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 [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0471
-- Wer: 25.1306
+- Loss: 0.0317
+- Wer: 16.4220
 
 ## Model description
 
@@ -43,18 +43,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 2000
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 5000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0748        | 0.2   | 500  | 0.1198          | 51.5053 |
-| 0.0445        | 0.4   | 1000 | 0.0727          | 35.6805 |
-| 0.0351        | 0.59  | 1500 | 0.0563          | 30.1319 |
-| 0.0267        | 0.79  | 2000 | 0.0471          | 25.1306 |
+| 0.0595        | 0.4   | 1000 | 0.0904          | 42.5230 |
+| 0.0339        | 0.79  | 2000 | 0.0593          | 30.1319 |
+| 0.0171        | 1.19  | 3000 | 0.0441          | 23.5133 |
+| 0.0133        | 1.58  | 4000 | 0.0363          | 19.1092 |
+| 0.0096        | 1.98  | 5000 | 0.0317          | 16.4220 |
 
 
 ### Framework versions