Training in progress, step 6590, 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 sha256:7e6971e922f6438241b2899a93583ba3168ce15b63dad10bbd907fe8630e8f8a
|
| 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:b19620f6c75f837a0c8c7ec2ec3e7e2eabe692dfe15e1acdb1a05a253a84e25d
|
| 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:f7fb7c203d44728f356fad31189fc021eb23287bc15d5b555f59e011d4df8e66
|
| 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": 50.
|
| 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,
|
|
@@ -11852,6 +11852,24 @@
|
|
| 11852 |
"mean_token_accuracy": 0.6445026308298111,
|
| 11853 |
"num_tokens": 23998733.0,
|
| 11854 |
"step": 6580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11855 |
}
|
| 11856 |
],
|
| 11857 |
"logging_steps": 5,
|
|
@@ -11871,7 +11889,7 @@
|
|
| 11871 |
"attributes": {}
|
| 11872 |
}
|
| 11873 |
},
|
| 11874 |
-
"total_flos": 1.
|
| 11875 |
"train_batch_size": 4,
|
| 11876 |
"trial_name": null,
|
| 11877 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11852 |
"mean_token_accuracy": 0.6445026308298111,
|
| 11853 |
"num_tokens": 23998733.0,
|
| 11854 |
"step": 6580
|
| 11855 |
+
},
|
| 11856 |
+
{
|
| 11857 |
+
"epoch": 50.65384615384615,
|
| 11858 |
+
"grad_norm": 0.0,
|
| 11859 |
+
"learning_rate": 1.7080000000000002e-05,
|
| 11860 |
+
"loss": 1.7202,
|
| 11861 |
+
"mean_token_accuracy": 0.6478159755468369,
|
| 11862 |
+
"num_tokens": 24017155.0,
|
| 11863 |
+
"step": 6585
|
| 11864 |
+
},
|
| 11865 |
+
{
|
| 11866 |
+
"epoch": 50.69230769230769,
|
| 11867 |
+
"grad_norm": 0.0,
|
| 11868 |
+
"learning_rate": 1.7055000000000002e-05,
|
| 11869 |
+
"loss": 1.7928,
|
| 11870 |
+
"mean_token_accuracy": 0.6426284611225128,
|
| 11871 |
+
"num_tokens": 24034300.0,
|
| 11872 |
+
"step": 6590
|
| 11873 |
}
|
| 11874 |
],
|
| 11875 |
"logging_steps": 5,
|
|
|
|
| 11889 |
"attributes": {}
|
| 11890 |
}
|
| 11891 |
},
|
| 11892 |
+
"total_flos": 1.218608194648965e+18,
|
| 11893 |
"train_batch_size": 4,
|
| 11894 |
"trial_name": null,
|
| 11895 |
"trial_params": null
|