Training in progress, step 2620, 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 sha256:363e161cf697911ac3377b7187a73c788011f893dfce569629c64c122ccf0192
|
| 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 sha256:48663e48ced74183f74d5aca1cd5b7aa22741b9faaabb81ea05e1d3fcdaf4a66
|
| 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:f0a21354ea034907ddb1530b239e2ea8cbd3030407e257f98e8c587ae5593fea
|
| 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": 20.
|
| 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,
|
|
@@ -4706,6 +4706,24 @@
|
|
| 4706 |
"mean_token_accuracy": 0.6314696133136749,
|
| 4707 |
"num_tokens": 9518008.0,
|
| 4708 |
"step": 2610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4709 |
}
|
| 4710 |
],
|
| 4711 |
"logging_steps": 5,
|
|
@@ -4725,7 +4743,7 @@
|
|
| 4725 |
"attributes": {}
|
| 4726 |
}
|
| 4727 |
},
|
| 4728 |
-
"total_flos": 4.
|
| 4729 |
"train_batch_size": 4,
|
| 4730 |
"trial_name": null,
|
| 4731 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4706 |
"mean_token_accuracy": 0.6314696133136749,
|
| 4707 |
"num_tokens": 9518008.0,
|
| 4708 |
"step": 2610
|
| 4709 |
+
},
|
| 4710 |
+
{
|
| 4711 |
+
"epoch": 20.115384615384617,
|
| 4712 |
+
"grad_norm": 0.0,
|
| 4713 |
+
"learning_rate": 3.693e-05,
|
| 4714 |
+
"loss": 1.7166,
|
| 4715 |
+
"mean_token_accuracy": 0.656936526298523,
|
| 4716 |
+
"num_tokens": 9536514.0,
|
| 4717 |
+
"step": 2615
|
| 4718 |
+
},
|
| 4719 |
+
{
|
| 4720 |
+
"epoch": 20.153846153846153,
|
| 4721 |
+
"grad_norm": 0.0,
|
| 4722 |
+
"learning_rate": 3.6905e-05,
|
| 4723 |
+
"loss": 1.7997,
|
| 4724 |
+
"mean_token_accuracy": 0.6421493351459503,
|
| 4725 |
+
"num_tokens": 9554049.0,
|
| 4726 |
+
"step": 2620
|
| 4727 |
}
|
| 4728 |
],
|
| 4729 |
"logging_steps": 5,
|
|
|
|
| 4743 |
"attributes": {}
|
| 4744 |
}
|
| 4745 |
},
|
| 4746 |
+
"total_flos": 4.842422585155584e+17,
|
| 4747 |
"train_batch_size": 4,
|
| 4748 |
"trial_name": null,
|
| 4749 |
"trial_params": null
|