Saving best model to hub

README.md

@@ -44,12 +44,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll    | F1 Micro | F1 Macro | Ece    | Aurc   |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:|
-| No log        | 1.0   | 200  | 64.9027         | 0.17     | 0.8760     | 7.1325 | 0.17     | 0.0466   | 0.2346 | 0.7601 |
+| No log        | 1.0   | 200  | 64.8970         | 0.17     | 0.8761     | 7.1182 | 0.17     | 0.0466   | 0.2430 | 0.7785 |
 
 
 ### Framework versions
 
 - Transformers 4.33.3
-- Pytorch 2.0.1
+- Pytorch 2.2.0.dev20231002
 - Datasets 2.7.1
 - Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39097b5e3f641f825c8480ee08daa134b2496b413853ae535db5a8d354b76cb4
-size 22791293
+oid sha256:583bcb6356f04daf2cd7e43d7bfef76fa5316bf7079249aa5e0401ab0e5e9b9d
+size 22794810

test-logits.npz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe97c29a02c10f9bb82e75ab0878f8725f4765e9db8fcb40b94202e97dc3b493
-size 90016
+oid sha256:fc9e2b4b11fda9b9d6aaf55e09ef56e9e3ab2d61aee98fcc2c23cb3ed3ef9244
+size 90321

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf6f3f6e09a7572d5a29b9d2573d4f319f64488c5dba8422ad6f677a127db41
-size 4347
+oid sha256:19ef72c1168cdec9410273d602e80dd13d2f450cdc296960f31684bf53441421
+size 4792

validation-logits.npz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3a3ff3a485f33f25214ffc42a98836999ce6efc32695d489029b2a12bc0ebe
-size 7499
+oid sha256:20a837d4bdd664415985376876b186f8e96d68d74a4d164af8c7ddc9a866f175
+size 7513