Training in progress, step 2140, 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 sha256:1c5960f6b8ee018825e24c09c0a050c242c6347eb095f83abdf843c353df8b3c
|
| 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 sha256:646ae5d67137abd095d5038224618ef76b438e58eb0b6ce9b46954796856893e
|
| 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 sha256:58efa71a177a14110a59f8999d6a0b2ca9fb7e10bea61d5fb53416a9e42c298b
|
| 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,
|
|
@@ -3842,6 +3842,24 @@
|
|
| 3842 |
"mean_token_accuracy": 0.6485352158546448,
|
| 3843 |
"num_tokens": 7768389.0,
|
| 3844 |
"step": 2130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3845 |
}
|
| 3846 |
],
|
| 3847 |
"logging_steps": 5,
|
|
@@ -3861,7 +3879,7 @@
|
|
| 3861 |
"attributes": {}
|
| 3862 |
}
|
| 3863 |
},
|
| 3864 |
-
"total_flos": 3.
|
| 3865 |
"train_batch_size": 4,
|
| 3866 |
"trial_name": null,
|
| 3867 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3842 |
"mean_token_accuracy": 0.6485352158546448,
|
| 3843 |
"num_tokens": 7768389.0,
|
| 3844 |
"step": 2130
|
| 3845 |
+
},
|
| 3846 |
+
{
|
| 3847 |
+
"epoch": 16.423076923076923,
|
| 3848 |
+
"grad_norm": 0.0,
|
| 3849 |
+
"learning_rate": 3.933e-05,
|
| 3850 |
+
"loss": 1.6815,
|
| 3851 |
+
"mean_token_accuracy": 0.6569307982921601,
|
| 3852 |
+
"num_tokens": 7787655.0,
|
| 3853 |
+
"step": 2135
|
| 3854 |
+
},
|
| 3855 |
+
{
|
| 3856 |
+
"epoch": 16.46153846153846,
|
| 3857 |
+
"grad_norm": 0.0,
|
| 3858 |
+
"learning_rate": 3.9305000000000004e-05,
|
| 3859 |
+
"loss": 1.7333,
|
| 3860 |
+
"mean_token_accuracy": 0.6505914777517319,
|
| 3861 |
+
"num_tokens": 7805096.0,
|
| 3862 |
+
"step": 2140
|
| 3863 |
}
|
| 3864 |
],
|
| 3865 |
"logging_steps": 5,
|
|
|
|
| 3879 |
"attributes": {}
|
| 3880 |
}
|
| 3881 |
},
|
| 3882 |
+
"total_flos": 3.9540866055634944e+17,
|
| 3883 |
"train_batch_size": 4,
|
| 3884 |
"trial_name": null,
|
| 3885 |
"trial_params": null
|