Training in progress, step 10100, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c460a9a82c14d2fe05d808ad8250e283d2a838af7de4e2ab2969847fca8278f
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28e44e37a7369efd435ae5c721029ca3da5da15b66d46a770051ef9dbb86caa6
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50b95657bd538a85d491c5cffed1785af7a207b73ac96db1d07dcc68a9b0aa61
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f38a6c848cdc806b22f3e675b5fa3efe91046d6b0ce8c324b0fb49f72070b958
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -867,6 +867,13 @@
|
|
| 867 |
"eval_samples_per_second": 19.869,
|
| 868 |
"eval_steps_per_second": 2.485,
|
| 869 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 870 |
}
|
| 871 |
],
|
| 872 |
"logging_steps": 100,
|
|
@@ -886,7 +893,7 @@
|
|
| 886 |
"attributes": {}
|
| 887 |
}
|
| 888 |
},
|
| 889 |
-
"total_flos": 1.
|
| 890 |
"train_batch_size": 8,
|
| 891 |
"trial_name": null,
|
| 892 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.196844243087018,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 10100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 867 |
"eval_samples_per_second": 19.869,
|
| 868 |
"eval_steps_per_second": 2.485,
|
| 869 |
"step": 10000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 20.196844243087018,
|
| 873 |
+
"grad_norm": 0.23550644516944885,
|
| 874 |
+
"learning_rate": 3.266666666666667e-05,
|
| 875 |
+
"loss": 1.2207,
|
| 876 |
+
"step": 10100
|
| 877 |
}
|
| 878 |
],
|
| 879 |
"logging_steps": 100,
|
|
|
|
| 893 |
"attributes": {}
|
| 894 |
}
|
| 895 |
},
|
| 896 |
+
"total_flos": 1.576338895259933e+19,
|
| 897 |
"train_batch_size": 8,
|
| 898 |
"trial_name": null,
|
| 899 |
"trial_params": null
|