Training in progress, step 5400, 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:cf62c6d3d3e5c9b83cfde41e07526c7595b5893401cee1efadbcc7c450c5a1fa
|
| 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:b3c2fa4f9a95bc74cce3f24aff34c8d8499fada7cac7777800edab4c62d92fde
|
| 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:da5c34fc1c6de5329c3a48723fa1835bb2f6c45b6e6b3049ba6f5db11d9c1951
|
| 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,
|
|
@@ -9710,6 +9710,24 @@
|
|
| 9710 |
"mean_token_accuracy": 0.641742405295372,
|
| 9711 |
"num_tokens": 19657464.0,
|
| 9712 |
"step": 5390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9713 |
}
|
| 9714 |
],
|
| 9715 |
"logging_steps": 5,
|
|
@@ -9729,7 +9747,7 @@
|
|
| 9729 |
"attributes": {}
|
| 9730 |
}
|
| 9731 |
},
|
| 9732 |
-
"total_flos": 9.
|
| 9733 |
"train_batch_size": 4,
|
| 9734 |
"trial_name": null,
|
| 9735 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 41.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9710 |
"mean_token_accuracy": 0.641742405295372,
|
| 9711 |
"num_tokens": 19657464.0,
|
| 9712 |
"step": 5390
|
| 9713 |
+
},
|
| 9714 |
+
{
|
| 9715 |
+
"epoch": 41.5,
|
| 9716 |
+
"grad_norm": 0.0,
|
| 9717 |
+
"learning_rate": 2.303e-05,
|
| 9718 |
+
"loss": 1.7207,
|
| 9719 |
+
"mean_token_accuracy": 0.6533408045768738,
|
| 9720 |
+
"num_tokens": 19676214.0,
|
| 9721 |
+
"step": 5395
|
| 9722 |
+
},
|
| 9723 |
+
{
|
| 9724 |
+
"epoch": 41.53846153846154,
|
| 9725 |
+
"grad_norm": 0.0,
|
| 9726 |
+
"learning_rate": 2.3005e-05,
|
| 9727 |
+
"loss": 1.7098,
|
| 9728 |
+
"mean_token_accuracy": 0.6526803016662598,
|
| 9729 |
+
"num_tokens": 19694850.0,
|
| 9730 |
+
"step": 5400
|
| 9731 |
}
|
| 9732 |
],
|
| 9733 |
"logging_steps": 5,
|
|
|
|
| 9747 |
"attributes": {}
|
| 9748 |
}
|
| 9749 |
},
|
| 9750 |
+
"total_flos": 9.979255051060838e+17,
|
| 9751 |
"train_batch_size": 4,
|
| 9752 |
"trial_name": null,
|
| 9753 |
"trial_params": null
|