Training in progress, step 1550, 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 sha256:300339dfe383b0a3bb11aaef4261f06083179ae53f288176abe344ca87d3b75a
|
| 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:af2725002d585692095173c2aafeea6b1ac9e833fd2d1055d616f4204665d5cb
|
| 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:b38871718b3c21e76d305342366ed29975ae5a12b6739d0ad89221dbd86dbaff
|
| 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": 11.
|
| 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,
|
|
@@ -2780,6 +2780,24 @@
|
|
| 2780 |
"mean_token_accuracy": 0.6489449918270112,
|
| 2781 |
"num_tokens": 5616381.0,
|
| 2782 |
"step": 1540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2783 |
}
|
| 2784 |
],
|
| 2785 |
"logging_steps": 5,
|
|
@@ -2799,7 +2817,7 @@
|
|
| 2799 |
"attributes": {}
|
| 2800 |
}
|
| 2801 |
},
|
| 2802 |
-
"total_flos": 2.
|
| 2803 |
"train_batch_size": 4,
|
| 2804 |
"trial_name": null,
|
| 2805 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2780 |
"mean_token_accuracy": 0.6489449918270112,
|
| 2781 |
"num_tokens": 5616381.0,
|
| 2782 |
"step": 1540
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 11.884615384615385,
|
| 2786 |
+
"grad_norm": 0.0,
|
| 2787 |
+
"learning_rate": 4.228e-05,
|
| 2788 |
+
"loss": 1.7094,
|
| 2789 |
+
"mean_token_accuracy": 0.6595662713050843,
|
| 2790 |
+
"num_tokens": 5635297.0,
|
| 2791 |
+
"step": 1545
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 11.923076923076923,
|
| 2795 |
+
"grad_norm": 0.0,
|
| 2796 |
+
"learning_rate": 4.2255e-05,
|
| 2797 |
+
"loss": 1.7149,
|
| 2798 |
+
"mean_token_accuracy": 0.6520039916038514,
|
| 2799 |
+
"num_tokens": 5653729.0,
|
| 2800 |
+
"step": 1550
|
| 2801 |
}
|
| 2802 |
],
|
| 2803 |
"logging_steps": 5,
|
|
|
|
| 2817 |
"attributes": {}
|
| 2818 |
}
|
| 2819 |
},
|
| 2820 |
+
"total_flos": 2.8639201020198912e+17,
|
| 2821 |
"train_batch_size": 4,
|
| 2822 |
"trial_name": null,
|
| 2823 |
"trial_params": null
|