Training in progress, step 970, 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 sha256:803a1b7e128f8b412deb0d7af000767249f3990df6d8e249407d4bc3d4231f8f
|
| 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 sha256:6fd4690e89e7b527bd685fc9a149fe08bf9ba153d96849278a4dfb0eea708bd0
|
| 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 sha256:2ab79edcd7cc3f4846e7982168bd73d90e21d8f6fbb74808b4fc7f6e33729f30
|
| 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,
|
|
@@ -1736,6 +1736,24 @@
|
|
| 1736 |
"mean_token_accuracy": 0.6442375689744949,
|
| 1737 |
"num_tokens": 3500954.0,
|
| 1738 |
"step": 960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1739 |
}
|
| 1740 |
],
|
| 1741 |
"logging_steps": 5,
|
|
@@ -1755,7 +1773,7 @@
|
|
| 1755 |
"attributes": {}
|
| 1756 |
}
|
| 1757 |
},
|
| 1758 |
-
"total_flos": 1.
|
| 1759 |
"train_batch_size": 4,
|
| 1760 |
"trial_name": null,
|
| 1761 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1736 |
"mean_token_accuracy": 0.6442375689744949,
|
| 1737 |
"num_tokens": 3500954.0,
|
| 1738 |
"step": 960
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 7.423076923076923,
|
| 1742 |
+
"grad_norm": 0.0,
|
| 1743 |
+
"learning_rate": 4.518e-05,
|
| 1744 |
+
"loss": 1.807,
|
| 1745 |
+
"mean_token_accuracy": 0.6401415497064591,
|
| 1746 |
+
"num_tokens": 3519001.0,
|
| 1747 |
+
"step": 965
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 7.461538461538462,
|
| 1751 |
+
"grad_norm": 0.0,
|
| 1752 |
+
"learning_rate": 4.5155000000000004e-05,
|
| 1753 |
+
"loss": 1.7395,
|
| 1754 |
+
"mean_token_accuracy": 0.6544391065835953,
|
| 1755 |
+
"num_tokens": 3537230.0,
|
| 1756 |
+
"step": 970
|
| 1757 |
}
|
| 1758 |
],
|
| 1759 |
"logging_steps": 5,
|
|
|
|
| 1773 |
"attributes": {}
|
| 1774 |
}
|
| 1775 |
},
|
| 1776 |
+
"total_flos": 1.7928515541860352e+17,
|
| 1777 |
"train_batch_size": 4,
|
| 1778 |
"trial_name": null,
|
| 1779 |
"trial_params": null
|