Training in progress, step 7680, 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:a3f81dbf9bf76cbbebe8c6d2a43da29bb865fc5230bfcd4d2df328e92de58a75
|
| 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 sha256:026994e56eac19471d7ed93664a4aa5535e65f5255914be14a738bf522362548
|
| 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 sha256:61f0a5e7f3c3c02c6640c2dc645506d58bc731a1db30fb48a85b289f1edaaec0
|
| 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": 59.
|
| 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,
|
|
@@ -13814,6 +13814,24 @@
|
|
| 13814 |
"mean_token_accuracy": 0.6526497393846512,
|
| 13815 |
"num_tokens": 27972195.0,
|
| 13816 |
"step": 7670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13817 |
}
|
| 13818 |
],
|
| 13819 |
"logging_steps": 5,
|
|
@@ -13833,7 +13851,7 @@
|
|
| 13833 |
"attributes": {}
|
| 13834 |
}
|
| 13835 |
},
|
| 13836 |
-
"total_flos": 1.
|
| 13837 |
"train_batch_size": 4,
|
| 13838 |
"trial_name": null,
|
| 13839 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13814 |
"mean_token_accuracy": 0.6526497393846512,
|
| 13815 |
"num_tokens": 27972195.0,
|
| 13816 |
"step": 7670
|
| 13817 |
+
},
|
| 13818 |
+
{
|
| 13819 |
+
"epoch": 59.03846153846154,
|
| 13820 |
+
"grad_norm": 0.0,
|
| 13821 |
+
"learning_rate": 1.163e-05,
|
| 13822 |
+
"loss": 1.7736,
|
| 13823 |
+
"mean_token_accuracy": 0.6459016293287277,
|
| 13824 |
+
"num_tokens": 27989703.0,
|
| 13825 |
+
"step": 7675
|
| 13826 |
+
},
|
| 13827 |
+
{
|
| 13828 |
+
"epoch": 59.07692307692308,
|
| 13829 |
+
"grad_norm": 0.0,
|
| 13830 |
+
"learning_rate": 1.1605e-05,
|
| 13831 |
+
"loss": 1.7243,
|
| 13832 |
+
"mean_token_accuracy": 0.6570581525564194,
|
| 13833 |
+
"num_tokens": 28007876.0,
|
| 13834 |
+
"step": 7680
|
| 13835 |
}
|
| 13836 |
],
|
| 13837 |
"logging_steps": 5,
|
|
|
|
| 13851 |
"attributes": {}
|
| 13852 |
}
|
| 13853 |
},
|
| 13854 |
+
"total_flos": 1.4199974713530778e+18,
|
| 13855 |
"train_batch_size": 4,
|
| 13856 |
"trial_name": null,
|
| 13857 |
"trial_params": null
|