Training in progress, step 5990, 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 sha256:9d114196ae5a7ae0d11f87366f7d0981910fec84544bd82dee1f8db8fa64b390
|
| 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:b5ed9777b261d79fba24d02984b17429229d6d0c3f7a5069a879bb8fd0ce08e5
|
| 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 sha256:38f3f87163d374d3ee5f481deb79051a567cf24a4476976dff2bfde400f9fb47
|
| 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": 46.
|
| 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,
|
|
@@ -10772,6 +10772,24 @@
|
|
| 10772 |
"mean_token_accuracy": 0.6510831654071808,
|
| 10773 |
"num_tokens": 21808830.0,
|
| 10774 |
"step": 5980
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10775 |
}
|
| 10776 |
],
|
| 10777 |
"logging_steps": 5,
|
|
@@ -10791,7 +10809,7 @@
|
|
| 10791 |
"attributes": {}
|
| 10792 |
}
|
| 10793 |
},
|
| 10794 |
-
"total_flos": 1.
|
| 10795 |
"train_batch_size": 4,
|
| 10796 |
"trial_name": null,
|
| 10797 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5990,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10772 |
"mean_token_accuracy": 0.6510831654071808,
|
| 10773 |
"num_tokens": 21808830.0,
|
| 10774 |
"step": 5980
|
| 10775 |
+
},
|
| 10776 |
+
{
|
| 10777 |
+
"epoch": 46.03846153846154,
|
| 10778 |
+
"grad_norm": 0.0,
|
| 10779 |
+
"learning_rate": 2.008e-05,
|
| 10780 |
+
"loss": 1.7729,
|
| 10781 |
+
"mean_token_accuracy": 0.6468154609203338,
|
| 10782 |
+
"num_tokens": 21826336.0,
|
| 10783 |
+
"step": 5985
|
| 10784 |
+
},
|
| 10785 |
+
{
|
| 10786 |
+
"epoch": 46.07692307692308,
|
| 10787 |
+
"grad_norm": 0.0,
|
| 10788 |
+
"learning_rate": 2.0055e-05,
|
| 10789 |
+
"loss": 1.7439,
|
| 10790 |
+
"mean_token_accuracy": 0.657364284992218,
|
| 10791 |
+
"num_tokens": 21844521.0,
|
| 10792 |
+
"step": 5990
|
| 10793 |
}
|
| 10794 |
],
|
| 10795 |
"logging_steps": 5,
|
|
|
|
| 10809 |
"attributes": {}
|
| 10810 |
}
|
| 10811 |
},
|
| 10812 |
+
"total_flos": 1.1070026503151616e+18,
|
| 10813 |
"train_batch_size": 4,
|
| 10814 |
"trial_name": null,
|
| 10815 |
"trial_params": null
|