Training in progress, step 2170, 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 sha256:4862a59c5429445e8ad29c3631edd3bfd2ae72a03a98eb2e5fe1e412db6b98c5
|
| 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 sha256:3e8f1d0f8787186c33cdc8601a65c839db5e58e34ff14497289b30b762bff43a
|
| 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 sha256:87c2b6b68df13674eeffb3b67e23fe18ef912341716f1d0f01c600a13cf64af8
|
| 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,
|
|
@@ -3896,6 +3896,24 @@
|
|
| 3896 |
"mean_token_accuracy": 0.6480809897184372,
|
| 3897 |
"num_tokens": 7877839.0,
|
| 3898 |
"step": 2160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3899 |
}
|
| 3900 |
],
|
| 3901 |
"logging_steps": 5,
|
|
@@ -3915,7 +3933,7 @@
|
|
| 3915 |
"attributes": {}
|
| 3916 |
}
|
| 3917 |
},
|
| 3918 |
-
"total_flos":
|
| 3919 |
"train_batch_size": 4,
|
| 3920 |
"trial_name": null,
|
| 3921 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3896 |
"mean_token_accuracy": 0.6480809897184372,
|
| 3897 |
"num_tokens": 7877839.0,
|
| 3898 |
"step": 2160
|
| 3899 |
+
},
|
| 3900 |
+
{
|
| 3901 |
+
"epoch": 16.653846153846153,
|
| 3902 |
+
"grad_norm": 0.0,
|
| 3903 |
+
"learning_rate": 3.918e-05,
|
| 3904 |
+
"loss": 1.66,
|
| 3905 |
+
"mean_token_accuracy": 0.6657153934240341,
|
| 3906 |
+
"num_tokens": 7896808.0,
|
| 3907 |
+
"step": 2165
|
| 3908 |
+
},
|
| 3909 |
+
{
|
| 3910 |
+
"epoch": 16.692307692307693,
|
| 3911 |
+
"grad_norm": 0.0,
|
| 3912 |
+
"learning_rate": 3.9155e-05,
|
| 3913 |
+
"loss": 1.6743,
|
| 3914 |
+
"mean_token_accuracy": 0.6643134742975235,
|
| 3915 |
+
"num_tokens": 7915776.0,
|
| 3916 |
+
"step": 2170
|
| 3917 |
}
|
| 3918 |
],
|
| 3919 |
"logging_steps": 5,
|
|
|
|
| 3933 |
"attributes": {}
|
| 3934 |
}
|
| 3935 |
},
|
| 3936 |
+
"total_flos": 4.0109930515759104e+17,
|
| 3937 |
"train_batch_size": 4,
|
| 3938 |
"trial_name": null,
|
| 3939 |
"trial_params": null
|