End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2267
-- Accuracy: 0.7765
+- Loss: 0.2268
+- Accuracy: 0.775
 
 ## Model description
 
@@ -44,15 +44,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.1165        | 1.0   | 8584  | 0.0932          | 0.8965   |
-| 0.1054        | 2.0   | 17168 | 0.0879          | 0.9050   |
-| 0.1006        | 3.0   | 25752 | 0.0878          | 0.9072   |
+| 0.1164        | 1.0   | 8584  | 0.0933          | 0.8966   |
+| 0.1054        | 2.0   | 17168 | 0.0878          | 0.9053   |
+| 0.1006        | 3.0   | 25752 | 0.0879          | 0.9072   |
 
 
 ### Framework versions

runs/Jan21_15-39-47_gl1501.arc-ts.umich.edu/events.out.tfevents.1705876478.gl1501.arc-ts.umich.edu.468276.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57084279c69aad7db45fda0009d38779f97a1236456253bf4a4d14d12fac1b18
+size 1404