Training in progress, step 45000
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 402587859
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69ffd19a39486f3a31aacb5cff794472bd0f86e212ef68386e865c4f9001187a
|
3 |
size 402587859
|
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:da376d63afaf62c4e412e7718b08bb7a4eeb2c5e041b58f6d26daa627e7dcd61
|
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:d733fe62ab79b3e90f46530915d151ccf1bb68c9ebd5001ae36b09bc21f231c4
|
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 sha256:7a7eff06a1ae4a9a1d3b773f9bf6f7dd7532068d9ada1dda3aef4e7a544d1de0
|
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:d031facca7b25f6213872c1ea7a80d1bbffd3983acdfd8005bd54b16098b3d88
|
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:d713fe92ec549eeb480469548862810b4e2f1191e9ca01298fbb5799c420d07b
|
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:ea6f915d5332a6f33b6e80c84d4a13b39d758deb4af7feeb7ca680b60e573e89
|
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:a3f6afd0ca8d8a5548a4d1ee2bfd5c6ed3d46bc226e641f25e9ce162c9435de3
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -486,6 +486,66 @@
|
|
486 |
"learning_rate": 0.0001478024616707538,
|
487 |
"loss": 0.3683,
|
488 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
489 |
}
|
490 |
],
|
491 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7659509280772079,
|
5 |
+
"global_step": 45000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
486 |
"learning_rate": 0.0001478024616707538,
|
487 |
"loss": 0.3683,
|
488 |
"step": 40000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.69,
|
492 |
+
"learning_rate": 0.00014774756815776608,
|
493 |
+
"loss": 0.368,
|
494 |
+
"step": 40500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.7,
|
498 |
+
"learning_rate": 0.00014769189666559521,
|
499 |
+
"loss": 0.3679,
|
500 |
+
"step": 41000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.71,
|
504 |
+
"learning_rate": 0.00014763555708173254,
|
505 |
+
"loss": 0.3676,
|
506 |
+
"step": 41500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.71,
|
510 |
+
"learning_rate": 0.0001475785499622271,
|
511 |
+
"loss": 0.3669,
|
512 |
+
"step": 42000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.72,
|
516 |
+
"learning_rate": 0.00014752087586971605,
|
517 |
+
"loss": 0.3673,
|
518 |
+
"step": 42500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.73,
|
522 |
+
"learning_rate": 0.0001474626527191014,
|
523 |
+
"loss": 0.3668,
|
524 |
+
"step": 43000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.74,
|
528 |
+
"learning_rate": 0.00014740364772589337,
|
529 |
+
"loss": 0.3666,
|
530 |
+
"step": 43500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.75,
|
534 |
+
"learning_rate": 0.00014734397748589426,
|
535 |
+
"loss": 0.3665,
|
536 |
+
"step": 44000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.76,
|
540 |
+
"learning_rate": 0.0001472836425880252,
|
541 |
+
"loss": 0.366,
|
542 |
+
"step": 44500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.77,
|
546 |
+
"learning_rate": 0.00014722264362776731,
|
547 |
+
"loss": 0.3657,
|
548 |
+
"step": 45000
|
549 |
}
|
550 |
],
|
551 |
"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:da376d63afaf62c4e412e7718b08bb7a4eeb2c5e041b58f6d26daa627e7dcd61
|
3 |
size 201355195
|