Training in progress, step 8900, 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:af860c731cb9e45b9f42a34e51237ce465b8fedfbf8bb67f8cd78f5ec9245722
|
| 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 sha256:06e00f01e8ddc2da284d5972a314608b20449af0742e1f51803c13d70983553b
|
| 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 sha256:0b95016e498763380b87827c3c299016c6b9cfb8011e8962d026d673b242c281
|
| 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:f2cfd92f75a8a8524159c58ce7d52a6880278954694731b8071536b3902c6c11
|
| 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,
|
|
@@ -759,6 +759,13 @@
|
|
| 759 |
"learning_rate": 4.133333333333333e-05,
|
| 760 |
"loss": 1.2307,
|
| 761 |
"step": 8800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 762 |
}
|
| 763 |
],
|
| 764 |
"logging_steps": 100,
|
|
@@ -778,7 +785,7 @@
|
|
| 778 |
"attributes": {}
|
| 779 |
}
|
| 780 |
},
|
| 781 |
-
"total_flos": 1.
|
| 782 |
"train_batch_size": 8,
|
| 783 |
"trial_name": null,
|
| 784 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 17.79721918450242,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 8900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 759 |
"learning_rate": 4.133333333333333e-05,
|
| 760 |
"loss": 1.2307,
|
| 761 |
"step": 8800
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 17.79721918450242,
|
| 765 |
+
"grad_norm": 0.23070693016052246,
|
| 766 |
+
"learning_rate": 4.066666666666667e-05,
|
| 767 |
+
"loss": 1.2278,
|
| 768 |
+
"step": 8900
|
| 769 |
}
|
| 770 |
],
|
| 771 |
"logging_steps": 100,
|
|
|
|
| 785 |
"attributes": {}
|
| 786 |
}
|
| 787 |
},
|
| 788 |
+
"total_flos": 1.3890516768952156e+19,
|
| 789 |
"train_batch_size": 8,
|
| 790 |
"trial_name": null,
|
| 791 |
"trial_params": null
|