Training in progress, step 9800, 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 sha256:06ed1c3f948ca8e65ef4c7a913be61b0053350808fc304bab5905b7a5167e9c8
|
| 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 sha256:976d77794db95a7c4ec4e8058d7a96c843b6e71a4dea0960e601dc4e8ff3c033
|
| 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 sha256:142a6af3b22b1a384c838cbf0fde87c2d3d59a9114a47630219fa66ba1dbfe95
|
| 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 sha256:50f382c108a2940dc2dfbbca456f01a406e682bf99790c0216ced372e60f9c1a
|
| 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": 19.
|
| 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,
|
|
@@ -838,6 +838,13 @@
|
|
| 838 |
"learning_rate": 3.5333333333333336e-05,
|
| 839 |
"loss": 1.227,
|
| 840 |
"step": 9700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 841 |
}
|
| 842 |
],
|
| 843 |
"logging_steps": 100,
|
|
@@ -857,7 +864,7 @@
|
|
| 857 |
"attributes": {}
|
| 858 |
}
|
| 859 |
},
|
| 860 |
-
"total_flos": 1.
|
| 861 |
"train_batch_size": 8,
|
| 862 |
"trial_name": null,
|
| 863 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.59693797844087,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 838 |
"learning_rate": 3.5333333333333336e-05,
|
| 839 |
"loss": 1.227,
|
| 840 |
"step": 9700
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 19.59693797844087,
|
| 844 |
+
"grad_norm": 0.2371227890253067,
|
| 845 |
+
"learning_rate": 3.466666666666667e-05,
|
| 846 |
+
"loss": 1.2268,
|
| 847 |
+
"step": 9800
|
| 848 |
}
|
| 849 |
],
|
| 850 |
"logging_steps": 100,
|
|
|
|
| 864 |
"attributes": {}
|
| 865 |
}
|
| 866 |
},
|
| 867 |
+
"total_flos": 1.5295173195905106e+19,
|
| 868 |
"train_batch_size": 8,
|
| 869 |
"trial_name": null,
|
| 870 |
"trial_params": null
|