Training in progress, step 8120, 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 sha256:9b630698a860b01ccfda762b748f6441fdd787166f73c13d72ab8167946b02cd
|
| 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 sha256:2427b3c702219e1925584d2631211de1915cb8faf9080d50913f523e6dbc5ed9
|
| 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 sha256:417e7c299f415cf4077d2e171e409328eff0968587496df4e5e95713f9586d94
|
| 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": 62.
|
| 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,
|
|
@@ -14606,6 +14606,24 @@
|
|
| 14606 |
"mean_token_accuracy": 0.6581447750329972,
|
| 14607 |
"num_tokens": 29576445.0,
|
| 14608 |
"step": 8110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14609 |
}
|
| 14610 |
],
|
| 14611 |
"logging_steps": 5,
|
|
@@ -14625,7 +14643,7 @@
|
|
| 14625 |
"attributes": {}
|
| 14626 |
}
|
| 14627 |
},
|
| 14628 |
-
"total_flos": 1.
|
| 14629 |
"train_batch_size": 4,
|
| 14630 |
"trial_name": null,
|
| 14631 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14606 |
"mean_token_accuracy": 0.6581447750329972,
|
| 14607 |
"num_tokens": 29576445.0,
|
| 14608 |
"step": 8110
|
| 14609 |
+
},
|
| 14610 |
+
{
|
| 14611 |
+
"epoch": 62.42307692307692,
|
| 14612 |
+
"grad_norm": 0.0,
|
| 14613 |
+
"learning_rate": 9.43e-06,
|
| 14614 |
+
"loss": 1.8141,
|
| 14615 |
+
"mean_token_accuracy": 0.634006318449974,
|
| 14616 |
+
"num_tokens": 29594170.0,
|
| 14617 |
+
"step": 8115
|
| 14618 |
+
},
|
| 14619 |
+
{
|
| 14620 |
+
"epoch": 62.46153846153846,
|
| 14621 |
+
"grad_norm": 0.0,
|
| 14622 |
+
"learning_rate": 9.405e-06,
|
| 14623 |
+
"loss": 1.6697,
|
| 14624 |
+
"mean_token_accuracy": 0.6640021294355393,
|
| 14625 |
+
"num_tokens": 29612931.0,
|
| 14626 |
+
"step": 8120
|
| 14627 |
}
|
| 14628 |
],
|
| 14629 |
"logging_steps": 5,
|
|
|
|
| 14643 |
"attributes": {}
|
| 14644 |
}
|
| 14645 |
},
|
| 14646 |
+
"total_flos": 1.501465145939067e+18,
|
| 14647 |
"train_batch_size": 4,
|
| 14648 |
"trial_name": null,
|
| 14649 |
"trial_params": null
|