Theoreticallyhugo
commited on
Commit
•
f5bf907
1
Parent(s):
6d8ab85
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 sha256:82b4353bc6ae7b0fa76c9dc1ab47f260da041f421f6466ff6b50fd10eb226a47
|
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 sha256:0729795449dff4d5b7b9743b356bb4af62fab1ba9caede09715f4975292df4af
|
3 |
size 1014645498
|
checkpoint-1134/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:893c8bb9dc01140014975f0b09745bc27939854e3a02dfb50707603e8fb93135
|
3 |
size 14244
|
checkpoint-1134/trainer_state.json
CHANGED
@@ -11,560 +11,560 @@
|
|
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": 4.
|
40 |
-
"eval_samples_per_second": 17.
|
41 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
79 |
-
"eval_samples_per_second": 17.
|
80 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
118 |
-
"eval_samples_per_second": 17.
|
119 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
157 |
-
"eval_samples_per_second": 17.
|
158 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
196 |
-
"eval_samples_per_second": 17.
|
197 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
235 |
-
"eval_samples_per_second": 17.
|
236 |
-
"eval_steps_per_second": 2.
|
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": 1.7530864197530865e-05,
|
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": 4.
|
281 |
-
"eval_samples_per_second": 17.
|
282 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
320 |
-
"eval_samples_per_second": 17.
|
321 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
359 |
-
"eval_samples_per_second": 17.
|
360 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
398 |
-
"eval_samples_per_second": 17.
|
399 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
437 |
-
"eval_samples_per_second": 17.
|
438 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
476 |
-
"eval_samples_per_second": 17.
|
477 |
-
"eval_steps_per_second": 2.
|
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": 0.
|
489 |
"learning_rate": 1.506172839506173e-05,
|
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": 4.
|
522 |
-
"eval_samples_per_second": 17.
|
523 |
-
"eval_steps_per_second": 2.
|
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": 4.
|
561 |
-
"eval_samples_per_second": 17.
|
562 |
-
"eval_steps_per_second": 2.
|
563 |
"eval_weighted avg": {
|
564 |
-
"f1-score": 0.
|
565 |
-
"precision": 0.
|
566 |
-
"recall": 0.
|
567 |
-
"support":
|
568 |
},
|
569 |
"step": 1134
|
570 |
}
|
@@ -574,7 +574,7 @@
|
|
574 |
"num_input_tokens_seen": 0,
|
575 |
"num_train_epochs": 50,
|
576 |
"save_steps": 500,
|
577 |
-
"total_flos":
|
578 |
"train_batch_size": 4,
|
579 |
"trial_name": null,
|
580 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
+
"f1-score": 0.8266764382557715,
|
15 |
+
"precision": 0.7866108786610879,
|
16 |
+
"recall": 0.871042471042471,
|
17 |
+
"support": 1295.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9410658617447671,
|
21 |
+
"precision": 0.9344077040239768,
|
22 |
+
"recall": 0.9478195863443808,
|
23 |
+
"support": 20065.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8562443302086484,
|
27 |
+
"precision": 0.8789421405512788,
|
28 |
+
"recall": 0.8346893055064262,
|
29 |
+
"support": 8481.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.912335377500754,
|
32 |
+
"eval_loss": 0.2450982630252838,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.8746622100697291,
|
35 |
+
"precision": 0.8666535744121145,
|
36 |
+
"recall": 0.8845171209644261,
|
37 |
+
"support": 29841.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 4.6269,
|
40 |
+
"eval_samples_per_second": 17.29,
|
41 |
+
"eval_steps_per_second": 2.161,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.9119949287205363,
|
44 |
+
"precision": 0.9122301519092053,
|
45 |
+
"recall": 0.912335377500754,
|
46 |
+
"support": 29841.0
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8833395452851286,
|
54 |
+
"precision": 0.8537463976945245,
|
55 |
+
"recall": 0.915057915057915,
|
56 |
+
"support": 1295.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9549518227873249,
|
60 |
+
"precision": 0.9516903430183636,
|
61 |
+
"recall": 0.958235733864939,
|
62 |
+
"support": 20065.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.88924750463212,
|
66 |
+
"precision": 0.9016969696969697,
|
67 |
+
"recall": 0.877137130055418,
|
68 |
+
"support": 8481.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9333132267685399,
|
71 |
+
"eval_loss": 0.20076116919517517,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.9091796242348579,
|
74 |
+
"precision": 0.9023779034699526,
|
75 |
+
"recall": 0.916810259659424,
|
76 |
+
"support": 29841.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 4.6524,
|
79 |
+
"eval_samples_per_second": 17.195,
|
80 |
+
"eval_steps_per_second": 2.149,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.9331705077630417,
|
83 |
+
"precision": 0.9332314707173981,
|
84 |
+
"recall": 0.9333132267685399,
|
85 |
+
"support": 29841.0
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8927335640138409,
|
93 |
+
"precision": 0.8889739663093414,
|
94 |
+
"recall": 0.8965250965250965,
|
95 |
+
"support": 1295.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.9590235396687009,
|
99 |
+
"precision": 0.9586653386454184,
|
100 |
+
"recall": 0.9593820084724645,
|
101 |
+
"support": 20065.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.9006849315068494,
|
105 |
+
"precision": 0.9020697811945594,
|
106 |
+
"recall": 0.8993043273198915,
|
107 |
+
"support": 8481.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.9395797727958178,
|
110 |
+
"eval_loss": 0.19863653182983398,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.9174806783964637,
|
113 |
+
"precision": 0.9165696953831063,
|
114 |
+
"recall": 0.9184038107724842,
|
115 |
+
"support": 29841.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 4.655,
|
118 |
+
"eval_samples_per_second": 17.186,
|
119 |
+
"eval_steps_per_second": 2.148,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9395665759512081,
|
122 |
+
"precision": 0.9395561516236713,
|
123 |
+
"recall": 0.9395797727958178,
|
124 |
+
"support": 29841.0
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8999616711383672,
|
132 |
+
"precision": 0.893455098934551,
|
133 |
+
"recall": 0.9065637065637066,
|
134 |
+
"support": 1295.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.9612657113512985,
|
138 |
+
"precision": 0.9436362763454799,
|
139 |
+
"recall": 0.9795664091701969,
|
140 |
+
"support": 20065.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.8996847765622102,
|
144 |
+
"precision": 0.9454403741231489,
|
145 |
+
"recall": 0.8581535196321188,
|
146 |
+
"support": 8481.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9418920277470594,
|
149 |
+
"eval_loss": 0.19743724167346954,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.920304053017292,
|
152 |
+
"precision": 0.9275105831343932,
|
153 |
+
"recall": 0.9147612117886741,
|
154 |
+
"support": 29841.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 4.6615,
|
157 |
+
"eval_samples_per_second": 17.162,
|
158 |
+
"eval_steps_per_second": 2.145,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9411036309913238,
|
161 |
+
"precision": 0.9419713163409645,
|
162 |
+
"recall": 0.9418920277470594,
|
163 |
+
"support": 29841.0
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.8953846153846153,
|
171 |
+
"precision": 0.8919540229885058,
|
172 |
+
"recall": 0.8988416988416988,
|
173 |
+
"support": 1295.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.9602426713742261,
|
177 |
+
"precision": 0.9581224570804803,
|
178 |
+
"recall": 0.9623722900573137,
|
179 |
+
"support": 20065.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.9022119433078337,
|
183 |
+
"precision": 0.9075399665950847,
|
184 |
+
"recall": 0.8969461148449476,
|
185 |
+
"support": 8481.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9410207432726785,
|
188 |
+
"eval_loss": 0.2340461015701294,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.9192797433555584,
|
191 |
+
"precision": 0.9192054822213569,
|
192 |
+
"recall": 0.9193867012479867,
|
193 |
+
"support": 29841.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 4.6719,
|
196 |
+
"eval_samples_per_second": 17.124,
|
197 |
+
"eval_steps_per_second": 2.14,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9409353496612266,
|
200 |
+
"precision": 0.9408751053176122,
|
201 |
+
"recall": 0.9410207432726785,
|
202 |
+
"support": 29841.0
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.8929831438651511,
|
210 |
+
"precision": 0.9068471337579618,
|
211 |
+
"recall": 0.8795366795366796,
|
212 |
+
"support": 1295.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9522293798155866,
|
216 |
+
"precision": 0.9655225409836066,
|
217 |
+
"recall": 0.9392972838275604,
|
218 |
+
"support": 20065.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.8885216003647556,
|
222 |
+
"precision": 0.8599007170435742,
|
223 |
+
"recall": 0.919113312109421,
|
224 |
+
"support": 8481.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.930967460875976,
|
227 |
+
"eval_loss": 0.21774999797344208,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9112447080151643,
|
230 |
+
"precision": 0.9107567972617142,
|
231 |
+
"recall": 0.9126490918245537,
|
232 |
+
"support": 29841.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 4.647,
|
235 |
+
"eval_samples_per_second": 17.215,
|
236 |
+
"eval_steps_per_second": 2.152,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.9315521386682287,
|
239 |
+
"precision": 0.9329578366776978,
|
240 |
+
"recall": 0.930967460875976,
|
241 |
+
"support": 29841.0
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
+
"grad_norm": 9.310327529907227,
|
248 |
"learning_rate": 1.7530864197530865e-05,
|
249 |
+
"loss": 0.1627,
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
+
"f1-score": 0.8936490041337843,
|
256 |
+
"precision": 0.8704245973645681,
|
257 |
+
"recall": 0.9181467181467181,
|
258 |
+
"support": 1295.0
|
259 |
},
|
260 |
"eval_I": {
|
261 |
+
"f1-score": 0.9599271850630982,
|
262 |
+
"precision": 0.9477800446905664,
|
263 |
+
"recall": 0.9723897333665587,
|
264 |
+
"support": 20065.0
|
265 |
},
|
266 |
"eval_O": {
|
267 |
+
"f1-score": 0.8979841172877214,
|
268 |
+
"precision": 0.9316770186335404,
|
269 |
+
"recall": 0.8666430845419172,
|
270 |
+
"support": 8481.0
|
271 |
},
|
272 |
+
"eval_accuracy": 0.9399819040916859,
|
273 |
+
"eval_loss": 0.27376389503479004,
|
274 |
"eval_macro avg": {
|
275 |
+
"f1-score": 0.9171867688282013,
|
276 |
+
"precision": 0.9166272202295582,
|
277 |
+
"recall": 0.9190598453517312,
|
278 |
+
"support": 29841.0
|
279 |
+
},
|
280 |
+
"eval_runtime": 4.6671,
|
281 |
+
"eval_samples_per_second": 17.141,
|
282 |
+
"eval_steps_per_second": 2.143,
|
283 |
"eval_weighted avg": {
|
284 |
+
"f1-score": 0.9394463230910989,
|
285 |
+
"precision": 0.9398464945991887,
|
286 |
+
"recall": 0.9399819040916859,
|
287 |
+
"support": 29841.0
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
+
"f1-score": 0.8948545861297539,
|
295 |
+
"precision": 0.8651766402307137,
|
296 |
+
"recall": 0.9266409266409267,
|
297 |
+
"support": 1295.0
|
298 |
},
|
299 |
"eval_I": {
|
300 |
+
"f1-score": 0.9590139880661254,
|
301 |
+
"precision": 0.9414702069429106,
|
302 |
+
"recall": 0.9772240219287316,
|
303 |
+
"support": 20065.0
|
304 |
},
|
305 |
"eval_O": {
|
306 |
+
"f1-score": 0.8927241122423641,
|
307 |
+
"precision": 0.9427035531663825,
|
308 |
+
"recall": 0.8477773847423653,
|
309 |
+
"support": 8481.0
|
310 |
},
|
311 |
+
"eval_accuracy": 0.9382393351429241,
|
312 |
+
"eval_loss": 0.3103167414665222,
|
313 |
"eval_macro avg": {
|
314 |
+
"f1-score": 0.9155308954794145,
|
315 |
+
"precision": 0.916450133446669,
|
316 |
+
"recall": 0.9172141111040079,
|
317 |
+
"support": 29841.0
|
318 |
+
},
|
319 |
+
"eval_runtime": 4.6339,
|
320 |
+
"eval_samples_per_second": 17.264,
|
321 |
+
"eval_steps_per_second": 2.158,
|
322 |
"eval_weighted avg": {
|
323 |
+
"f1-score": 0.9373896838414373,
|
324 |
+
"precision": 0.9385098450391195,
|
325 |
+
"recall": 0.9382393351429241,
|
326 |
+
"support": 29841.0
|
327 |
},
|
328 |
"step": 648
|
329 |
},
|
330 |
{
|
331 |
"epoch": 9.0,
|
332 |
"eval_B": {
|
333 |
+
"f1-score": 0.9011235955056179,
|
334 |
+
"precision": 0.8749090909090909,
|
335 |
+
"recall": 0.9289575289575289,
|
336 |
+
"support": 1295.0
|
337 |
},
|
338 |
"eval_I": {
|
339 |
+
"f1-score": 0.9615119937082186,
|
340 |
+
"precision": 0.9485040973670175,
|
341 |
+
"recall": 0.9748816346872664,
|
342 |
+
"support": 20065.0
|
343 |
},
|
344 |
"eval_O": {
|
345 |
+
"f1-score": 0.9013722126929674,
|
346 |
+
"precision": 0.9380339155935229,
|
347 |
+
"recall": 0.8674684589081476,
|
348 |
+
"support": 8481.0
|
349 |
},
|
350 |
+
"eval_accuracy": 0.9423611809255722,
|
351 |
+
"eval_loss": 0.32883673906326294,
|
352 |
"eval_macro avg": {
|
353 |
+
"f1-score": 0.9213359339689347,
|
354 |
+
"precision": 0.9204823679565438,
|
355 |
+
"recall": 0.9237692075176476,
|
356 |
+
"support": 29841.0
|
357 |
+
},
|
358 |
+
"eval_runtime": 4.6714,
|
359 |
+
"eval_samples_per_second": 17.126,
|
360 |
+
"eval_steps_per_second": 2.141,
|
361 |
"eval_weighted avg": {
|
362 |
+
"f1-score": 0.9417992341337168,
|
363 |
+
"precision": 0.9423346276781992,
|
364 |
+
"recall": 0.9423611809255722,
|
365 |
+
"support": 29841.0
|
366 |
},
|
367 |
"step": 729
|
368 |
},
|
369 |
{
|
370 |
"epoch": 10.0,
|
371 |
"eval_B": {
|
372 |
+
"f1-score": 0.8935361216730039,
|
373 |
+
"precision": 0.8801498127340824,
|
374 |
+
"recall": 0.9073359073359073,
|
375 |
+
"support": 1295.0
|
376 |
},
|
377 |
"eval_I": {
|
378 |
+
"f1-score": 0.9632332861646931,
|
379 |
+
"precision": 0.9596359319351009,
|
380 |
+
"recall": 0.9668577124345876,
|
381 |
+
"support": 20065.0
|
382 |
},
|
383 |
"eval_O": {
|
384 |
+
"f1-score": 0.9095462405342556,
|
385 |
+
"precision": 0.9200241254523522,
|
386 |
+
"recall": 0.8993043273198915,
|
387 |
+
"support": 8481.0
|
388 |
},
|
389 |
+
"eval_accuracy": 0.9450755671726819,
|
390 |
+
"eval_loss": 0.3041447699069977,
|
391 |
"eval_macro avg": {
|
392 |
+
"f1-score": 0.9221052161239841,
|
393 |
+
"precision": 0.9199366233738452,
|
394 |
+
"recall": 0.9244993156967954,
|
395 |
+
"support": 29841.0
|
396 |
+
},
|
397 |
+
"eval_runtime": 4.6532,
|
398 |
+
"eval_samples_per_second": 17.193,
|
399 |
+
"eval_steps_per_second": 2.149,
|
400 |
"eval_weighted avg": {
|
401 |
+
"f1-score": 0.9449504651463465,
|
402 |
+
"precision": 0.9449285744355027,
|
403 |
+
"recall": 0.9450755671726819,
|
404 |
+
"support": 29841.0
|
405 |
},
|
406 |
"step": 810
|
407 |
},
|
408 |
{
|
409 |
"epoch": 11.0,
|
410 |
"eval_B": {
|
411 |
+
"f1-score": 0.8924122310305775,
|
412 |
+
"precision": 0.8729689807976366,
|
413 |
+
"recall": 0.9127413127413128,
|
414 |
+
"support": 1295.0
|
415 |
},
|
416 |
"eval_I": {
|
417 |
+
"f1-score": 0.9588723786993913,
|
418 |
+
"precision": 0.9483330083837005,
|
419 |
+
"recall": 0.9696486419137802,
|
420 |
+
"support": 20065.0
|
421 |
},
|
422 |
"eval_O": {
|
423 |
+
"f1-score": 0.8956965718453683,
|
424 |
+
"precision": 0.9243507715468574,
|
425 |
+
"recall": 0.8687654757693668,
|
426 |
+
"support": 8481.0
|
427 |
},
|
428 |
+
"eval_accuracy": 0.9385074226735028,
|
429 |
+
"eval_loss": 0.3531416654586792,
|
430 |
"eval_macro avg": {
|
431 |
+
"f1-score": 0.9156603938584458,
|
432 |
+
"precision": 0.9152175869093981,
|
433 |
+
"recall": 0.9170518101414866,
|
434 |
+
"support": 29841.0
|
435 |
+
},
|
436 |
+
"eval_runtime": 4.6508,
|
437 |
+
"eval_samples_per_second": 17.201,
|
438 |
+
"eval_steps_per_second": 2.15,
|
439 |
"eval_weighted avg": {
|
440 |
+
"f1-score": 0.938033267772811,
|
441 |
+
"precision": 0.9382465579853486,
|
442 |
+
"recall": 0.9385074226735028,
|
443 |
+
"support": 29841.0
|
444 |
},
|
445 |
"step": 891
|
446 |
},
|
447 |
{
|
448 |
"epoch": 12.0,
|
449 |
"eval_B": {
|
450 |
+
"f1-score": 0.8970199924556771,
|
451 |
+
"precision": 0.8768436578171092,
|
452 |
+
"recall": 0.9181467181467181,
|
453 |
+
"support": 1295.0
|
454 |
},
|
455 |
"eval_I": {
|
456 |
+
"f1-score": 0.9595004897159647,
|
457 |
+
"precision": 0.9431046931407943,
|
458 |
+
"recall": 0.9764764515325193,
|
459 |
+
"support": 20065.0
|
460 |
},
|
461 |
"eval_O": {
|
462 |
+
"f1-score": 0.8953122104873078,
|
463 |
+
"precision": 0.9400778210116731,
|
464 |
+
"recall": 0.8546162009197029,
|
465 |
+
"support": 8481.0
|
466 |
},
|
467 |
+
"eval_accuracy": 0.9393116852652391,
|
468 |
+
"eval_loss": 0.4237186312675476,
|
469 |
"eval_macro avg": {
|
470 |
+
"f1-score": 0.9172775642196499,
|
471 |
+
"precision": 0.9200087239898588,
|
472 |
+
"recall": 0.9164131235329801,
|
473 |
+
"support": 29841.0
|
474 |
+
},
|
475 |
+
"eval_runtime": 4.6388,
|
476 |
+
"eval_samples_per_second": 17.246,
|
477 |
+
"eval_steps_per_second": 2.156,
|
478 |
"eval_weighted avg": {
|
479 |
+
"f1-score": 0.9385463313402296,
|
480 |
+
"precision": 0.9393689288141548,
|
481 |
+
"recall": 0.9393116852652391,
|
482 |
+
"support": 29841.0
|
483 |
},
|
484 |
"step": 972
|
485 |
},
|
486 |
{
|
487 |
"epoch": 12.35,
|
488 |
+
"grad_norm": 0.5223535895347595,
|
489 |
"learning_rate": 1.506172839506173e-05,
|
490 |
+
"loss": 0.0196,
|
491 |
"step": 1000
|
492 |
},
|
493 |
{
|
494 |
"epoch": 13.0,
|
495 |
"eval_B": {
|
496 |
+
"f1-score": 0.8891411275066211,
|
497 |
+
"precision": 0.8716617210682492,
|
498 |
+
"recall": 0.9073359073359073,
|
499 |
+
"support": 1295.0
|
500 |
},
|
501 |
"eval_I": {
|
502 |
+
"f1-score": 0.9610692322951795,
|
503 |
+
"precision": 0.9563736860287223,
|
504 |
+
"recall": 0.9658111138798904,
|
505 |
+
"support": 20065.0
|
506 |
},
|
507 |
"eval_O": {
|
508 |
+
"f1-score": 0.9043145233678416,
|
509 |
+
"precision": 0.918104495747266,
|
510 |
+
"recall": 0.8909326730338404,
|
511 |
+
"support": 8481.0
|
512 |
},
|
513 |
+
"eval_accuracy": 0.9419925605710264,
|
514 |
+
"eval_loss": 0.4308999180793762,
|
515 |
"eval_macro avg": {
|
516 |
+
"f1-score": 0.9181749610565474,
|
517 |
+
"precision": 0.9153799676147458,
|
518 |
+
"recall": 0.9213598980832126,
|
519 |
+
"support": 29841.0
|
520 |
+
},
|
521 |
+
"eval_runtime": 4.6555,
|
522 |
+
"eval_samples_per_second": 17.184,
|
523 |
+
"eval_steps_per_second": 2.148,
|
524 |
"eval_weighted avg": {
|
525 |
+
"f1-score": 0.9418177466843106,
|
526 |
+
"precision": 0.9418211242043584,
|
527 |
+
"recall": 0.9419925605710264,
|
528 |
+
"support": 29841.0
|
529 |
},
|
530 |
"step": 1053
|
531 |
},
|
532 |
{
|
533 |
"epoch": 14.0,
|
534 |
"eval_B": {
|
535 |
+
"f1-score": 0.9025601834161253,
|
536 |
+
"precision": 0.8933434190620272,
|
537 |
+
"recall": 0.911969111969112,
|
538 |
+
"support": 1295.0
|
539 |
},
|
540 |
"eval_I": {
|
541 |
+
"f1-score": 0.960806215404473,
|
542 |
+
"precision": 0.9570764513895758,
|
543 |
+
"recall": 0.9645651632195366,
|
544 |
+
"support": 20065.0
|
545 |
},
|
546 |
"eval_O": {
|
547 |
+
"f1-score": 0.9030873763261413,
|
548 |
+
"precision": 0.9131011208870676,
|
549 |
+
"recall": 0.8932908855087843,
|
550 |
+
"support": 8481.0
|
551 |
},
|
552 |
+
"eval_accuracy": 0.9420260715123487,
|
553 |
+
"eval_loss": 0.4198700487613678,
|
554 |
"eval_macro avg": {
|
555 |
+
"f1-score": 0.9221512583822467,
|
556 |
+
"precision": 0.9211736637795568,
|
557 |
+
"recall": 0.9232750535658111,
|
558 |
+
"support": 29841.0
|
559 |
+
},
|
560 |
+
"eval_runtime": 4.6834,
|
561 |
+
"eval_samples_per_second": 17.082,
|
562 |
+
"eval_steps_per_second": 2.135,
|
563 |
"eval_weighted avg": {
|
564 |
+
"f1-score": 0.9418744743217934,
|
565 |
+
"precision": 0.9418125843993292,
|
566 |
+
"recall": 0.9420260715123487,
|
567 |
+
"support": 29841.0
|
568 |
},
|
569 |
"step": 1134
|
570 |
}
|
|
|
574 |
"num_input_tokens_seen": 0,
|
575 |
"num_train_epochs": 50,
|
576 |
"save_steps": 500,
|
577 |
+
"total_flos": 2013013138298400.0,
|
578 |
"train_batch_size": 4,
|
579 |
"trial_name": null,
|
580 |
"trial_params": null
|
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:d229d7bc9127d222c880edfd3fa9418a9ccede656fe27f7f0aa04990c9605be4
|
3 |
size 4856
|