Training in progress, step 980, 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 sha256:1cea9b78a59d5ad9450345fd911f6b4fa239d0c0ba0604479adb9f9bfb41f79f
|
| 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 sha256:92a155a694476558eb5bf46cac3177603c74dbe68257b744f8c61daf5508cefc
|
| 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 sha256:7f47c7fb52ca876b8489597f207e950129a3d79e6563f99805bc042ad03eb04d
|
| 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,
|
|
@@ -1754,6 +1754,24 @@
|
|
| 1754 |
"mean_token_accuracy": 0.6544391065835953,
|
| 1755 |
"num_tokens": 3537230.0,
|
| 1756 |
"step": 970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1757 |
}
|
| 1758 |
],
|
| 1759 |
"logging_steps": 5,
|
|
@@ -1773,7 +1791,7 @@
|
|
| 1773 |
"attributes": {}
|
| 1774 |
}
|
| 1775 |
},
|
| 1776 |
-
"total_flos": 1.
|
| 1777 |
"train_batch_size": 4,
|
| 1778 |
"trial_name": null,
|
| 1779 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1754 |
"mean_token_accuracy": 0.6544391065835953,
|
| 1755 |
"num_tokens": 3537230.0,
|
| 1756 |
"step": 970
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 7.5,
|
| 1760 |
+
"grad_norm": 0.0,
|
| 1761 |
+
"learning_rate": 4.513e-05,
|
| 1762 |
+
"loss": 1.7505,
|
| 1763 |
+
"mean_token_accuracy": 0.6461744338274003,
|
| 1764 |
+
"num_tokens": 3555470.0,
|
| 1765 |
+
"step": 975
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 7.538461538461538,
|
| 1769 |
+
"grad_norm": 0.0,
|
| 1770 |
+
"learning_rate": 4.5105e-05,
|
| 1771 |
+
"loss": 1.7005,
|
| 1772 |
+
"mean_token_accuracy": 0.6609607338905334,
|
| 1773 |
+
"num_tokens": 3574088.0,
|
| 1774 |
+
"step": 980
|
| 1775 |
}
|
| 1776 |
],
|
| 1777 |
"logging_steps": 5,
|
|
|
|
| 1791 |
"attributes": {}
|
| 1792 |
}
|
| 1793 |
},
|
| 1794 |
+
"total_flos": 1.8114493555851264e+17,
|
| 1795 |
"train_batch_size": 4,
|
| 1796 |
"trial_name": null,
|
| 1797 |
"trial_params": null
|