Training in progress, step 9940, 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 sha256:7175e95acfc10be1c99ef5be6dbb445950fe7960fa10215fa67d68cabea687c4
|
| 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 sha256:3979884e9579b87865c9c600e9840a852469fb52464c844b1e199bd519df6ccd
|
| 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:db849a663e08cfe1040409170bc118f155064dad14c6346fb8073f2592cf7bdf
|
| 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": 76.
|
| 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,
|
|
@@ -17882,6 +17882,24 @@
|
|
| 17882 |
"mean_token_accuracy": 0.6548255890607834,
|
| 17883 |
"num_tokens": 36214515.0,
|
| 17884 |
"step": 9930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17885 |
}
|
| 17886 |
],
|
| 17887 |
"logging_steps": 5,
|
|
@@ -17901,7 +17919,7 @@
|
|
| 17901 |
"attributes": {}
|
| 17902 |
}
|
| 17903 |
},
|
| 17904 |
-
"total_flos": 1.
|
| 17905 |
"train_batch_size": 4,
|
| 17906 |
"trial_name": null,
|
| 17907 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 76.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17882 |
"mean_token_accuracy": 0.6548255890607834,
|
| 17883 |
"num_tokens": 36214515.0,
|
| 17884 |
"step": 9930
|
| 17885 |
+
},
|
| 17886 |
+
{
|
| 17887 |
+
"epoch": 76.42307692307692,
|
| 17888 |
+
"grad_norm": 0.0,
|
| 17889 |
+
"learning_rate": 3.3e-07,
|
| 17890 |
+
"loss": 1.7909,
|
| 17891 |
+
"mean_token_accuracy": 0.6404381603002548,
|
| 17892 |
+
"num_tokens": 36231874.0,
|
| 17893 |
+
"step": 9935
|
| 17894 |
+
},
|
| 17895 |
+
{
|
| 17896 |
+
"epoch": 76.46153846153847,
|
| 17897 |
+
"grad_norm": 0.0,
|
| 17898 |
+
"learning_rate": 3.0500000000000004e-07,
|
| 17899 |
+
"loss": 1.7498,
|
| 17900 |
+
"mean_token_accuracy": 0.6454123288393021,
|
| 17901 |
+
"num_tokens": 36250099.0,
|
| 17902 |
+
"step": 9940
|
| 17903 |
}
|
| 17904 |
],
|
| 17905 |
"logging_steps": 5,
|
|
|
|
| 17919 |
"attributes": {}
|
| 17920 |
}
|
| 17921 |
},
|
| 17922 |
+
"total_flos": 1.838176966829998e+18,
|
| 17923 |
"train_batch_size": 4,
|
| 17924 |
"trial_name": null,
|
| 17925 |
"trial_params": null
|