Training in progress, step 3790, 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 sha256:1a21554aabd6f0756e52811f8f52267d35dba58293cd53175e0c042b06adb891
|
| 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:e7d6a5506baa0a3b101b932d7ce1aa5ac611b72284e266448d6997c4ff76dfb9
|
| 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:f397161743031ce3d2bd5cbb2b48ebfa2cd4d9e581d0fd78a946a424fb04b1f8
|
| 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,
|
|
@@ -6812,6 +6812,24 @@
|
|
| 6812 |
"mean_token_accuracy": 0.645610973238945,
|
| 6813 |
"num_tokens": 13785732.0,
|
| 6814 |
"step": 3780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6815 |
}
|
| 6816 |
],
|
| 6817 |
"logging_steps": 5,
|
|
@@ -6831,7 +6849,7 @@
|
|
| 6831 |
"attributes": {}
|
| 6832 |
}
|
| 6833 |
},
|
| 6834 |
-
"total_flos":
|
| 6835 |
"train_batch_size": 4,
|
| 6836 |
"trial_name": null,
|
| 6837 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6812 |
"mean_token_accuracy": 0.645610973238945,
|
| 6813 |
"num_tokens": 13785732.0,
|
| 6814 |
"step": 3780
|
| 6815 |
+
},
|
| 6816 |
+
{
|
| 6817 |
+
"epoch": 29.115384615384617,
|
| 6818 |
+
"grad_norm": 0.0,
|
| 6819 |
+
"learning_rate": 3.108e-05,
|
| 6820 |
+
"loss": 1.7157,
|
| 6821 |
+
"mean_token_accuracy": 0.6572709828615189,
|
| 6822 |
+
"num_tokens": 13804149.0,
|
| 6823 |
+
"step": 3785
|
| 6824 |
+
},
|
| 6825 |
+
{
|
| 6826 |
+
"epoch": 29.153846153846153,
|
| 6827 |
+
"grad_norm": 0.0,
|
| 6828 |
+
"learning_rate": 3.1055e-05,
|
| 6829 |
+
"loss": 1.7041,
|
| 6830 |
+
"mean_token_accuracy": 0.6564319849014282,
|
| 6831 |
+
"num_tokens": 13822922.0,
|
| 6832 |
+
"step": 3790
|
| 6833 |
}
|
| 6834 |
],
|
| 6835 |
"logging_steps": 5,
|
|
|
|
| 6849 |
"attributes": {}
|
| 6850 |
}
|
| 6851 |
},
|
| 6852 |
+
"total_flos": 7.004824663257907e+17,
|
| 6853 |
"train_batch_size": 4,
|
| 6854 |
"trial_name": null,
|
| 6855 |
"trial_params": null
|