Training in progress, step 4250, 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 108113968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c51d9d75e23bd39abb95c8cda0401cc8344a8f283dca77f99a110f324728c19b
|
| 3 |
size 108113968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 57081771
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e59c19bfd3c9b6c355ba3afc399b8d2a692c07081fc6078f9dc0759ccca23914
|
| 3 |
size 57081771
|
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:ca93fa2a7c0a014ad4631c41bb445afb88ec996cb1cdb3916b2657338d0520a8
|
| 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": 300,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1698,6 +1698,16 @@
|
|
| 1698 |
"mean_token_accuracy": 0.946036446094513,
|
| 1699 |
"num_tokens": 825991.0,
|
| 1700 |
"step": 4225
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1701 |
}
|
| 1702 |
],
|
| 1703 |
"logging_steps": 25,
|
|
@@ -1717,7 +1727,7 @@
|
|
| 1717 |
"attributes": {}
|
| 1718 |
}
|
| 1719 |
},
|
| 1720 |
-
"total_flos": 3.
|
| 1721 |
"train_batch_size": 4,
|
| 1722 |
"trial_name": null,
|
| 1723 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9661286656058196,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 4250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1698 |
"mean_token_accuracy": 0.946036446094513,
|
| 1699 |
"num_tokens": 825991.0,
|
| 1700 |
"step": 4225
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"entropy": 0.15503519803285598,
|
| 1704 |
+
"epoch": 0.9661286656058196,
|
| 1705 |
+
"grad_norm": 0.28532683849334717,
|
| 1706 |
+
"learning_rate": 0.0002,
|
| 1707 |
+
"loss": 0.15653125762939454,
|
| 1708 |
+
"mean_token_accuracy": 0.9473757338523865,
|
| 1709 |
+
"num_tokens": 855996.0,
|
| 1710 |
+
"step": 4250
|
| 1711 |
}
|
| 1712 |
],
|
| 1713 |
"logging_steps": 25,
|
|
|
|
| 1727 |
"attributes": {}
|
| 1728 |
}
|
| 1729 |
},
|
| 1730 |
+
"total_flos": 3.655736438855854e+17,
|
| 1731 |
"train_batch_size": 4,
|
| 1732 |
"trial_name": null,
|
| 1733 |
"trial_params": null
|