Training in progress, step 960, 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 sha256:17a0f551c0a6fb4e3a3696e2dd745ec6fb95002000d5f140a3981645a7cd5d64
|
| 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:da7cd36806399c550e6a598e2d7baebacf052eeb7d7357b9d975d95c41c30e05
|
| 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:f0a957fc6527bdf60970fdb6cb547fe9db060625d896423c0328279ebe907024
|
| 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": 7.
|
| 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,
|
|
@@ -1718,6 +1718,24 @@
|
|
| 1718 |
"mean_token_accuracy": 0.6401316851377488,
|
| 1719 |
"num_tokens": 3465037.0,
|
| 1720 |
"step": 950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1721 |
}
|
| 1722 |
],
|
| 1723 |
"logging_steps": 5,
|
|
@@ -1737,7 +1755,7 @@
|
|
| 1737 |
"attributes": {}
|
| 1738 |
}
|
| 1739 |
},
|
| 1740 |
-
"total_flos": 1.
|
| 1741 |
"train_batch_size": 4,
|
| 1742 |
"trial_name": null,
|
| 1743 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1718 |
"mean_token_accuracy": 0.6401316851377488,
|
| 1719 |
"num_tokens": 3465037.0,
|
| 1720 |
"step": 950
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 7.346153846153846,
|
| 1724 |
+
"grad_norm": 0.0,
|
| 1725 |
+
"learning_rate": 4.523e-05,
|
| 1726 |
+
"loss": 1.7542,
|
| 1727 |
+
"mean_token_accuracy": 0.6487213045358657,
|
| 1728 |
+
"num_tokens": 3483393.0,
|
| 1729 |
+
"step": 955
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 7.384615384615385,
|
| 1733 |
+
"grad_norm": 0.0,
|
| 1734 |
+
"learning_rate": 4.5205000000000005e-05,
|
| 1735 |
+
"loss": 1.7863,
|
| 1736 |
+
"mean_token_accuracy": 0.6442375689744949,
|
| 1737 |
+
"num_tokens": 3500954.0,
|
| 1738 |
+
"step": 960
|
| 1739 |
}
|
| 1740 |
],
|
| 1741 |
"logging_steps": 5,
|
|
|
|
| 1755 |
"attributes": {}
|
| 1756 |
}
|
| 1757 |
},
|
| 1758 |
+
"total_flos": 1.774642761695232e+17,
|
| 1759 |
"train_batch_size": 4,
|
| 1760 |
"trial_name": null,
|
| 1761 |
"trial_params": null
|