Training in progress, step 5960, 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 sha256:881c3e206f9b82c9edf8763a41b5664cc634e71a31c32c43293aa5f99f5ce285
|
| 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 sha256:1d061bc576194d399c8a3c3926df4e1221e2a9c5e3d125c2cac8c16ad5cd97ec
|
| 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:b55b9777ee4507e01df3f69826a23875662ae35cc2da436d64e04cb4f6d1dea3
|
| 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": 45.
|
| 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,
|
|
@@ -10718,6 +10718,24 @@
|
|
| 10718 |
"mean_token_accuracy": 0.6448839485645295,
|
| 10719 |
"num_tokens": 21699251.0,
|
| 10720 |
"step": 5950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10721 |
}
|
| 10722 |
],
|
| 10723 |
"logging_steps": 5,
|
|
@@ -10737,7 +10755,7 @@
|
|
| 10737 |
"attributes": {}
|
| 10738 |
}
|
| 10739 |
},
|
| 10740 |
-
"total_flos": 1.
|
| 10741 |
"train_batch_size": 4,
|
| 10742 |
"trial_name": null,
|
| 10743 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10718 |
"mean_token_accuracy": 0.6448839485645295,
|
| 10719 |
"num_tokens": 21699251.0,
|
| 10720 |
"step": 5950
|
| 10721 |
+
},
|
| 10722 |
+
{
|
| 10723 |
+
"epoch": 45.80769230769231,
|
| 10724 |
+
"grad_norm": 0.0,
|
| 10725 |
+
"learning_rate": 2.023e-05,
|
| 10726 |
+
"loss": 1.8038,
|
| 10727 |
+
"mean_token_accuracy": 0.6432386726140976,
|
| 10728 |
+
"num_tokens": 21716596.0,
|
| 10729 |
+
"step": 5955
|
| 10730 |
+
},
|
| 10731 |
+
{
|
| 10732 |
+
"epoch": 45.84615384615385,
|
| 10733 |
+
"grad_norm": 0.0,
|
| 10734 |
+
"learning_rate": 2.0205e-05,
|
| 10735 |
+
"loss": 1.768,
|
| 10736 |
+
"mean_token_accuracy": 0.6459046006202698,
|
| 10737 |
+
"num_tokens": 21734632.0,
|
| 10738 |
+
"step": 5960
|
| 10739 |
}
|
| 10740 |
],
|
| 10741 |
"logging_steps": 5,
|
|
|
|
| 10755 |
"attributes": {}
|
| 10756 |
}
|
| 10757 |
},
|
| 10758 |
+
"total_flos": 1.1013753585932698e+18,
|
| 10759 |
"train_batch_size": 4,
|
| 10760 |
"trial_name": null,
|
| 10761 |
"trial_params": null
|