Training in progress, step 290000
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/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- 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 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51b14eff4a4273c6d3b74abfacfc73b884cf9b9b7c89a08f51ead1f04044721d
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0869ad7d95645188dccb3e4d87a800a424ce412e68cf67a7641e510484c467e
|
3 |
size 201355195
|
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 sha256:12b3f1f4ef7d54ab74f08b6a6f7af18fc022998fa9e7e56e07868a564d491d66
|
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 sha256:9135594bbb586f075b7638cecd4126fb3316150a75a6fdf73a4dbcbfa23edf9f
|
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 sha256:36e6eeeb63a7d5efe3d89e51c42e86fbccb201f0a76f81a39558ea2786f8b6a1
|
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 sha256:43d15bd14eb8428e51e4855f72917c2a4075d4c0c1aa4a9dd827fec888eb9fd9
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e94f3f55189c88e8c606f8b356b8d855b941bd1572eb843a4126c797cf5f785
|
3 |
size 559
|
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 sha256:6efbd14b80e31c442e70702f490a0feb0bba9ae059c89f649541b88541b74c6a
|
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": 4.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -3426,6 +3426,66 @@
|
|
3426 |
"learning_rate": 6.477890930484919e-05,
|
3427 |
"loss": 0.3269,
|
3428 |
"step": 285000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3429 |
}
|
3430 |
],
|
3431 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.936162245427698,
|
5 |
+
"global_step": 290000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3426 |
"learning_rate": 6.477890930484919e-05,
|
3427 |
"loss": 0.3269,
|
3428 |
"step": 285000
|
3429 |
+
},
|
3430 |
+
{
|
3431 |
+
"epoch": 4.86,
|
3432 |
+
"learning_rate": 6.456433515923394e-05,
|
3433 |
+
"loss": 0.3271,
|
3434 |
+
"step": 285500
|
3435 |
+
},
|
3436 |
+
{
|
3437 |
+
"epoch": 4.87,
|
3438 |
+
"learning_rate": 6.434991335739906e-05,
|
3439 |
+
"loss": 0.3268,
|
3440 |
+
"step": 286000
|
3441 |
+
},
|
3442 |
+
{
|
3443 |
+
"epoch": 4.88,
|
3444 |
+
"learning_rate": 6.413564601560114e-05,
|
3445 |
+
"loss": 0.3267,
|
3446 |
+
"step": 286500
|
3447 |
+
},
|
3448 |
+
{
|
3449 |
+
"epoch": 4.89,
|
3450 |
+
"learning_rate": 6.392196331243996e-05,
|
3451 |
+
"loss": 0.3266,
|
3452 |
+
"step": 287000
|
3453 |
+
},
|
3454 |
+
{
|
3455 |
+
"epoch": 4.89,
|
3456 |
+
"learning_rate": 6.370801091388329e-05,
|
3457 |
+
"loss": 0.3265,
|
3458 |
+
"step": 287500
|
3459 |
+
},
|
3460 |
+
{
|
3461 |
+
"epoch": 4.9,
|
3462 |
+
"learning_rate": 6.349421931068155e-05,
|
3463 |
+
"loss": 0.3265,
|
3464 |
+
"step": 288000
|
3465 |
+
},
|
3466 |
+
{
|
3467 |
+
"epoch": 4.91,
|
3468 |
+
"learning_rate": 6.328059061287157e-05,
|
3469 |
+
"loss": 0.3263,
|
3470 |
+
"step": 288500
|
3471 |
+
},
|
3472 |
+
{
|
3473 |
+
"epoch": 4.92,
|
3474 |
+
"learning_rate": 6.306712692888235e-05,
|
3475 |
+
"loss": 0.3263,
|
3476 |
+
"step": 289000
|
3477 |
+
},
|
3478 |
+
{
|
3479 |
+
"epoch": 4.93,
|
3480 |
+
"learning_rate": 6.285383036551425e-05,
|
3481 |
+
"loss": 0.3262,
|
3482 |
+
"step": 289500
|
3483 |
+
},
|
3484 |
+
{
|
3485 |
+
"epoch": 4.94,
|
3486 |
+
"learning_rate": 6.264070302791827e-05,
|
3487 |
+
"loss": 0.3263,
|
3488 |
+
"step": 290000
|
3489 |
}
|
3490 |
],
|
3491 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0869ad7d95645188dccb3e4d87a800a424ce412e68cf67a7641e510484c467e
|
3 |
size 201355195
|