Training in progress, step 44000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1001681601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58d7908b60759dc21ccb2c8e7e0912f4f93a76d680317cd5fec5ae118ab7f2c7
|
3 |
size 1001681601
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cecc6aeb658ce5cddba59472bfbea3e76852b232a433f21fe1213ccd1ba34907
|
3 |
size 551185105
|
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:d9640f7e701d01460e354f09734e46a7a40d5d9a9364ed130984bf2e740abc77
|
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:be5d33d56fa8110787b4a768e6ee5c083b024ac4d60c4bcbcaa263471474ae4f
|
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,
|
@@ -528,11 +528,17 @@
|
|
528 |
"learning_rate": 1.1727272727272726e-09,
|
529 |
"loss": 0.0266,
|
530 |
"step": 43500
|
|
|
|
|
|
|
|
|
|
|
|
|
531 |
}
|
532 |
],
|
533 |
"max_steps": 44000,
|
534 |
"num_train_epochs": 1,
|
535 |
-
"total_flos": 4.
|
536 |
"trial_name": null,
|
537 |
"trial_params": null
|
538 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5968691500040696,
|
5 |
+
"global_step": 44000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
528 |
"learning_rate": 1.1727272727272726e-09,
|
529 |
"loss": 0.0266,
|
530 |
"step": 43500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.6,
|
534 |
+
"learning_rate": 3.636363636363636e-11,
|
535 |
+
"loss": 0.0235,
|
536 |
+
"step": 44000
|
537 |
}
|
538 |
],
|
539 |
"max_steps": 44000,
|
540 |
"num_train_epochs": 1,
|
541 |
+
"total_flos": 4.597453878932275e+16,
|
542 |
"trial_name": null,
|
543 |
"trial_params": null
|
544 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cecc6aeb658ce5cddba59472bfbea3e76852b232a433f21fe1213ccd1ba34907
|
3 |
size 551185105
|
runs/Oct24_08-39-52_00e58a194ed0/events.out.tfevents.1666601028.00e58a194ed0.23.0
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 sha256:70aa64d38f00c629e0d695193504dbd9d1c9a74cc208e6ead396e01e9d5275df
|
3 |
+
size 59630
|