End of training

README.md

@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6636
+- Loss: 1.4304
 - Accuracy: 0.0
 
 ## Model description
@@ -61,10 +61,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 20
-- training_steps: 10
+- num_epochs: 5
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7246        | 0.32  | 25   | 0.6956          | 0.5054   |
+| 0.6873        | 0.64  | 50   | 0.6589          | 0.6462   |
+| 0.5328        | 0.96  | 75   | 0.5163          | 0.7942   |
+| 0.3942        | 1.28  | 100  | 0.3964          | 0.8556   |
+| 0.3563        | 1.6   | 125  | 0.3320          | 0.8917   |
+| 0.2756        | 1.92  | 150  | 0.4182          | 0.8520   |
+| 0.1572        | 2.24  | 175  | 0.4141          | 0.8700   |
+| 0.1338        | 2.56  | 200  | 0.5244          | 0.8628   |
+| 0.1802        | 2.88  | 225  | 0.8758          | 0.8700   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d174af7d9ca7f63ac5314b942f55ef40fb9b88b2061d8ae4a1abdbf6d04e21
+oid sha256:25c7f10b88fde9d6420bc9707afe722c46110d5485f2901b714dfb36b89169b3
 size 2955086993