joelniklaus
commited on
Commit
•
5247e04
1
Parent(s):
e2d481a
Training in progress, step 100000
Browse files- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +311 -3
- pytorch_model.bin +1 -1
- runs/Feb06_07-50-48_t1v-n-ddbbc52f-w-0/events.out.tfevents.1675669872.t1v-n-ddbbc52f-w-0.12174.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7de678e3eb4316d13ed15337255de818fcba19dc468fc2e664978fa5840e0f6
|
3 |
+
size 885325017
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 442675755
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fff60c38fbce30a0d0970841e11987d536dd4e121b40c196a768bef52288bf27
|
3 |
size 442675755
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feaad036623e0818c278e7df0b8c3dc501e6b5b74f677795a14ca972139ab142
|
3 |
size 13611
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feaad036623e0818c278e7df0b8c3dc501e6b5b74f677795a14ca972139ab142
|
3 |
size 13611
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feaad036623e0818c278e7df0b8c3dc501e6b5b74f677795a14ca972139ab142
|
3 |
size 13611
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feaad036623e0818c278e7df0b8c3dc501e6b5b74f677795a14ca972139ab142
|
3 |
size 13611
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feaad036623e0818c278e7df0b8c3dc501e6b5b74f677795a14ca972139ab142
|
3 |
size 13611
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feaad036623e0818c278e7df0b8c3dc501e6b5b74f677795a14ca972139ab142
|
3 |
size 13611
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feaad036623e0818c278e7df0b8c3dc501e6b5b74f677795a14ca972139ab142
|
3 |
size 13611
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feaad036623e0818c278e7df0b8c3dc501e6b5b74f677795a14ca972139ab142
|
3 |
size 13611
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4178362c6bd24374be7907f1b74df811389bf304534a9b4cb11df3bada4d661b
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -314,11 +314,319 @@
|
|
314 |
"eval_samples_per_second": 266.161,
|
315 |
"eval_steps_per_second": 2.129,
|
316 |
"step": 50000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
317 |
}
|
318 |
],
|
319 |
"max_steps": 200000,
|
320 |
"num_train_epochs": 9223372036854775807,
|
321 |
-
"total_flos":
|
322 |
"trial_name": null,
|
323 |
"trial_params": null
|
324 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 24.00176,
|
5 |
+
"global_step": 100000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
314 |
"eval_samples_per_second": 266.161,
|
315 |
"eval_steps_per_second": 2.129,
|
316 |
"step": 50000
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 12.01,
|
320 |
+
"learning_rate": 8.894386393810563e-05,
|
321 |
+
"loss": 0.8543,
|
322 |
+
"step": 51000
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 12.01,
|
326 |
+
"learning_rate": 8.842005554284296e-05,
|
327 |
+
"loss": 0.7843,
|
328 |
+
"step": 52000
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 12.02,
|
332 |
+
"learning_rate": 8.788574348801675e-05,
|
333 |
+
"loss": 0.7706,
|
334 |
+
"step": 53000
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 13.0,
|
338 |
+
"learning_rate": 8.73410738492077e-05,
|
339 |
+
"loss": 0.8663,
|
340 |
+
"step": 54000
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 13.01,
|
344 |
+
"learning_rate": 8.678619553365659e-05,
|
345 |
+
"loss": 0.8679,
|
346 |
+
"step": 55000
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 13.01,
|
350 |
+
"learning_rate": 8.622126023955446e-05,
|
351 |
+
"loss": 0.7686,
|
352 |
+
"step": 56000
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 13.02,
|
356 |
+
"learning_rate": 8.564642241456986e-05,
|
357 |
+
"loss": 0.7342,
|
358 |
+
"step": 57000
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 13.02,
|
362 |
+
"learning_rate": 8.506183921362443e-05,
|
363 |
+
"loss": 0.8567,
|
364 |
+
"step": 58000
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 14.0,
|
368 |
+
"learning_rate": 8.44676704559283e-05,
|
369 |
+
"loss": 0.86,
|
370 |
+
"step": 59000
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 14.01,
|
374 |
+
"learning_rate": 8.386407858128706e-05,
|
375 |
+
"loss": 0.777,
|
376 |
+
"step": 60000
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 14.01,
|
380 |
+
"learning_rate": 8.32512286056924e-05,
|
381 |
+
"loss": 0.7027,
|
382 |
+
"step": 61000
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 14.02,
|
386 |
+
"learning_rate": 8.262928807620843e-05,
|
387 |
+
"loss": 0.8554,
|
388 |
+
"step": 62000
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 15.0,
|
392 |
+
"learning_rate": 8.199842702516583e-05,
|
393 |
+
"loss": 0.8428,
|
394 |
+
"step": 63000
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 15.01,
|
398 |
+
"learning_rate": 8.135881792367686e-05,
|
399 |
+
"loss": 0.7819,
|
400 |
+
"step": 64000
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 15.01,
|
404 |
+
"learning_rate": 8.07106356344834e-05,
|
405 |
+
"loss": 0.6988,
|
406 |
+
"step": 65000
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 15.02,
|
410 |
+
"learning_rate": 8.005405736415126e-05,
|
411 |
+
"loss": 0.8313,
|
412 |
+
"step": 66000
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 16.0,
|
416 |
+
"learning_rate": 7.938926261462366e-05,
|
417 |
+
"loss": 0.823,
|
418 |
+
"step": 67000
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 16.01,
|
422 |
+
"learning_rate": 7.871643313414718e-05,
|
423 |
+
"loss": 0.7899,
|
424 |
+
"step": 68000
|
425 |
+
},
|
426 |
+
{
|
427 |
+
"epoch": 16.01,
|
428 |
+
"learning_rate": 7.803575286758364e-05,
|
429 |
+
"loss": 0.7085,
|
430 |
+
"step": 69000
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 16.02,
|
434 |
+
"learning_rate": 7.734740790612136e-05,
|
435 |
+
"loss": 0.7936,
|
436 |
+
"step": 70000
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 17.0,
|
440 |
+
"learning_rate": 7.66515864363997e-05,
|
441 |
+
"loss": 0.8175,
|
442 |
+
"step": 71000
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"epoch": 17.01,
|
446 |
+
"learning_rate": 7.594847868906076e-05,
|
447 |
+
"loss": 0.8032,
|
448 |
+
"step": 72000
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 17.01,
|
452 |
+
"learning_rate": 7.52382768867422e-05,
|
453 |
+
"loss": 0.7058,
|
454 |
+
"step": 73000
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 17.02,
|
458 |
+
"learning_rate": 7.452117519152542e-05,
|
459 |
+
"loss": 0.762,
|
460 |
+
"step": 74000
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 18.0,
|
464 |
+
"learning_rate": 7.379736965185368e-05,
|
465 |
+
"loss": 0.8109,
|
466 |
+
"step": 75000
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 18.01,
|
470 |
+
"learning_rate": 7.30670581489344e-05,
|
471 |
+
"loss": 0.7983,
|
472 |
+
"step": 76000
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 18.01,
|
476 |
+
"learning_rate": 7.233044034264034e-05,
|
477 |
+
"loss": 0.7184,
|
478 |
+
"step": 77000
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 18.02,
|
482 |
+
"learning_rate": 7.158771761692464e-05,
|
483 |
+
"loss": 0.7324,
|
484 |
+
"step": 78000
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 19.0,
|
488 |
+
"learning_rate": 7.083909302476453e-05,
|
489 |
+
"loss": 0.8052,
|
490 |
+
"step": 79000
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 19.01,
|
494 |
+
"learning_rate": 7.008477123264848e-05,
|
495 |
+
"loss": 0.7942,
|
496 |
+
"step": 80000
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 19.01,
|
500 |
+
"learning_rate": 6.932495846462261e-05,
|
501 |
+
"loss": 0.728,
|
502 |
+
"step": 81000
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 19.02,
|
506 |
+
"learning_rate": 6.855986244591104e-05,
|
507 |
+
"loss": 0.7019,
|
508 |
+
"step": 82000
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 19.02,
|
512 |
+
"learning_rate": 6.778969234612584e-05,
|
513 |
+
"loss": 0.8063,
|
514 |
+
"step": 83000
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 20.0,
|
518 |
+
"learning_rate": 6.701465872208216e-05,
|
519 |
+
"loss": 0.8064,
|
520 |
+
"step": 84000
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 20.01,
|
524 |
+
"learning_rate": 6.623497346023418e-05,
|
525 |
+
"loss": 0.7211,
|
526 |
+
"step": 85000
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 20.01,
|
530 |
+
"learning_rate": 6.545084971874738e-05,
|
531 |
+
"loss": 0.6696,
|
532 |
+
"step": 86000
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 20.02,
|
536 |
+
"learning_rate": 6.466250186922325e-05,
|
537 |
+
"loss": 0.804,
|
538 |
+
"step": 87000
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 21.0,
|
542 |
+
"learning_rate": 6.387014543809223e-05,
|
543 |
+
"loss": 0.7977,
|
544 |
+
"step": 88000
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 21.01,
|
548 |
+
"learning_rate": 6.307399704769099e-05,
|
549 |
+
"loss": 0.7326,
|
550 |
+
"step": 89000
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 21.01,
|
554 |
+
"learning_rate": 6.227427435703997e-05,
|
555 |
+
"loss": 0.6482,
|
556 |
+
"step": 90000
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 21.02,
|
560 |
+
"learning_rate": 6.147119600233758e-05,
|
561 |
+
"loss": 0.806,
|
562 |
+
"step": 91000
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 22.0,
|
566 |
+
"learning_rate": 6.066498153718735e-05,
|
567 |
+
"loss": 0.7806,
|
568 |
+
"step": 92000
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 22.01,
|
572 |
+
"learning_rate": 5.985585137257401e-05,
|
573 |
+
"loss": 0.7416,
|
574 |
+
"step": 93000
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 22.01,
|
578 |
+
"learning_rate": 5.90440267166055e-05,
|
579 |
+
"loss": 0.6584,
|
580 |
+
"step": 94000
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 22.02,
|
584 |
+
"learning_rate": 5.8229729514036705e-05,
|
585 |
+
"loss": 0.7708,
|
586 |
+
"step": 95000
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 23.0,
|
590 |
+
"learning_rate": 5.74131823855921e-05,
|
591 |
+
"loss": 0.7716,
|
592 |
+
"step": 96000
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 23.01,
|
596 |
+
"learning_rate": 5.6594608567103456e-05,
|
597 |
+
"loss": 0.7505,
|
598 |
+
"step": 97000
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 23.01,
|
602 |
+
"learning_rate": 5.577423184847932e-05,
|
603 |
+
"loss": 0.6682,
|
604 |
+
"step": 98000
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 23.02,
|
608 |
+
"learning_rate": 5.495227651252315e-05,
|
609 |
+
"loss": 0.7379,
|
610 |
+
"step": 99000
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 24.0,
|
614 |
+
"learning_rate": 5.4128967273616625e-05,
|
615 |
+
"loss": 0.7713,
|
616 |
+
"step": 100000
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 24.0,
|
620 |
+
"eval_loss": 0.5763441324234009,
|
621 |
+
"eval_runtime": 12.9231,
|
622 |
+
"eval_samples_per_second": 386.903,
|
623 |
+
"eval_steps_per_second": 3.095,
|
624 |
+
"step": 100000
|
625 |
}
|
626 |
],
|
627 |
"max_steps": 200000,
|
628 |
"num_train_epochs": 9223372036854775807,
|
629 |
+
"total_flos": 1.6845398605824e+18,
|
630 |
"trial_name": null,
|
631 |
"trial_params": null
|
632 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 442675755
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fff60c38fbce30a0d0970841e11987d536dd4e121b40c196a768bef52288bf27
|
3 |
size 442675755
|
runs/Feb06_07-50-48_t1v-n-ddbbc52f-w-0/events.out.tfevents.1675669872.t1v-n-ddbbc52f-w-0.12174.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c703b616824f0a6fdb8ae91d275f2d3277c3eb20d53e9d923ddec1d24b229ac9
|
3 |
+
size 20274
|