Training in progress, step 245, 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:f46b71e95a580f108269251cfe3defd72132358de06c0d928b83f8aefd50304d
|
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 sha256:99106769548268574aadd158585d14f464e53c8ad6243c5158dc3c182ccfe6a5
|
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:e1164145c3cb1723f88e8b2678949166f87c794da442d33d7cc2eddf22f1da61
|
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,
|
@@ -1701,6 +1701,27 @@
|
|
1701 |
"learning_rate": 9.242424242424242e-05,
|
1702 |
"loss": 1.2732,
|
1703 |
"step": 242
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1704 |
}
|
1705 |
],
|
1706 |
"logging_steps": 1,
|
@@ -1720,7 +1741,7 @@
|
|
1720 |
"attributes": {}
|
1721 |
}
|
1722 |
},
|
1723 |
-
"total_flos":
|
1724 |
"train_batch_size": 4,
|
1725 |
"trial_name": null,
|
1726 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6721536351165981,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 245,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1701 |
"learning_rate": 9.242424242424242e-05,
|
1702 |
"loss": 1.2732,
|
1703 |
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.6666666666666666,
|
1707 |
+
"grad_norm": 0.16092891991138458,
|
1708 |
+
"learning_rate": 9.166666666666667e-05,
|
1709 |
+
"loss": 1.1607,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.6694101508916324,
|
1714 |
+
"grad_norm": 0.1687157154083252,
|
1715 |
+
"learning_rate": 9.090909090909092e-05,
|
1716 |
+
"loss": 1.1149,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.6721536351165981,
|
1721 |
+
"grad_norm": 0.18511663377285004,
|
1722 |
+
"learning_rate": 9.015151515151515e-05,
|
1723 |
+
"loss": 1.1934,
|
1724 |
+
"step": 245
|
1725 |
}
|
1726 |
],
|
1727 |
"logging_steps": 1,
|
|
|
1741 |
"attributes": {}
|
1742 |
}
|
1743 |
},
|
1744 |
+
"total_flos": 3.031087305198797e+17,
|
1745 |
"train_batch_size": 4,
|
1746 |
"trial_name": null,
|
1747 |
"trial_params": null
|