End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0374
+- Loss: 0.0127
 
 ## Model description
 
@@ -41,18 +41,21 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.2772        | 0.5510 | 200  | 0.0929          |
-| 0.1424        | 1.1019 | 400  | 0.0616          |
-| 0.1055        | 1.6529 | 600  | 0.0458          |
-| 0.0825        | 2.2039 | 800  | 0.0401          |
-| 0.0752        | 2.7548 | 1000 | 0.0374          |
+| 0.0866        | 0.1182 | 1000 | 0.0282          |
+| 0.0455        | 0.2364 | 2000 | 0.0202          |
+| 0.0338        | 0.3545 | 3000 | 0.0169          |
+| 0.0287        | 0.4727 | 4000 | 0.0153          |
+| 0.0241        | 0.5909 | 5000 | 0.0142          |
+| 0.023         | 0.7091 | 6000 | 0.0138          |
+| 0.0202        | 0.8272 | 7000 | 0.0132          |
+| 0.0206        | 0.9454 | 8000 | 0.0127          |
 
 
 ### Framework versions