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 [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6952
-- Wer: 1.0447
+- Loss: 1.3263
+- Wer: 1.0593
 
 ## Model description
 
@@ -45,14 +45,19 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 30
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 40
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 5.079         | 25.0  | 400  | 0.6952          | 1.0447 |
+| 6.0662        | 6.25  | 100  | 3.4034          | 1.0    |
+| 3.348         | 12.5  | 200  | 3.1795          | 1.0    |
+| 2.4085        | 18.75 | 300  | 1.5518          | 1.0432 |
+| 1.0433        | 25.0  | 400  | 1.2322          | 1.0514 |
+| 0.5163        | 31.25 | 500  | 1.2808          | 1.0495 |
+| 0.3625        | 37.5  | 600  | 1.3263          | 1.0593 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e3dc396b51f1f0434d2e3b32b368436530e2352073cb80a5642e426802bda4
+oid sha256:3e1fab6413c4667e8e61499a710ee29c56cb9164ca39cd222dafc9d2a7c3e308
 size 1262180653