Training in progress, step 3760, 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 sha256:35cbb294ca131bf71e08da9541046263bc6cf9c0cded313a47a61d42609b7d66
|
| 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:d3008f9a48d2b37d474060de2dad5c0aca2cda94e9e3b59cbb5699f6e0eedec4
|
| 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:cf42325a1cd17968c48d9389be187faf9cddbbb4ca6e358455bb5548a8f7fb0c
|
| 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:cf8dc1d66d843e6daf41e0f9a415fde2893c0bdb3049573e320e768417beee06
|
| 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,
|
|
@@ -3768,6 +3768,16 @@
|
|
| 3768 |
"mean_token_accuracy": 0.7524963855743408,
|
| 3769 |
"num_tokens": 17474234.0,
|
| 3770 |
"step": 3750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3771 |
}
|
| 3772 |
],
|
| 3773 |
"logging_steps": 10,
|
|
@@ -3787,7 +3797,7 @@
|
|
| 3787 |
"attributes": {}
|
| 3788 |
}
|
| 3789 |
},
|
| 3790 |
-
"total_flos": 8.
|
| 3791 |
"train_batch_size": 4,
|
| 3792 |
"trial_name": null,
|
| 3793 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8021333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3768 |
"mean_token_accuracy": 0.7524963855743408,
|
| 3769 |
"num_tokens": 17474234.0,
|
| 3770 |
"step": 3750
|
| 3771 |
+
},
|
| 3772 |
+
{
|
| 3773 |
+
"entropy": 0.9401593998074531,
|
| 3774 |
+
"epoch": 0.8021333333333334,
|
| 3775 |
+
"grad_norm": 0.2025330811738968,
|
| 3776 |
+
"learning_rate": 6.82432662762483e-05,
|
| 3777 |
+
"loss": 1.0459843635559083,
|
| 3778 |
+
"mean_token_accuracy": 0.7684256717562675,
|
| 3779 |
+
"num_tokens": 17519106.0,
|
| 3780 |
+
"step": 3760
|
| 3781 |
}
|
| 3782 |
],
|
| 3783 |
"logging_steps": 10,
|
|
|
|
| 3797 |
"attributes": {}
|
| 3798 |
}
|
| 3799 |
},
|
| 3800 |
+
"total_flos": 8.29500696186962e+16,
|
| 3801 |
"train_batch_size": 4,
|
| 3802 |
"trial_name": null,
|
| 3803 |
"trial_params": null
|