MohamedAhmedAE
commited on
Commit
•
d435078
1
Parent(s):
8473296
Training in progress, step 9800, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1423793692
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9d3097201c581d2fc1e0ac63741fdb2046404d91572a71ec0a2d1df566229b9
|
3 |
size 1423793692
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2847809392
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95ea64d249ea2c1d4b60471ad44dd1911880e972b512c7a1a2c13af619a6f036
|
3 |
size 2847809392
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13990
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b67ac0dc56e87afd828d12fa63e2974563d42a9d56163f968e03e8ed24c8b3d
|
3 |
size 13990
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4063efcf27ef2e21873156771b92a5297bf15faaf7ac9fcdd7d3704dc05c483
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -686,6 +686,13 @@
|
|
686 |
"learning_rate": 1.9999483906005676e-05,
|
687 |
"loss": 7.1899,
|
688 |
"step": 9700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
689 |
}
|
690 |
],
|
691 |
"logging_steps": 100,
|
@@ -705,7 +712,7 @@
|
|
705 |
"attributes": {}
|
706 |
}
|
707 |
},
|
708 |
-
"total_flos":
|
709 |
"train_batch_size": 1,
|
710 |
"trial_name": null,
|
711 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.16344774675606258,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 9800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
686 |
"learning_rate": 1.9999483906005676e-05,
|
687 |
"loss": 7.1899,
|
688 |
"step": 9700
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.16344774675606258,
|
692 |
+
"grad_norm": 34.184627532958984,
|
693 |
+
"learning_rate": 1.9999473204590722e-05,
|
694 |
+
"loss": 7.0871,
|
695 |
+
"step": 9800
|
696 |
}
|
697 |
],
|
698 |
"logging_steps": 100,
|
|
|
712 |
"attributes": {}
|
713 |
}
|
714 |
},
|
715 |
+
"total_flos": 487830390535296.0,
|
716 |
"train_batch_size": 1,
|
717 |
"trial_name": null,
|
718 |
"trial_params": null
|