Training in progress, step 4850, 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 sha256:2983c3b179e22a509b8675bfa20e42f62978a6898e4c8a08bcc100d148a6c36b
|
| 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 sha256:8f28304af17a4e8bf3411d9299c517779b6dea9e3a6d4c931a528058d1067128
|
| 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 sha256:245424343634764355b10fa116cf3bfc53257af008ed3f6a3f77359b67155662
|
| 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": 37.
|
| 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,
|
|
@@ -8720,6 +8720,24 @@
|
|
| 8720 |
"mean_token_accuracy": 0.6458623111248016,
|
| 8721 |
"num_tokens": 17651657.0,
|
| 8722 |
"step": 4840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8723 |
}
|
| 8724 |
],
|
| 8725 |
"logging_steps": 5,
|
|
@@ -8739,7 +8757,7 @@
|
|
| 8739 |
"attributes": {}
|
| 8740 |
}
|
| 8741 |
},
|
| 8742 |
-
"total_flos": 8.
|
| 8743 |
"train_batch_size": 4,
|
| 8744 |
"trial_name": null,
|
| 8745 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8720 |
"mean_token_accuracy": 0.6458623111248016,
|
| 8721 |
"num_tokens": 17651657.0,
|
| 8722 |
"step": 4840
|
| 8723 |
+
},
|
| 8724 |
+
{
|
| 8725 |
+
"epoch": 37.26923076923077,
|
| 8726 |
+
"grad_norm": 0.0,
|
| 8727 |
+
"learning_rate": 2.5779999999999997e-05,
|
| 8728 |
+
"loss": 1.7854,
|
| 8729 |
+
"mean_token_accuracy": 0.6410915940999985,
|
| 8730 |
+
"num_tokens": 17669527.0,
|
| 8731 |
+
"step": 4845
|
| 8732 |
+
},
|
| 8733 |
+
{
|
| 8734 |
+
"epoch": 37.30769230769231,
|
| 8735 |
+
"grad_norm": 0.0,
|
| 8736 |
+
"learning_rate": 2.5755e-05,
|
| 8737 |
+
"loss": 1.7162,
|
| 8738 |
+
"mean_token_accuracy": 0.6470267534255981,
|
| 8739 |
+
"num_tokens": 17688130.0,
|
| 8740 |
+
"step": 4850
|
| 8741 |
}
|
| 8742 |
],
|
| 8743 |
"logging_steps": 5,
|
|
|
|
| 8757 |
"attributes": {}
|
| 8758 |
}
|
| 8759 |
},
|
| 8760 |
+
"total_flos": 8.963773494534144e+17,
|
| 8761 |
"train_batch_size": 4,
|
| 8762 |
"trial_name": null,
|
| 8763 |
"trial_params": null
|