End of training

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 35.6246
+- Loss: 6.1698
 - Wer: 1.0
 
 ## Model description
@@ -45,15 +45,16 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
-- training_steps: 10
+- lr_scheduler_warmup_steps: 250
+- training_steps: 1500
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| No log        | 1.0   | 5    | 36.2698         | 1.0 |
-| 48.2162       | 2.0   | 10   | 35.6246         | 1.0 |
+| 10.4741       | 100.0 | 500  | 6.2781          | 1.0 |
+| 6.9012        | 200.0 | 1000 | 6.9850          | 1.0 |
+| 7.1133        | 300.0 | 1500 | 6.1698          | 1.0 |
 
 
 ### Framework versions