Training in progress, step 8760, 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 sha256:5646b173b71606a7f54383d53c903986d67023269ef1078b51a7c44cf3699e0c
|
| 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:ae8a3f04e3bf630fdb57df48464f1bd1247334974e0e9b83060023aed5b198c9
|
| 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 sha256:6296103e633954dcc5faa858b7fb7d922cc89199591de225e775e99c85be5609
|
| 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": 67.
|
| 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,
|
|
@@ -15758,6 +15758,24 @@
|
|
| 15758 |
"mean_token_accuracy": 0.639714989066124,
|
| 15759 |
"num_tokens": 31911351.0,
|
| 15760 |
"step": 8750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15761 |
}
|
| 15762 |
],
|
| 15763 |
"logging_steps": 5,
|
|
@@ -15777,7 +15795,7 @@
|
|
| 15777 |
"attributes": {}
|
| 15778 |
}
|
| 15779 |
},
|
| 15780 |
-
"total_flos": 1.
|
| 15781 |
"train_batch_size": 4,
|
| 15782 |
"trial_name": null,
|
| 15783 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15758 |
"mean_token_accuracy": 0.639714989066124,
|
| 15759 |
"num_tokens": 31911351.0,
|
| 15760 |
"step": 8750
|
| 15761 |
+
},
|
| 15762 |
+
{
|
| 15763 |
+
"epoch": 67.34615384615384,
|
| 15764 |
+
"grad_norm": 0.0,
|
| 15765 |
+
"learning_rate": 6.2300000000000005e-06,
|
| 15766 |
+
"loss": 1.7045,
|
| 15767 |
+
"mean_token_accuracy": 0.653382807970047,
|
| 15768 |
+
"num_tokens": 31930240.0,
|
| 15769 |
+
"step": 8755
|
| 15770 |
+
},
|
| 15771 |
+
{
|
| 15772 |
+
"epoch": 67.38461538461539,
|
| 15773 |
+
"grad_norm": 0.0,
|
| 15774 |
+
"learning_rate": 6.205000000000001e-06,
|
| 15775 |
+
"loss": 1.8023,
|
| 15776 |
+
"mean_token_accuracy": 0.6487904995679855,
|
| 15777 |
+
"num_tokens": 31947197.0,
|
| 15778 |
+
"step": 8760
|
| 15779 |
}
|
| 15780 |
],
|
| 15781 |
"logging_steps": 5,
|
|
|
|
| 15795 |
"attributes": {}
|
| 15796 |
}
|
| 15797 |
},
|
| 15798 |
+
"total_flos": 1.6199140714758144e+18,
|
| 15799 |
"train_batch_size": 4,
|
| 15800 |
"trial_name": null,
|
| 15801 |
"trial_params": null
|