Theoreticallyhugo
commited on
Commit
•
911648d
1
Parent(s):
79429ca
Training in progress, epoch 14, checkpoint
Browse files
checkpoint-1134/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592318676
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81be16fcef6861639ab1d7dc2a0b57bb0395142c0eb4bc342266adcf0fd537bc
|
3 |
size 592318676
|
checkpoint-1134/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014645498
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7d52305fd80970a572bd126e844e6d8687f1d7669713a1cb571941f2611b7e9
|
3 |
size 1014645498
|
checkpoint-1134/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:597b4af46402de550809c9388e42f2a2ec66bffe613bfb15b48cafe52a9de8a6
|
3 |
size 1064
|
checkpoint-1134/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint":
|
4 |
"epoch": 14.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1134,
|
@@ -11,568 +11,568 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_I": {
|
20 |
-
"f1-score": 0.
|
21 |
-
"precision": 0.
|
22 |
-
"recall": 0.
|
23 |
-
"support":
|
24 |
},
|
25 |
"eval_O": {
|
26 |
-
"f1-score": 0.
|
27 |
-
"precision": 0.
|
28 |
-
"recall": 0.
|
29 |
-
"support":
|
30 |
},
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"eval_loss": 0.
|
33 |
"eval_macro avg": {
|
34 |
-
"f1-score": 0.
|
35 |
-
"precision": 0.
|
36 |
-
"recall": 0.
|
37 |
-
"support":
|
38 |
-
},
|
39 |
-
"eval_runtime":
|
40 |
-
"eval_samples_per_second":
|
41 |
-
"eval_steps_per_second":
|
42 |
"eval_weighted avg": {
|
43 |
-
"f1-score": 0.
|
44 |
-
"precision": 0.
|
45 |
-
"recall": 0.
|
46 |
-
"support":
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
-
"f1-score": 0.
|
54 |
-
"precision": 0.
|
55 |
-
"recall": 0.
|
56 |
-
"support":
|
57 |
},
|
58 |
"eval_I": {
|
59 |
-
"f1-score": 0.
|
60 |
-
"precision": 0.
|
61 |
-
"recall": 0.
|
62 |
-
"support":
|
63 |
},
|
64 |
"eval_O": {
|
65 |
-
"f1-score": 0.
|
66 |
-
"precision": 0.
|
67 |
-
"recall": 0.
|
68 |
-
"support":
|
69 |
},
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_loss": 0.
|
72 |
"eval_macro avg": {
|
73 |
-
"f1-score": 0.
|
74 |
-
"precision": 0.
|
75 |
-
"recall": 0.
|
76 |
-
"support":
|
77 |
-
},
|
78 |
-
"eval_runtime":
|
79 |
-
"eval_samples_per_second":
|
80 |
-
"eval_steps_per_second":
|
81 |
"eval_weighted avg": {
|
82 |
-
"f1-score": 0.
|
83 |
-
"precision": 0.
|
84 |
-
"recall": 0.
|
85 |
-
"support":
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
-
"f1-score": 0.
|
93 |
-
"precision": 0.
|
94 |
-
"recall": 0.
|
95 |
-
"support":
|
96 |
},
|
97 |
"eval_I": {
|
98 |
-
"f1-score": 0.
|
99 |
-
"precision": 0.
|
100 |
-
"recall": 0.
|
101 |
-
"support":
|
102 |
},
|
103 |
"eval_O": {
|
104 |
-
"f1-score": 0.
|
105 |
-
"precision": 0.
|
106 |
-
"recall": 0.
|
107 |
-
"support":
|
108 |
},
|
109 |
-
"eval_accuracy": 0.
|
110 |
-
"eval_loss": 0.
|
111 |
"eval_macro avg": {
|
112 |
-
"f1-score": 0.
|
113 |
-
"precision": 0.
|
114 |
-
"recall": 0.
|
115 |
-
"support":
|
116 |
-
},
|
117 |
-
"eval_runtime":
|
118 |
-
"eval_samples_per_second":
|
119 |
-
"eval_steps_per_second":
|
120 |
"eval_weighted avg": {
|
121 |
-
"f1-score": 0.
|
122 |
-
"precision": 0.
|
123 |
-
"recall": 0.
|
124 |
-
"support":
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
-
"f1-score": 0.
|
132 |
-
"precision": 0.
|
133 |
-
"recall": 0.
|
134 |
-
"support":
|
135 |
},
|
136 |
"eval_I": {
|
137 |
-
"f1-score": 0.
|
138 |
-
"precision": 0.
|
139 |
-
"recall": 0.
|
140 |
-
"support":
|
141 |
},
|
142 |
"eval_O": {
|
143 |
-
"f1-score": 0.
|
144 |
-
"precision": 0.
|
145 |
-
"recall": 0.
|
146 |
-
"support":
|
147 |
},
|
148 |
-
"eval_accuracy": 0.
|
149 |
-
"eval_loss": 0.
|
150 |
"eval_macro avg": {
|
151 |
-
"f1-score": 0.
|
152 |
-
"precision": 0.
|
153 |
-
"recall": 0.
|
154 |
-
"support":
|
155 |
-
},
|
156 |
-
"eval_runtime":
|
157 |
-
"eval_samples_per_second":
|
158 |
-
"eval_steps_per_second":
|
159 |
"eval_weighted avg": {
|
160 |
-
"f1-score": 0.
|
161 |
-
"precision": 0.
|
162 |
-
"recall": 0.
|
163 |
-
"support":
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
-
"f1-score": 0.
|
171 |
-
"precision": 0.
|
172 |
-
"recall": 0.
|
173 |
-
"support":
|
174 |
},
|
175 |
"eval_I": {
|
176 |
-
"f1-score": 0.
|
177 |
-
"precision": 0.
|
178 |
-
"recall": 0.
|
179 |
-
"support":
|
180 |
},
|
181 |
"eval_O": {
|
182 |
-
"f1-score": 0.
|
183 |
-
"precision": 0.
|
184 |
-
"recall": 0.
|
185 |
-
"support":
|
186 |
},
|
187 |
-
"eval_accuracy": 0.
|
188 |
-
"eval_loss": 0.
|
189 |
"eval_macro avg": {
|
190 |
-
"f1-score": 0.
|
191 |
-
"precision": 0.
|
192 |
-
"recall": 0.
|
193 |
-
"support":
|
194 |
-
},
|
195 |
-
"eval_runtime":
|
196 |
-
"eval_samples_per_second":
|
197 |
-
"eval_steps_per_second":
|
198 |
"eval_weighted avg": {
|
199 |
-
"f1-score": 0.
|
200 |
-
"precision": 0.
|
201 |
-
"recall": 0.
|
202 |
-
"support":
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
-
"f1-score": 0.
|
210 |
-
"precision": 0.
|
211 |
-
"recall": 0.
|
212 |
-
"support":
|
213 |
},
|
214 |
"eval_I": {
|
215 |
-
"f1-score": 0.
|
216 |
-
"precision": 0.
|
217 |
-
"recall": 0.
|
218 |
-
"support":
|
219 |
},
|
220 |
"eval_O": {
|
221 |
-
"f1-score": 0.
|
222 |
-
"precision": 0.
|
223 |
-
"recall": 0.
|
224 |
-
"support":
|
225 |
},
|
226 |
-
"eval_accuracy": 0.
|
227 |
-
"eval_loss": 0.
|
228 |
"eval_macro avg": {
|
229 |
-
"f1-score": 0.
|
230 |
-
"precision": 0.
|
231 |
-
"recall": 0.
|
232 |
-
"support":
|
233 |
-
},
|
234 |
-
"eval_runtime":
|
235 |
-
"eval_samples_per_second":
|
236 |
-
"eval_steps_per_second":
|
237 |
"eval_weighted avg": {
|
238 |
-
"f1-score": 0.
|
239 |
-
"precision": 0.
|
240 |
-
"recall": 0.
|
241 |
-
"support":
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
-
"grad_norm":
|
248 |
-
"learning_rate": 1.
|
249 |
-
"loss": 0.
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
-
"f1-score": 0.
|
256 |
-
"precision": 0.
|
257 |
-
"recall": 0.
|
258 |
-
"support":
|
259 |
},
|
260 |
"eval_I": {
|
261 |
-
"f1-score": 0.
|
262 |
-
"precision": 0.
|
263 |
-
"recall": 0.
|
264 |
-
"support":
|
265 |
},
|
266 |
"eval_O": {
|
267 |
-
"f1-score": 0.
|
268 |
-
"precision": 0.
|
269 |
-
"recall": 0.
|
270 |
-
"support":
|
271 |
},
|
272 |
-
"eval_accuracy": 0.
|
273 |
-
"eval_loss": 0.
|
274 |
"eval_macro avg": {
|
275 |
-
"f1-score": 0.
|
276 |
-
"precision": 0.
|
277 |
-
"recall": 0.
|
278 |
-
"support":
|
279 |
-
},
|
280 |
-
"eval_runtime":
|
281 |
-
"eval_samples_per_second":
|
282 |
-
"eval_steps_per_second":
|
283 |
"eval_weighted avg": {
|
284 |
-
"f1-score": 0.
|
285 |
-
"precision": 0.
|
286 |
-
"recall": 0.
|
287 |
-
"support":
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
-
"f1-score": 0.
|
295 |
-
"precision": 0.
|
296 |
-
"recall": 0.
|
297 |
-
"support":
|
298 |
},
|
299 |
"eval_I": {
|
300 |
-
"f1-score": 0.
|
301 |
-
"precision": 0.
|
302 |
-
"recall": 0.
|
303 |
-
"support":
|
304 |
},
|
305 |
"eval_O": {
|
306 |
-
"f1-score": 0.
|
307 |
-
"precision": 0.
|
308 |
-
"recall": 0.
|
309 |
-
"support":
|
310 |
},
|
311 |
-
"eval_accuracy": 0.
|
312 |
-
"eval_loss": 0.
|
313 |
"eval_macro avg": {
|
314 |
-
"f1-score": 0.
|
315 |
-
"precision": 0.
|
316 |
-
"recall": 0.
|
317 |
-
"support":
|
318 |
-
},
|
319 |
-
"eval_runtime":
|
320 |
-
"eval_samples_per_second":
|
321 |
-
"eval_steps_per_second":
|
322 |
"eval_weighted avg": {
|
323 |
-
"f1-score": 0.
|
324 |
-
"precision": 0.
|
325 |
-
"recall": 0.
|
326 |
-
"support":
|
327 |
},
|
328 |
"step": 648
|
329 |
},
|
330 |
{
|
331 |
"epoch": 9.0,
|
332 |
"eval_B": {
|
333 |
-
"f1-score": 0.
|
334 |
-
"precision": 0.
|
335 |
-
"recall": 0.
|
336 |
-
"support":
|
337 |
},
|
338 |
"eval_I": {
|
339 |
-
"f1-score": 0.
|
340 |
-
"precision": 0.
|
341 |
-
"recall": 0.
|
342 |
-
"support":
|
343 |
},
|
344 |
"eval_O": {
|
345 |
-
"f1-score": 0.
|
346 |
-
"precision": 0.
|
347 |
-
"recall": 0.
|
348 |
-
"support":
|
349 |
},
|
350 |
-
"eval_accuracy": 0.
|
351 |
-
"eval_loss": 0.
|
352 |
"eval_macro avg": {
|
353 |
-
"f1-score": 0.
|
354 |
-
"precision": 0.
|
355 |
-
"recall": 0.
|
356 |
-
"support":
|
357 |
-
},
|
358 |
-
"eval_runtime":
|
359 |
-
"eval_samples_per_second":
|
360 |
-
"eval_steps_per_second":
|
361 |
"eval_weighted avg": {
|
362 |
-
"f1-score": 0.
|
363 |
-
"precision": 0.
|
364 |
-
"recall": 0.
|
365 |
-
"support":
|
366 |
},
|
367 |
"step": 729
|
368 |
},
|
369 |
{
|
370 |
"epoch": 10.0,
|
371 |
"eval_B": {
|
372 |
-
"f1-score": 0.
|
373 |
-
"precision": 0.
|
374 |
-
"recall": 0.
|
375 |
-
"support":
|
376 |
},
|
377 |
"eval_I": {
|
378 |
-
"f1-score": 0.
|
379 |
-
"precision": 0.
|
380 |
-
"recall": 0.
|
381 |
-
"support":
|
382 |
},
|
383 |
"eval_O": {
|
384 |
-
"f1-score": 0.
|
385 |
-
"precision": 0.
|
386 |
-
"recall": 0.
|
387 |
-
"support":
|
388 |
},
|
389 |
-
"eval_accuracy": 0.
|
390 |
-
"eval_loss": 0.
|
391 |
"eval_macro avg": {
|
392 |
-
"f1-score": 0.
|
393 |
-
"precision": 0.
|
394 |
-
"recall": 0.
|
395 |
-
"support":
|
396 |
-
},
|
397 |
-
"eval_runtime":
|
398 |
-
"eval_samples_per_second":
|
399 |
-
"eval_steps_per_second":
|
400 |
"eval_weighted avg": {
|
401 |
-
"f1-score": 0.
|
402 |
-
"precision": 0.
|
403 |
-
"recall": 0.
|
404 |
-
"support":
|
405 |
},
|
406 |
"step": 810
|
407 |
},
|
408 |
{
|
409 |
"epoch": 11.0,
|
410 |
"eval_B": {
|
411 |
-
"f1-score": 0.
|
412 |
-
"precision": 0.
|
413 |
-
"recall": 0.
|
414 |
-
"support":
|
415 |
},
|
416 |
"eval_I": {
|
417 |
-
"f1-score": 0.
|
418 |
-
"precision": 0.
|
419 |
-
"recall": 0.
|
420 |
-
"support":
|
421 |
},
|
422 |
"eval_O": {
|
423 |
-
"f1-score": 0.
|
424 |
-
"precision": 0.
|
425 |
-
"recall": 0.
|
426 |
-
"support":
|
427 |
},
|
428 |
-
"eval_accuracy": 0.
|
429 |
-
"eval_loss": 0.
|
430 |
"eval_macro avg": {
|
431 |
-
"f1-score": 0.
|
432 |
-
"precision": 0.
|
433 |
-
"recall": 0.
|
434 |
-
"support":
|
435 |
-
},
|
436 |
-
"eval_runtime":
|
437 |
-
"eval_samples_per_second":
|
438 |
-
"eval_steps_per_second":
|
439 |
"eval_weighted avg": {
|
440 |
-
"f1-score": 0.
|
441 |
-
"precision": 0.
|
442 |
-
"recall": 0.
|
443 |
-
"support":
|
444 |
},
|
445 |
"step": 891
|
446 |
},
|
447 |
{
|
448 |
"epoch": 12.0,
|
449 |
"eval_B": {
|
450 |
-
"f1-score": 0.
|
451 |
-
"precision": 0.
|
452 |
-
"recall": 0.
|
453 |
-
"support":
|
454 |
},
|
455 |
"eval_I": {
|
456 |
-
"f1-score": 0.
|
457 |
-
"precision": 0.
|
458 |
-
"recall": 0.
|
459 |
-
"support":
|
460 |
},
|
461 |
"eval_O": {
|
462 |
-
"f1-score": 0.
|
463 |
-
"precision": 0.
|
464 |
-
"recall": 0.
|
465 |
-
"support":
|
466 |
},
|
467 |
-
"eval_accuracy": 0.
|
468 |
-
"eval_loss": 0.
|
469 |
"eval_macro avg": {
|
470 |
-
"f1-score": 0.
|
471 |
-
"precision": 0.
|
472 |
-
"recall": 0.
|
473 |
-
"support":
|
474 |
-
},
|
475 |
-
"eval_runtime":
|
476 |
-
"eval_samples_per_second":
|
477 |
-
"eval_steps_per_second":
|
478 |
"eval_weighted avg": {
|
479 |
-
"f1-score": 0.
|
480 |
-
"precision": 0.
|
481 |
-
"recall": 0.
|
482 |
-
"support":
|
483 |
},
|
484 |
"step": 972
|
485 |
},
|
486 |
{
|
487 |
"epoch": 12.35,
|
488 |
-
"grad_norm":
|
489 |
-
"learning_rate":
|
490 |
-
"loss": 0.
|
491 |
"step": 1000
|
492 |
},
|
493 |
{
|
494 |
"epoch": 13.0,
|
495 |
"eval_B": {
|
496 |
-
"f1-score": 0.
|
497 |
-
"precision": 0.
|
498 |
-
"recall": 0.
|
499 |
-
"support":
|
500 |
},
|
501 |
"eval_I": {
|
502 |
-
"f1-score": 0.
|
503 |
-
"precision": 0.
|
504 |
-
"recall": 0.
|
505 |
-
"support":
|
506 |
},
|
507 |
"eval_O": {
|
508 |
-
"f1-score": 0.
|
509 |
-
"precision": 0.
|
510 |
-
"recall": 0.
|
511 |
-
"support":
|
512 |
},
|
513 |
-
"eval_accuracy": 0.
|
514 |
-
"eval_loss": 0.
|
515 |
"eval_macro avg": {
|
516 |
-
"f1-score": 0.
|
517 |
-
"precision": 0.
|
518 |
-
"recall": 0.
|
519 |
-
"support":
|
520 |
-
},
|
521 |
-
"eval_runtime":
|
522 |
-
"eval_samples_per_second":
|
523 |
-
"eval_steps_per_second":
|
524 |
"eval_weighted avg": {
|
525 |
-
"f1-score": 0.
|
526 |
-
"precision": 0.
|
527 |
-
"recall": 0.
|
528 |
-
"support":
|
529 |
},
|
530 |
"step": 1053
|
531 |
},
|
532 |
{
|
533 |
"epoch": 14.0,
|
534 |
"eval_B": {
|
535 |
-
"f1-score": 0.
|
536 |
-
"precision": 0.
|
537 |
-
"recall": 0.
|
538 |
-
"support":
|
539 |
},
|
540 |
"eval_I": {
|
541 |
-
"f1-score": 0.
|
542 |
-
"precision": 0.
|
543 |
-
"recall": 0.
|
544 |
-
"support":
|
545 |
},
|
546 |
"eval_O": {
|
547 |
-
"f1-score": 0.
|
548 |
-
"precision": 0.
|
549 |
-
"recall": 0.
|
550 |
-
"support":
|
551 |
},
|
552 |
-
"eval_accuracy": 0.
|
553 |
-
"eval_loss": 0.
|
554 |
"eval_macro avg": {
|
555 |
-
"f1-score": 0.
|
556 |
-
"precision": 0.
|
557 |
-
"recall": 0.
|
558 |
-
"support":
|
559 |
-
},
|
560 |
-
"eval_runtime":
|
561 |
-
"eval_samples_per_second":
|
562 |
-
"eval_steps_per_second":
|
563 |
"eval_weighted avg": {
|
564 |
-
"f1-score": 0.
|
565 |
-
"precision": 0.
|
566 |
-
"recall": 0.
|
567 |
-
"support":
|
568 |
},
|
569 |
"step": 1134
|
570 |
}
|
571 |
],
|
572 |
"logging_steps": 500,
|
573 |
-
"max_steps":
|
574 |
"num_input_tokens_seen": 0,
|
575 |
-
"num_train_epochs":
|
576 |
"save_steps": 500,
|
577 |
"total_flos": 2013013138298400.0,
|
578 |
"train_batch_size": 4,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.2252955436706543,
|
3 |
+
"best_model_checkpoint": "longformer-spans/checkpoint-162",
|
4 |
"epoch": 14.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1134,
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
+
"f1-score": 0.816,
|
15 |
+
"precision": 0.7461594732991953,
|
16 |
+
"recall": 0.9002647837599294,
|
17 |
+
"support": 1133.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9321376763813793,
|
21 |
+
"precision": 0.9024103768767235,
|
22 |
+
"recall": 0.9638902525500463,
|
23 |
+
"support": 18333.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8560784528570645,
|
27 |
+
"precision": 0.931782945736434,
|
28 |
+
"recall": 0.7917511147142278,
|
29 |
+
"support": 9868.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.9035249198881844,
|
32 |
+
"eval_loss": 0.2619660496711731,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.8680720430794812,
|
35 |
+
"precision": 0.860117598637451,
|
36 |
+
"recall": 0.8853020503414012,
|
37 |
+
"support": 29334.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 5.5032,
|
40 |
+
"eval_samples_per_second": 14.537,
|
41 |
+
"eval_steps_per_second": 1.817,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.9020655278480035,
|
44 |
+
"precision": 0.9062562975065145,
|
45 |
+
"recall": 0.9035249198881844,
|
46 |
+
"support": 29334.0
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8512256973795435,
|
54 |
+
"precision": 0.8167072181670721,
|
55 |
+
"recall": 0.8887908208296558,
|
56 |
+
"support": 1133.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9416781438711729,
|
60 |
+
"precision": 0.9152551099212274,
|
61 |
+
"recall": 0.9696721758577429,
|
62 |
+
"support": 18333.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.8778173190984578,
|
66 |
+
"precision": 0.9380041484212952,
|
67 |
+
"recall": 0.8248885285772193,
|
68 |
+
"support": 9868.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9178427763005387,
|
71 |
+
"eval_loss": 0.2252955436706543,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.8902403867830581,
|
74 |
+
"precision": 0.8899888255031981,
|
75 |
+
"recall": 0.8944505084215394,
|
76 |
+
"support": 29334.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 5.4972,
|
79 |
+
"eval_samples_per_second": 14.553,
|
80 |
+
"eval_steps_per_second": 1.819,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.9167016237671239,
|
83 |
+
"precision": 0.9191015935430046,
|
84 |
+
"recall": 0.9178427763005387,
|
85 |
+
"support": 29334.0
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8531120331950207,
|
93 |
+
"precision": 0.8050117462803446,
|
94 |
+
"recall": 0.9073256840247131,
|
95 |
+
"support": 1133.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.9469915571230095,
|
99 |
+
"precision": 0.9280963603037444,
|
100 |
+
"recall": 0.9666721213112965,
|
101 |
+
"support": 18333.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.8903876792352629,
|
105 |
+
"precision": 0.9353938852934612,
|
106 |
+
"recall": 0.8495135792460479,
|
107 |
+
"support": 9868.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.9249676143724006,
|
110 |
+
"eval_loss": 0.22786012291908264,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.8968304231844311,
|
113 |
+
"precision": 0.8895006639591835,
|
114 |
+
"recall": 0.9078371281940192,
|
115 |
+
"support": 29334.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 5.5036,
|
118 |
+
"eval_samples_per_second": 14.536,
|
119 |
+
"eval_steps_per_second": 1.817,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9243239165827936,
|
122 |
+
"precision": 0.9257972230878861,
|
123 |
+
"recall": 0.9249676143724006,
|
124 |
+
"support": 29334.0
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8567807351077312,
|
132 |
+
"precision": 0.8217179902755267,
|
133 |
+
"recall": 0.8949691085613416,
|
134 |
+
"support": 1133.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.9472597903427299,
|
138 |
+
"precision": 0.9432635621180161,
|
139 |
+
"recall": 0.9512900234549719,
|
140 |
+
"support": 18333.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.8979927100980543,
|
144 |
+
"precision": 0.9099989595255437,
|
145 |
+
"recall": 0.8862991487636805,
|
146 |
+
"support": 9868.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9272516533715143,
|
149 |
+
"eval_loss": 0.23897655308246613,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.9006777451828384,
|
152 |
+
"precision": 0.8916601706396955,
|
153 |
+
"recall": 0.910852760259998,
|
154 |
+
"support": 29334.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 5.4904,
|
157 |
+
"eval_samples_per_second": 14.571,
|
158 |
+
"eval_steps_per_second": 1.821,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9271915992526735,
|
161 |
+
"precision": 0.9273787107073643,
|
162 |
+
"recall": 0.9272516533715143,
|
163 |
+
"support": 29334.0
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.8624407072013798,
|
171 |
+
"precision": 0.8431703204047217,
|
172 |
+
"recall": 0.8826125330979699,
|
173 |
+
"support": 1133.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.948190701170407,
|
177 |
+
"precision": 0.9335059992600032,
|
178 |
+
"recall": 0.9633447880870561,
|
179 |
+
"support": 18333.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.8955333298423835,
|
183 |
+
"precision": 0.9265359193845487,
|
184 |
+
"recall": 0.8665383056343737,
|
185 |
+
"support": 9868.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9276607349832958,
|
188 |
+
"eval_loss": 0.25390708446502686,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.9020549127380568,
|
191 |
+
"precision": 0.9010707463497579,
|
192 |
+
"recall": 0.9041652089397999,
|
193 |
+
"support": 29334.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 5.4919,
|
196 |
+
"eval_samples_per_second": 14.567,
|
197 |
+
"eval_steps_per_second": 1.821,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9271646670996412,
|
200 |
+
"precision": 0.9276721180179627,
|
201 |
+
"recall": 0.9276607349832958,
|
202 |
+
"support": 29334.0
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.8601036269430052,
|
210 |
+
"precision": 0.841927303465765,
|
211 |
+
"recall": 0.8790820829655781,
|
212 |
+
"support": 1133.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9474285714285714,
|
216 |
+
"precision": 0.9452679589509693,
|
217 |
+
"recall": 0.9495990836197021,
|
218 |
+
"support": 18333.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.8983777165595348,
|
222 |
+
"precision": 0.9045613314156564,
|
223 |
+
"recall": 0.8922780705310093,
|
224 |
+
"support": 9868.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.9275925547146656,
|
227 |
+
"eval_loss": 0.29299432039260864,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9019699716437038,
|
230 |
+
"precision": 0.8972521979441302,
|
231 |
+
"recall": 0.9069864123720964,
|
232 |
+
"support": 29334.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 5.4971,
|
235 |
+
"eval_samples_per_second": 14.553,
|
236 |
+
"eval_steps_per_second": 1.819,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.9275549436263691,
|
239 |
+
"precision": 0.9275827485063247,
|
240 |
+
"recall": 0.9275925547146656,
|
241 |
+
"support": 29334.0
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
+
"grad_norm": 2.853372573852539,
|
248 |
+
"learning_rate": 1.3827160493827162e-05,
|
249 |
+
"loss": 0.1621,
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
+
"f1-score": 0.8665526090675792,
|
256 |
+
"precision": 0.8406639004149378,
|
257 |
+
"recall": 0.8940864960282436,
|
258 |
+
"support": 1133.0
|
259 |
},
|
260 |
"eval_I": {
|
261 |
+
"f1-score": 0.9492722371967655,
|
262 |
+
"precision": 0.9382959450098577,
|
263 |
+
"recall": 0.9605083728795069,
|
264 |
+
"support": 18333.0
|
265 |
},
|
266 |
"eval_O": {
|
267 |
+
"f1-score": 0.8984919396775871,
|
268 |
+
"precision": 0.9227729117709891,
|
269 |
+
"recall": 0.8754560194568302,
|
270 |
+
"support": 9868.0
|
271 |
},
|
272 |
+
"eval_accuracy": 0.9293311515647371,
|
273 |
+
"eval_loss": 0.3148973286151886,
|
274 |
"eval_macro avg": {
|
275 |
+
"f1-score": 0.9047722619806439,
|
276 |
+
"precision": 0.9005775857319281,
|
277 |
+
"recall": 0.9100169627881934,
|
278 |
+
"support": 29334.0
|
279 |
+
},
|
280 |
+
"eval_runtime": 5.4821,
|
281 |
+
"eval_samples_per_second": 14.593,
|
282 |
+
"eval_steps_per_second": 1.824,
|
283 |
"eval_weighted avg": {
|
284 |
+
"f1-score": 0.9289946986889036,
|
285 |
+
"precision": 0.9293030221719495,
|
286 |
+
"recall": 0.9293311515647371,
|
287 |
+
"support": 29334.0
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
+
"f1-score": 0.8624629707998307,
|
295 |
+
"precision": 0.8284552845528456,
|
296 |
+
"recall": 0.8993821712268314,
|
297 |
+
"support": 1133.0
|
298 |
},
|
299 |
"eval_I": {
|
300 |
+
"f1-score": 0.9467755410030451,
|
301 |
+
"precision": 0.9356556940449557,
|
302 |
+
"recall": 0.9581628756886489,
|
303 |
+
"support": 18333.0
|
304 |
},
|
305 |
"eval_O": {
|
306 |
+
"f1-score": 0.8934263985831857,
|
307 |
+
"precision": 0.9191854233654877,
|
308 |
+
"recall": 0.8690717470612079,
|
309 |
+
"support": 9868.0
|
310 |
},
|
311 |
+
"eval_accuracy": 0.9259221381332242,
|
312 |
+
"eval_loss": 0.34766319394111633,
|
313 |
"eval_macro avg": {
|
314 |
+
"f1-score": 0.9008883034620205,
|
315 |
+
"precision": 0.8944321339877629,
|
316 |
+
"recall": 0.9088722646588961,
|
317 |
+
"support": 29334.0
|
318 |
+
},
|
319 |
+
"eval_runtime": 5.5202,
|
320 |
+
"eval_samples_per_second": 14.492,
|
321 |
+
"eval_steps_per_second": 1.812,
|
322 |
"eval_weighted avg": {
|
323 |
+
"f1-score": 0.9255723133682386,
|
324 |
+
"precision": 0.9259745494680297,
|
325 |
+
"recall": 0.9259221381332242,
|
326 |
+
"support": 29334.0
|
327 |
},
|
328 |
"step": 648
|
329 |
},
|
330 |
{
|
331 |
"epoch": 9.0,
|
332 |
"eval_B": {
|
333 |
+
"f1-score": 0.8654012079378774,
|
334 |
+
"precision": 0.8464135021097047,
|
335 |
+
"recall": 0.8852603706972639,
|
336 |
+
"support": 1133.0
|
337 |
},
|
338 |
"eval_I": {
|
339 |
+
"f1-score": 0.9474813007694164,
|
340 |
+
"precision": 0.9316216786166175,
|
341 |
+
"recall": 0.9638902525500463,
|
342 |
+
"support": 18333.0
|
343 |
},
|
344 |
"eval_O": {
|
345 |
+
"f1-score": 0.8933802299333298,
|
346 |
+
"precision": 0.9268053588933667,
|
347 |
+
"recall": 0.8622821240372922,
|
348 |
+
"support": 9868.0
|
349 |
},
|
350 |
+
"eval_accuracy": 0.9266721210881571,
|
351 |
+
"eval_loss": 0.3807723820209503,
|
352 |
"eval_macro avg": {
|
353 |
+
"f1-score": 0.9020875795468745,
|
354 |
+
"precision": 0.9016135132065629,
|
355 |
+
"recall": 0.9038109157615342,
|
356 |
+
"support": 29334.0
|
357 |
+
},
|
358 |
+
"eval_runtime": 5.532,
|
359 |
+
"eval_samples_per_second": 14.461,
|
360 |
+
"eval_steps_per_second": 1.808,
|
361 |
"eval_weighted avg": {
|
362 |
+
"f1-score": 0.9261113508073029,
|
363 |
+
"precision": 0.9267103706800465,
|
364 |
+
"recall": 0.9266721210881571,
|
365 |
+
"support": 29334.0
|
366 |
},
|
367 |
"step": 729
|
368 |
},
|
369 |
{
|
370 |
"epoch": 10.0,
|
371 |
"eval_B": {
|
372 |
+
"f1-score": 0.8593548387096774,
|
373 |
+
"precision": 0.8380872483221476,
|
374 |
+
"recall": 0.881729920564872,
|
375 |
+
"support": 1133.0
|
376 |
},
|
377 |
"eval_I": {
|
378 |
+
"f1-score": 0.9447995351539802,
|
379 |
+
"precision": 0.9158687080751703,
|
380 |
+
"recall": 0.9756177385043364,
|
381 |
+
"support": 18333.0
|
382 |
},
|
383 |
"eval_O": {
|
384 |
+
"f1-score": 0.8826362209837131,
|
385 |
+
"precision": 0.9469406710786021,
|
386 |
+
"recall": 0.8265099310903932,
|
387 |
+
"support": 9868.0
|
388 |
},
|
389 |
+
"eval_accuracy": 0.9218313220154087,
|
390 |
+
"eval_loss": 0.46634167432785034,
|
391 |
"eval_macro avg": {
|
392 |
+
"f1-score": 0.8955968649491236,
|
393 |
+
"precision": 0.9002988758253068,
|
394 |
+
"recall": 0.8946191967198672,
|
395 |
+
"support": 29334.0
|
396 |
+
},
|
397 |
+
"eval_runtime": 5.5106,
|
398 |
+
"eval_samples_per_second": 14.517,
|
399 |
+
"eval_steps_per_second": 1.815,
|
400 |
"eval_weighted avg": {
|
401 |
+
"f1-score": 0.9205874800198834,
|
402 |
+
"precision": 0.9233171207368492,
|
403 |
+
"recall": 0.9218313220154087,
|
404 |
+
"support": 29334.0
|
405 |
},
|
406 |
"step": 810
|
407 |
},
|
408 |
{
|
409 |
"epoch": 11.0,
|
410 |
"eval_B": {
|
411 |
+
"f1-score": 0.8585028126352229,
|
412 |
+
"precision": 0.8421052631578947,
|
413 |
+
"recall": 0.8755516328331863,
|
414 |
+
"support": 1133.0
|
415 |
},
|
416 |
"eval_I": {
|
417 |
+
"f1-score": 0.9467715680954965,
|
418 |
+
"precision": 0.941814648890808,
|
419 |
+
"recall": 0.9517809414716631,
|
420 |
+
"support": 18333.0
|
421 |
},
|
422 |
"eval_O": {
|
423 |
+
"f1-score": 0.8955223880597014,
|
424 |
+
"precision": 0.906636203136359,
|
425 |
+
"recall": 0.8846777462505067,
|
426 |
+
"support": 9868.0
|
427 |
},
|
428 |
+
"eval_accuracy": 0.9262630394763756,
|
429 |
+
"eval_loss": 0.39979249238967896,
|
430 |
"eval_macro avg": {
|
431 |
+
"f1-score": 0.9002655895968069,
|
432 |
+
"precision": 0.8968520383950206,
|
433 |
+
"recall": 0.9040034401851186,
|
434 |
+
"support": 29334.0
|
435 |
+
},
|
436 |
+
"eval_runtime": 5.5098,
|
437 |
+
"eval_samples_per_second": 14.52,
|
438 |
+
"eval_steps_per_second": 1.815,
|
439 |
"eval_weighted avg": {
|
440 |
+
"f1-score": 0.9261219666592889,
|
441 |
+
"precision": 0.9261293813943774,
|
442 |
+
"recall": 0.9262630394763756,
|
443 |
+
"support": 29334.0
|
444 |
},
|
445 |
"step": 891
|
446 |
},
|
447 |
{
|
448 |
"epoch": 12.0,
|
449 |
"eval_B": {
|
450 |
+
"f1-score": 0.8661758336942399,
|
451 |
+
"precision": 0.8503401360544217,
|
452 |
+
"recall": 0.8826125330979699,
|
453 |
+
"support": 1133.0
|
454 |
},
|
455 |
"eval_I": {
|
456 |
+
"f1-score": 0.9483851819874267,
|
457 |
+
"precision": 0.9383342231713828,
|
458 |
+
"recall": 0.9586537937053401,
|
459 |
+
"support": 18333.0
|
460 |
},
|
461 |
"eval_O": {
|
462 |
+
"f1-score": 0.8972844112769486,
|
463 |
+
"precision": 0.9182223165040305,
|
464 |
+
"recall": 0.8772800972841508,
|
465 |
+
"support": 9868.0
|
466 |
},
|
467 |
+
"eval_accuracy": 0.9283425376695984,
|
468 |
+
"eval_loss": 0.4524174630641937,
|
469 |
"eval_macro avg": {
|
470 |
+
"f1-score": 0.9039484756528716,
|
471 |
+
"precision": 0.9022988919099451,
|
472 |
+
"recall": 0.906182141362487,
|
473 |
+
"support": 29334.0
|
474 |
+
},
|
475 |
+
"eval_runtime": 5.5194,
|
476 |
+
"eval_samples_per_second": 14.494,
|
477 |
+
"eval_steps_per_second": 1.812,
|
478 |
"eval_weighted avg": {
|
479 |
+
"f1-score": 0.9280195449455239,
|
480 |
+
"precision": 0.9281698543264606,
|
481 |
+
"recall": 0.9283425376695984,
|
482 |
+
"support": 29334.0
|
483 |
},
|
484 |
"step": 972
|
485 |
},
|
486 |
{
|
487 |
"epoch": 12.35,
|
488 |
+
"grad_norm": 1.163489818572998,
|
489 |
+
"learning_rate": 7.654320987654322e-06,
|
490 |
+
"loss": 0.0212,
|
491 |
"step": 1000
|
492 |
},
|
493 |
{
|
494 |
"epoch": 13.0,
|
495 |
"eval_B": {
|
496 |
+
"f1-score": 0.8624407072013798,
|
497 |
+
"precision": 0.8431703204047217,
|
498 |
+
"recall": 0.8826125330979699,
|
499 |
+
"support": 1133.0
|
500 |
},
|
501 |
"eval_I": {
|
502 |
+
"f1-score": 0.94720379658092,
|
503 |
+
"precision": 0.9365968111768783,
|
504 |
+
"recall": 0.9580537827960508,
|
505 |
+
"support": 18333.0
|
506 |
},
|
507 |
"eval_O": {
|
508 |
+
"f1-score": 0.8942532315838654,
|
509 |
+
"precision": 0.9167642362959021,
|
510 |
+
"recall": 0.8728212403729225,
|
511 |
+
"support": 9868.0
|
512 |
},
|
513 |
+
"eval_accuracy": 0.9264675802822663,
|
514 |
+
"eval_loss": 0.45370540022850037,
|
515 |
"eval_macro avg": {
|
516 |
+
"f1-score": 0.9012992451220551,
|
517 |
+
"precision": 0.8988437892925006,
|
518 |
+
"recall": 0.9044958520889811,
|
519 |
+
"support": 29334.0
|
520 |
+
},
|
521 |
+
"eval_runtime": 5.5225,
|
522 |
+
"eval_samples_per_second": 14.486,
|
523 |
+
"eval_steps_per_second": 1.811,
|
524 |
"eval_weighted avg": {
|
525 |
+
"f1-score": 0.9261172500595471,
|
526 |
+
"precision": 0.926316588126141,
|
527 |
+
"recall": 0.9264675802822663,
|
528 |
+
"support": 29334.0
|
529 |
},
|
530 |
"step": 1053
|
531 |
},
|
532 |
{
|
533 |
"epoch": 14.0,
|
534 |
"eval_B": {
|
535 |
+
"f1-score": 0.8689595124074879,
|
536 |
+
"precision": 0.8573883161512027,
|
537 |
+
"recall": 0.880847308031774,
|
538 |
+
"support": 1133.0
|
539 |
},
|
540 |
"eval_I": {
|
541 |
+
"f1-score": 0.9480582004921365,
|
542 |
+
"precision": 0.9300970873786408,
|
543 |
+
"recall": 0.9667266677575956,
|
544 |
+
"support": 18333.0
|
545 |
},
|
546 |
"eval_O": {
|
547 |
+
"f1-score": 0.8934309645472265,
|
548 |
+
"precision": 0.9303346132748217,
|
549 |
+
"recall": 0.8593433319821646,
|
550 |
+
"support": 9868.0
|
551 |
},
|
552 |
+
"eval_accuracy": 0.9272857435058294,
|
553 |
+
"eval_loss": 0.49018412828445435,
|
554 |
"eval_macro avg": {
|
555 |
+
"f1-score": 0.9034828924822836,
|
556 |
+
"precision": 0.9059400056015551,
|
557 |
+
"recall": 0.9023057692571781,
|
558 |
+
"support": 29334.0
|
559 |
+
},
|
560 |
+
"eval_runtime": 5.5116,
|
561 |
+
"eval_samples_per_second": 14.515,
|
562 |
+
"eval_steps_per_second": 1.814,
|
563 |
"eval_weighted avg": {
|
564 |
+
"f1-score": 0.9266264019680934,
|
565 |
+
"precision": 0.9273686789700647,
|
566 |
+
"recall": 0.9272857435058294,
|
567 |
+
"support": 29334.0
|
568 |
},
|
569 |
"step": 1134
|
570 |
}
|
571 |
],
|
572 |
"logging_steps": 500,
|
573 |
+
"max_steps": 1620,
|
574 |
"num_input_tokens_seen": 0,
|
575 |
+
"num_train_epochs": 20,
|
576 |
"save_steps": 500,
|
577 |
"total_flos": 2013013138298400.0,
|
578 |
"train_batch_size": 4,
|
checkpoint-1134/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1094850123635c13193a80398a7bb1e351dd871416d3ce265431b259bf603290
|
3 |
size 4856
|