Theoreticallyhugo commited on
Commit
cae9601
1 Parent(s): 8e7b25b

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:bc431db88957a585280816f57e4b96ae38f064c384dba8a731417633aacd382a
3
  size 592324828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69e6ea5750d150ff1dd4ce0fc02f96f3acc47be838d2c909f35f2ad669195b9
3
  size 592324828
checkpoint-492/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:792abab89fd6bbc2028f41f1dd932b0921994ca64b5791503fe505df9851ab7a
3
  size 1014657786
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe87b27ef7dc6558599788bf7c725a37cd83a22683b28b897ec393311785eef
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": 0.3926645091693635,
15
- "precision": 0.4813399941228328,
16
- "recall": 0.33157894736842103,
17
- "support": 4940.0
18
  },
19
  "eval_MajorClaim": {
20
- "f1-score": 0.5305101700566855,
21
- "precision": 0.41758530183727033,
22
- "recall": 0.7271480804387569,
23
- "support": 2188.0
24
  },
25
  "eval_O": {
26
- "f1-score": 0.8568685802054334,
27
- "precision": 0.8614998552263295,
28
- "recall": 0.8522868328081734,
29
- "support": 10473.0
30
  },
31
  "eval_Premise": {
32
- "f1-score": 0.8535428122545169,
33
- "precision": 0.8528192892126083,
34
- "recall": 0.8542675639977357,
35
- "support": 15899.0
36
  },
37
- "eval_accuracy": 0.7682686567164179,
38
- "eval_loss": 0.6236585974693298,
39
  "eval_macro avg": {
40
- "f1-score": 0.6583965179214999,
41
- "precision": 0.6533111100997602,
42
- "recall": 0.6913203561532717,
43
- "support": 33500.0
44
- },
45
- "eval_runtime": 1.4247,
46
- "eval_samples_per_second": 56.854,
47
- "eval_steps_per_second": 7.721,
48
  "eval_weighted avg": {
49
- "f1-score": 0.7655218131315448,
50
- "precision": 0.7723271066974134,
51
- "recall": 0.7682686567164179,
52
- "support": 33500.0
53
  },
54
  "step": 41
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
- "f1-score": 0.5235859602056785,
60
- "precision": 0.5846230654018971,
61
- "recall": 0.47408906882591095,
62
- "support": 4940.0
63
  },
64
  "eval_MajorClaim": {
65
- "f1-score": 0.7206085753803596,
66
- "precision": 0.7269767441860465,
67
- "recall": 0.7143510054844607,
68
- "support": 2188.0
69
  },
70
  "eval_O": {
71
- "f1-score": 0.8884743765953269,
72
- "precision": 0.9142337609859582,
73
- "recall": 0.8641268022534135,
74
- "support": 10473.0
75
  },
76
  "eval_Premise": {
77
- "f1-score": 0.8745201535508637,
78
- "precision": 0.8357695614789338,
79
- "recall": 0.917038807472168,
80
- "support": 15899.0
81
  },
82
- "eval_accuracy": 0.8219402985074626,
83
- "eval_loss": 0.47505903244018555,
84
  "eval_macro avg": {
85
- "f1-score": 0.7517972664330571,
86
- "precision": 0.7654007830132088,
87
- "recall": 0.7424014210089883,
88
- "support": 33500.0
89
- },
90
- "eval_runtime": 1.4322,
91
- "eval_samples_per_second": 56.557,
92
- "eval_steps_per_second": 7.681,
93
  "eval_weighted avg": {
94
- "f1-score": 0.8170804260816812,
95
- "precision": 0.816159208839521,
96
- "recall": 0.8219402985074626,
97
- "support": 33500.0
98
  },
99
  "step": 82
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
- "f1-score": 0.5033996474439688,
105
- "precision": 0.6658894070619586,
106
- "recall": 0.4046558704453441,
107
- "support": 4940.0
108
  },
109
  "eval_MajorClaim": {
110
- "f1-score": 0.7934708682838358,
111
- "precision": 0.7872244714349977,
112
- "recall": 0.79981718464351,
113
- "support": 2188.0
114
  },
115
  "eval_O": {
116
- "f1-score": 0.9017883608339096,
117
- "precision": 0.9342819121711536,
118
- "recall": 0.8714790413444095,
119
- "support": 10473.0
120
  },
121
  "eval_Premise": {
122
- "f1-score": 0.8787676209853219,
123
- "precision": 0.8168702042580784,
124
- "recall": 0.9508145166362665,
125
- "support": 15899.0
126
  },
127
- "eval_accuracy": 0.8356119402985075,
128
- "eval_loss": 0.458564430475235,
129
  "eval_macro avg": {
130
- "f1-score": 0.7693566243867591,
131
- "precision": 0.8010664987315472,
132
- "recall": 0.7566916532673825,
133
- "support": 33500.0
134
- },
135
- "eval_runtime": 1.4302,
136
- "eval_samples_per_second": 56.636,
137
- "eval_steps_per_second": 7.691,
138
  "eval_weighted avg": {
139
- "f1-score": 0.8250407291712659,
140
- "precision": 0.8293759599418965,
141
- "recall": 0.8356119402985075,
142
- "support": 33500.0
143
  },
144
  "step": 123
145
  },
146
  {
147
  "epoch": 4.0,
148
  "eval_Claim": {
149
- "f1-score": 0.6119839240043845,
150
- "precision": 0.5575898801597869,
151
- "recall": 0.6781376518218624,
152
- "support": 4940.0
153
  },
154
  "eval_MajorClaim": {
155
- "f1-score": 0.8013553578991952,
156
- "precision": 0.7466456195737964,
157
- "recall": 0.8647166361974405,
158
- "support": 2188.0
159
  },
160
  "eval_O": {
161
- "f1-score": 0.9009650063359004,
162
- "precision": 0.9201592832254853,
163
- "recall": 0.8825551417931825,
164
- "support": 10473.0
165
  },
166
  "eval_Premise": {
167
- "f1-score": 0.8636894716344281,
168
- "precision": 0.8922416683430564,
169
- "recall": 0.836907981634065,
170
- "support": 15899.0
171
  },
172
- "eval_accuracy": 0.8295820895522388,
173
- "eval_loss": 0.45249882340431213,
174
  "eval_macro avg": {
175
- "f1-score": 0.7944984399684771,
176
- "precision": 0.7791591128255312,
177
- "recall": 0.8155793528616375,
178
- "support": 33500.0
179
- },
180
- "eval_runtime": 1.4313,
181
- "eval_samples_per_second": 56.59,
182
- "eval_steps_per_second": 7.685,
183
  "eval_weighted avg": {
184
- "f1-score": 0.8341543739861718,
185
- "precision": 0.8421114352783158,
186
- "recall": 0.8295820895522388,
187
- "support": 33500.0
188
  },
189
  "step": 164
190
  },
191
  {
192
  "epoch": 5.0,
193
  "eval_Claim": {
194
- "f1-score": 0.6177297297297297,
195
- "precision": 0.662877030162413,
196
- "recall": 0.5783400809716599,
197
- "support": 4940.0
198
  },
199
  "eval_MajorClaim": {
200
- "f1-score": 0.8327169893408746,
201
- "precision": 0.7945205479452054,
202
- "recall": 0.8747714808043876,
203
- "support": 2188.0
204
  },
205
  "eval_O": {
206
- "f1-score": 0.9074411905904946,
207
- "precision": 0.9125229313507772,
208
- "recall": 0.9024157357013273,
209
- "support": 10473.0
210
  },
211
  "eval_Premise": {
212
- "f1-score": 0.8867988738669058,
213
- "precision": 0.8726254262055528,
214
- "recall": 0.9014403421598842,
215
- "support": 15899.0
216
  },
217
- "eval_accuracy": 0.8523582089552239,
218
- "eval_loss": 0.47209030389785767,
219
  "eval_macro avg": {
220
- "f1-score": 0.8111716958820011,
221
- "precision": 0.8106364839159872,
222
- "recall": 0.8142419099093148,
223
- "support": 33500.0
224
- },
225
- "eval_runtime": 1.4276,
226
- "eval_samples_per_second": 56.738,
227
- "eval_steps_per_second": 7.705,
228
  "eval_weighted avg": {
229
- "f1-score": 0.8500422842449816,
230
- "precision": 0.8490670984831405,
231
- "recall": 0.8523582089552239,
232
- "support": 33500.0
233
  },
234
  "step": 205
235
  },
236
  {
237
  "epoch": 6.0,
238
  "eval_Claim": {
239
- "f1-score": 0.6278612118073537,
240
- "precision": 0.6428419936373276,
241
- "recall": 0.6135627530364373,
242
- "support": 4940.0
243
  },
244
  "eval_MajorClaim": {
245
- "f1-score": 0.83248730964467,
246
- "precision": 0.804950917626974,
247
- "recall": 0.8619744058500914,
248
- "support": 2188.0
249
  },
250
  "eval_O": {
251
- "f1-score": 0.9114601059950406,
252
- "precision": 0.9285714285714286,
253
- "recall": 0.8949680129857729,
254
- "support": 10473.0
255
  },
256
  "eval_Premise": {
257
- "f1-score": 0.8842993146649301,
258
- "precision": 0.872155615365794,
259
- "recall": 0.8967859613812189,
260
- "support": 15899.0
261
  },
262
- "eval_accuracy": 0.8521791044776119,
263
- "eval_loss": 0.47916167974472046,
264
  "eval_macro avg": {
265
- "f1-score": 0.8140269855279986,
266
- "precision": 0.812129988800381,
267
- "recall": 0.8168227833133802,
268
- "support": 33500.0
269
- },
270
- "eval_runtime": 1.4308,
271
- "eval_samples_per_second": 56.613,
272
- "eval_steps_per_second": 7.688,
273
  "eval_weighted avg": {
274
- "f1-score": 0.8515914362320791,
275
- "precision": 0.8515881419840463,
276
- "recall": 0.8521791044776119,
277
- "support": 33500.0
278
  },
279
  "step": 246
280
  },
281
  {
282
  "epoch": 7.0,
283
  "eval_Claim": {
284
- "f1-score": 0.5961820851688694,
285
- "precision": 0.6744186046511628,
286
- "recall": 0.5342105263157895,
287
- "support": 4940.0
288
  },
289
  "eval_MajorClaim": {
290
- "f1-score": 0.8332962385933673,
291
- "precision": 0.8121475054229935,
292
- "recall": 0.8555758683729433,
293
- "support": 2188.0
294
  },
295
  "eval_O": {
296
- "f1-score": 0.9087219135056778,
297
- "precision": 0.9198786930150655,
298
- "recall": 0.8978325217225246,
299
- "support": 10473.0
300
  },
301
  "eval_Premise": {
302
- "f1-score": 0.8884371491853515,
303
- "precision": 0.8582063305978898,
304
- "recall": 0.9208755267626895,
305
- "support": 15899.0
306
  },
307
- "eval_accuracy": 0.8523880597014926,
308
- "eval_loss": 0.5201511383056641,
309
  "eval_macro avg": {
310
- "f1-score": 0.8066593466133165,
311
- "precision": 0.816162783421778,
312
- "recall": 0.8021236107934867,
313
- "support": 33500.0
314
- },
315
- "eval_runtime": 1.436,
316
- "eval_samples_per_second": 56.406,
317
- "eval_steps_per_second": 7.66,
318
  "eval_weighted avg": {
319
- "f1-score": 0.8480805524125185,
320
- "precision": 0.8473766761482054,
321
- "recall": 0.8523880597014926,
322
- "support": 33500.0
323
  },
324
  "step": 287
325
  },
326
  {
327
  "epoch": 8.0,
328
  "eval_Claim": {
329
- "f1-score": 0.6418997361477573,
330
- "precision": 0.6705622932745314,
331
- "recall": 0.6155870445344129,
332
- "support": 4940.0
333
  },
334
  "eval_MajorClaim": {
335
- "f1-score": 0.8422907488986784,
336
- "precision": 0.8129251700680272,
337
- "recall": 0.8738574040219378,
338
- "support": 2188.0
339
  },
340
  "eval_O": {
341
- "f1-score": 0.909046716251033,
342
- "precision": 0.9259259259259259,
343
- "recall": 0.89277188962093,
344
- "support": 10473.0
345
  },
346
  "eval_Premise": {
347
- "f1-score": 0.8894304929968533,
348
- "precision": 0.8728428701180745,
349
- "recall": 0.9066607962764954,
350
- "support": 15899.0
351
  },
352
- "eval_accuracy": 0.8572537313432835,
353
- "eval_loss": 0.5458493232727051,
354
  "eval_macro avg": {
355
- "f1-score": 0.8206669235735804,
356
- "precision": 0.8205640648466398,
357
- "recall": 0.822219283613444,
358
- "support": 33500.0
359
- },
360
- "eval_runtime": 1.4343,
361
- "eval_samples_per_second": 56.474,
362
- "eval_steps_per_second": 7.669,
363
  "eval_weighted avg": {
364
- "f1-score": 0.8559826424660975,
365
- "precision": 0.8556957914959558,
366
- "recall": 0.8572537313432835,
367
- "support": 33500.0
368
  },
369
  "step": 328
370
  },
371
  {
372
  "epoch": 9.0,
373
  "eval_Claim": {
374
- "f1-score": 0.6331998768093625,
375
- "precision": 0.6423661737138097,
376
- "recall": 0.6242914979757085,
377
- "support": 4940.0
378
  },
379
  "eval_MajorClaim": {
380
- "f1-score": 0.8381555153707052,
381
- "precision": 0.8291592128801432,
382
- "recall": 0.8473491773308958,
383
- "support": 2188.0
384
  },
385
  "eval_O": {
386
- "f1-score": 0.9061017111633034,
387
- "precision": 0.909720885466795,
388
- "recall": 0.9025112193258856,
389
- "support": 10473.0
390
  },
391
  "eval_Premise": {
392
- "f1-score": 0.8844614037282621,
393
- "precision": 0.8796739874323399,
394
- "recall": 0.8893012139128247,
395
- "support": 15899.0
396
  },
397
- "eval_accuracy": 0.8516119402985075,
398
- "eval_loss": 0.5549963116645813,
399
  "eval_macro avg": {
400
- "f1-score": 0.8154796267679083,
401
- "precision": 0.8152300648732719,
402
- "recall": 0.8158632771363286,
403
- "support": 33500.0
404
- },
405
- "eval_runtime": 1.4235,
406
- "eval_samples_per_second": 56.902,
407
- "eval_steps_per_second": 7.727,
408
  "eval_weighted avg": {
409
- "f1-score": 0.8511506488942767,
410
- "precision": 0.8507741138987609,
411
- "recall": 0.8516119402985075,
412
- "support": 33500.0
413
  },
414
  "step": 369
415
  },
416
  {
417
  "epoch": 10.0,
418
  "eval_Claim": {
419
- "f1-score": 0.6263982102908278,
420
- "precision": 0.6611198560827524,
421
- "recall": 0.5951417004048583,
422
- "support": 4940.0
423
  },
424
  "eval_MajorClaim": {
425
- "f1-score": 0.8409399005874378,
426
- "precision": 0.8315460232350312,
427
- "recall": 0.8505484460694699,
428
- "support": 2188.0
429
  },
430
  "eval_O": {
431
- "f1-score": 0.9098583349505143,
432
- "precision": 0.9248446592366111,
433
- "recall": 0.8953499474840065,
434
- "support": 10473.0
435
  },
436
  "eval_Premise": {
437
- "f1-score": 0.8851573292402148,
438
- "precision": 0.8645358599184456,
439
- "recall": 0.9067865903515945,
440
- "support": 15899.0
441
  },
442
- "eval_accuracy": 0.8535820895522388,
443
- "eval_loss": 0.5788276791572571,
444
  "eval_macro avg": {
445
- "f1-score": 0.8155884437672487,
446
- "precision": 0.8205115996182102,
447
- "recall": 0.8119566710774824,
448
- "support": 33500.0
449
- },
450
- "eval_runtime": 1.4232,
451
- "eval_samples_per_second": 56.912,
452
- "eval_steps_per_second": 7.729,
453
  "eval_weighted avg": {
454
- "f1-score": 0.8518342203238483,
455
- "precision": 0.851239060922849,
456
- "recall": 0.8535820895522388,
457
- "support": 33500.0
458
  },
459
  "step": 410
460
  },
461
  {
462
  "epoch": 11.0,
463
  "eval_Claim": {
464
- "f1-score": 0.6328578975171685,
465
- "precision": 0.661878453038674,
466
- "recall": 0.6062753036437247,
467
- "support": 4940.0
468
  },
469
  "eval_MajorClaim": {
470
- "f1-score": 0.8469798657718122,
471
- "precision": 0.829535495179667,
472
- "recall": 0.8651736745886655,
473
- "support": 2188.0
474
  },
475
  "eval_O": {
476
- "f1-score": 0.9110819097678493,
477
- "precision": 0.9291244788564622,
478
- "recall": 0.8937267258665139,
479
- "support": 10473.0
480
  },
481
  "eval_Premise": {
482
- "f1-score": 0.88966111076942,
483
- "precision": 0.8703893134364282,
484
- "recall": 0.9098056481539719,
485
- "support": 15899.0
486
  },
487
- "eval_accuracy": 0.8571044776119403,
488
- "eval_loss": 0.5865030288696289,
489
  "eval_macro avg": {
490
- "f1-score": 0.8201451959565625,
491
- "precision": 0.8227319351278078,
492
- "recall": 0.818745338063219,
493
- "support": 33500.0
494
- },
495
- "eval_runtime": 1.4299,
496
- "eval_samples_per_second": 56.648,
497
- "eval_steps_per_second": 7.693,
498
  "eval_weighted avg": {
499
- "f1-score": 0.8557012776467233,
500
- "precision": 0.8553356293389153,
501
- "recall": 0.8571044776119403,
502
- "support": 33500.0
503
  },
504
  "step": 451
505
  },
506
  {
507
  "epoch": 12.0,
508
  "eval_Claim": {
509
- "f1-score": 0.6447044940505456,
510
- "precision": 0.6268885064065787,
511
- "recall": 0.6635627530364372,
512
- "support": 4940.0
513
  },
514
  "eval_MajorClaim": {
515
- "f1-score": 0.8387389430709912,
516
- "precision": 0.8325078793336335,
517
- "recall": 0.8450639853747715,
518
- "support": 2188.0
519
  },
520
  "eval_O": {
521
- "f1-score": 0.9096724171351037,
522
- "precision": 0.923546196989078,
523
- "recall": 0.896209300105032,
524
- "support": 10473.0
525
  },
526
  "eval_Premise": {
527
- "f1-score": 0.885106650726735,
528
- "precision": 0.885440926543715,
529
- "recall": 0.8847726272092584,
530
- "support": 15899.0
531
  },
532
- "eval_accuracy": 0.8531343283582089,
533
- "eval_loss": 0.6139675378799438,
534
  "eval_macro avg": {
535
- "f1-score": 0.8195556262458439,
536
- "precision": 0.8170958773182513,
537
- "recall": 0.8224021664313748,
538
- "support": 33500.0
539
- },
540
- "eval_runtime": 1.4276,
541
- "eval_samples_per_second": 56.739,
542
- "eval_steps_per_second": 7.705,
543
  "eval_weighted avg": {
544
- "f1-score": 0.8543077872420695,
545
- "precision": 0.8557695842930038,
546
- "recall": 0.8531343283582089,
547
- "support": 33500.0
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": 0.31881702957426067,
15
+ "precision": 0.49395770392749244,
16
+ "recall": 0.23536468330134358,
17
+ "support": 4168.0
18
  },
19
  "eval_MajorClaim": {
20
+ "f1-score": 0.5882107894188711,
21
+ "precision": 0.5330313325783315,
22
+ "recall": 0.6561338289962825,
23
+ "support": 2152.0
24
  },
25
  "eval_O": {
26
+ "f1-score": 0.8686845568461407,
27
+ "precision": 0.9200096957944491,
28
+ "recall": 0.82278343810969,
29
+ "support": 9226.0
30
  },
31
  "eval_Premise": {
32
+ "f1-score": 0.8547340147728121,
33
+ "precision": 0.777574153261386,
34
+ "recall": 0.9488942267870455,
35
+ "support": 12073.0
36
  },
37
+ "eval_accuracy": 0.7762772004779318,
38
+ "eval_loss": 0.5690305829048157,
39
  "eval_macro avg": {
40
+ "f1-score": 0.6576115976530211,
41
+ "precision": 0.6811432213904147,
42
+ "recall": 0.6657940442985903,
43
+ "support": 27619.0
44
+ },
45
+ "eval_runtime": 1.3776,
46
+ "eval_samples_per_second": 58.074,
47
+ "eval_steps_per_second": 7.259,
48
  "eval_weighted avg": {
49
+ "f1-score": 0.7577517824653167,
50
+ "precision": 0.7632992267425562,
51
+ "recall": 0.7762772004779318,
52
+ "support": 27619.0
53
  },
54
  "step": 41
55
  },
56
  {
57
  "epoch": 2.0,
58
  "eval_Claim": {
59
+ "f1-score": 0.5093288777499304,
60
+ "precision": 0.6068347710683477,
61
+ "recall": 0.43881957773512476,
62
+ "support": 4168.0
63
  },
64
  "eval_MajorClaim": {
65
+ "f1-score": 0.7403386886669561,
66
+ "precision": 0.6947840260798696,
67
+ "recall": 0.7922862453531598,
68
+ "support": 2152.0
69
  },
70
  "eval_O": {
71
+ "f1-score": 0.8998096943915818,
72
+ "precision": 0.930324074074074,
73
+ "recall": 0.8712334706264904,
74
+ "support": 9226.0
75
  },
76
  "eval_Premise": {
77
+ "f1-score": 0.8735146966854284,
78
+ "precision": 0.8270298275479239,
79
+ "recall": 0.9255363207156465,
80
+ "support": 12073.0
81
  },
82
+ "eval_accuracy": 0.823563488902567,
83
+ "eval_loss": 0.44297581911087036,
84
  "eval_macro avg": {
85
+ "f1-score": 0.7557479893734742,
86
+ "precision": 0.7647431746925538,
87
+ "recall": 0.7569689036076054,
88
+ "support": 27619.0
89
+ },
90
+ "eval_runtime": 1.3774,
91
+ "eval_samples_per_second": 58.08,
92
+ "eval_steps_per_second": 7.26,
93
  "eval_weighted avg": {
94
+ "f1-score": 0.8169621924766614,
95
+ "precision": 0.8180007808150275,
96
+ "recall": 0.823563488902567,
97
+ "support": 27619.0
98
  },
99
  "step": 82
100
  },
101
  {
102
  "epoch": 3.0,
103
  "eval_Claim": {
104
+ "f1-score": 0.6003528892809882,
105
+ "precision": 0.5555102040816327,
106
+ "recall": 0.6530710172744721,
107
+ "support": 4168.0
108
  },
109
  "eval_MajorClaim": {
110
+ "f1-score": 0.7456098718557191,
111
+ "precision": 0.7618816682832201,
112
+ "recall": 0.7300185873605948,
113
+ "support": 2152.0
114
  },
115
  "eval_O": {
116
+ "f1-score": 0.9073143179892686,
117
+ "precision": 0.9472815190470575,
118
+ "recall": 0.8705831346195534,
119
+ "support": 9226.0
120
  },
121
  "eval_Premise": {
122
+ "f1-score": 0.8768298214506619,
123
+ "precision": 0.8730497618656594,
124
+ "recall": 0.8806427565642343,
125
+ "support": 12073.0
126
  },
127
+ "eval_accuracy": 0.8312031572468228,
128
+ "eval_loss": 0.42804914712905884,
129
  "eval_macro avg": {
130
+ "f1-score": 0.7825267251441594,
131
+ "precision": 0.7844307883193924,
132
+ "recall": 0.7835788739547136,
133
+ "support": 27619.0
134
+ },
135
+ "eval_runtime": 1.3753,
136
+ "eval_samples_per_second": 58.17,
137
+ "eval_steps_per_second": 7.271,
138
  "eval_weighted avg": {
139
+ "f1-score": 0.8350654121763821,
140
+ "precision": 0.8412645262496828,
141
+ "recall": 0.8312031572468228,
142
+ "support": 27619.0
143
  },
144
  "step": 123
145
  },
146
  {
147
  "epoch": 4.0,
148
  "eval_Claim": {
149
+ "f1-score": 0.5695364238410595,
150
+ "precision": 0.6521200866604766,
151
+ "recall": 0.5055182341650671,
152
+ "support": 4168.0
153
  },
154
  "eval_MajorClaim": {
155
+ "f1-score": 0.7937086847503988,
156
+ "precision": 0.7789709172259508,
157
+ "recall": 0.8090148698884758,
158
+ "support": 2152.0
159
  },
160
  "eval_O": {
161
+ "f1-score": 0.9155632732797916,
162
+ "precision": 0.91675722668985,
163
+ "recall": 0.9143724257533059,
164
+ "support": 9226.0
165
  },
166
  "eval_Premise": {
167
+ "f1-score": 0.8839514066496164,
168
+ "precision": 0.85398810902633,
169
+ "recall": 0.9160937629421022,
170
+ "support": 12073.0
171
  },
172
+ "eval_accuracy": 0.8452152503711213,
173
+ "eval_loss": 0.4198084771633148,
174
  "eval_macro avg": {
175
+ "f1-score": 0.7906899471302166,
176
+ "precision": 0.8004590849006519,
177
+ "recall": 0.7862498231872379,
178
+ "support": 27619.0
179
+ },
180
+ "eval_runtime": 1.3806,
181
+ "eval_samples_per_second": 57.945,
182
+ "eval_steps_per_second": 7.243,
183
  "eval_weighted avg": {
184
+ "f1-score": 0.8400311740436862,
185
+ "precision": 0.8386466761572305,
186
+ "recall": 0.8452152503711213,
187
+ "support": 27619.0
188
  },
189
  "step": 164
190
  },
191
  {
192
  "epoch": 5.0,
193
  "eval_Claim": {
194
+ "f1-score": 0.6163734776725303,
195
+ "precision": 0.5814893617021276,
196
+ "recall": 0.6557101727447217,
197
+ "support": 4168.0
198
  },
199
  "eval_MajorClaim": {
200
+ "f1-score": 0.7828498293515358,
201
+ "precision": 0.7235804416403786,
202
+ "recall": 0.8526951672862454,
203
+ "support": 2152.0
204
  },
205
  "eval_O": {
206
+ "f1-score": 0.9165979438121942,
207
+ "precision": 0.9300457436126297,
208
+ "recall": 0.9035334923043572,
209
+ "support": 9226.0
210
  },
211
  "eval_Premise": {
212
+ "f1-score": 0.8766015408845188,
213
+ "precision": 0.9016637478108581,
214
+ "recall": 0.8528948894226787,
215
+ "support": 12073.0
216
  },
217
+ "eval_accuracy": 0.8400376552373366,
218
+ "eval_loss": 0.44705528020858765,
219
  "eval_macro avg": {
220
+ "f1-score": 0.7981056979301948,
221
+ "precision": 0.7841948236914985,
222
+ "recall": 0.8162084304395008,
223
+ "support": 27619.0
224
+ },
225
+ "eval_runtime": 1.3758,
226
+ "eval_samples_per_second": 58.148,
227
+ "eval_steps_per_second": 7.268,
228
  "eval_weighted avg": {
229
+ "f1-score": 0.843386093646175,
230
+ "precision": 0.8489511288560475,
231
+ "recall": 0.8400376552373366,
232
+ "support": 27619.0
233
  },
234
  "step": 205
235
  },
236
  {
237
  "epoch": 6.0,
238
  "eval_Claim": {
239
+ "f1-score": 0.6241953385127637,
240
+ "precision": 0.5807517554729451,
241
+ "recall": 0.6746641074856046,
242
+ "support": 4168.0
243
  },
244
  "eval_MajorClaim": {
245
+ "f1-score": 0.7921387283236995,
246
+ "precision": 0.7883110906580764,
247
+ "recall": 0.796003717472119,
248
+ "support": 2152.0
249
  },
250
  "eval_O": {
251
+ "f1-score": 0.9180380767989674,
252
+ "precision": 0.9110802732707088,
253
+ "recall": 0.925102969867765,
254
+ "support": 9226.0
255
  },
256
  "eval_Premise": {
257
+ "f1-score": 0.8717662705392766,
258
+ "precision": 0.9042363830544677,
259
+ "recall": 0.8415472542035948,
260
+ "support": 12073.0
261
  },
262
+ "eval_accuracy": 0.8407255874579094,
263
+ "eval_loss": 0.4595077633857727,
264
  "eval_macro avg": {
265
+ "f1-score": 0.8015346035436768,
266
+ "precision": 0.7960948756140495,
267
+ "recall": 0.8093295122572709,
268
+ "support": 27619.0
269
+ },
270
+ "eval_runtime": 1.3748,
271
+ "eval_samples_per_second": 58.192,
272
+ "eval_steps_per_second": 7.274,
273
  "eval_weighted avg": {
274
+ "f1-score": 0.8436577064716956,
275
+ "precision": 0.8486726976979458,
276
+ "recall": 0.8407255874579094,
277
+ "support": 27619.0
278
  },
279
  "step": 246
280
  },
281
  {
282
  "epoch": 7.0,
283
  "eval_Claim": {
284
+ "f1-score": 0.5836049135121585,
285
+ "precision": 0.6110236220472441,
286
+ "recall": 0.5585412667946257,
287
+ "support": 4168.0
288
  },
289
  "eval_MajorClaim": {
290
+ "f1-score": 0.7928268050967437,
291
+ "precision": 0.8053691275167785,
292
+ "recall": 0.7806691449814126,
293
+ "support": 2152.0
294
  },
295
  "eval_O": {
296
+ "f1-score": 0.9194612574295218,
297
+ "precision": 0.9251618566882476,
298
+ "recall": 0.9138304790808585,
299
+ "support": 9226.0
300
  },
301
  "eval_Premise": {
302
+ "f1-score": 0.8797147834541992,
303
+ "precision": 0.8609833465503569,
304
+ "recall": 0.8992793837488611,
305
+ "support": 12073.0
306
  },
307
+ "eval_accuracy": 0.8434773163402006,
308
+ "eval_loss": 0.5069454908370972,
309
  "eval_macro avg": {
310
+ "f1-score": 0.7939019398731558,
311
+ "precision": 0.8006344882006567,
312
+ "recall": 0.7880800686514394,
313
+ "support": 27619.0
314
+ },
315
+ "eval_runtime": 1.3807,
316
+ "eval_samples_per_second": 57.943,
317
+ "eval_steps_per_second": 7.243,
318
  "eval_weighted avg": {
319
+ "f1-score": 0.8415357075120093,
320
+ "precision": 0.8403669956123412,
321
+ "recall": 0.8434773163402006,
322
+ "support": 27619.0
323
  },
324
  "step": 287
325
  },
326
  {
327
  "epoch": 8.0,
328
  "eval_Claim": {
329
+ "f1-score": 0.5933731413183467,
330
+ "precision": 0.5794648982391951,
331
+ "recall": 0.6079654510556622,
332
+ "support": 4168.0
333
  },
334
  "eval_MajorClaim": {
335
+ "f1-score": 0.7907602601480151,
336
+ "precision": 0.7641959254442999,
337
+ "recall": 0.8192379182156134,
338
+ "support": 2152.0
339
  },
340
  "eval_O": {
341
+ "f1-score": 0.9148948106591865,
342
+ "precision": 0.9482497964879637,
343
+ "recall": 0.8838066334272707,
344
+ "support": 9226.0
345
  },
346
  "eval_Premise": {
347
+ "f1-score": 0.8765821488551183,
348
+ "precision": 0.86709886547812,
349
+ "recall": 0.8862751594466992,
350
+ "support": 12073.0
351
  },
352
+ "eval_accuracy": 0.8382273072884608,
353
+ "eval_loss": 0.548562228679657,
354
  "eval_macro avg": {
355
+ "f1-score": 0.7939025902451666,
356
+ "precision": 0.7897523714123946,
357
+ "recall": 0.7993212905363115,
358
+ "support": 27619.0
359
+ },
360
+ "eval_runtime": 1.3817,
361
+ "eval_samples_per_second": 57.901,
362
+ "eval_steps_per_second": 7.238,
363
  "eval_weighted avg": {
364
+ "f1-score": 0.8399540584062747,
365
+ "precision": 0.8427820179127555,
366
+ "recall": 0.8382273072884608,
367
+ "support": 27619.0
368
  },
369
  "step": 328
370
  },
371
  {
372
  "epoch": 9.0,
373
  "eval_Claim": {
374
+ "f1-score": 0.6135836554389841,
375
+ "precision": 0.5684468999386126,
376
+ "recall": 0.6665067178502879,
377
+ "support": 4168.0
378
  },
379
  "eval_MajorClaim": {
380
+ "f1-score": 0.7970061238376048,
381
+ "precision": 0.7784669915817457,
382
+ "recall": 0.8164498141263941,
383
+ "support": 2152.0
384
  },
385
  "eval_O": {
386
+ "f1-score": 0.9169912095248693,
387
+ "precision": 0.9420438957475995,
388
+ "recall": 0.893236505527856,
389
+ "support": 9226.0
390
  },
391
  "eval_Premise": {
392
+ "f1-score": 0.8721008403361344,
393
+ "precision": 0.8849663170461328,
394
+ "recall": 0.8596040752091444,
395
+ "support": 12073.0
396
  },
397
+ "eval_accuracy": 0.8383359281653934,
398
+ "eval_loss": 0.562429666519165,
399
  "eval_macro avg": {
400
+ "f1-score": 0.7999204572843982,
401
+ "precision": 0.7934810260785227,
402
+ "recall": 0.8089492781784205,
403
+ "support": 27619.0
404
+ },
405
+ "eval_runtime": 1.3808,
406
+ "eval_samples_per_second": 57.936,
407
+ "eval_steps_per_second": 7.242,
408
  "eval_weighted avg": {
409
+ "f1-score": 0.8422320938058151,
410
+ "precision": 0.8479685351639584,
411
+ "recall": 0.8383359281653934,
412
+ "support": 27619.0
413
  },
414
  "step": 369
415
  },
416
  {
417
  "epoch": 10.0,
418
  "eval_Claim": {
419
+ "f1-score": 0.612128418549346,
420
+ "precision": 0.6067892503536068,
421
+ "recall": 0.6175623800383877,
422
+ "support": 4168.0
423
  },
424
  "eval_MajorClaim": {
425
+ "f1-score": 0.7968056787932565,
426
+ "precision": 0.7623089983022071,
427
+ "recall": 0.8345724907063197,
428
+ "support": 2152.0
429
  },
430
  "eval_O": {
431
+ "f1-score": 0.9155905337249902,
432
+ "precision": 0.9368265850062379,
433
+ "recall": 0.8952959028831563,
434
+ "support": 9226.0
435
  },
436
  "eval_Premise": {
437
+ "f1-score": 0.879186060880669,
438
+ "precision": 0.8744673877417241,
439
+ "recall": 0.8839559347303901,
440
+ "support": 12073.0
441
  },
442
+ "eval_accuracy": 0.8436945580940657,
443
+ "eval_loss": 0.5923005938529968,
444
  "eval_macro avg": {
445
+ "f1-score": 0.8009276729870654,
446
+ "precision": 0.795098055350944,
447
+ "recall": 0.8078466770895635,
448
+ "support": 27619.0
449
+ },
450
+ "eval_runtime": 1.3753,
451
+ "eval_samples_per_second": 58.169,
452
+ "eval_steps_per_second": 7.271,
453
  "eval_weighted avg": {
454
+ "f1-score": 0.8446261141401151,
455
+ "precision": 0.846163633922067,
456
+ "recall": 0.8436945580940657,
457
+ "support": 27619.0
458
  },
459
  "step": 410
460
  },
461
  {
462
  "epoch": 11.0,
463
  "eval_Claim": {
464
+ "f1-score": 0.6184452621895125,
465
+ "precision": 0.5938604240282686,
466
+ "recall": 0.6451535508637236,
467
+ "support": 4168.0
468
  },
469
  "eval_MajorClaim": {
470
+ "f1-score": 0.7804655408489276,
471
+ "precision": 0.7668161434977578,
472
+ "recall": 0.7946096654275093,
473
+ "support": 2152.0
474
  },
475
  "eval_O": {
476
+ "f1-score": 0.9165973031463293,
477
+ "precision": 0.9390562819783969,
478
+ "recall": 0.8951875135486668,
479
+ "support": 9226.0
480
  },
481
  "eval_Premise": {
482
+ "f1-score": 0.8779154066034218,
483
+ "precision": 0.8781700646444555,
484
+ "recall": 0.8776608962146939,
485
+ "support": 12073.0
486
  },
487
+ "eval_accuracy": 0.841956624063145,
488
+ "eval_loss": 0.6036468148231506,
489
  "eval_macro avg": {
490
+ "f1-score": 0.7983558781970478,
491
+ "precision": 0.7944757285372197,
492
+ "recall": 0.8031529065136485,
493
+ "support": 27619.0
494
+ },
495
+ "eval_runtime": 1.3761,
496
+ "eval_samples_per_second": 58.137,
497
+ "eval_steps_per_second": 7.267,
498
  "eval_weighted avg": {
499
+ "f1-score": 0.8440870820617664,
500
+ "precision": 0.8469270804932185,
501
+ "recall": 0.841956624063145,
502
+ "support": 27619.0
503
  },
504
  "step": 451
505
  },
506
  {
507
  "epoch": 12.0,
508
  "eval_Claim": {
509
+ "f1-score": 0.6014948392454621,
510
+ "precision": 0.594930767425487,
511
+ "recall": 0.6082053742802304,
512
+ "support": 4168.0
513
  },
514
  "eval_MajorClaim": {
515
+ "f1-score": 0.7777515908555267,
516
+ "precision": 0.7890961262553802,
517
+ "recall": 0.766728624535316,
518
+ "support": 2152.0
519
  },
520
  "eval_O": {
521
+ "f1-score": 0.9159474465394976,
522
+ "precision": 0.9292805354155047,
523
+ "recall": 0.9029915456319099,
524
+ "support": 9226.0
525
  },
526
  "eval_Premise": {
527
+ "f1-score": 0.8807384615384615,
528
+ "precision": 0.872541050235734,
529
+ "recall": 0.8890913608879317,
530
+ "support": 12073.0
531
  },
532
+ "eval_accuracy": 0.8418117962272349,
533
+ "eval_loss": 0.6291709542274475,
534
  "eval_macro avg": {
535
+ "f1-score": 0.7939830845447369,
536
+ "precision": 0.7964621198330264,
537
+ "recall": 0.791754226333847,
538
+ "support": 27619.0
539
+ },
540
+ "eval_runtime": 1.3752,
541
+ "eval_samples_per_second": 58.171,
542
+ "eval_steps_per_second": 7.271,
543
  "eval_weighted avg": {
544
+ "f1-score": 0.8423345704559697,
545
+ "precision": 0.8430984692266364,
546
+ "recall": 0.8418117962272349,
547
+ "support": 27619.0
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:a34106aa46561666831adcdfa68f4d8530a86618e19859d53733fffd662fa99f
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c1709ee996939c9fcadfbefb05efc50420ff427d1c0c0c37492208bad18716
3
  size 4664