Training in progress, step 3720, 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:fed03047f8a22f30a60771279cb9f401aa028cf5b7c28c4f6afa63da8a66de0d
|
| 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 sha256:610e5cd6850b4f1155f57ec9e3a51fdaa7132bdbe78558c6428d9588aa2418da
|
| 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:dc859553334a81e340c2a92f66b52d91e20116f359733a3c2d3040d60d53db29
|
| 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": 28.
|
| 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,
|
|
@@ -6686,6 +6686,24 @@
|
|
| 6686 |
"mean_token_accuracy": 0.6466316103935241,
|
| 6687 |
"num_tokens": 13529925.0,
|
| 6688 |
"step": 3710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6689 |
}
|
| 6690 |
],
|
| 6691 |
"logging_steps": 5,
|
|
@@ -6705,7 +6723,7 @@
|
|
| 6705 |
"attributes": {}
|
| 6706 |
}
|
| 6707 |
},
|
| 6708 |
-
"total_flos": 6.
|
| 6709 |
"train_batch_size": 4,
|
| 6710 |
"trial_name": null,
|
| 6711 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6686 |
"mean_token_accuracy": 0.6466316103935241,
|
| 6687 |
"num_tokens": 13529925.0,
|
| 6688 |
"step": 3710
|
| 6689 |
+
},
|
| 6690 |
+
{
|
| 6691 |
+
"epoch": 28.576923076923077,
|
| 6692 |
+
"grad_norm": 0.0,
|
| 6693 |
+
"learning_rate": 3.143e-05,
|
| 6694 |
+
"loss": 1.6938,
|
| 6695 |
+
"mean_token_accuracy": 0.663212212920189,
|
| 6696 |
+
"num_tokens": 13548438.0,
|
| 6697 |
+
"step": 3715
|
| 6698 |
+
},
|
| 6699 |
+
{
|
| 6700 |
+
"epoch": 28.615384615384617,
|
| 6701 |
+
"grad_norm": 0.0,
|
| 6702 |
+
"learning_rate": 3.1405e-05,
|
| 6703 |
+
"loss": 1.7596,
|
| 6704 |
+
"mean_token_accuracy": 0.6495319962501526,
|
| 6705 |
+
"num_tokens": 13566473.0,
|
| 6706 |
+
"step": 3720
|
| 6707 |
}
|
| 6708 |
],
|
| 6709 |
"logging_steps": 5,
|
|
|
|
| 6723 |
"attributes": {}
|
| 6724 |
}
|
| 6725 |
},
|
| 6726 |
+
"total_flos": 6.875746744113562e+17,
|
| 6727 |
"train_batch_size": 4,
|
| 6728 |
"trial_name": null,
|
| 6729 |
"trial_params": null
|