lowem1/t5_nlp_aug-small

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4586
+- Loss: 0.6868
 
 ## Model description
 
@@ -46,10 +46,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6801        | 1.85  | 250  | 1.4853          |
-| 1.7054        | 3.7   | 500  | 1.4706          |
-| 1.6714        | 5.56  | 750  | 1.4625          |
-| 1.6358        | 7.41  | 1000 | 1.4586          |
+| 2.5103        | 1.85  | 250  | 0.9290          |
+| 0.9967        | 3.7   | 500  | 0.7657          |
+| 0.8762        | 5.56  | 750  | 0.7081          |
+| 0.8353        | 7.41  | 1000 | 0.6868          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71064abc3cb97d000eecec35177e5ff90c98660868ca32226661b9a37f351a56
+oid sha256:a29278068b3489455fcd6c520a9c1b2e63aa9c7847c171ba56f19857cb59ca06
 size 242071641

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4670b683022fb17ce5b11e67df8c6b886c684610b1e57db2dff81ede667473
+oid sha256:1a8a26f49a659e3d87ecd33eb6187a4b483c5e510c3e560d01c6dad864724250
 size 3963