Training in progress, step 43500
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:dacd1bd530089f9772c1e743e6dead1614a1c56894879265ec37bf87d6ca0119
|
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:ad59514cae31c7ff756f23dd6e74504f5f2b98ccf84df34d70583eb7500422b3
|
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 sha256:4458dc90a89464e6e59718d96232a722bd5b4b4cb80b60d0ce7ac85658b08f78
|
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 sha256:0eda94196eca56e150feb2c2925165d39ba3d1a0940f4099807fdaf86e4a6b0e
|
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,
|
@@ -522,11 +522,17 @@
|
|
522 |
"learning_rate": 2.309090909090909e-09,
|
523 |
"loss": 0.0257,
|
524 |
"step": 43000
|
|
|
|
|
|
|
|
|
|
|
|
|
525 |
}
|
526 |
],
|
527 |
"max_steps": 44000,
|
528 |
"num_train_epochs": 1,
|
529 |
-
"total_flos": 4.
|
530 |
"trial_name": null,
|
531 |
"trial_params": null
|
532 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5900865460267506,
|
5 |
+
"global_step": 43500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
522 |
"learning_rate": 2.309090909090909e-09,
|
523 |
"loss": 0.0257,
|
524 |
"step": 43000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.59,
|
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": 4.545212459463475e+16,
|
536 |
"trial_name": null,
|
537 |
"trial_params": null
|
538 |
}
|
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:ad59514cae31c7ff756f23dd6e74504f5f2b98ccf84df34d70583eb7500422b3
|
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:f92baba32c33b824e6e4ce211b996ad3c2ce0b2ecc2c553cbc31c00abfd9e3ec
|
3 |
+
size 59470
|