Training in progress, step 480000
Browse files- last-checkpoint/optimizer.pt +1 -1
- 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 +203 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 202194449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ba54747756499885166d5b2a3615c3f228992a4cee7828e07b2b46d49d2b67c
|
3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee18b8656f6a0b3440508e619212cead3b138d9483fe935cb4bd5e4c76ccfc89
|
3 |
size 102501541
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53b80add2f721b313442c1bb213a82292246deee0ccb0a8adb5825cf71645364
|
3 |
size 14503
|
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:ebbfa680b1187d22cc7371654116ef29dab3c85749ad34b845956736ad3b3612
|
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,
|
@@ -9406,11 +9406,211 @@
|
|
9406 |
"eval_samples_per_second": 1509.326,
|
9407 |
"eval_steps_per_second": 24.034,
|
9408 |
"step": 470000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9409 |
}
|
9410 |
],
|
9411 |
"max_steps": 500000,
|
9412 |
"num_train_epochs": 12,
|
9413 |
-
"total_flos": 1.
|
9414 |
"trial_name": null,
|
9415 |
"trial_params": null
|
9416 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.183857965003844,
|
5 |
+
"global_step": 480000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
9406 |
"eval_samples_per_second": 1509.326,
|
9407 |
"eval_steps_per_second": 24.034,
|
9408 |
"step": 470000
|
9409 |
+
},
|
9410 |
+
{
|
9411 |
+
"epoch": 10.96,
|
9412 |
+
"learning_rate": 1.2751163567020592e-05,
|
9413 |
+
"loss": 0.251,
|
9414 |
+
"step": 470500
|
9415 |
+
},
|
9416 |
+
{
|
9417 |
+
"epoch": 10.97,
|
9418 |
+
"learning_rate": 1.2658977796373478e-05,
|
9419 |
+
"loss": 0.2508,
|
9420 |
+
"step": 471000
|
9421 |
+
},
|
9422 |
+
{
|
9423 |
+
"epoch": 10.97,
|
9424 |
+
"eval_loss": 0.2342199683189392,
|
9425 |
+
"eval_runtime": 1.4356,
|
9426 |
+
"eval_samples_per_second": 1531.079,
|
9427 |
+
"eval_steps_per_second": 24.38,
|
9428 |
+
"step": 471000
|
9429 |
+
},
|
9430 |
+
{
|
9431 |
+
"epoch": 10.99,
|
9432 |
+
"learning_rate": 1.2568348644340153e-05,
|
9433 |
+
"loss": 0.2509,
|
9434 |
+
"step": 471500
|
9435 |
+
},
|
9436 |
+
{
|
9437 |
+
"epoch": 11.0,
|
9438 |
+
"learning_rate": 1.2479277102026465e-05,
|
9439 |
+
"loss": 0.2508,
|
9440 |
+
"step": 472000
|
9441 |
+
},
|
9442 |
+
{
|
9443 |
+
"epoch": 11.0,
|
9444 |
+
"eval_loss": 0.23464734852313995,
|
9445 |
+
"eval_runtime": 1.4438,
|
9446 |
+
"eval_samples_per_second": 1522.38,
|
9447 |
+
"eval_steps_per_second": 24.242,
|
9448 |
+
"step": 472000
|
9449 |
+
},
|
9450 |
+
{
|
9451 |
+
"epoch": 11.01,
|
9452 |
+
"learning_rate": 1.2391764143504556e-05,
|
9453 |
+
"loss": 0.2504,
|
9454 |
+
"step": 472500
|
9455 |
+
},
|
9456 |
+
{
|
9457 |
+
"epoch": 11.02,
|
9458 |
+
"learning_rate": 1.2305810725802118e-05,
|
9459 |
+
"loss": 0.2509,
|
9460 |
+
"step": 473000
|
9461 |
+
},
|
9462 |
+
{
|
9463 |
+
"epoch": 11.02,
|
9464 |
+
"eval_loss": 0.23320455849170685,
|
9465 |
+
"eval_runtime": 1.4791,
|
9466 |
+
"eval_samples_per_second": 1486.056,
|
9467 |
+
"eval_steps_per_second": 23.663,
|
9468 |
+
"step": 473000
|
9469 |
+
},
|
9470 |
+
{
|
9471 |
+
"epoch": 11.03,
|
9472 |
+
"learning_rate": 1.222141778889195e-05,
|
9473 |
+
"loss": 0.2508,
|
9474 |
+
"step": 473500
|
9475 |
+
},
|
9476 |
+
{
|
9477 |
+
"epoch": 11.04,
|
9478 |
+
"learning_rate": 1.2138586255681707e-05,
|
9479 |
+
"loss": 0.2506,
|
9480 |
+
"step": 474000
|
9481 |
+
},
|
9482 |
+
{
|
9483 |
+
"epoch": 11.04,
|
9484 |
+
"eval_loss": 0.23511675000190735,
|
9485 |
+
"eval_runtime": 1.4624,
|
9486 |
+
"eval_samples_per_second": 1503.027,
|
9487 |
+
"eval_steps_per_second": 23.934,
|
9488 |
+
"step": 474000
|
9489 |
+
},
|
9490 |
+
{
|
9491 |
+
"epoch": 11.06,
|
9492 |
+
"learning_rate": 1.2057317032003731e-05,
|
9493 |
+
"loss": 0.2508,
|
9494 |
+
"step": 474500
|
9495 |
+
},
|
9496 |
+
{
|
9497 |
+
"epoch": 11.07,
|
9498 |
+
"learning_rate": 1.1977611006605263e-05,
|
9499 |
+
"loss": 0.2506,
|
9500 |
+
"step": 475000
|
9501 |
+
},
|
9502 |
+
{
|
9503 |
+
"epoch": 11.07,
|
9504 |
+
"eval_loss": 0.23173680901527405,
|
9505 |
+
"eval_runtime": 1.4544,
|
9506 |
+
"eval_samples_per_second": 1511.25,
|
9507 |
+
"eval_steps_per_second": 24.064,
|
9508 |
+
"step": 475000
|
9509 |
+
},
|
9510 |
+
{
|
9511 |
+
"epoch": 11.08,
|
9512 |
+
"learning_rate": 1.1899469051138602e-05,
|
9513 |
+
"loss": 0.2507,
|
9514 |
+
"step": 475500
|
9515 |
+
},
|
9516 |
+
{
|
9517 |
+
"epoch": 11.09,
|
9518 |
+
"learning_rate": 1.1822892020151667e-05,
|
9519 |
+
"loss": 0.2508,
|
9520 |
+
"step": 476000
|
9521 |
+
},
|
9522 |
+
{
|
9523 |
+
"epoch": 11.09,
|
9524 |
+
"eval_loss": 0.23393820226192474,
|
9525 |
+
"eval_runtime": 1.4377,
|
9526 |
+
"eval_samples_per_second": 1528.825,
|
9527 |
+
"eval_steps_per_second": 24.344,
|
9528 |
+
"step": 476000
|
9529 |
+
},
|
9530 |
+
{
|
9531 |
+
"epoch": 11.1,
|
9532 |
+
"learning_rate": 1.1747880751078614e-05,
|
9533 |
+
"loss": 0.2506,
|
9534 |
+
"step": 476500
|
9535 |
+
},
|
9536 |
+
{
|
9537 |
+
"epoch": 11.11,
|
9538 |
+
"learning_rate": 1.1674436064230637e-05,
|
9539 |
+
"loss": 0.2506,
|
9540 |
+
"step": 477000
|
9541 |
+
},
|
9542 |
+
{
|
9543 |
+
"epoch": 11.11,
|
9544 |
+
"eval_loss": 0.2342890352010727,
|
9545 |
+
"eval_runtime": 1.4636,
|
9546 |
+
"eval_samples_per_second": 1501.77,
|
9547 |
+
"eval_steps_per_second": 23.914,
|
9548 |
+
"step": 477000
|
9549 |
+
},
|
9550 |
+
{
|
9551 |
+
"epoch": 11.13,
|
9552 |
+
"learning_rate": 1.1602558762787069e-05,
|
9553 |
+
"loss": 0.2507,
|
9554 |
+
"step": 477500
|
9555 |
+
},
|
9556 |
+
{
|
9557 |
+
"epoch": 11.14,
|
9558 |
+
"learning_rate": 1.1532249632786582e-05,
|
9559 |
+
"loss": 0.2506,
|
9560 |
+
"step": 478000
|
9561 |
+
},
|
9562 |
+
{
|
9563 |
+
"epoch": 11.14,
|
9564 |
+
"eval_loss": 0.23357579112052917,
|
9565 |
+
"eval_runtime": 1.4711,
|
9566 |
+
"eval_samples_per_second": 1494.153,
|
9567 |
+
"eval_steps_per_second": 23.792,
|
9568 |
+
"step": 478000
|
9569 |
+
},
|
9570 |
+
{
|
9571 |
+
"epoch": 11.15,
|
9572 |
+
"learning_rate": 1.1463509443118552e-05,
|
9573 |
+
"loss": 0.2506,
|
9574 |
+
"step": 478500
|
9575 |
+
},
|
9576 |
+
{
|
9577 |
+
"epoch": 11.16,
|
9578 |
+
"learning_rate": 1.1396338945514663e-05,
|
9579 |
+
"loss": 0.2508,
|
9580 |
+
"step": 479000
|
9581 |
+
},
|
9582 |
+
{
|
9583 |
+
"epoch": 11.16,
|
9584 |
+
"eval_loss": 0.23314166069030762,
|
9585 |
+
"eval_runtime": 1.4516,
|
9586 |
+
"eval_samples_per_second": 1514.175,
|
9587 |
+
"eval_steps_per_second": 24.111,
|
9588 |
+
"step": 479000
|
9589 |
+
},
|
9590 |
+
{
|
9591 |
+
"epoch": 11.17,
|
9592 |
+
"learning_rate": 1.133073887454072e-05,
|
9593 |
+
"loss": 0.2505,
|
9594 |
+
"step": 479500
|
9595 |
+
},
|
9596 |
+
{
|
9597 |
+
"epoch": 11.18,
|
9598 |
+
"learning_rate": 1.1266709947588599e-05,
|
9599 |
+
"loss": 0.2507,
|
9600 |
+
"step": 480000
|
9601 |
+
},
|
9602 |
+
{
|
9603 |
+
"epoch": 11.18,
|
9604 |
+
"eval_loss": 0.2337002009153366,
|
9605 |
+
"eval_runtime": 1.4605,
|
9606 |
+
"eval_samples_per_second": 1504.998,
|
9607 |
+
"eval_steps_per_second": 23.965,
|
9608 |
+
"step": 480000
|
9609 |
}
|
9610 |
],
|
9611 |
"max_steps": 500000,
|
9612 |
"num_train_epochs": 12,
|
9613 |
+
"total_flos": 1.5335355194276026e+22,
|
9614 |
"trial_name": null,
|
9615 |
"trial_params": null
|
9616 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee18b8656f6a0b3440508e619212cead3b138d9483fe935cb4bd5e4c76ccfc89
|
3 |
size 102501541
|