Training in progress, step 4880, 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:c3d4ba6a445245b8b36d7411d3b657589f5a25c689e55a89b554dab840262aa6
|
| 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 sha256:3d08a386f9919d8cbf459a9ec82b01ccf16003875984e04027e75af482faf033
|
| 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 sha256:914bcfae7138274bb77119c833903ef0bb5fef720e13a3722ebef661091793e4
|
| 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,
|
|
@@ -8774,6 +8774,24 @@
|
|
| 8774 |
"mean_token_accuracy": 0.6577517062425613,
|
| 8775 |
"num_tokens": 17761170.0,
|
| 8776 |
"step": 4870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8777 |
}
|
| 8778 |
],
|
| 8779 |
"logging_steps": 5,
|
|
@@ -8793,7 +8811,7 @@
|
|
| 8793 |
"attributes": {}
|
| 8794 |
}
|
| 8795 |
},
|
| 8796 |
-
"total_flos": 9.
|
| 8797 |
"train_batch_size": 4,
|
| 8798 |
"trial_name": null,
|
| 8799 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8774 |
"mean_token_accuracy": 0.6577517062425613,
|
| 8775 |
"num_tokens": 17761170.0,
|
| 8776 |
"step": 4870
|
| 8777 |
+
},
|
| 8778 |
+
{
|
| 8779 |
+
"epoch": 37.5,
|
| 8780 |
+
"grad_norm": 0.0,
|
| 8781 |
+
"learning_rate": 2.5629999999999997e-05,
|
| 8782 |
+
"loss": 1.7832,
|
| 8783 |
+
"mean_token_accuracy": 0.6425192266702652,
|
| 8784 |
+
"num_tokens": 17778997.0,
|
| 8785 |
+
"step": 4875
|
| 8786 |
+
},
|
| 8787 |
+
{
|
| 8788 |
+
"epoch": 37.53846153846154,
|
| 8789 |
+
"grad_norm": 0.0,
|
| 8790 |
+
"learning_rate": 2.5605e-05,
|
| 8791 |
+
"loss": 1.7689,
|
| 8792 |
+
"mean_token_accuracy": 0.6469813168048859,
|
| 8793 |
+
"num_tokens": 17796705.0,
|
| 8794 |
+
"step": 4880
|
| 8795 |
}
|
| 8796 |
],
|
| 8797 |
"logging_steps": 5,
|
|
|
|
| 8811 |
"attributes": {}
|
| 8812 |
}
|
| 8813 |
},
|
| 8814 |
+
"total_flos": 9.018426864461414e+17,
|
| 8815 |
"train_batch_size": 4,
|
| 8816 |
"trial_name": null,
|
| 8817 |
"trial_params": null
|