Training in progress, step 1660, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f9d58831071360a35659cf15859d720870dd5bca791d6b5ef4db3f017efb314
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76bb23b9b2f9987e127010a61664f4b2dcc038676c054206ca45c07f299a20bf
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a61a42f20232ca9ef90b9f39f996673b0dcc8f74a881ac1edcca5a6ad9e6e508
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c41cb454e63e95755003d1433dc03d985aff582ffe54efca1871f6649c0aff5c
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1668,6 +1668,16 @@
|
|
| 1668 |
"mean_token_accuracy": 0.7478319302201271,
|
| 1669 |
"num_tokens": 7666080.0,
|
| 1670 |
"step": 1650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1671 |
}
|
| 1672 |
],
|
| 1673 |
"logging_steps": 10,
|
|
@@ -1687,7 +1697,7 @@
|
|
| 1687 |
"attributes": {}
|
| 1688 |
}
|
| 1689 |
},
|
| 1690 |
-
"total_flos": 3.
|
| 1691 |
"train_batch_size": 4,
|
| 1692 |
"trial_name": null,
|
| 1693 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.35413333333333336,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1668 |
"mean_token_accuracy": 0.7478319302201271,
|
| 1669 |
"num_tokens": 7666080.0,
|
| 1670 |
"step": 1650
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"entropy": 0.9726508021354675,
|
| 1674 |
+
"epoch": 0.35413333333333336,
|
| 1675 |
+
"grad_norm": 0.23199768364429474,
|
| 1676 |
+
"learning_rate": 9.456916830314548e-05,
|
| 1677 |
+
"loss": 1.043684482574463,
|
| 1678 |
+
"mean_token_accuracy": 0.7573757611215115,
|
| 1679 |
+
"num_tokens": 7717686.0,
|
| 1680 |
+
"step": 1660
|
| 1681 |
}
|
| 1682 |
],
|
| 1683 |
"logging_steps": 10,
|
|
|
|
| 1697 |
"attributes": {}
|
| 1698 |
}
|
| 1699 |
},
|
| 1700 |
+
"total_flos": 3.662491918502707e+16,
|
| 1701 |
"train_batch_size": 4,
|
| 1702 |
"trial_name": null,
|
| 1703 |
"trial_params": null
|