Training in progress, step 410, 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 sha256:142683c5c654afc276b8900b85d6d8f79ff82c09a923c01c51f14c5925113431
|
| 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 sha256:7b3b9bd5baf1e58de5133b86d98e1d42b4be655eba11dac5c34f2703e7c84b17
|
| 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:d9e0c640d6699d17fc3efed425f11e6703381802a9cd742e901327286f90145c
|
| 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": 3.
|
| 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,
|
|
@@ -728,6 +728,24 @@
|
|
| 728 |
"mean_token_accuracy": 0.6484371930360794,
|
| 729 |
"num_tokens": 1458704.0,
|
| 730 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 731 |
}
|
| 732 |
],
|
| 733 |
"logging_steps": 5,
|
|
@@ -747,7 +765,7 @@
|
|
| 747 |
"attributes": {}
|
| 748 |
}
|
| 749 |
},
|
| 750 |
-
"total_flos": 7.
|
| 751 |
"train_batch_size": 4,
|
| 752 |
"trial_name": null,
|
| 753 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.1538461538461537,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 728 |
"mean_token_accuracy": 0.6484371930360794,
|
| 729 |
"num_tokens": 1458704.0,
|
| 730 |
"step": 400
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 3.1153846153846154,
|
| 734 |
+
"grad_norm": 0.0,
|
| 735 |
+
"learning_rate": 4.7980000000000005e-05,
|
| 736 |
+
"loss": 1.7741,
|
| 737 |
+
"mean_token_accuracy": 0.6491596013307571,
|
| 738 |
+
"num_tokens": 1476178.0,
|
| 739 |
+
"step": 405
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 3.1538461538461537,
|
| 743 |
+
"grad_norm": 0.0,
|
| 744 |
+
"learning_rate": 4.7955e-05,
|
| 745 |
+
"loss": 1.7011,
|
| 746 |
+
"mean_token_accuracy": 0.6573891878128052,
|
| 747 |
+
"num_tokens": 1494800.0,
|
| 748 |
+
"step": 410
|
| 749 |
}
|
| 750 |
],
|
| 751 |
"logging_steps": 5,
|
|
|
|
| 765 |
"attributes": {}
|
| 766 |
}
|
| 767 |
},
|
| 768 |
+
"total_flos": 7.564365550190592e+16,
|
| 769 |
"train_batch_size": 4,
|
| 770 |
"trial_name": null,
|
| 771 |
"trial_params": null
|