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 [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0429
-- Accuracy: 0.3669
+- Loss: 1.3461
+- Accuracy: 0.6417
 
 ## Model description
 
@@ -47,13 +47,17 @@ The following hyperparameters were used during training:
 - 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_ratio: 0.1
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.0335        | 0.9863 | 54   | 2.0429          | 0.3669   |
+| 2.0345        | 0.9863 | 54   | 1.9866          | 0.4024   |
+| 1.7716        | 1.9817 | 108  | 1.7311          | 0.4533   |
+| 1.5297        | 2.9772 | 162  | 1.5755          | 0.5026   |
+| 1.4237        | 3.9909 | 217  | 1.3966          | 0.6142   |
+| 1.3141        | 4.9680 | 270  | 1.3461          | 0.6417   |
 
 
 ### Framework versions