Training in progress, step 990, 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 sha256:3114383156d9575104158de4bcf40952cb6f5a16e04ab0d60e8589625d852e67
|
| 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 sha256:35866db7c0a9d60605c0f7ddd4fbab5a27e31148d3f5e0c0a29b78f286b2fcfa
|
| 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:f6b5900329526cfc2d44d73947cb0bc8c19931a4ea1ed3d80485192d4179755e
|
| 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,
|
|
@@ -1772,6 +1772,24 @@
|
|
| 1772 |
"mean_token_accuracy": 0.6609607338905334,
|
| 1773 |
"num_tokens": 3574088.0,
|
| 1774 |
"step": 980
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1775 |
}
|
| 1776 |
],
|
| 1777 |
"logging_steps": 5,
|
|
@@ -1791,7 +1809,7 @@
|
|
| 1791 |
"attributes": {}
|
| 1792 |
}
|
| 1793 |
},
|
| 1794 |
-
"total_flos": 1.
|
| 1795 |
"train_batch_size": 4,
|
| 1796 |
"trial_name": null,
|
| 1797 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 990,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1772 |
"mean_token_accuracy": 0.6609607338905334,
|
| 1773 |
"num_tokens": 3574088.0,
|
| 1774 |
"step": 980
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 7.576923076923077,
|
| 1778 |
+
"grad_norm": 0.0,
|
| 1779 |
+
"learning_rate": 4.508e-05,
|
| 1780 |
+
"loss": 1.7752,
|
| 1781 |
+
"mean_token_accuracy": 0.6407621741294861,
|
| 1782 |
+
"num_tokens": 3592361.0,
|
| 1783 |
+
"step": 985
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 7.615384615384615,
|
| 1787 |
+
"grad_norm": 0.0,
|
| 1788 |
+
"learning_rate": 4.5055e-05,
|
| 1789 |
+
"loss": 1.7903,
|
| 1790 |
+
"mean_token_accuracy": 0.6438402742147445,
|
| 1791 |
+
"num_tokens": 3610243.0,
|
| 1792 |
+
"step": 990
|
| 1793 |
}
|
| 1794 |
],
|
| 1795 |
"logging_steps": 5,
|
|
|
|
| 1809 |
"attributes": {}
|
| 1810 |
}
|
| 1811 |
},
|
| 1812 |
+
"total_flos": 1.8299169580843008e+17,
|
| 1813 |
"train_batch_size": 4,
|
| 1814 |
"trial_name": null,
|
| 1815 |
"trial_params": null
|