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 sha256:9d3eb68fa02e883aaa77e6e8f619617b55e664cc8a57a878cbf1d9fc92191064
|
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:d92f649cc1be09c25d1de2eac713bc5fe2a01c10562d1c55cb2c1e2b0a4fe777
|
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 sha256:266a493b1d4f11c84a2a446f7b05f185deed0afc35dcf4b1327407af28455a70
|
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:bf26b472625b4dfacc68b255c299c3ddfcaa059ba3bb67965e544cb6df147e80
|
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": 5.818181818181818e-07,
|
529 |
"loss": 0.0291,
|
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": 5.818181818181818e-07,
|
529 |
"loss": 0.0291,
|
530 |
"step": 43500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.6,
|
534 |
+
"learning_rate": 1.3636363636363638e-08,
|
535 |
+
"loss": 0.0284,
|
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:d92f649cc1be09c25d1de2eac713bc5fe2a01c10562d1c55cb2c1e2b0a4fe777
|
3 |
size 551185105
|
runs/Oct19_12-48-30_40567d3bb726/events.out.tfevents.1666183950.40567d3bb726.23.0
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:b58275f1d66c18089503e63408a4084389605843c72ac469471e8e377215e29e
|
3 |
+
size 59630
|