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-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0181
-- Wer: 19.6254
+- Loss: 0.0171
+- Wer: 20.5156
 
 ## Model description
 
@@ -43,18 +43,18 @@ 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: 1600
+- lr_scheduler_warmup_steps: 320
+- training_steps: 3200
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0171        | 0.1634 | 400  | 0.0192          | 20.5479 |
-| 0.0182        | 0.3268 | 800  | 0.0196          | 20.9673 |
-| 0.0206        | 0.4902 | 1200 | 0.0189          | 20.5479 |
-| 0.0179        | 0.6536 | 1600 | 0.0181          | 19.6254 |
+| 0.0204        | 0.3268 | 800  | 0.0194          | 22.4152 |
+| 0.0205        | 0.6536 | 1600 | 0.0185          | 22.0081 |
+| 0.021         | 0.9804 | 2400 | 0.0173          | 20.7870 |
+| 0.0142        | 1.3072 | 3200 | 0.0171          | 20.5156 |
 
 
 ### Framework versions