Training in progress, step 3850, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2410ddacea7b473afaac489732934f9c540f497d79cf6b60a98d929ea39df69
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85e811af2c2a9f963ee406d446900419cdc84ff390a7e74127bda4b4a6405e74
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a0259f8e3bf9c77a92b5e0e3d456145ed86baf8ad5dc82ed5a5a1026b5cb7d6
|
| 3 |
size 14645
|
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 sha256:453378b63b1b1c33c9a175bc7e074387855366e3868ae732f66d3a9dd7c27f78
|
| 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": 0.
|
| 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,
|
|
@@ -3858,6 +3858,16 @@
|
|
| 3858 |
"mean_token_accuracy": 0.7578480765223503,
|
| 3859 |
"num_tokens": 17897760.0,
|
| 3860 |
"step": 3840
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3861 |
}
|
| 3862 |
],
|
| 3863 |
"logging_steps": 10,
|
|
@@ -3877,7 +3887,7 @@
|
|
| 3877 |
"attributes": {}
|
| 3878 |
}
|
| 3879 |
},
|
| 3880 |
-
"total_flos": 8.
|
| 3881 |
"train_batch_size": 4,
|
| 3882 |
"trial_name": null,
|
| 3883 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8213333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3858 |
"mean_token_accuracy": 0.7578480765223503,
|
| 3859 |
"num_tokens": 17897760.0,
|
| 3860 |
"step": 3840
|
| 3861 |
+
},
|
| 3862 |
+
{
|
| 3863 |
+
"entropy": 0.8759050570428372,
|
| 3864 |
+
"epoch": 0.8213333333333334,
|
| 3865 |
+
"grad_norm": 0.27374961972236633,
|
| 3866 |
+
"learning_rate": 6.678438953651401e-05,
|
| 3867 |
+
"loss": 0.9380218505859375,
|
| 3868 |
+
"mean_token_accuracy": 0.7734792202711105,
|
| 3869 |
+
"num_tokens": 17939963.0,
|
| 3870 |
+
"step": 3850
|
| 3871 |
}
|
| 3872 |
],
|
| 3873 |
"logging_steps": 10,
|
|
|
|
| 3887 |
"attributes": {}
|
| 3888 |
}
|
| 3889 |
},
|
| 3890 |
+
"total_flos": 8.495502114897408e+16,
|
| 3891 |
"train_batch_size": 4,
|
| 3892 |
"trial_name": null,
|
| 3893 |
"trial_params": null
|