Training in progress, step 3880, 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 sha256:3c39def02705a70ce20f1721c1b6374c9026afe8759391f6d24c1aa08ec2c0d7
|
| 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:b0336041dde10d1cdab5c9ab4ed75ac8a436a9d51c414a2e3a2d63fba2340634
|
| 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 sha256:4ab55047b640768d70beef601e3adf2afa6d49c4fb4899893490afeb5b5370ab
|
| 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": 29.
|
| 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,
|
|
@@ -6974,6 +6974,24 @@
|
|
| 6974 |
"mean_token_accuracy": 0.6524263739585876,
|
| 6975 |
"num_tokens": 14114433.0,
|
| 6976 |
"step": 3870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6977 |
}
|
| 6978 |
],
|
| 6979 |
"logging_steps": 5,
|
|
@@ -6993,7 +7011,7 @@
|
|
| 6993 |
"attributes": {}
|
| 6994 |
}
|
| 6995 |
},
|
| 6996 |
-
"total_flos": 7.
|
| 6997 |
"train_batch_size": 4,
|
| 6998 |
"trial_name": null,
|
| 6999 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6974 |
"mean_token_accuracy": 0.6524263739585876,
|
| 6975 |
"num_tokens": 14114433.0,
|
| 6976 |
"step": 3870
|
| 6977 |
+
},
|
| 6978 |
+
{
|
| 6979 |
+
"epoch": 29.807692307692307,
|
| 6980 |
+
"grad_norm": 0.0,
|
| 6981 |
+
"learning_rate": 3.063e-05,
|
| 6982 |
+
"loss": 1.7631,
|
| 6983 |
+
"mean_token_accuracy": 0.6457651436328888,
|
| 6984 |
+
"num_tokens": 14132433.0,
|
| 6985 |
+
"step": 3875
|
| 6986 |
+
},
|
| 6987 |
+
{
|
| 6988 |
+
"epoch": 29.846153846153847,
|
| 6989 |
+
"grad_norm": 0.0,
|
| 6990 |
+
"learning_rate": 3.0605e-05,
|
| 6991 |
+
"loss": 1.7735,
|
| 6992 |
+
"mean_token_accuracy": 0.6389037370681763,
|
| 6993 |
+
"num_tokens": 14150572.0,
|
| 6994 |
+
"step": 3880
|
| 6995 |
}
|
| 6996 |
],
|
| 6997 |
"logging_steps": 5,
|
|
|
|
| 7011 |
"attributes": {}
|
| 7012 |
}
|
| 7013 |
},
|
| 7014 |
+
"total_flos": 7.170529755856896e+17,
|
| 7015 |
"train_batch_size": 4,
|
| 7016 |
"trial_name": null,
|
| 7017 |
"trial_params": null
|