Training in progress, step 9790, 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:a39e3d2c6092ab8b6c4bbd3de3c47e4a644dc7d1ac9b4acda882cb8563d2a08f
|
| 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 sha256:947e8f69fcfd8cefb3d253cadec5fc9c5b263515dbd7c312e8b30c8c1cb7cb46
|
| 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 sha256:480b1eae85772525598b2d56d79a25b75a4454c597c9860279dc1fe66dbd14d5
|
| 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": 75.
|
| 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,
|
|
@@ -17612,6 +17612,24 @@
|
|
| 17612 |
"mean_token_accuracy": 0.6435405910015106,
|
| 17613 |
"num_tokens": 35666156.0,
|
| 17614 |
"step": 9780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17615 |
}
|
| 17616 |
],
|
| 17617 |
"logging_steps": 5,
|
|
@@ -17631,7 +17649,7 @@
|
|
| 17631 |
"attributes": {}
|
| 17632 |
}
|
| 17633 |
},
|
| 17634 |
-
"total_flos": 1.
|
| 17635 |
"train_batch_size": 4,
|
| 17636 |
"trial_name": null,
|
| 17637 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 75.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17612 |
"mean_token_accuracy": 0.6435405910015106,
|
| 17613 |
"num_tokens": 35666156.0,
|
| 17614 |
"step": 9780
|
| 17615 |
+
},
|
| 17616 |
+
{
|
| 17617 |
+
"epoch": 75.26923076923077,
|
| 17618 |
+
"grad_norm": 0.0,
|
| 17619 |
+
"learning_rate": 1.08e-06,
|
| 17620 |
+
"loss": 1.7269,
|
| 17621 |
+
"mean_token_accuracy": 0.6546905755996704,
|
| 17622 |
+
"num_tokens": 35684367.0,
|
| 17623 |
+
"step": 9785
|
| 17624 |
+
},
|
| 17625 |
+
{
|
| 17626 |
+
"epoch": 75.3076923076923,
|
| 17627 |
+
"grad_norm": 0.0,
|
| 17628 |
+
"learning_rate": 1.055e-06,
|
| 17629 |
+
"loss": 1.7454,
|
| 17630 |
+
"mean_token_accuracy": 0.6543306648731232,
|
| 17631 |
+
"num_tokens": 35703139.0,
|
| 17632 |
+
"step": 9790
|
| 17633 |
}
|
| 17634 |
],
|
| 17635 |
"logging_steps": 5,
|
|
|
|
| 17649 |
"attributes": {}
|
| 17650 |
}
|
| 17651 |
},
|
| 17652 |
+
"total_flos": 1.8105827390049485e+18,
|
| 17653 |
"train_batch_size": 4,
|
| 17654 |
"trial_name": null,
|
| 17655 |
"trial_params": null
|