Training in progress, step 3760, checkpoint
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 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3dfe0e2b66df3f30713862f8d1fbe98418c6ae4e8081fff021be3118efce0f4
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f3fd66606594212d1f887b8fec17148ae87f8f509b01ab71f923b865580a2de
|
| 3 |
size 14709
|
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 sha256:3309b234f42943242c1479ec1e0af3b1748b9fee9b07c51b1ce7d4989f0ff9a8
|
| 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": 28.
|
| 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,
|
|
@@ -6758,6 +6758,24 @@
|
|
| 6758 |
"mean_token_accuracy": 0.6427496522665024,
|
| 6759 |
"num_tokens": 13676355.0,
|
| 6760 |
"step": 3750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6761 |
}
|
| 6762 |
],
|
| 6763 |
"logging_steps": 5,
|
|
@@ -6777,7 +6795,7 @@
|
|
| 6777 |
"attributes": {}
|
| 6778 |
}
|
| 6779 |
},
|
| 6780 |
-
"total_flos": 6.
|
| 6781 |
"train_batch_size": 4,
|
| 6782 |
"trial_name": null,
|
| 6783 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6758 |
"mean_token_accuracy": 0.6427496522665024,
|
| 6759 |
"num_tokens": 13676355.0,
|
| 6760 |
"step": 3750
|
| 6761 |
+
},
|
| 6762 |
+
{
|
| 6763 |
+
"epoch": 28.884615384615383,
|
| 6764 |
+
"grad_norm": 0.0,
|
| 6765 |
+
"learning_rate": 3.1230000000000004e-05,
|
| 6766 |
+
"loss": 1.7997,
|
| 6767 |
+
"mean_token_accuracy": 0.6400014579296112,
|
| 6768 |
+
"num_tokens": 13693987.0,
|
| 6769 |
+
"step": 3755
|
| 6770 |
+
},
|
| 6771 |
+
{
|
| 6772 |
+
"epoch": 28.923076923076923,
|
| 6773 |
+
"grad_norm": 0.0,
|
| 6774 |
+
"learning_rate": 3.1205000000000004e-05,
|
| 6775 |
+
"loss": 1.698,
|
| 6776 |
+
"mean_token_accuracy": 0.6581391155719757,
|
| 6777 |
+
"num_tokens": 13712942.0,
|
| 6778 |
+
"step": 3760
|
| 6779 |
}
|
| 6780 |
],
|
| 6781 |
"logging_steps": 5,
|
|
|
|
| 6795 |
"attributes": {}
|
| 6796 |
}
|
| 6797 |
},
|
| 6798 |
+
"total_flos": 6.949666375645594e+17,
|
| 6799 |
"train_batch_size": 4,
|
| 6800 |
"trial_name": null,
|
| 6801 |
"trial_params": null
|