Training in progress, step 2100, 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:ae36fe9c7a05602d50fb4c2a88cd9660abf9e50dbf3aeeed51c6690424e66755
|
| 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 sha256:2de1016cb7791297d9ae07cee01fdb952f82f349c8146dacd8becfba92fb5167
|
| 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:dc43a3754a8946d02131bf60441bb11f616cc7337794e73e5496052a4ff765c6
|
| 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": 16.
|
| 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,
|
|
@@ -3770,6 +3770,24 @@
|
|
| 3770 |
"mean_token_accuracy": 0.6667103677988052,
|
| 3771 |
"num_tokens": 7622647.0,
|
| 3772 |
"step": 2090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3773 |
}
|
| 3774 |
],
|
| 3775 |
"logging_steps": 5,
|
|
@@ -3789,7 +3807,7 @@
|
|
| 3789 |
"attributes": {}
|
| 3790 |
}
|
| 3791 |
},
|
| 3792 |
-
"total_flos": 3.
|
| 3793 |
"train_batch_size": 4,
|
| 3794 |
"trial_name": null,
|
| 3795 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3770 |
"mean_token_accuracy": 0.6667103677988052,
|
| 3771 |
"num_tokens": 7622647.0,
|
| 3772 |
"step": 2090
|
| 3773 |
+
},
|
| 3774 |
+
{
|
| 3775 |
+
"epoch": 16.115384615384617,
|
| 3776 |
+
"grad_norm": 0.0,
|
| 3777 |
+
"learning_rate": 3.953e-05,
|
| 3778 |
+
"loss": 1.7433,
|
| 3779 |
+
"mean_token_accuracy": 0.652290990948677,
|
| 3780 |
+
"num_tokens": 7640570.0,
|
| 3781 |
+
"step": 2095
|
| 3782 |
+
},
|
| 3783 |
+
{
|
| 3784 |
+
"epoch": 16.153846153846153,
|
| 3785 |
+
"grad_norm": 0.0,
|
| 3786 |
+
"learning_rate": 3.9505e-05,
|
| 3787 |
+
"loss": 1.6936,
|
| 3788 |
+
"mean_token_accuracy": 0.6566350907087326,
|
| 3789 |
+
"num_tokens": 7658920.0,
|
| 3790 |
+
"step": 2100
|
| 3791 |
}
|
| 3792 |
],
|
| 3793 |
"logging_steps": 5,
|
|
|
|
| 3807 |
"attributes": {}
|
| 3808 |
}
|
| 3809 |
},
|
| 3810 |
+
"total_flos": 3.880422608456909e+17,
|
| 3811 |
"train_batch_size": 4,
|
| 3812 |
"trial_name": null,
|
| 3813 |
"trial_params": null
|