Theoreticallyhugo commited on
Commit
a026216
1 Parent(s): 672bf51

Training in progress, epoch 7, checkpoint

Browse files
checkpoint-567/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60412acb72f83fedb9248d0a7ee1769e52aa232b71b130b017c10f51d17e28ae
3
  size 592330980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:596824d28705696f937cd813ca7963f5f8f9cbf5ee6a9d7fe491a68f4d6fe2cb
3
  size 592330980
checkpoint-567/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87eafd7446cd1277f3cbabb568f8a4d97354f03981954188b2a1d29a53927da5
3
  size 1014670074
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b376490aa83e6dbb9665168250ec42810c006985b6c9c75f4147bceebe2844d7
3
  size 1014670074
checkpoint-567/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a37c3795111d23ad6190712c2991585b141e7dd666ac9350ac9e35c845a45539
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df74477c8049c831c537fb964d31e59ec8d12121ecfdafd2834f9022f29cfdc5
3
  size 14244
checkpoint-567/trainer_state.json CHANGED
@@ -11,448 +11,448 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_B-Claim": {
14
- "f1-score": 0.18764302059496568,
15
- "precision": 0.3416666666666667,
16
- "recall": 0.12933753943217666,
17
- "support": 317.0
18
  },
19
  "eval_B-MajorClaim": {
20
- "f1-score": 0.19540229885057472,
21
- "precision": 0.8947368421052632,
22
- "recall": 0.10967741935483871,
23
- "support": 155.0
24
  },
25
  "eval_B-Premise": {
26
- "f1-score": 0.8476339053562143,
27
- "precision": 0.740909090909091,
28
- "recall": 0.9902794653705954,
29
- "support": 823.0
30
  },
31
  "eval_I-Claim": {
32
- "f1-score": 0.4315998169894769,
33
- "precision": 0.6394035246272028,
34
- "recall": 0.3257366482504604,
35
- "support": 4344.0
36
  },
37
  "eval_I-MajorClaim": {
38
- "f1-score": 0.7779799818016379,
39
- "precision": 0.7493426818580193,
40
- "recall": 0.8088930936613056,
41
- "support": 2114.0
42
  },
43
  "eval_I-Premise": {
44
- "f1-score": 0.8948683715038855,
45
- "precision": 0.8376057421174058,
46
- "recall": 0.9605350187403542,
47
- "support": 13607.0
48
  },
49
  "eval_O": {
50
- "f1-score": 0.9980147987727848,
51
- "precision": 0.9970251509961237,
52
- "recall": 0.9990064131514769,
53
- "support": 11071.0
54
  },
55
- "eval_accuracy": 0.8673183065585397,
56
- "eval_loss": 0.3193369209766388,
57
  "eval_macro avg": {
58
- "f1-score": 0.6190203134099342,
59
- "precision": 0.7429556713256817,
60
- "recall": 0.6176379425658869,
61
- "support": 32431.0
62
- },
63
- "eval_runtime": 4.9083,
64
- "eval_samples_per_second": 16.299,
65
- "eval_steps_per_second": 2.037,
66
  "eval_weighted avg": {
67
- "f1-score": 0.8489527906249091,
68
- "precision": 0.8526967051825685,
69
- "recall": 0.8673183065585397,
70
- "support": 32431.0
71
  },
72
  "step": 81
73
  },
74
  {
75
  "epoch": 2.0,
76
  "eval_B-Claim": {
77
- "f1-score": 0.583941605839416,
78
- "precision": 0.6926406926406926,
79
- "recall": 0.5047318611987381,
80
- "support": 317.0
81
  },
82
  "eval_B-MajorClaim": {
83
- "f1-score": 0.8117647058823529,
84
- "precision": 0.745945945945946,
85
- "recall": 0.8903225806451613,
86
- "support": 155.0
87
  },
88
  "eval_B-Premise": {
89
- "f1-score": 0.8943661971830986,
90
- "precision": 0.8649262202043133,
91
- "recall": 0.9258809234507898,
92
- "support": 823.0
93
  },
94
  "eval_I-Claim": {
95
- "f1-score": 0.6197740770932805,
96
- "precision": 0.6271506009898656,
97
- "recall": 0.6125690607734806,
98
- "support": 4344.0
99
  },
100
  "eval_I-MajorClaim": {
101
- "f1-score": 0.8298737427776589,
102
- "precision": 0.7577178585384916,
103
- "recall": 0.9172185430463576,
104
- "support": 2114.0
105
  },
106
  "eval_I-Premise": {
107
- "f1-score": 0.9013697613125952,
108
- "precision": 0.9106660666066607,
109
- "recall": 0.8922613360770192,
110
- "support": 13607.0
111
  },
112
  "eval_O": {
113
- "f1-score": 0.9961487925331883,
114
- "precision": 0.9993636363636363,
115
- "recall": 0.9929545659831993,
116
- "support": 11071.0
117
  },
118
- "eval_accuracy": 0.887854213561099,
119
- "eval_loss": 0.26407390832901,
120
  "eval_macro avg": {
121
- "f1-score": 0.8053198403745129,
122
- "precision": 0.7997730030413723,
123
- "recall": 0.8194198387392494,
124
- "support": 32431.0
125
- },
126
- "eval_runtime": 4.9329,
127
- "eval_samples_per_second": 16.218,
128
- "eval_steps_per_second": 2.027,
129
  "eval_weighted avg": {
130
- "f1-score": 0.8876368199002541,
131
- "precision": 0.8889201304482091,
132
- "recall": 0.887854213561099,
133
- "support": 32431.0
134
  },
135
  "step": 162
136
  },
137
  {
138
  "epoch": 3.0,
139
  "eval_B-Claim": {
140
- "f1-score": 0.5895522388059701,
141
- "precision": 0.7214611872146118,
142
- "recall": 0.49842271293375395,
143
- "support": 317.0
144
  },
145
  "eval_B-MajorClaim": {
146
- "f1-score": 0.8668941979522183,
147
- "precision": 0.9202898550724637,
148
- "recall": 0.8193548387096774,
149
- "support": 155.0
150
  },
151
  "eval_B-Premise": {
152
- "f1-score": 0.8929178470254956,
153
- "precision": 0.8365180467091295,
154
- "recall": 0.9574726609963548,
155
- "support": 823.0
156
  },
157
  "eval_I-Claim": {
158
- "f1-score": 0.6548140728684112,
159
- "precision": 0.7178149876475433,
160
- "recall": 0.6019797421731123,
161
- "support": 4344.0
162
  },
163
  "eval_I-MajorClaim": {
164
- "f1-score": 0.8815622622368754,
165
- "precision": 0.9502460360852925,
166
- "recall": 0.8221381267738883,
167
- "support": 2114.0
168
  },
169
  "eval_I-Premise": {
170
- "f1-score": 0.9169943670953343,
171
- "precision": 0.8852257181942544,
172
- "recall": 0.9511280958330272,
173
- "support": 13607.0
174
  },
175
  "eval_O": {
176
- "f1-score": 0.9984170774727511,
177
- "precision": 0.9998188405797102,
178
- "recall": 0.9970192394544305,
179
- "support": 11071.0
180
  },
181
- "eval_accuracy": 0.9067250470229101,
182
- "eval_loss": 0.25323203206062317,
183
  "eval_macro avg": {
184
- "f1-score": 0.8287360090652937,
185
- "precision": 0.8616249530718579,
186
- "recall": 0.8067879166963207,
187
- "support": 32431.0
188
- },
189
- "eval_runtime": 4.9025,
190
- "eval_samples_per_second": 16.318,
191
- "eval_steps_per_second": 2.04,
192
  "eval_weighted avg": {
193
- "f1-score": 0.9033110548907601,
194
- "precision": 0.9034896128542845,
195
- "recall": 0.9067250470229101,
196
- "support": 32431.0
197
  },
198
  "step": 243
199
  },
200
  {
201
  "epoch": 4.0,
202
  "eval_B-Claim": {
203
- "f1-score": 0.6806136680613668,
204
- "precision": 0.61,
205
- "recall": 0.7697160883280757,
206
- "support": 317.0
207
  },
208
  "eval_B-MajorClaim": {
209
- "f1-score": 0.8861538461538462,
210
- "precision": 0.8470588235294118,
211
- "recall": 0.9290322580645162,
212
- "support": 155.0
213
  },
214
  "eval_B-Premise": {
215
- "f1-score": 0.8687258687258688,
216
- "precision": 0.9233926128590971,
217
- "recall": 0.8201701093560145,
218
- "support": 823.0
219
  },
220
  "eval_I-Claim": {
221
- "f1-score": 0.656155854589275,
222
- "precision": 0.5819380121125757,
223
- "recall": 0.7520718232044199,
224
- "support": 4344.0
225
  },
226
  "eval_I-MajorClaim": {
227
- "f1-score": 0.8818897637795275,
228
- "precision": 0.8408408408408409,
229
- "recall": 0.9271523178807947,
230
- "support": 2114.0
231
  },
232
  "eval_I-Premise": {
233
- "f1-score": 0.8829758349171871,
234
- "precision": 0.9349433218334154,
235
- "recall": 0.836481222899978,
236
- "support": 13607.0
237
  },
238
  "eval_O": {
239
- "f1-score": 0.9971017118014671,
240
- "precision": 0.9998183634547271,
241
- "recall": 0.9943997832174148,
242
- "support": 11071.0
243
  },
244
- "eval_accuracy": 0.8843698930036077,
245
- "eval_loss": 0.2791365385055542,
246
  "eval_macro avg": {
247
- "f1-score": 0.8362309354326484,
248
- "precision": 0.8197131392328668,
249
- "recall": 0.8612890861358877,
250
- "support": 32431.0
251
- },
252
- "eval_runtime": 4.9234,
253
- "eval_samples_per_second": 16.249,
254
- "eval_steps_per_second": 2.031,
255
  "eval_weighted avg": {
256
- "f1-score": 0.889158243622726,
257
- "precision": 0.8997827813567029,
258
- "recall": 0.8843698930036077,
259
- "support": 32431.0
260
  },
261
  "step": 324
262
  },
263
  {
264
  "epoch": 5.0,
265
  "eval_B-Claim": {
266
- "f1-score": 0.6078799249530958,
267
- "precision": 0.75,
268
- "recall": 0.5110410094637224,
269
- "support": 317.0
270
  },
271
  "eval_B-MajorClaim": {
272
- "f1-score": 0.8971962616822431,
273
- "precision": 0.8674698795180723,
274
- "recall": 0.9290322580645162,
275
- "support": 155.0
276
  },
277
  "eval_B-Premise": {
278
- "f1-score": 0.893739230327398,
279
- "precision": 0.8474945533769063,
280
- "recall": 0.945321992709599,
281
- "support": 823.0
282
  },
283
  "eval_I-Claim": {
284
- "f1-score": 0.6119813135476778,
285
- "precision": 0.7590320381731425,
286
- "recall": 0.5126611418047882,
287
- "support": 4344.0
288
  },
289
  "eval_I-MajorClaim": {
290
- "f1-score": 0.8889393595275948,
291
- "precision": 0.854958497160332,
292
- "recall": 0.9257332071901608,
293
- "support": 2114.0
294
  },
295
  "eval_I-Premise": {
296
- "f1-score": 0.9137743463765573,
297
- "precision": 0.874462654486835,
298
- "recall": 0.956786947894466,
299
- "support": 13607.0
300
  },
301
  "eval_O": {
302
- "f1-score": 0.9976913675252366,
303
- "precision": 1.0,
304
- "recall": 0.9953933700659381,
305
- "support": 11071.0
306
  },
307
- "eval_accuracy": 0.9036724121982054,
308
- "eval_loss": 0.3500836193561554,
309
  "eval_macro avg": {
310
- "f1-score": 0.8301716862771149,
311
- "precision": 0.8504882318164697,
312
- "recall": 0.8251385610275985,
313
- "support": 32431.0
314
- },
315
- "eval_runtime": 4.9239,
316
- "eval_samples_per_second": 16.247,
317
- "eval_steps_per_second": 2.031,
318
  "eval_weighted avg": {
319
- "f1-score": 0.8968007164885599,
320
- "precision": 0.8986502613295283,
321
- "recall": 0.9036724121982054,
322
- "support": 32431.0
323
  },
324
  "step": 405
325
  },
326
  {
327
  "epoch": 6.0,
328
  "eval_B-Claim": {
329
- "f1-score": 0.672077922077922,
330
- "precision": 0.6923076923076923,
331
- "recall": 0.6529968454258676,
332
- "support": 317.0
333
  },
334
  "eval_B-MajorClaim": {
335
- "f1-score": 0.8910256410256411,
336
- "precision": 0.8853503184713376,
337
- "recall": 0.896774193548387,
338
- "support": 155.0
339
  },
340
  "eval_B-Premise": {
341
- "f1-score": 0.8907563025210083,
342
- "precision": 0.8801897983392646,
343
- "recall": 0.9015795868772782,
344
- "support": 823.0
345
  },
346
  "eval_I-Claim": {
347
- "f1-score": 0.6666666666666667,
348
- "precision": 0.6998228296633764,
349
- "recall": 0.6365101289134438,
350
- "support": 4344.0
351
  },
352
  "eval_I-MajorClaim": {
353
- "f1-score": 0.8853370396108408,
354
- "precision": 0.867453472537449,
355
- "recall": 0.9039735099337748,
356
- "support": 2114.0
357
  },
358
  "eval_I-Premise": {
359
- "f1-score": 0.9098497495826378,
360
- "precision": 0.8987595898759589,
361
- "recall": 0.9212170206511354,
362
- "support": 13607.0
363
  },
364
  "eval_O": {
365
- "f1-score": 0.998190209030857,
366
- "precision": 1.0,
367
- "recall": 0.9963869569144612,
368
- "support": 11071.0
369
  },
370
- "eval_accuracy": 0.9043816101877833,
371
- "eval_loss": 0.30672115087509155,
372
  "eval_macro avg": {
373
- "f1-score": 0.8448433615022248,
374
- "precision": 0.8462691001707254,
375
- "recall": 0.8442054631806213,
376
- "support": 32431.0
377
- },
378
- "eval_runtime": 4.9018,
379
- "eval_samples_per_second": 16.321,
380
- "eval_steps_per_second": 2.04,
381
  "eval_weighted avg": {
382
- "f1-score": 0.9029367568413356,
383
- "precision": 0.9020793621628027,
384
- "recall": 0.9043816101877833,
385
- "support": 32431.0
386
  },
387
  "step": 486
388
  },
389
  {
390
  "epoch": 6.17,
391
- "grad_norm": 0.43724608421325684,
392
  "learning_rate": 1.7530864197530865e-05,
393
- "loss": 0.2434,
394
  "step": 500
395
  },
396
  {
397
  "epoch": 7.0,
398
  "eval_B-Claim": {
399
- "f1-score": 0.6763285024154589,
400
- "precision": 0.6907894736842105,
401
- "recall": 0.6624605678233438,
402
- "support": 317.0
403
  },
404
  "eval_B-MajorClaim": {
405
- "f1-score": 0.8952380952380952,
406
- "precision": 0.88125,
407
- "recall": 0.9096774193548387,
408
- "support": 155.0
409
  },
410
  "eval_B-Premise": {
411
- "f1-score": 0.8941034897713597,
412
- "precision": 0.8855780691299165,
413
- "recall": 0.9027946537059538,
414
- "support": 823.0
415
  },
416
  "eval_I-Claim": {
417
- "f1-score": 0.6960393719240684,
418
- "precision": 0.7088305489260143,
419
- "recall": 0.6837016574585635,
420
- "support": 4344.0
421
  },
422
  "eval_I-MajorClaim": {
423
- "f1-score": 0.9140037593984962,
424
- "precision": 0.9080298786181139,
425
- "recall": 0.9200567644276254,
426
- "support": 2114.0
427
  },
428
  "eval_I-Premise": {
429
- "f1-score": 0.9164355568530141,
430
- "precision": 0.9101253895774444,
431
- "recall": 0.9228338355258323,
432
- "support": 13607.0
433
  },
434
  "eval_O": {
435
- "f1-score": 0.9967376529225193,
436
  "precision": 1.0,
437
- "recall": 0.9934965224460302,
438
- "support": 11071.0
439
  },
440
- "eval_accuracy": 0.9116277635595572,
441
- "eval_loss": 0.34577852487564087,
442
  "eval_macro avg": {
443
- "f1-score": 0.855555204074716,
444
- "precision": 0.8549433371336713,
445
- "recall": 0.8564316315345982,
446
- "support": 32431.0
447
- },
448
- "eval_runtime": 4.8989,
449
- "eval_samples_per_second": 16.33,
450
- "eval_steps_per_second": 2.041,
451
  "eval_weighted avg": {
452
- "f1-score": 0.9111536914902465,
453
- "precision": 0.910801887328957,
454
- "recall": 0.9116277635595572,
455
- "support": 32431.0
456
  },
457
  "step": 567
458
  }
@@ -462,7 +462,7 @@
462
  "num_input_tokens_seen": 0,
463
  "num_train_epochs": 50,
464
  "save_steps": 500,
465
- "total_flos": 1006535689026000.0,
466
  "train_batch_size": 4,
467
  "trial_name": null,
468
  "trial_params": null
 
11
  {
12
  "epoch": 1.0,
13
  "eval_B-Claim": {
14
+ "f1-score": 0.17153996101364524,
15
+ "precision": 0.25287356321839083,
16
+ "recall": 0.12979351032448377,
17
+ "support": 339.0
18
  },
19
  "eval_B-MajorClaim": {
20
+ "f1-score": 0.08383233532934131,
21
+ "precision": 1.0,
22
+ "recall": 0.04375,
23
+ "support": 160.0
24
  },
25
  "eval_B-Premise": {
26
+ "f1-score": 0.8469620831429876,
27
+ "precision": 0.7427884615384616,
28
+ "recall": 0.9851222104144527,
29
+ "support": 941.0
30
  },
31
  "eval_I-Claim": {
32
+ "f1-score": 0.5420081967213116,
33
+ "precision": 0.6803858520900321,
34
+ "recall": 0.4504044274159217,
35
+ "support": 4698.0
36
  },
37
  "eval_I-MajorClaim": {
38
+ "f1-score": 0.8343351767251743,
39
+ "precision": 0.8141717503519474,
40
+ "recall": 0.8555226824457594,
41
+ "support": 2028.0
42
  },
43
  "eval_I-Premise": {
44
+ "f1-score": 0.9004323458767015,
45
+ "precision": 0.8590809093131264,
46
+ "recall": 0.9459659511472983,
47
+ "support": 14861.0
48
  },
49
  "eval_O": {
50
+ "f1-score": 0.9988389078242631,
51
+ "precision": 0.9991008541885209,
52
+ "recall": 0.9985770987793006,
53
+ "support": 13353.0
54
  },
55
+ "eval_accuracy": 0.8856789444749863,
56
+ "eval_loss": 0.28347474336624146,
57
  "eval_macro avg": {
58
+ "f1-score": 0.6254212866619178,
59
+ "precision": 0.76405734152864,
60
+ "recall": 0.629876554361031,
61
+ "support": 36380.0
62
+ },
63
+ "eval_runtime": 5.0448,
64
+ "eval_samples_per_second": 16.056,
65
+ "eval_steps_per_second": 2.18,
66
  "eval_weighted avg": {
67
+ "f1-score": 0.8748148382495958,
68
+ "precision": 0.8768575102351055,
69
+ "recall": 0.8856789444749863,
70
+ "support": 36380.0
71
  },
72
  "step": 81
73
  },
74
  {
75
  "epoch": 2.0,
76
  "eval_B-Claim": {
77
+ "f1-score": 0.5137931034482759,
78
+ "precision": 0.6182572614107884,
79
+ "recall": 0.43952802359882004,
80
+ "support": 339.0
81
  },
82
  "eval_B-MajorClaim": {
83
+ "f1-score": 0.7622641509433963,
84
+ "precision": 0.9619047619047619,
85
+ "recall": 0.63125,
86
+ "support": 160.0
87
  },
88
  "eval_B-Premise": {
89
+ "f1-score": 0.8853910477127397,
90
+ "precision": 0.8241758241758241,
91
+ "recall": 0.9564293304994687,
92
+ "support": 941.0
93
  },
94
  "eval_I-Claim": {
95
+ "f1-score": 0.5413588470388762,
96
+ "precision": 0.6279853891542568,
97
+ "recall": 0.47573435504469985,
98
+ "support": 4698.0
99
  },
100
  "eval_I-MajorClaim": {
101
+ "f1-score": 0.7949260042283298,
102
+ "precision": 0.856492027334852,
103
+ "recall": 0.7416173570019724,
104
+ "support": 2028.0
105
  },
106
  "eval_I-Premise": {
107
+ "f1-score": 0.9007064868336545,
108
+ "precision": 0.8614779777627618,
109
+ "recall": 0.9436780835744566,
110
+ "support": 14861.0
111
  },
112
  "eval_O": {
113
+ "f1-score": 0.9988389947942025,
114
+ "precision": 0.9990260713215463,
115
+ "recall": 0.9986519883172321,
116
+ "support": 13353.0
117
  },
118
+ "eval_accuracy": 0.8864211105002748,
119
+ "eval_loss": 0.2809496521949768,
120
  "eval_macro avg": {
121
+ "f1-score": 0.7710398049999251,
122
+ "precision": 0.8213313304378275,
123
+ "recall": 0.7409841625766643,
124
+ "support": 36380.0
125
+ },
126
+ "eval_runtime": 5.0579,
127
+ "eval_samples_per_second": 16.014,
128
+ "eval_steps_per_second": 2.175,
129
  "eval_weighted avg": {
130
+ "f1-score": 0.8798131143596267,
131
+ "precision": 0.8787439244541853,
132
+ "recall": 0.8864211105002748,
133
+ "support": 36380.0
134
  },
135
  "step": 162
136
  },
137
  {
138
  "epoch": 3.0,
139
  "eval_B-Claim": {
140
+ "f1-score": 0.6401137980085349,
141
+ "precision": 0.6181318681318682,
142
+ "recall": 0.6637168141592921,
143
+ "support": 339.0
144
  },
145
  "eval_B-MajorClaim": {
146
+ "f1-score": 0.7918781725888324,
147
+ "precision": 0.6666666666666666,
148
+ "recall": 0.975,
149
+ "support": 160.0
150
  },
151
  "eval_B-Premise": {
152
+ "f1-score": 0.8866442199775534,
153
+ "precision": 0.93935790725327,
154
+ "recall": 0.8395324123273114,
155
+ "support": 941.0
156
  },
157
  "eval_I-Claim": {
158
+ "f1-score": 0.6254390633315594,
159
+ "precision": 0.6255056418990845,
160
+ "recall": 0.6253724989357173,
161
+ "support": 4698.0
162
  },
163
  "eval_I-MajorClaim": {
164
+ "f1-score": 0.76480605487228,
165
+ "precision": 0.6205096714768191,
166
+ "recall": 0.9965483234714004,
167
+ "support": 2028.0
168
  },
169
  "eval_I-Premise": {
170
+ "f1-score": 0.9049205625504156,
171
+ "precision": 0.9449897450922942,
172
+ "recall": 0.868111163447951,
173
+ "support": 14861.0
174
  },
175
  "eval_O": {
176
+ "f1-score": 0.9988758992805756,
177
+ "precision": 0.9995500562429697,
178
+ "recall": 0.9982026510896428,
179
+ "support": 13353.0
180
  },
181
+ "eval_accuracy": 0.8894997251236944,
182
+ "eval_loss": 0.318760484457016,
183
  "eval_macro avg": {
184
+ "f1-score": 0.8018111100871074,
185
+ "precision": 0.7735302223947104,
186
+ "recall": 0.852354837633045,
187
+ "support": 36380.0
188
+ },
189
+ "eval_runtime": 5.0862,
190
+ "eval_samples_per_second": 15.925,
191
+ "eval_steps_per_second": 2.163,
192
  "eval_weighted avg": {
193
+ "f1-score": 0.8920666591013163,
194
+ "precision": 0.9012548868310761,
195
+ "recall": 0.8894997251236944,
196
+ "support": 36380.0
197
  },
198
  "step": 243
199
  },
200
  {
201
  "epoch": 4.0,
202
  "eval_B-Claim": {
203
+ "f1-score": 0.7034883720930232,
204
+ "precision": 0.6934097421203438,
205
+ "recall": 0.7138643067846607,
206
+ "support": 339.0
207
  },
208
  "eval_B-MajorClaim": {
209
+ "f1-score": 0.8958990536277602,
210
+ "precision": 0.9044585987261147,
211
+ "recall": 0.8875,
212
+ "support": 160.0
213
  },
214
  "eval_B-Premise": {
215
+ "f1-score": 0.9051172707889126,
216
+ "precision": 0.9080213903743316,
217
+ "recall": 0.9022316684378321,
218
+ "support": 941.0
219
  },
220
  "eval_I-Claim": {
221
+ "f1-score": 0.6932699265998139,
222
+ "precision": 0.6739698492462312,
223
+ "recall": 0.7137079608343976,
224
+ "support": 4698.0
225
  },
226
  "eval_I-MajorClaim": {
227
+ "f1-score": 0.8904009720534629,
228
+ "precision": 0.877815045519885,
229
+ "recall": 0.903353057199211,
230
+ "support": 2028.0
231
  },
232
  "eval_I-Premise": {
233
+ "f1-score": 0.9127480293558032,
234
+ "precision": 0.9218310342461052,
235
+ "recall": 0.9038422717179194,
236
+ "support": 14861.0
237
  },
238
  "eval_O": {
239
+ "f1-score": 0.9981619715668254,
240
+ "precision": 0.9999248459341651,
241
+ "recall": 0.9964053021792856,
242
+ "support": 13353.0
243
  },
244
+ "eval_accuracy": 0.9113523914238593,
245
+ "eval_loss": 0.2517726719379425,
246
  "eval_macro avg": {
247
+ "f1-score": 0.8570122280122289,
248
+ "precision": 0.8542043580238825,
249
+ "recall": 0.8601292238790438,
250
+ "support": 36380.0
251
+ },
252
+ "eval_runtime": 5.062,
253
+ "eval_samples_per_second": 16.002,
254
+ "eval_steps_per_second": 2.173,
255
  "eval_weighted avg": {
256
+ "f1-score": 0.9122886837716081,
257
+ "precision": 0.9134709768686261,
258
+ "recall": 0.9113523914238593,
259
+ "support": 36380.0
260
  },
261
  "step": 324
262
  },
263
  {
264
  "epoch": 5.0,
265
  "eval_B-Claim": {
266
+ "f1-score": 0.6590538336052201,
267
+ "precision": 0.7372262773722628,
268
+ "recall": 0.5958702064896755,
269
+ "support": 339.0
270
  },
271
  "eval_B-MajorClaim": {
272
+ "f1-score": 0.9078947368421054,
273
+ "precision": 0.9583333333333334,
274
+ "recall": 0.8625,
275
+ "support": 160.0
276
  },
277
  "eval_B-Premise": {
278
+ "f1-score": 0.9066802651708312,
279
+ "precision": 0.8715686274509804,
280
+ "recall": 0.944739638682253,
281
+ "support": 941.0
282
  },
283
  "eval_I-Claim": {
284
+ "f1-score": 0.6513589503280225,
285
+ "precision": 0.7243355914538823,
286
+ "recall": 0.5917411664538101,
287
+ "support": 4698.0
288
  },
289
  "eval_I-MajorClaim": {
290
+ "f1-score": 0.8981975120588981,
291
+ "precision": 0.9256933542647828,
292
+ "recall": 0.8722879684418146,
293
+ "support": 2028.0
294
  },
295
  "eval_I-Premise": {
296
+ "f1-score": 0.9158848058378942,
297
+ "precision": 0.8877170824123777,
298
+ "recall": 0.9458986609245676,
299
+ "support": 14861.0
300
  },
301
  "eval_O": {
302
+ "f1-score": 0.9994384336041331,
303
+ "precision": 0.9992513849378649,
304
+ "recall": 0.9996255523103422,
305
+ "support": 13353.0
306
  },
307
+ "eval_accuracy": 0.9121220450797142,
308
+ "eval_loss": 0.2739432156085968,
309
  "eval_macro avg": {
310
+ "f1-score": 0.8483583624924435,
311
+ "precision": 0.8720179501750691,
312
+ "recall": 0.8303804561860663,
313
+ "support": 36380.0
314
+ },
315
+ "eval_runtime": 5.0932,
316
+ "eval_samples_per_second": 15.904,
317
+ "eval_steps_per_second": 2.16,
318
  "eval_weighted avg": {
319
+ "f1-score": 0.9087400479269403,
320
+ "precision": 0.9081638580455985,
321
+ "recall": 0.9121220450797142,
322
+ "support": 36380.0
323
  },
324
  "step": 405
325
  },
326
  {
327
  "epoch": 6.0,
328
  "eval_B-Claim": {
329
+ "f1-score": 0.6675461741424802,
330
+ "precision": 0.60381861575179,
331
+ "recall": 0.7463126843657817,
332
+ "support": 339.0
333
  },
334
  "eval_B-MajorClaim": {
335
+ "f1-score": 0.887608069164265,
336
+ "precision": 0.8235294117647058,
337
+ "recall": 0.9625,
338
+ "support": 160.0
339
  },
340
  "eval_B-Premise": {
341
+ "f1-score": 0.8737316798196167,
342
+ "precision": 0.9303721488595438,
343
+ "recall": 0.8235919234856536,
344
+ "support": 941.0
345
  },
346
  "eval_I-Claim": {
347
+ "f1-score": 0.6529236868186323,
348
+ "precision": 0.6109050445103857,
349
+ "recall": 0.7011494252873564,
350
+ "support": 4698.0
351
  },
352
  "eval_I-MajorClaim": {
353
+ "f1-score": 0.8689320388349515,
354
+ "precision": 0.7863418530351438,
355
+ "recall": 0.9709072978303748,
356
+ "support": 2028.0
357
  },
358
  "eval_I-Premise": {
359
+ "f1-score": 0.8937734066010992,
360
+ "precision": 0.9312910284463894,
361
+ "recall": 0.8591615638247763,
362
+ "support": 14861.0
363
  },
364
  "eval_O": {
365
+ "f1-score": 0.9988009592326139,
366
+ "precision": 0.9994750656167979,
367
+ "recall": 0.9981277615517112,
368
+ "support": 13353.0
369
  },
370
+ "eval_accuracy": 0.8944749862561847,
371
+ "eval_loss": 0.37784042954444885,
372
  "eval_macro avg": {
373
+ "f1-score": 0.8347594306590942,
374
+ "precision": 0.8122475954263937,
375
+ "recall": 0.8659643794779507,
376
+ "support": 36380.0
377
+ },
378
+ "eval_runtime": 5.0734,
379
+ "eval_samples_per_second": 15.966,
380
+ "eval_steps_per_second": 2.168,
381
  "eval_weighted avg": {
382
+ "f1-score": 0.8971820344797716,
383
+ "precision": 0.9033144340485707,
384
+ "recall": 0.8944749862561847,
385
+ "support": 36380.0
386
  },
387
  "step": 486
388
  },
389
  {
390
  "epoch": 6.17,
391
+ "grad_norm": 21.778270721435547,
392
  "learning_rate": 1.7530864197530865e-05,
393
+ "loss": 0.2481,
394
  "step": 500
395
  },
396
  {
397
  "epoch": 7.0,
398
  "eval_B-Claim": {
399
+ "f1-score": 0.6489859594383774,
400
+ "precision": 0.6887417218543046,
401
+ "recall": 0.6135693215339233,
402
+ "support": 339.0
403
  },
404
  "eval_B-MajorClaim": {
405
+ "f1-score": 0.8852459016393444,
406
+ "precision": 0.9310344827586207,
407
+ "recall": 0.84375,
408
+ "support": 160.0
409
  },
410
  "eval_B-Premise": {
411
+ "f1-score": 0.9011898603207449,
412
+ "precision": 0.8780241935483871,
413
+ "recall": 0.9256110520722636,
414
+ "support": 941.0
415
  },
416
  "eval_I-Claim": {
417
+ "f1-score": 0.626564114338193,
418
+ "precision": 0.6800398704211313,
419
+ "recall": 0.5808854831843338,
420
+ "support": 4698.0
421
  },
422
  "eval_I-MajorClaim": {
423
+ "f1-score": 0.8813559322033898,
424
+ "precision": 0.9049350649350649,
425
+ "recall": 0.8589743589743589,
426
+ "support": 2028.0
427
  },
428
  "eval_I-Premise": {
429
+ "f1-score": 0.9073595340161655,
430
+ "precision": 0.8831698305516626,
431
+ "recall": 0.9329116479375547,
432
+ "support": 14861.0
433
  },
434
  "eval_O": {
435
+ "f1-score": 0.9981994148098132,
436
  "precision": 1.0,
437
+ "recall": 0.9964053021792856,
438
+ "support": 13353.0
439
  },
440
+ "eval_accuracy": 0.9030786146234194,
441
+ "eval_loss": 0.4109443426132202,
442
  "eval_macro avg": {
443
+ "f1-score": 0.8355572452522898,
444
+ "precision": 0.8522778805813102,
445
+ "recall": 0.8217295951259599,
446
+ "support": 36380.0
447
+ },
448
+ "eval_runtime": 5.0454,
449
+ "eval_samples_per_second": 16.054,
450
+ "eval_steps_per_second": 2.18,
451
  "eval_weighted avg": {
452
+ "f1-score": 0.9003265559019435,
453
+ "precision": 0.8992988510674564,
454
+ "recall": 0.9030786146234194,
455
+ "support": 36380.0
456
  },
457
  "step": 567
458
  }
 
462
  "num_input_tokens_seen": 0,
463
  "num_train_epochs": 50,
464
  "save_steps": 500,
465
+ "total_flos": 1003409801793000.0,
466
  "train_batch_size": 4,
467
  "trial_name": null,
468
  "trial_params": null
checkpoint-567/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2f0bdafd19c0347fe87a3f27a2ea54a847df1f75da4e3bbd7bf587c614e2949
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3de2ea286aed4cce53d86abf84d503faba79a292e98a5c89e444e2125b5ea5
3
  size 4920