Training in progress, step 8770, 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:ddbb692dd1a3e3a1166139087b49abb6694866653de6184015e9c90a49f8cb9b
|
| 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 sha256:7a120891df3dd0279973f7dc4e98693cd8b5697f4239328c813b8f4a934874a9
|
| 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 sha256:0212fb68f8cc59d6ecc8e6c314ce2e02a90ecc66cff1c9da95341edff6391cac
|
| 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": 67.
|
| 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,
|
|
@@ -15776,6 +15776,24 @@
|
|
| 15776 |
"mean_token_accuracy": 0.6487904995679855,
|
| 15777 |
"num_tokens": 31947197.0,
|
| 15778 |
"step": 8760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15779 |
}
|
| 15780 |
],
|
| 15781 |
"logging_steps": 5,
|
|
@@ -15795,7 +15813,7 @@
|
|
| 15795 |
"attributes": {}
|
| 15796 |
}
|
| 15797 |
},
|
| 15798 |
-
"total_flos": 1.
|
| 15799 |
"train_batch_size": 4,
|
| 15800 |
"trial_name": null,
|
| 15801 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15776 |
"mean_token_accuracy": 0.6487904995679855,
|
| 15777 |
"num_tokens": 31947197.0,
|
| 15778 |
"step": 8760
|
| 15779 |
+
},
|
| 15780 |
+
{
|
| 15781 |
+
"epoch": 67.42307692307692,
|
| 15782 |
+
"grad_norm": 0.0,
|
| 15783 |
+
"learning_rate": 6.18e-06,
|
| 15784 |
+
"loss": 1.7365,
|
| 15785 |
+
"mean_token_accuracy": 0.6566553086042404,
|
| 15786 |
+
"num_tokens": 31965045.0,
|
| 15787 |
+
"step": 8765
|
| 15788 |
+
},
|
| 15789 |
+
{
|
| 15790 |
+
"epoch": 67.46153846153847,
|
| 15791 |
+
"grad_norm": 0.0,
|
| 15792 |
+
"learning_rate": 6.155e-06,
|
| 15793 |
+
"loss": 1.7982,
|
| 15794 |
+
"mean_token_accuracy": 0.6392051458358765,
|
| 15795 |
+
"num_tokens": 31982476.0,
|
| 15796 |
+
"step": 8770
|
| 15797 |
}
|
| 15798 |
],
|
| 15799 |
"logging_steps": 5,
|
|
|
|
| 15813 |
"attributes": {}
|
| 15814 |
}
|
| 15815 |
},
|
| 15816 |
+
"total_flos": 1.6217041475705242e+18,
|
| 15817 |
"train_batch_size": 4,
|
| 15818 |
"trial_name": null,
|
| 15819 |
"trial_params": null
|