Training in progress, step 7800, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc5bbbbe1284d8d4301943eeb408bd8eece895cd68d659e77190b79c83116216
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69c9ccc02542d2bbcd615a6030ac17beac42ec41c629efd7c5a22af681850617
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b59adf55a7232b8639c4c7b5b4cf6b9bc203f08ad3c39177fc5a91efffd82471
|
| 3 |
size 15006
|
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:dcbc5a934aad1fca80fe095846252077289ce9a9cbc4bde3cd2d3d9f45999a01
|
| 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": 15.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -666,6 +666,13 @@
|
|
| 666 |
"learning_rate": 4.866666666666667e-05,
|
| 667 |
"loss": 1.2372,
|
| 668 |
"step": 7700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 669 |
}
|
| 670 |
],
|
| 671 |
"logging_steps": 100,
|
|
@@ -685,7 +692,7 @@
|
|
| 685 |
"attributes": {}
|
| 686 |
}
|
| 687 |
},
|
| 688 |
-
"total_flos": 1.
|
| 689 |
"train_batch_size": 8,
|
| 690 |
"trial_name": null,
|
| 691 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.597562880799876,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 666 |
"learning_rate": 4.866666666666667e-05,
|
| 667 |
"loss": 1.2372,
|
| 668 |
"step": 7700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 15.597562880799876,
|
| 672 |
+
"grad_norm": 0.22396279871463776,
|
| 673 |
+
"learning_rate": 4.8e-05,
|
| 674 |
+
"loss": 1.234,
|
| 675 |
+
"step": 7800
|
| 676 |
}
|
| 677 |
],
|
| 678 |
"logging_steps": 100,
|
|
|
|
| 692 |
"attributes": {}
|
| 693 |
}
|
| 694 |
},
|
| 695 |
+
"total_flos": 1.2173710399622873e+19,
|
| 696 |
"train_batch_size": 8,
|
| 697 |
"trial_name": null,
|
| 698 |
"trial_params": null
|