Theoreticallyhugo commited on
Commit
c99e875
1 Parent(s): f4ade46

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 sha256:0267fe63479a22e7ce7f2cbb00685e6955a8072ed4d58773ed25418e709f932c
3
  size 592330980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60412acb72f83fedb9248d0a7ee1769e52aa232b71b130b017c10f51d17e28ae
3
  size 592330980
checkpoint-567/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5773e7cd0bae70ef31990a7b487c8b6b7de6e46880299cda51a00e627ddc721
3
  size 1014670074
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87eafd7446cd1277f3cbabb568f8a4d97354f03981954188b2a1d29a53927da5
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:df74477c8049c831c537fb964d31e59ec8d12121ecfdafd2834f9022f29cfdc5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37c3795111d23ad6190712c2991585b141e7dd666ac9350ac9e35c845a45539
3
  size 14244
checkpoint-567/trainer_state.json CHANGED
@@ -11,384 +11,384 @@
11
  {
12
  "epoch": 1.0,
13
  "eval_B-Claim": {
14
- "f1-score": 0.32421052631578945,
15
- "precision": 0.42777777777777776,
16
- "recall": 0.26101694915254237,
17
- "support": 295.0
18
  },
19
  "eval_B-MajorClaim": {
20
- "f1-score": 0.192090395480226,
21
- "precision": 0.8095238095238095,
22
- "recall": 0.10897435897435898,
23
- "support": 156.0
24
  },
25
  "eval_B-Premise": {
26
- "f1-score": 0.8566265060240965,
27
- "precision": 0.7620578778135049,
28
- "recall": 0.9779917469050894,
29
- "support": 727.0
30
  },
31
  "eval_I-Claim": {
32
- "f1-score": 0.5001390820584144,
33
- "precision": 0.5900886117492615,
34
- "recall": 0.43398503499879315,
35
- "support": 4143.0
36
  },
37
  "eval_I-MajorClaim": {
38
- "f1-score": 0.776470588235294,
39
- "precision": 0.6649333766655834,
40
- "recall": 0.93296853625171,
41
- "support": 2193.0
42
  },
43
  "eval_I-Premise": {
44
- "f1-score": 0.8861458374413376,
45
- "precision": 0.8781460059402845,
46
- "recall": 0.8942927644670858,
47
- "support": 12563.0
48
  },
49
  "eval_O": {
50
- "f1-score": 0.9987647926046939,
51
- "precision": 0.9977708781147998,
52
- "recall": 0.9997606892150607,
53
- "support": 12536.0
54
  },
55
- "eval_accuracy": 0.8713396498328887,
56
- "eval_loss": 0.3092103600502014,
57
  "eval_macro avg": {
58
- "f1-score": 0.647778246879979,
59
- "precision": 0.732899762512146,
60
- "recall": 0.6584271542806628,
61
- "support": 32613.0
62
- },
63
- "eval_runtime": 4.965,
64
- "eval_samples_per_second": 16.314,
65
- "eval_steps_per_second": 2.215,
66
  "eval_weighted avg": {
67
- "f1-score": 0.8639627599323451,
68
- "precision": 0.8662078389010613,
69
- "recall": 0.8713396498328887,
70
- "support": 32613.0
71
  },
72
  "step": 81
73
  },
74
  {
75
  "epoch": 2.0,
76
  "eval_B-Claim": {
77
- "f1-score": 0.6186291739894552,
78
- "precision": 0.6423357664233577,
79
- "recall": 0.5966101694915255,
80
- "support": 295.0
81
  },
82
  "eval_B-MajorClaim": {
83
- "f1-score": 0.8113879003558718,
84
- "precision": 0.912,
85
- "recall": 0.7307692307692307,
86
- "support": 156.0
87
  },
88
  "eval_B-Premise": {
89
- "f1-score": 0.8871181938911022,
90
- "precision": 0.8575096277278562,
91
- "recall": 0.9188445667125172,
92
- "support": 727.0
93
  },
94
  "eval_I-Claim": {
95
- "f1-score": 0.656253149249219,
96
- "precision": 0.5633217993079584,
97
- "recall": 0.7859039343470915,
98
- "support": 4143.0
99
  },
100
  "eval_I-MajorClaim": {
101
- "f1-score": 0.8368159203980099,
102
- "precision": 0.9206349206349206,
103
- "recall": 0.7669858641130871,
104
- "support": 2193.0
105
  },
106
  "eval_I-Premise": {
107
- "f1-score": 0.8831027253668763,
108
- "precision": 0.933020288827855,
109
- "recall": 0.8382551938231314,
110
- "support": 12563.0
111
  },
112
  "eval_O": {
113
- "f1-score": 0.9998006141085457,
114
- "precision": 0.9996013077107089,
115
- "recall": 1.0,
116
- "support": 12536.0
117
  },
118
- "eval_accuracy": 0.8880814399165977,
119
- "eval_loss": 0.2581149935722351,
120
  "eval_macro avg": {
121
- "f1-score": 0.8133010967655829,
122
- "precision": 0.8326319586618081,
123
- "recall": 0.8053384227509405,
124
- "support": 32613.0
125
- },
126
- "eval_runtime": 5.0296,
127
- "eval_samples_per_second": 16.105,
128
- "eval_steps_per_second": 2.187,
129
  "eval_weighted avg": {
130
- "f1-score": 0.8933836566327042,
131
- "precision": 0.9064023864086126,
132
- "recall": 0.8880814399165977,
133
- "support": 32613.0
134
  },
135
  "step": 162
136
  },
137
  {
138
  "epoch": 3.0,
139
  "eval_B-Claim": {
140
- "f1-score": 0.6576271186440678,
141
- "precision": 0.6576271186440678,
142
- "recall": 0.6576271186440678,
143
- "support": 295.0
144
  },
145
  "eval_B-MajorClaim": {
146
- "f1-score": 0.8673139158576051,
147
- "precision": 0.8758169934640523,
148
- "recall": 0.8589743589743589,
149
- "support": 156.0
150
  },
151
  "eval_B-Premise": {
152
- "f1-score": 0.8838487972508591,
153
- "precision": 0.8832417582417582,
154
- "recall": 0.8844566712517193,
155
- "support": 727.0
156
  },
157
  "eval_I-Claim": {
158
- "f1-score": 0.6468460321049062,
159
- "precision": 0.6083351052519669,
160
- "recall": 0.6905623944001931,
161
- "support": 4143.0
162
  },
163
  "eval_I-MajorClaim": {
164
- "f1-score": 0.8695855771482088,
165
- "precision": 0.8936477382098171,
166
- "recall": 0.8467852257181943,
167
- "support": 2193.0
168
  },
169
  "eval_I-Premise": {
170
- "f1-score": 0.8926256077795786,
171
- "precision": 0.9090533960551291,
172
- "recall": 0.8767810236408501,
173
- "support": 12563.0
174
  },
175
  "eval_O": {
176
- "f1-score": 0.9998803589232302,
177
- "precision": 0.9997607464710104,
178
- "recall": 1.0,
179
- "support": 12536.0
180
  },
181
- "eval_accuracy": 0.8965749854352559,
182
- "eval_loss": 0.2399493306875229,
183
  "eval_macro avg": {
184
- "f1-score": 0.8311039153869222,
185
- "precision": 0.8324975509054003,
186
- "recall": 0.8307409703756262,
187
- "support": 32613.0
188
- },
189
- "eval_runtime": 5.0024,
190
- "eval_samples_per_second": 16.192,
191
- "eval_steps_per_second": 2.199,
192
  "eval_weighted avg": {
193
- "f1-score": 0.8986385496019461,
194
- "precision": 0.9016737059631544,
195
- "recall": 0.8965749854352559,
196
- "support": 32613.0
197
  },
198
  "step": 243
199
  },
200
  {
201
  "epoch": 4.0,
202
  "eval_B-Claim": {
203
- "f1-score": 0.6106346483704975,
204
- "precision": 0.6180555555555556,
205
- "recall": 0.6033898305084746,
206
- "support": 295.0
207
  },
208
  "eval_B-MajorClaim": {
209
- "f1-score": 0.8498583569405098,
210
- "precision": 0.7614213197969543,
211
- "recall": 0.9615384615384616,
212
- "support": 156.0
213
  },
214
  "eval_B-Premise": {
215
- "f1-score": 0.8746478873239436,
216
- "precision": 0.8961038961038961,
217
- "recall": 0.8541953232462174,
218
- "support": 727.0
219
  },
220
  "eval_I-Claim": {
221
- "f1-score": 0.5964912280701754,
222
- "precision": 0.6109845608706657,
223
- "recall": 0.5826695631185131,
224
- "support": 4143.0
225
  },
226
  "eval_I-MajorClaim": {
227
- "f1-score": 0.8631961259079903,
228
- "precision": 0.7741585233441911,
229
- "recall": 0.9753761969904241,
230
- "support": 2193.0
231
  },
232
  "eval_I-Premise": {
233
- "f1-score": 0.8933694290678411,
234
- "precision": 0.9071885770556376,
235
- "recall": 0.8799649765183475,
236
- "support": 12563.0
237
  },
238
  "eval_O": {
239
- "f1-score": 0.9999601132782897,
240
- "precision": 1.0,
241
- "recall": 0.9999202297383536,
242
- "support": 12536.0
243
  },
244
- "eval_accuracy": 0.8920369177935179,
245
- "eval_loss": 0.2815629839897156,
246
  "eval_macro avg": {
247
- "f1-score": 0.8125939698513209,
248
- "precision": 0.7954160618181286,
249
- "recall": 0.8367220830941131,
250
- "support": 32613.0
251
- },
252
- "eval_runtime": 4.9474,
253
- "eval_samples_per_second": 16.372,
254
- "eval_steps_per_second": 2.223,
255
  "eval_weighted avg": {
256
- "f1-score": 0.8914155863760895,
257
- "precision": 0.892730641712682,
258
- "recall": 0.8920369177935179,
259
- "support": 32613.0
260
  },
261
  "step": 324
262
  },
263
  {
264
  "epoch": 5.0,
265
  "eval_B-Claim": {
266
- "f1-score": 0.6796116504854369,
267
- "precision": 0.6501547987616099,
268
- "recall": 0.711864406779661,
269
- "support": 295.0
270
  },
271
  "eval_B-MajorClaim": {
272
- "f1-score": 0.8746177370030581,
273
- "precision": 0.8362573099415205,
274
- "recall": 0.9166666666666666,
275
- "support": 156.0
276
  },
277
  "eval_B-Premise": {
278
- "f1-score": 0.8836879432624114,
279
- "precision": 0.9121522693997072,
280
- "recall": 0.8569463548830811,
281
- "support": 727.0
282
  },
283
  "eval_I-Claim": {
284
- "f1-score": 0.6557152635181382,
285
- "precision": 0.6216742375081116,
286
- "recall": 0.6937002172338885,
287
- "support": 4143.0
288
  },
289
  "eval_I-MajorClaim": {
290
- "f1-score": 0.8859746610357857,
291
- "precision": 0.8642671292281006,
292
- "recall": 0.9088007295941632,
293
- "support": 2193.0
294
  },
295
  "eval_I-Premise": {
296
- "f1-score": 0.8956745077255495,
297
- "precision": 0.9180177168644492,
298
- "recall": 0.874393058982727,
299
- "support": 12563.0
300
  },
301
  "eval_O": {
302
- "f1-score": 0.9998006141085457,
303
- "precision": 0.9996013077107089,
304
- "recall": 1.0,
305
- "support": 12536.0
306
  },
307
- "eval_accuracy": 0.9003771502161715,
308
- "eval_loss": 0.2959797978401184,
309
  "eval_macro avg": {
310
- "f1-score": 0.839297482448418,
311
- "precision": 0.8288749670591724,
312
- "recall": 0.8517673477343124,
313
- "support": 32613.0
314
- },
315
- "eval_runtime": 4.9768,
316
- "eval_samples_per_second": 16.275,
317
- "eval_steps_per_second": 2.21,
318
  "eval_weighted avg": {
319
- "f1-score": 0.9022413468876027,
320
- "precision": 0.9051721478141229,
321
- "recall": 0.9003771502161715,
322
- "support": 32613.0
323
  },
324
  "step": 405
325
  },
326
  {
327
  "epoch": 6.0,
328
  "eval_B-Claim": {
329
- "f1-score": 0.6655518394648828,
330
- "precision": 0.6567656765676567,
331
- "recall": 0.6745762711864407,
332
- "support": 295.0
333
  },
334
  "eval_B-MajorClaim": {
335
- "f1-score": 0.8807339449541285,
336
- "precision": 0.8421052631578947,
337
- "recall": 0.9230769230769231,
338
- "support": 156.0
339
  },
340
  "eval_B-Premise": {
341
- "f1-score": 0.8812849162011174,
342
- "precision": 0.8950354609929078,
343
- "recall": 0.8679504814305364,
344
- "support": 727.0
345
  },
346
  "eval_I-Claim": {
347
- "f1-score": 0.634203994799669,
348
- "precision": 0.6213524779990737,
349
- "recall": 0.647598358677287,
350
- "support": 4143.0
351
  },
352
  "eval_I-MajorClaim": {
353
- "f1-score": 0.8926454445664106,
354
- "precision": 0.8607112616426758,
355
- "recall": 0.9270405836753306,
356
- "support": 2193.0
357
  },
358
  "eval_I-Premise": {
359
- "f1-score": 0.8911586596689544,
360
- "precision": 0.9041533546325878,
361
- "recall": 0.8785321977234737,
362
- "support": 12563.0
363
  },
364
  "eval_O": {
365
- "f1-score": 0.9995614559661922,
366
- "precision": 0.9991232964055152,
367
- "recall": 1.0,
368
- "support": 12536.0
369
  },
370
- "eval_accuracy": 0.8972802256768774,
371
- "eval_loss": 0.33718833327293396,
372
  "eval_macro avg": {
373
- "f1-score": 0.8350200365173363,
374
- "precision": 0.8256066844854731,
375
- "recall": 0.8455392593957132,
376
- "support": 32613.0
377
- },
378
- "eval_runtime": 4.9878,
379
- "eval_samples_per_second": 16.24,
380
- "eval_steps_per_second": 2.205,
381
  "eval_weighted avg": {
382
- "f1-score": 0.8979742337698349,
383
- "precision": 0.8990738793396261,
384
- "recall": 0.8972802256768774,
385
- "support": 32613.0
386
  },
387
  "step": 486
388
  },
389
  {
390
  "epoch": 6.17,
391
- "grad_norm": 10.722956657409668,
392
  "learning_rate": 1.7530864197530865e-05,
393
  "loss": 0.2434,
394
  "step": 500
@@ -396,63 +396,63 @@
396
  {
397
  "epoch": 7.0,
398
  "eval_B-Claim": {
399
- "f1-score": 0.6608695652173914,
400
- "precision": 0.6785714285714286,
401
- "recall": 0.6440677966101694,
402
- "support": 295.0
403
  },
404
  "eval_B-MajorClaim": {
405
- "f1-score": 0.875,
406
- "precision": 0.8536585365853658,
407
- "recall": 0.8974358974358975,
408
- "support": 156.0
409
  },
410
  "eval_B-Premise": {
411
- "f1-score": 0.8905608755129958,
412
- "precision": 0.8857142857142857,
413
- "recall": 0.8954607977991746,
414
- "support": 727.0
415
  },
416
  "eval_I-Claim": {
417
- "f1-score": 0.6306948332909138,
418
- "precision": 0.6670255720053836,
419
- "recall": 0.5981173062997828,
420
- "support": 4143.0
421
  },
422
  "eval_I-MajorClaim": {
423
- "f1-score": 0.890302764370338,
424
- "precision": 0.8579281183932347,
425
- "recall": 0.9252165982672138,
426
- "support": 2193.0
427
  },
428
  "eval_I-Premise": {
429
- "f1-score": 0.9037468972853708,
430
- "precision": 0.8947573724449992,
431
- "recall": 0.9129188888004458,
432
- "support": 12563.0
433
  },
434
  "eval_O": {
435
- "f1-score": 1.0,
436
  "precision": 1.0,
437
- "recall": 1.0,
438
- "support": 12536.0
439
  },
440
- "eval_accuracy": 0.9043326280930917,
441
- "eval_loss": 0.43479764461517334,
442
  "eval_macro avg": {
443
- "f1-score": 0.8358821336681442,
444
- "precision": 0.8339507591020997,
445
- "recall": 0.8390310407446692,
446
- "support": 32613.0
447
- },
448
- "eval_runtime": 4.9479,
449
- "eval_samples_per_second": 16.371,
450
- "eval_steps_per_second": 2.223,
451
  "eval_weighted avg": {
452
- "f1-score": 0.9025256555797259,
453
- "precision": 0.9014510706568353,
454
- "recall": 0.9043326280930917,
455
- "support": 32613.0
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": 1003409801793000.0,
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": 0.18764302059496568,
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
 
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
  "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
checkpoint-567/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eff186592c44100b7fd5c301c21b9eebfc7f8bd335567cdc6ffe4a4d32ec927
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f0bdafd19c0347fe87a3f27a2ea54a847df1f75da4e3bbd7bf587c614e2949
3
  size 4920