Training in progress, step 242, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d7f289734593a3f7ee939562d24196078125028a858356847a6bb957f59a600
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6942bdb9d086b28b0925199c7fe1fdaa7b25eebd757be776937103f7a5f230b8
|
3 |
size 37430836
|
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:db79331c8992e3a7af2306518ac9df31b4a39a542a11b37b6cba8afaa66b1eba
|
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": 0.
|
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,
|
@@ -1694,6 +1694,13 @@
|
|
1694 |
"learning_rate": 9.318181818181818e-05,
|
1695 |
"loss": 1.2155,
|
1696 |
"step": 241
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1697 |
}
|
1698 |
],
|
1699 |
"logging_steps": 1,
|
@@ -1713,7 +1720,7 @@
|
|
1713 |
"attributes": {}
|
1714 |
}
|
1715 |
},
|
1716 |
-
"total_flos": 2.
|
1717 |
"train_batch_size": 4,
|
1718 |
"trial_name": null,
|
1719 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.663923182441701,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 242,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1694 |
"learning_rate": 9.318181818181818e-05,
|
1695 |
"loss": 1.2155,
|
1696 |
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.663923182441701,
|
1700 |
+
"grad_norm": 0.16223277151584625,
|
1701 |
+
"learning_rate": 9.242424242424242e-05,
|
1702 |
+
"loss": 1.2732,
|
1703 |
+
"step": 242
|
1704 |
}
|
1705 |
],
|
1706 |
"logging_steps": 1,
|
|
|
1720 |
"attributes": {}
|
1721 |
}
|
1722 |
},
|
1723 |
+
"total_flos": 2.995266789026488e+17,
|
1724 |
"train_batch_size": 4,
|
1725 |
"trial_name": null,
|
1726 |
"trial_params": null
|