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 [St4n/wav2vec2-base-960h-demo-google-colab](https://huggingface.co/St4n/wav2vec2-base-960h-demo-google-colab) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9759
-- Wer: 1.0015
+- Loss: 0.6643
+- Wer: 0.9985
 
 ## Model description
 
@@ -44,14 +44,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 5
+- num_epochs: 30
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 4.2712        | 2.33  | 200  | 2.9361          | 1.0    |
-| 2.2594        | 4.65  | 400  | 0.9759          | 1.0015 |
+| 0.8048        | 5.81  | 500  | 0.5176          | 1.0    |
+| 0.353         | 11.63 | 1000 | 0.5259          | 1.0    |
+| 0.2843        | 17.44 | 1500 | 0.5725          | 0.9985 |
+| 0.3374        | 23.26 | 2000 | 0.6190          | 0.9985 |
+| 0.1625        | 29.07 | 2500 | 0.6643          | 0.9985 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:089057efa666038d1d71304ee3742eb214fd3326d87167c753895c8ca57a9b87
+oid sha256:07f301faab69a9084286879cdfe537b074aa13dadf138a3a9ee703664bf64bd2
 size 377658785

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adfbd002c83084049e447cc93c99215a9b99a17cd1df5ab7a8f64aa616dce91
+oid sha256:cb9f2a367312c8ebdc34e9673dbb73f0e2cfecfdb4978ed303ddb3d989d91a37
 size 4091