Training in progress, step 8800, 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 sha256:7757780af89912e735dbe8105f9436b517bec77bc86ead84b221561abe7a296d
|
| 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 sha256:8431521971fece40cb686bfc9e291a10646a93986a28990be1d27f0f9abbae59
|
| 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:a0ffd3aacbcb147c6ed382ad2dd8b147b0e5b9115eb8b744fcb864a112248a4f
|
| 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:c3868261845271e61a238c0da87c904f896cb24e82af8bdd1e74bf04ddadb87a
|
| 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": 17.
|
| 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,
|
|
@@ -752,6 +752,13 @@
|
|
| 752 |
"learning_rate": 4.2e-05,
|
| 753 |
"loss": 1.2371,
|
| 754 |
"step": 8700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 755 |
}
|
| 756 |
],
|
| 757 |
"logging_steps": 100,
|
|
@@ -771,7 +778,7 @@
|
|
| 771 |
"attributes": {}
|
| 772 |
}
|
| 773 |
},
|
| 774 |
-
"total_flos": 1.
|
| 775 |
"train_batch_size": 8,
|
| 776 |
"trial_name": null,
|
| 777 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 17.59725042962037,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 8800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 752 |
"learning_rate": 4.2e-05,
|
| 753 |
"loss": 1.2371,
|
| 754 |
"step": 8700
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 17.59725042962037,
|
| 758 |
+
"grad_norm": 0.23766712844371796,
|
| 759 |
+
"learning_rate": 4.133333333333333e-05,
|
| 760 |
+
"loss": 1.2307,
|
| 761 |
+
"step": 8800
|
| 762 |
}
|
| 763 |
],
|
| 764 |
"logging_steps": 100,
|
|
|
|
| 778 |
"attributes": {}
|
| 779 |
}
|
| 780 |
},
|
| 781 |
+
"total_flos": 1.373444179776399e+19,
|
| 782 |
"train_batch_size": 8,
|
| 783 |
"trial_name": null,
|
| 784 |
"trial_params": null
|