Training in progress, step 4830, 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 sha256:3f0483f322bf0419cddcb2f16cc3d0c29e45991c1a753cb9d87dbbc6d1a3e449
|
| 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 sha256:8d54369857a7eec42a8e0157acdc2b95d0b23810f59c962a4339d410a81c0839
|
| 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 sha256:6dcd9da80bccfe779ef9275360f8571312af506fe0742c3b0e4de70e4a2ca339
|
| 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,
|
|
@@ -8684,6 +8684,24 @@
|
|
| 8684 |
"mean_token_accuracy": 0.6465405881404876,
|
| 8685 |
"num_tokens": 17578412.0,
|
| 8686 |
"step": 4820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8687 |
}
|
| 8688 |
],
|
| 8689 |
"logging_steps": 5,
|
|
@@ -8703,7 +8721,7 @@
|
|
| 8703 |
"attributes": {}
|
| 8704 |
}
|
| 8705 |
},
|
| 8706 |
-
"total_flos": 8.
|
| 8707 |
"train_batch_size": 4,
|
| 8708 |
"trial_name": null,
|
| 8709 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8684 |
"mean_token_accuracy": 0.6465405881404876,
|
| 8685 |
"num_tokens": 17578412.0,
|
| 8686 |
"step": 4820
|
| 8687 |
+
},
|
| 8688 |
+
{
|
| 8689 |
+
"epoch": 37.11538461538461,
|
| 8690 |
+
"grad_norm": 0.0,
|
| 8691 |
+
"learning_rate": 2.588e-05,
|
| 8692 |
+
"loss": 1.667,
|
| 8693 |
+
"mean_token_accuracy": 0.6637176364660263,
|
| 8694 |
+
"num_tokens": 17597158.0,
|
| 8695 |
+
"step": 4825
|
| 8696 |
+
},
|
| 8697 |
+
{
|
| 8698 |
+
"epoch": 37.15384615384615,
|
| 8699 |
+
"grad_norm": 0.0,
|
| 8700 |
+
"learning_rate": 2.5855000000000002e-05,
|
| 8701 |
+
"loss": 1.6931,
|
| 8702 |
+
"mean_token_accuracy": 0.6589970797300339,
|
| 8703 |
+
"num_tokens": 17616052.0,
|
| 8704 |
+
"step": 4830
|
| 8705 |
}
|
| 8706 |
],
|
| 8707 |
"logging_steps": 5,
|
|
|
|
| 8721 |
"attributes": {}
|
| 8722 |
}
|
| 8723 |
},
|
| 8724 |
+
"total_flos": 8.927078046046618e+17,
|
| 8725 |
"train_batch_size": 4,
|
| 8726 |
"trial_name": null,
|
| 8727 |
"trial_params": null
|