Training in progress, step 3670, 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 sha256:32f135d5530c9257e92634ae42dd8c62a04a9b7b176e19b78e30d4fffc074713
|
| 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 sha256:6ba856bbaae28e323ae46450389c0d1babe0e111f523ed7bbc0af156e3756026
|
| 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 sha256:0cf146f45652c263b74dd26b43d5eda70cf58fda83ecb27842b380d002f458b2
|
| 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,
|
|
@@ -6596,6 +6596,24 @@
|
|
| 6596 |
"mean_token_accuracy": 0.6411935687065125,
|
| 6597 |
"num_tokens": 13346803.0,
|
| 6598 |
"step": 3660
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6599 |
}
|
| 6600 |
],
|
| 6601 |
"logging_steps": 5,
|
|
@@ -6615,7 +6633,7 @@
|
|
| 6615 |
"attributes": {}
|
| 6616 |
}
|
| 6617 |
},
|
| 6618 |
-
"total_flos": 6.
|
| 6619 |
"train_batch_size": 4,
|
| 6620 |
"trial_name": null,
|
| 6621 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3670,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6596 |
"mean_token_accuracy": 0.6411935687065125,
|
| 6597 |
"num_tokens": 13346803.0,
|
| 6598 |
"step": 3660
|
| 6599 |
+
},
|
| 6600 |
+
{
|
| 6601 |
+
"epoch": 28.192307692307693,
|
| 6602 |
+
"grad_norm": 0.0,
|
| 6603 |
+
"learning_rate": 3.168e-05,
|
| 6604 |
+
"loss": 1.6598,
|
| 6605 |
+
"mean_token_accuracy": 0.6662024825811386,
|
| 6606 |
+
"num_tokens": 13366046.0,
|
| 6607 |
+
"step": 3665
|
| 6608 |
+
},
|
| 6609 |
+
{
|
| 6610 |
+
"epoch": 28.23076923076923,
|
| 6611 |
+
"grad_norm": 0.0,
|
| 6612 |
+
"learning_rate": 3.1655e-05,
|
| 6613 |
+
"loss": 1.7028,
|
| 6614 |
+
"mean_token_accuracy": 0.6530542701482773,
|
| 6615 |
+
"num_tokens": 13384925.0,
|
| 6616 |
+
"step": 3670
|
| 6617 |
}
|
| 6618 |
],
|
| 6619 |
"logging_steps": 5,
|
|
|
|
| 6633 |
"attributes": {}
|
| 6634 |
}
|
| 6635 |
},
|
| 6636 |
+
"total_flos": 6.782794256321741e+17,
|
| 6637 |
"train_batch_size": 4,
|
| 6638 |
"trial_name": null,
|
| 6639 |
"trial_params": null
|