End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0557
-- Wer: 0.1819
+- Loss: 0.5138
+- Wer: 0.1293
 
 ## Model description
 
@@ -38,30 +38,32 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-06
-- train_batch_size: 16
+- learning_rate: 5e-06
+- train_batch_size: 32
 - eval_batch_size: 4
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 25
-- training_steps: 250
+- training_steps: 300
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer    |
 |:-------------:|:-------:|:----:|:---------------:|:------:|
-| 2.466         | 1.1364  | 25   | 2.3416          | 0.3281 |
-| 1.7788        | 2.2727  | 50   | 1.5774          | 0.2671 |
-| 1.2151        | 3.4091  | 75   | 1.2743          | 0.2429 |
-| 0.9613        | 4.5455  | 100  | 1.1783          | 0.2135 |
-| 0.8534        | 5.6818  | 125  | 1.1291          | 0.2008 |
-| 0.7617        | 6.8182  | 150  | 1.1021          | 0.1924 |
-| 0.77          | 7.9545  | 175  | 1.0804          | 0.1872 |
-| 0.7212        | 9.0909  | 200  | 1.0665          | 0.1819 |
-| 0.7186        | 10.2273 | 225  | 1.0592          | 0.1819 |
-| 0.6799        | 11.3636 | 250  | 1.0557          | 0.1819 |
+| 2.1712        | 2.2727  | 25   | 1.4956          | 0.2397 |
+| 0.8938        | 4.5455  | 50   | 0.9926          | 0.1682 |
+| 0.5426        | 6.8182  | 75   | 0.8672          | 0.1535 |
+| 0.4142        | 9.0909  | 100  | 0.7799          | 0.1462 |
+| 0.3002        | 11.3636 | 125  | 0.6942          | 0.1409 |
+| 0.2155        | 13.6364 | 150  | 0.6290          | 0.1346 |
+| 0.1524        | 15.9091 | 175  | 0.5800          | 0.1335 |
+| 0.1109        | 18.1818 | 200  | 0.5496          | 0.1314 |
+| 0.0826        | 20.4545 | 225  | 0.5317          | 0.1304 |
+| 0.0681        | 22.7273 | 250  | 0.5210          | 0.1304 |
+| 0.0575        | 25.0    | 275  | 0.5160          | 0.1293 |
+| 0.053         | 27.2727 | 300  | 0.5138          | 0.1293 |
 
 
 ### Framework versions