Training in progress, step 6620, 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:ec3c90641c7a23016613d25d800e1a71195b31dc093e8a892b4530c09e426a5f
|
| 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:c5e6b274de81c62d0adfe09b9d36e5ed272254af706eef57f8c29dea6866f99f
|
| 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 sha256:422eb295e6ac72d26f0b43b21131acaa00bbbc276746ee254f8b3d68f4f1573e
|
| 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": 50.
|
| 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,
|
|
@@ -11906,6 +11906,24 @@
|
|
| 11906 |
"mean_token_accuracy": 0.6584911167621612,
|
| 11907 |
"num_tokens": 24106472.0,
|
| 11908 |
"step": 6610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11909 |
}
|
| 11910 |
],
|
| 11911 |
"logging_steps": 5,
|
|
@@ -11925,7 +11943,7 @@
|
|
| 11925 |
"attributes": {}
|
| 11926 |
}
|
| 11927 |
},
|
| 11928 |
-
"total_flos": 1.
|
| 11929 |
"train_batch_size": 4,
|
| 11930 |
"trial_name": null,
|
| 11931 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11906 |
"mean_token_accuracy": 0.6584911167621612,
|
| 11907 |
"num_tokens": 24106472.0,
|
| 11908 |
"step": 6610
|
| 11909 |
+
},
|
| 11910 |
+
{
|
| 11911 |
+
"epoch": 50.88461538461539,
|
| 11912 |
+
"grad_norm": 0.0,
|
| 11913 |
+
"learning_rate": 1.6930000000000002e-05,
|
| 11914 |
+
"loss": 1.7469,
|
| 11915 |
+
"mean_token_accuracy": 0.6565795034170151,
|
| 11916 |
+
"num_tokens": 24124773.0,
|
| 11917 |
+
"step": 6615
|
| 11918 |
+
},
|
| 11919 |
+
{
|
| 11920 |
+
"epoch": 50.92307692307692,
|
| 11921 |
+
"grad_norm": 0.0,
|
| 11922 |
+
"learning_rate": 1.6905e-05,
|
| 11923 |
+
"loss": 1.7342,
|
| 11924 |
+
"mean_token_accuracy": 0.6567032128572464,
|
| 11925 |
+
"num_tokens": 24142871.0,
|
| 11926 |
+
"step": 6620
|
| 11927 |
}
|
| 11928 |
],
|
| 11929 |
"logging_steps": 5,
|
|
|
|
| 11943 |
"attributes": {}
|
| 11944 |
}
|
| 11945 |
},
|
| 11946 |
+
"total_flos": 1.2240651163469414e+18,
|
| 11947 |
"train_batch_size": 4,
|
| 11948 |
"trial_name": null,
|
| 11949 |
"trial_params": null
|