Training in progress, step 3880, 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:e553d1155f3fcf8ec061c863d691cad5e307ae36ae809eb14bc86a02bf8fb8e9
|
| 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 sha256:466d4684921cda2c67be02c88819c357af36b61a442ac97b64fe7cf88b0573c4
|
| 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 sha256:055d91b1cdd4d0871f9a24a2c2804ca7344e0797f263ca83f2135d59d74815a7
|
| 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 sha256:201b71d5d61574d3ccab1355b8b55414d420e48e265766a3693614c44d3eff02
|
| 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,
|
|
@@ -3888,6 +3888,16 @@
|
|
| 3888 |
"mean_token_accuracy": 0.7514252230525017,
|
| 3889 |
"num_tokens": 18044403.0,
|
| 3890 |
"step": 3870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3891 |
}
|
| 3892 |
],
|
| 3893 |
"logging_steps": 10,
|
|
@@ -3907,7 +3917,7 @@
|
|
| 3907 |
"attributes": {}
|
| 3908 |
}
|
| 3909 |
},
|
| 3910 |
-
"total_flos": 8.
|
| 3911 |
"train_batch_size": 4,
|
| 3912 |
"trial_name": null,
|
| 3913 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8277333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3888 |
"mean_token_accuracy": 0.7514252230525017,
|
| 3889 |
"num_tokens": 18044403.0,
|
| 3890 |
"step": 3870
|
| 3891 |
+
},
|
| 3892 |
+
{
|
| 3893 |
+
"entropy": 0.9075474604964257,
|
| 3894 |
+
"epoch": 0.8277333333333333,
|
| 3895 |
+
"grad_norm": 0.28175604343414307,
|
| 3896 |
+
"learning_rate": 6.629440736624977e-05,
|
| 3897 |
+
"loss": 0.9921407699584961,
|
| 3898 |
+
"mean_token_accuracy": 0.7708318918943405,
|
| 3899 |
+
"num_tokens": 18090208.0,
|
| 3900 |
+
"step": 3880
|
| 3901 |
}
|
| 3902 |
],
|
| 3903 |
"logging_steps": 10,
|
|
|
|
| 3917 |
"attributes": {}
|
| 3918 |
}
|
| 3919 |
},
|
| 3920 |
+
"total_flos": 8.564077929556992e+16,
|
| 3921 |
"train_batch_size": 4,
|
| 3922 |
"trial_name": null,
|
| 3923 |
"trial_params": null
|