
455
- "precision": 0.905500915362609,
456
- "recall": 0.9060803973875449,
457
- "support": 32613.0
458
  },
459
  "step": 410
460
  },
461
  {
462
  "epoch": 11.0,
463
  "eval_Claim": {
464
- "f1-score": 0.6478906714200832,
465
- "precision": 0.6712632356562424,
466
- "recall": 0.6260909508497933,
467
- "support": 4354.0
468
  },
469
  "eval_MajorClaim": {
470
- "f1-score": 0.8952419848887073,
471
- "precision": 0.8602825745682888,
472
- "recall": 0.9331630481055768,
473
- "support": 2349.0
474
  },
475
  "eval_O": {
476
- "f1-score": 0.9997607083034219,
477
- "precision": 0.999680969851651,
478
- "recall": 0.9998404594767071,
479
- "support": 12536.0
480
  },
481
  "eval_Premise": {
482
- "f1-score": 0.9058867362146051,
483
- "precision": 0.9027922174365067,
484
- "recall": 0.9090025422461493,
485
- "support": 13374.0
486
  },
487
- "eval_accuracy": 0.9078894919203998,
488
- "eval_loss": 0.3783251941204071,
489
  "eval_macro avg": {
490
- "f1-score": 0.8621950252067043,
491
- "precision": 0.8585047493781722,
492
- "recall": 0.8670242501695566,
493
- "support": 32613.0
494
- },
495
- "eval_runtime": 1.4193,
496
- "eval_samples_per_second": 57.069,
497
- "eval_steps_per_second": 7.75,
498
  "eval_weighted avg": {
499
- "f1-score": 0.9067601525554976,
500
- "precision": 0.9060628476302188,
501
- "recall": 0.9078894919203998,
502
- "support": 32613.0
503
  },
504
  "step": 451
505
  },
506
  {
507
  "epoch": 12.0,
508
  "eval_Claim": {
509
- "f1-score": 0.6313421644588852,
510
- "precision": 0.6924342105263158,
511
- "recall": 0.5801561782269178,
512
- "support": 4354.0
513
  },
514
  "eval_MajorClaim": {
515
- "f1-score": 0.9006842214389384,
516
- "precision": 0.8779304769603881,
517
- "recall": 0.9246487867177522,
518
- "support": 2349.0
519
  },
520
  "eval_O": {
521
- "f1-score": 0.9998005982053838,
522
- "precision": 0.9996809952946806,
523
- "recall": 0.9999202297383536,
524
- "support": 12536.0
525
  },
526
  "eval_Premise": {
527
- "f1-score": 0.9077069457659372,
528
- "precision": 0.8889048165137615,
529
- "recall": 0.927321668909825,
530
- "support": 13374.0
531
  },
532
- "eval_accuracy": 0.908686720019624,
533
- "eval_loss": 0.4068906903266907,
534
  "eval_macro avg": {
535
- "f1-score": 0.8598834824672862,
536
- "precision": 0.8647376248237866,
537
- "recall": 0.8580117158982121,
538
- "support": 32613.0
539
- },
540
- "eval_runtime": 1.418,
541
- "eval_samples_per_second": 57.122,
542
- "eval_steps_per_second": 7.757,
543
  "eval_weighted avg": {
544
- "f1-score": 0.905704596694275,
545
- "precision": 0.9044654345224509,
546
- "recall": 0.908686720019624,
547
- "support": 32613.0
548
  },
549
  "step": 492
550
  }
@@ -554,7 +554,7 @@
554
  "num_input_tokens_seen": 0,
555
  "num_train_epochs": 16,
556
  "save_steps": 500,
557
- "total_flos": 1720106206408800.0,
558
  "train_batch_size": 8,
559
  "trial_name": null,
560
  "trial_params": null
 
11
  {
12
  "epoch": 1.0,
13
  "eval_Claim": {
14
+ "f1-score": 0.5675116962245675,
15
+ "precision": 0.5627967198964178,
16
+ "recall": 0.5723063418915953,
17
+ "support": 4557.0
18
  },
19
  "eval_MajorClaim": {
20
+ "f1-score": 0.7021748779405237,
21
+ "precision": 0.7071971390254805,
22
+ "recall": 0.6972234464521816,
23
+ "support": 2269.0
24
  },
25
  "eval_O": {
26
+ "f1-score": 0.9884124087591241,
27
+ "precision": 0.9985252096967463,
28
+ "recall": 0.9785023936410442,
29
+ "support": 11071.0
30
  },
31
  "eval_Premise": {
32
+ "f1-score": 0.8946486578902376,
33
+ "precision": 0.8892665352457345,
34
+ "recall": 0.900096325856612,
35
+ "support": 14534.0
36
  },
37
+ "eval_accuracy": 0.8666091085689618,
38
+ "eval_loss": 0.35281190276145935,
39
  "eval_macro avg": {
40
+ "f1-score": 0.7881869102036132,
41
+ "precision": 0.7894464009660948,
42
+ "recall": 0.7870321269603583,
43
+ "support": 32431.0
44
+ },
45
+ "eval_runtime": 1.4161,
46
+ "eval_samples_per_second": 56.493,
47
+ "eval_steps_per_second": 7.062,
48
  "eval_weighted avg": {
49
+ "f1-score": 0.8672234272421873,
50
+ "precision": 0.8679524954775053,
51
+ "recall": 0.8666091085689618,
52
+ "support": 32431.0
53
  },
54
  "step": 41
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
+ "f1-score": 0.5799535003874967,
60
+ "precision": 0.7048665620094191,
61
+ "recall": 0.4926486723721747,
62
+ "support": 4557.0
63
  },
64
  "eval_MajorClaim": {
65
+ "f1-score": 0.8542402826855124,
66
+ "precision": 0.8561310314298363,
67
+ "recall": 0.8523578669017188,
68
+ "support": 2269.0
69
  },
70
  "eval_O": {
71
+ "f1-score": 0.9957381211461733,
72
+ "precision": 0.9996358670914884,
73
+ "recall": 0.9918706530575377,
74
+ "support": 11071.0
75
  },
76
  "eval_Premise": {
77
+ "f1-score": 0.9081739586062353,
78
+ "precision": 0.8665166854143233,
79
+ "recall": 0.954038805559378,
80
+ "support": 14534.0
81
  },
82
+ "eval_accuracy": 0.8950078628472757,
83
+ "eval_loss": 0.266658216714859,
84
  "eval_macro avg": {
85
+ "f1-score": 0.8345264657063545,
86
+ "precision": 0.8567875364862668,
87
+ "recall": 0.8227289994727023,
88
+ "support": 32431.0
89
+ },
90
+ "eval_runtime": 1.4081,
91
+ "eval_samples_per_second": 56.815,
92
+ "eval_steps_per_second": 7.102,
93
  "eval_weighted avg": {
94
+ "f1-score": 0.8881729319562012,
95
+ "precision": 0.8885190226564973,
96
+ "recall": 0.8950078628472757,
97
+ "support": 32431.0
98
  },
99
  "step": 82
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
+ "f1-score": 0.6576058546785155,
105
+ "precision": 0.6279952076677316,
106
+ "recall": 0.6901470265525566,
107
+ "support": 4557.0
108
  },
109
  "eval_MajorClaim": {
110
+ "f1-score": 0.836495761001211,
111
+ "precision": 0.7716945996275605,
112
+ "recall": 0.9131776112825033,
113
+ "support": 2269.0
114
  },
115
  "eval_O": {
116
+ "f1-score": 0.997964077274578,
117
+ "precision": 0.9997280638143582,
118
+ "recall": 0.9962063047601842,
119
+ "support": 11071.0
120
  },
121
  "eval_Premise": {
122
+ "f1-score": 0.9064447592067989,
123
+ "precision": 0.9338246023639282,
124
+ "recall": 0.8806247419843126,
125
+ "support": 14534.0
126
  },
127
+ "eval_accuracy": 0.8955937220560575,
128
+ "eval_loss": 0.2511727809906006,
129
  "eval_macro avg": {
130
+ "f1-score": 0.8496276130402758,
131
+ "precision": 0.8333106183683946,
132
+ "recall": 0.8700389211448892,
133
+ "support": 32431.0
134
+ },
135
+ "eval_runtime": 1.4062,
136
+ "eval_samples_per_second": 56.892,
137
+ "eval_steps_per_second": 7.112,
138
  "eval_weighted avg": {
139
+ "f1-score": 0.8978276091178259,
140
+ "precision": 0.9020056542549684,
141
+ "recall": 0.8955937220560575,
142
+ "support": 32431.0
143
  },
144
  "step": 123
145
  },
146
  {
147
  "epoch": 4.0,
148
  "eval_Claim": {
149
+ "f1-score": 0.6724791508718727,
150
+ "precision": 0.5918265221017515,
151
+ "recall": 0.7785824007022164,
152
+ "support": 4557.0
153
  },
154
  "eval_MajorClaim": {
155
+ "f1-score": 0.9030544488711819,
156
+ "precision": 0.9070698088039129,
157
+ "recall": 0.8990744821507272,
158
+ "support": 2269.0
159
  },
160
  "eval_O": {
161
+ "f1-score": 0.9991864039052614,
162
+ "precision": 1.0,
163
+ "recall": 0.9983741306115076,
164
+ "support": 11071.0
165
  },
166
  "eval_Premise": {
167
+ "f1-score": 0.8886077779384126,
168
+ "precision": 0.9359677173747526,
169
+ "recall": 0.8458098252373745,
170
+ "support": 14534.0
171
  },
172
+ "eval_accuracy": 0.8921710708889643,
173
+ "eval_loss": 0.24931207299232483,
174
  "eval_macro avg": {
175
+ "f1-score": 0.8658319453966822,
176
+ "precision": 0.8587160120701043,
177
+ "recall": 0.8804602096754564,
178
+ "support": 32431.0
179
+ },
180
+ "eval_runtime": 1.4073,
181
+ "eval_samples_per_second": 56.847,
182
+ "eval_steps_per_second": 7.106,
183
  "eval_weighted avg": {
184
+ "f1-score": 0.8969978155839744,
185
+ "precision": 0.907448110194518,
186
+ "recall": 0.8921710708889643,
187
+ "support": 32431.0
188
  },
189
  "step": 164
190
  },
191
  {
192
  "epoch": 5.0,
193
  "eval_Claim": {
194
+ "f1-score": 0.6831918505942275,
195
+ "precision": 0.7054698457223001,
196
+ "recall": 0.6622778143515471,
197
+ "support": 4557.0
198
  },
199
  "eval_MajorClaim": {
200
+ "f1-score": 0.9057110862262038,
201
+ "precision": 0.9207650273224044,
202
+ "recall": 0.8911414720141031,
203
+ "support": 2269.0
204
  },
205
  "eval_O": {
206
+ "f1-score": 0.9989149109322725,
207
+ "precision": 1.0,
208
+ "recall": 0.9978321741486768,
209
+ "support": 11071.0
210
  },
211
  "eval_Premise": {
212
+ "f1-score": 0.9169270479554409,
213
+ "precision": 0.9053655264922871,
214
+ "recall": 0.9287876702903537,
215
+ "support": 14534.0
216
  },
217
+ "eval_accuracy": 0.912275292158737,
218
+ "eval_loss": 0.22767245769500732,
219
  "eval_macro avg": {
220
+ "f1-score": 0.8761862239270362,
221
+ "precision": 0.8829000998842478,
222
+ "recall": 0.8700097827011701,
223
+ "support": 32431.0
224
+ },
225
+ "eval_runtime": 1.4166,
226
+ "eval_samples_per_second": 56.472,
227
+ "eval_steps_per_second": 7.059,
228
  "eval_weighted avg": {
229
+ "f1-score": 0.9112876078974042,
230
+ "precision": 0.9106603094566913,
231
+ "recall": 0.912275292158737,
232
+ "support": 32431.0
233
  },
234
  "step": 205
235
  },
236
  {
237
  "epoch": 6.0,
238
  "eval_Claim": {
239
+ "f1-score": 0.7047057585008949,
240
+ "precision": 0.6772561715904493,
241
+ "recall": 0.7344744349352644,
242
+ "support": 4557.0
243
  },
244
  "eval_MajorClaim": {
245
+ "f1-score": 0.9053571428571427,
246
+ "precision": 0.9172320217096337,
247
+ "recall": 0.8937858087263112,
248
+ "support": 2269.0
249
  },
250
  "eval_O": {
251
+ "f1-score": 0.9990960043391791,
252
+ "precision": 0.9999095268252963,
253
+ "recall": 0.998283804534369,
254
+ "support": 11071.0
255
  },
256
  "eval_Premise": {
257
+ "f1-score": 0.9127577454014394,
258
+ "precision": 0.9226713532513181,
259
+ "recall": 0.9030549057382689,
260
+ "support": 14534.0
261
  },
262
+ "eval_accuracy": 0.9112269125219697,
263
+ "eval_loss": 0.2558422088623047,
264
  "eval_macro avg": {
265
+ "f1-score": 0.880479162774664,
266
+ "precision": 0.8792672683441743,
267
+ "recall": 0.8823997384835534,
268
+ "support": 32431.0
269
+ },
270
+ "eval_runtime": 1.4147,
271
+ "eval_samples_per_second": 56.547,
272
+ "eval_steps_per_second": 7.068,
273
  "eval_weighted avg": {
274
+ "f1-score": 0.9124791845559805,
275
+ "precision": 0.9141734652287734,
276
+ "recall": 0.9112269125219697,
277
+ "support": 32431.0
278
  },
279
  "step": 246
280
  },
281
  {
282
  "epoch": 7.0,
283
  "eval_Claim": {
284
+ "f1-score": 0.671239246686817,
285
+ "precision": 0.7137206427688504,
286
+ "recall": 0.6335308316875137,
287
+ "support": 4557.0
288
  },
289
  "eval_MajorClaim": {
290
+ "f1-score": 0.9053934571175951,
291
+ "precision": 0.9082039911308204,
292
+ "recall": 0.9026002644336713,
293
+ "support": 2269.0
294
  },
295
  "eval_O": {
296
+ "f1-score": 0.999186477447347,
297
+ "precision": 0.9999095431931253,
298
+ "recall": 0.998464456688646,
299
+ "support": 11071.0
300
  },
301
  "eval_Premise": {
302
+ "f1-score": 0.9147585275244849,
303
+ "precision": 0.8983152029716105,
304
+ "recall": 0.9318150543553048,
305
+ "support": 14534.0
306
  },
307
+ "eval_accuracy": 0.910610218617989,
308
+ "eval_loss": 0.2902248203754425,
309
  "eval_macro avg": {
310
+ "f1-score": 0.872644427194061,
311
+ "precision": 0.8800373450161016,
312
+ "recall": 0.8666026517912839,
313
+ "support": 32431.0
314
+ },
315
+ "eval_runtime": 1.4074,
316
+ "eval_samples_per_second": 56.842,
317
+ "eval_steps_per_second": 7.105,
318
  "eval_weighted avg": {
319
+ "f1-score": 0.9087067599584377,
320
+ "precision": 0.9077503480513693,
321
+ "recall": 0.910610218617989,
322
+ "support": 32431.0
323
  },
324
  "step": 287
325
  },
326
  {
327
  "epoch": 8.0,
328
  "eval_Claim": {
329
+ "f1-score": 0.6637626559924652,
330
+ "precision": 0.7160274320548641,
331
+ "recall": 0.618608733816107,
332
+ "support": 4557.0
333
  },
334
  "eval_MajorClaim": {
335
+ "f1-score": 0.9002159827213824,
336
+ "precision": 0.8826768318509106,
337
+ "recall": 0.9184662847069194,
338
+ "support": 2269.0
339
  },
340
  "eval_O": {
341
+ "f1-score": 0.999186477447347,
342
+ "precision": 0.9999095431931253,
343
+ "recall": 0.998464456688646,
344
+ "support": 11071.0
345
  },
346
  "eval_Premise": {
347
+ "f1-score": 0.914696744563015,
348
+ "precision": 0.8981960472211169,
349
+ "recall": 0.9318150543553048,
350
+ "support": 14534.0
351
  },
352
+ "eval_accuracy": 0.9096235083716198,
353
+ "eval_loss": 0.3177148699760437,
354
  "eval_macro avg": {
355
+ "f1-score": 0.8694654651810524,
356
+ "precision": 0.8742024635800042,
357
+ "recall": 0.8668386323917443,
358
+ "support": 32431.0
359
+ },
360
+ "eval_runtime": 1.4095,
361
+ "eval_samples_per_second": 56.758,
362
+ "eval_steps_per_second": 7.095,
363
  "eval_weighted avg": {
364
+ "f1-score": 0.9072662719450809,
365
+ "precision": 0.906235103522757,
366
+ "recall": 0.9096235083716198,
367
+ "support": 32431.0
368
  },
369
  "step": 328
370
  },
371
  {
372
  "epoch": 9.0,
373
  "eval_Claim": {
374
+ "f1-score": 0.7096774193548386,
375
+ "precision": 0.6808467741935483,
376
+ "recall": 0.7410577134079438,
377
+ "support": 4557.0
378
  },
379
  "eval_MajorClaim": {
380
+ "f1-score": 0.8967198581560283,
381
+ "precision": 0.9019170753455193,
382
+ "recall": 0.8915821947994711,
383
+ "support": 2269.0
384
  },
385
  "eval_O": {
386
+ "f1-score": 0.9995030045633218,
387
+ "precision": 0.999909600433918,
388
+ "recall": 0.9990967392286153,
389
+ "support": 11071.0
390
  },
391
  "eval_Premise": {
392
+ "f1-score": 0.9160975609756098,
393
+ "precision": 0.927996611605252,
394
+ "recall": 0.9044997935874501,
395
+ "support": 14534.0
396
  },
397
+ "eval_accuracy": 0.9129228207579168,
398
+ "eval_loss": 0.31878241896629333,
399
  "eval_macro avg": {
400
+ "f1-score": 0.8804994607624497,
401
+ "precision": 0.8776675153945594,
402
+ "recall": 0.8840591102558701,
403
+ "support": 32431.0
404
+ },
405
+ "eval_runtime": 1.4158,
406
+ "eval_samples_per_second": 56.504,
407
+ "eval_steps_per_second": 7.063,
408
  "eval_weighted avg": {
409
+ "f1-score": 0.9142091539852634,
410
+ "precision": 0.9159930478071482,
411
+ "recall": 0.9129228207579168,
412
+ "support": 32431.0
413
  },
414
  "step": 369
415
  },
416
  {
417
  "epoch": 10.0,
418
  "eval_Claim": {
419
+ "f1-score": 0.6989775051124745,
420
+ "precision": 0.6544131725062224,
421
+ "recall": 0.750054860653939,
422
+ "support": 4557.0
423
  },
424
  "eval_MajorClaim": {
425
+ "f1-score": 0.8996763754045308,
426
+ "precision": 0.8812341504649197,
427
+ "recall": 0.9189070074922874,
428
+ "support": 2269.0
429
  },
430
  "eval_O": {
431
+ "f1-score": 0.9993221564462921,
432
+ "precision": 0.9999095677337674,
433
+ "recall": 0.9987354349200614,
434
+ "support": 11071.0
435
  },
436
  "eval_Premise": {
437
+ "f1-score": 0.9087506179814958,
438
+ "precision": 0.933473592571097,
439
+ "recall": 0.885303426448328,
440
+ "support": 14534.0
441
  },
442
+ "eval_accuracy": 0.90737257562209,
443
+ "eval_loss": 0.3552992045879364,
444
  "eval_macro avg": {
445
+ "f1-score": 0.8766816637361983,
446
+ "precision": 0.8672576208190016,
447
+ "recall": 0.888250182378654,
448
+ "support": 32431.0
449
+ },
450
+ "eval_runtime": 1.4067,
451
+ "eval_samples_per_second": 56.872,
452
+ "eval_steps_per_second": 7.109,
453
  "eval_weighted avg": {
454
+ "f1-score": 0.9095582394113776,
455
+ "precision": 0.9132862117518615,
456
+ "recall": 0.90737257562209,
457
+ "support": 32431.0
458
  },
459
  "step": 410
460
  },
461
  {
462
  "epoch": 11.0,
463
  "eval_Claim": {
464
+ "f1-score": 0.7129222520107238,
465
+ "precision": 0.6971476510067114,
466
+ "recall": 0.7294272547728768,
467
+ "support": 4557.0
468
  },
469
  "eval_MajorClaim": {
470
+ "f1-score": 0.8950740004417939,
471
+ "precision": 0.8972542072630647,
472
+ "recall": 0.8929043631555752,
473
+ "support": 2269.0
474
  },
475
  "eval_O": {
476
+ "f1-score": 0.9984622342831299,
477
+ "precision": 0.999909412084428,
478
+ "recall": 0.9970192394544305,
479
+ "support": 11071.0
480
  },
481
  "eval_Premise": {
482
+ "f1-score": 0.9182698961937715,
483
+ "precision": 0.9236391479883057,
484
+ "recall": 0.9129627081326545,
485
+ "support": 14534.0
486
  },
487
+ "eval_accuracy": 0.9144645555178688,
488
+ "eval_loss": 0.3296458423137665,
489
  "eval_macro avg": {
490
+ "f1-score": 0.8811820957323547,
491
+ "precision": 0.8794876045856275,
492
+ "recall": 0.8830783913788842,
493
+ "support": 32431.0
494
+ },
495
+ "eval_runtime": 1.4103,
496
+ "eval_samples_per_second": 56.725,
497
+ "eval_steps_per_second": 7.091,
498
  "eval_weighted avg": {
499
+ "f1-score": 0.9151681932855632,
500
+ "precision": 0.9160044438952304,
501
+ "recall": 0.9144645555178688,
502
+ "support": 32431.0
503
  },
504
  "step": 451
505
  },
506
  {
507
  "epoch": 12.0,
508
  "eval_Claim": {
509
+ "f1-score": 0.7077807250221043,
510
+ "precision": 0.7129815185927411,
511
+ "recall": 0.7026552556506473,
512
+ "support": 4557.0
513
  },
514
  "eval_MajorClaim": {
515
+ "f1-score": 0.8944790739091719,
516
+ "precision": 0.9037336932073774,
517
+ "recall": 0.8854120758043191,
518
+ "support": 2269.0
519
  },
520
  "eval_O": {
521
+ "f1-score": 0.9991415533366468,
522
+ "precision": 0.9995480021695896,
523
+ "recall": 0.9987354349200614,
524
+ "support": 11071.0
525
  },
526
  "eval_Premise": {
527
+ "f1-score": 0.9209633766144781,
528
+ "precision": 0.9171613783691572,
529
+ "recall": 0.9247970276592817,
530
+ "support": 14534.0
531
  },
532
+ "eval_accuracy": 0.9160679596682186,
533
+ "eval_loss": 0.3575716018676758,
534
  "eval_macro avg": {
535
+ "f1-score": 0.8805911822206004,
536
+ "precision": 0.8833561480847163,
537
+ "recall": 0.8778999485085774,
538
+ "support": 32431.0
539
+ },
540
+ "eval_runtime": 1.4095,
541
+ "eval_samples_per_second": 56.758,
542
+ "eval_steps_per_second": 7.095,
543
  "eval_weighted avg": {
544
+ "f1-score": 0.9158431018263538,
545
+ "precision": 0.9156562528245048,
546
+ "recall": 0.9160679596682186,
547
+ "support": 32431.0
548
  },
549
  "step": 492
550
  }
 
554
  "num_input_tokens_seen": 0,
555
  "num_train_epochs": 16,
556
  "save_steps": 500,
557
+ "total_flos": 1725464792721600.0,
558
  "train_batch_size": 8,
559
  "trial_name": null,
560
  "trial_params": null
checkpoint-492/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fa0ab387f66efa2185b605999d4a743ce5870243a43ebfb649f6fb9a993302b
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a875ae3b17c481d24bf195a549c4a53e60bc990aca9336c453f8458ad25ff8f3
3
  size 4664