Training in progress, step 3660, 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 sha256:39bed4b07fb27d88cd349dfac89fd158646500378a63d082a3a279c52d107aeb
|
| 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 sha256:93a83ced904d731f5c0d72364916eb9af1e889c237eef7d95584b3555088fd93
|
| 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:cca8629d0d689f0a6b6b7f1c80bd211e4bba9bd32af90799da12b91692619352
|
| 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,
|
|
@@ -6578,6 +6578,24 @@
|
|
| 6578 |
"mean_token_accuracy": 0.6506305515766144,
|
| 6579 |
"num_tokens": 13310902.0,
|
| 6580 |
"step": 3650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6581 |
}
|
| 6582 |
],
|
| 6583 |
"logging_steps": 5,
|
|
@@ -6597,7 +6615,7 @@
|
|
| 6597 |
"attributes": {}
|
| 6598 |
}
|
| 6599 |
},
|
| 6600 |
-
"total_flos": 6.
|
| 6601 |
"train_batch_size": 4,
|
| 6602 |
"trial_name": null,
|
| 6603 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6578 |
"mean_token_accuracy": 0.6506305515766144,
|
| 6579 |
"num_tokens": 13310902.0,
|
| 6580 |
"step": 3650
|
| 6581 |
+
},
|
| 6582 |
+
{
|
| 6583 |
+
"epoch": 28.115384615384617,
|
| 6584 |
+
"grad_norm": 0.0,
|
| 6585 |
+
"learning_rate": 3.173e-05,
|
| 6586 |
+
"loss": 1.7557,
|
| 6587 |
+
"mean_token_accuracy": 0.6501852482557297,
|
| 6588 |
+
"num_tokens": 13329266.0,
|
| 6589 |
+
"step": 3655
|
| 6590 |
+
},
|
| 6591 |
+
{
|
| 6592 |
+
"epoch": 28.153846153846153,
|
| 6593 |
+
"grad_norm": 0.0,
|
| 6594 |
+
"learning_rate": 3.1705e-05,
|
| 6595 |
+
"loss": 1.7799,
|
| 6596 |
+
"mean_token_accuracy": 0.6411935687065125,
|
| 6597 |
+
"num_tokens": 13346803.0,
|
| 6598 |
+
"step": 3660
|
| 6599 |
}
|
| 6600 |
],
|
| 6601 |
"logging_steps": 5,
|
|
|
|
| 6615 |
"attributes": {}
|
| 6616 |
}
|
| 6617 |
},
|
| 6618 |
+
"total_flos": 6.763000847951462e+17,
|
| 6619 |
"train_batch_size": 4,
|
| 6620 |
"trial_name": null,
|
| 6621 |
"trial_params": null
|