Training in progress, step 5420, 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 sha256:394dc8487c71cdd33a7e3585605c136c7b03dd5b529d3f02c4f29bc3da746501
|
| 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 sha256:81fb68c4af2d06e20d7d1e0dd8b6c122911bbdfec82fcbff2e9c0db1c182d309
|
| 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:e46503531fa9b243b00535a881eeb235a646c08f441605b6edb07b3a3a4789f7
|
| 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": 41.
|
| 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,
|
|
@@ -9746,6 +9746,24 @@
|
|
| 9746 |
"mean_token_accuracy": 0.6531447738409042,
|
| 9747 |
"num_tokens": 19731634.0,
|
| 9748 |
"step": 5410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9749 |
}
|
| 9750 |
],
|
| 9751 |
"logging_steps": 5,
|
|
@@ -9765,7 +9783,7 @@
|
|
| 9765 |
"attributes": {}
|
| 9766 |
}
|
| 9767 |
},
|
| 9768 |
-
"total_flos":
|
| 9769 |
"train_batch_size": 4,
|
| 9770 |
"trial_name": null,
|
| 9771 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9746 |
"mean_token_accuracy": 0.6531447738409042,
|
| 9747 |
"num_tokens": 19731634.0,
|
| 9748 |
"step": 5410
|
| 9749 |
+
},
|
| 9750 |
+
{
|
| 9751 |
+
"epoch": 41.65384615384615,
|
| 9752 |
+
"grad_norm": 0.0,
|
| 9753 |
+
"learning_rate": 2.2930000000000002e-05,
|
| 9754 |
+
"loss": 1.7672,
|
| 9755 |
+
"mean_token_accuracy": 0.6508445739746094,
|
| 9756 |
+
"num_tokens": 19748890.0,
|
| 9757 |
+
"step": 5415
|
| 9758 |
+
},
|
| 9759 |
+
{
|
| 9760 |
+
"epoch": 41.69230769230769,
|
| 9761 |
+
"grad_norm": 0.0,
|
| 9762 |
+
"learning_rate": 2.2905000000000002e-05,
|
| 9763 |
+
"loss": 1.7294,
|
| 9764 |
+
"mean_token_accuracy": 0.6476221710443497,
|
| 9765 |
+
"num_tokens": 19767058.0,
|
| 9766 |
+
"step": 5420
|
| 9767 |
}
|
| 9768 |
],
|
| 9769 |
"logging_steps": 5,
|
|
|
|
| 9783 |
"attributes": {}
|
| 9784 |
}
|
| 9785 |
},
|
| 9786 |
+
"total_flos": 1.0015756788989952e+18,
|
| 9787 |
"train_batch_size": 4,
|
| 9788 |
"trial_name": null,
|
| 9789 |
"trial_params": null
|