Training in progress, step 3820, 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 sha256:0e8d3c64f27e5934306a440b80eaed49a4463262c226901c25bee30fc256892a
|
| 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:a4420e2117afcddadbea17196298170e4eb4c670916004727ffb5145c0682f26
|
| 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 sha256:7dc8be5c2da0f9bfa384a3ddb4ea4604704f26d5d49706f2b90287cd26ed0bcb
|
| 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 sha256:8a08d6d83a98406c987328d0f90adfc90549eef5ad60ac4dff5af09d3535d3f1
|
| 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,
|
|
@@ -3828,6 +3828,16 @@
|
|
| 3828 |
"mean_token_accuracy": 0.7413103066384792,
|
| 3829 |
"num_tokens": 17751890.0,
|
| 3830 |
"step": 3810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3831 |
}
|
| 3832 |
],
|
| 3833 |
"logging_steps": 10,
|
|
@@ -3847,7 +3857,7 @@
|
|
| 3847 |
"attributes": {}
|
| 3848 |
}
|
| 3849 |
},
|
| 3850 |
-
"total_flos": 8.
|
| 3851 |
"train_batch_size": 4,
|
| 3852 |
"trial_name": null,
|
| 3853 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8149333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3828 |
"mean_token_accuracy": 0.7413103066384792,
|
| 3829 |
"num_tokens": 17751890.0,
|
| 3830 |
"step": 3810
|
| 3831 |
+
},
|
| 3832 |
+
{
|
| 3833 |
+
"entropy": 0.9753526367247105,
|
| 3834 |
+
"epoch": 0.8149333333333333,
|
| 3835 |
+
"grad_norm": 0.32060110569000244,
|
| 3836 |
+
"learning_rate": 6.72725618053283e-05,
|
| 3837 |
+
"loss": 1.051304244995117,
|
| 3838 |
+
"mean_token_accuracy": 0.7579805940389633,
|
| 3839 |
+
"num_tokens": 17796312.0,
|
| 3840 |
+
"step": 3820
|
| 3841 |
}
|
| 3842 |
],
|
| 3843 |
"logging_steps": 10,
|
|
|
|
| 3857 |
"attributes": {}
|
| 3858 |
}
|
| 3859 |
},
|
| 3860 |
+
"total_flos": 8.427403028090573e+16,
|
| 3861 |
"train_batch_size": 4,
|
| 3862 |
"trial_name": null,
|
| 3863 |
"trial_params": null
|