Training in progress, step 4870, 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:df555f9d66179f657af6605543fcf198e87038c2ae1b2b17828f4616adc3d9ec
|
| 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 sha256:6f85380a9d8e562dd4a64164daff6264561c77ec7d952dd14dea8fd901f41c62
|
| 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 sha256:36aad8c24c9ff6d3c00b58ccbd5af27acf91ea31b1e1364d25d1a192bde021f9
|
| 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": 37.
|
| 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,
|
|
@@ -8756,6 +8756,24 @@
|
|
| 8756 |
"mean_token_accuracy": 0.6404423266649246,
|
| 8757 |
"num_tokens": 17724627.0,
|
| 8758 |
"step": 4860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8759 |
}
|
| 8760 |
],
|
| 8761 |
"logging_steps": 5,
|
|
@@ -8775,7 +8793,7 @@
|
|
| 8775 |
"attributes": {}
|
| 8776 |
}
|
| 8777 |
},
|
| 8778 |
-
"total_flos":
|
| 8779 |
"train_batch_size": 4,
|
| 8780 |
"trial_name": null,
|
| 8781 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8756 |
"mean_token_accuracy": 0.6404423266649246,
|
| 8757 |
"num_tokens": 17724627.0,
|
| 8758 |
"step": 4860
|
| 8759 |
+
},
|
| 8760 |
+
{
|
| 8761 |
+
"epoch": 37.42307692307692,
|
| 8762 |
+
"grad_norm": 0.0,
|
| 8763 |
+
"learning_rate": 2.5679999999999998e-05,
|
| 8764 |
+
"loss": 1.7607,
|
| 8765 |
+
"mean_token_accuracy": 0.649592487514019,
|
| 8766 |
+
"num_tokens": 17742357.0,
|
| 8767 |
+
"step": 4865
|
| 8768 |
+
},
|
| 8769 |
+
{
|
| 8770 |
+
"epoch": 37.46153846153846,
|
| 8771 |
+
"grad_norm": 0.0,
|
| 8772 |
+
"learning_rate": 2.5655e-05,
|
| 8773 |
+
"loss": 1.7116,
|
| 8774 |
+
"mean_token_accuracy": 0.6577517062425613,
|
| 8775 |
+
"num_tokens": 17761170.0,
|
| 8776 |
+
"step": 4870
|
| 8777 |
}
|
| 8778 |
],
|
| 8779 |
"logging_steps": 5,
|
|
|
|
| 8793 |
"attributes": {}
|
| 8794 |
}
|
| 8795 |
},
|
| 8796 |
+
"total_flos": 9.000778562356838e+17,
|
| 8797 |
"train_batch_size": 4,
|
| 8798 |
"trial_name": null,
|
| 8799 |
"trial_params": null
|