Training in progress, step 2090, 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 sha256:8b4159bba7b9e17b9ea0bc643eea6d281521d5f8b9d3accd9fede2221f6db5d0
|
| 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:b148666ae5f8f02be2a8ec2667abdde9549e8d6854255be0f3f8c17b03d5f805
|
| 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:dd2c20d8b555623e4443db39f1f45e2169e91464751ee6ffb68b157d3bf365f4
|
| 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": 16.
|
| 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,
|
|
@@ -3752,6 +3752,24 @@
|
|
| 3752 |
"mean_token_accuracy": 0.6406063586473465,
|
| 3753 |
"num_tokens": 7585680.0,
|
| 3754 |
"step": 2080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3755 |
}
|
| 3756 |
],
|
| 3757 |
"logging_steps": 5,
|
|
@@ -3771,7 +3789,7 @@
|
|
| 3771 |
"attributes": {}
|
| 3772 |
}
|
| 3773 |
},
|
| 3774 |
-
"total_flos": 3.
|
| 3775 |
"train_batch_size": 4,
|
| 3776 |
"trial_name": null,
|
| 3777 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3752 |
"mean_token_accuracy": 0.6406063586473465,
|
| 3753 |
"num_tokens": 7585680.0,
|
| 3754 |
"step": 2080
|
| 3755 |
+
},
|
| 3756 |
+
{
|
| 3757 |
+
"epoch": 16.03846153846154,
|
| 3758 |
+
"grad_norm": 0.0,
|
| 3759 |
+
"learning_rate": 3.958e-05,
|
| 3760 |
+
"loss": 1.7458,
|
| 3761 |
+
"mean_token_accuracy": 0.6477556735277176,
|
| 3762 |
+
"num_tokens": 7604192.0,
|
| 3763 |
+
"step": 2085
|
| 3764 |
+
},
|
| 3765 |
+
{
|
| 3766 |
+
"epoch": 16.076923076923077,
|
| 3767 |
+
"grad_norm": 0.0,
|
| 3768 |
+
"learning_rate": 3.9555e-05,
|
| 3769 |
+
"loss": 1.67,
|
| 3770 |
+
"mean_token_accuracy": 0.6667103677988052,
|
| 3771 |
+
"num_tokens": 7622647.0,
|
| 3772 |
+
"step": 2090
|
| 3773 |
}
|
| 3774 |
],
|
| 3775 |
"logging_steps": 5,
|
|
|
|
| 3789 |
"attributes": {}
|
| 3790 |
}
|
| 3791 |
},
|
| 3792 |
+
"total_flos": 3.8619947007442944e+17,
|
| 3793 |
"train_batch_size": 4,
|
| 3794 |
"trial_name": null,
|
| 3795 |
"trial_params": null
|