End of training

README.md

@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [glob-asr/wav2vec2-large-xls-r-300m-guarani-small](https://huggingface.co/glob-asr/wav2vec2-large-xls-r-300m-guarani-small) on the Common Voice 16 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3492
-- Cer: 8.0760
+- Loss: 0.3309
+- Cer: 7.5608
 
 ## Model description
 
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Cer    |
 |:-------------:|:------:|:----:|:---------------:|:------:|
-| 1.1581        | 0.0574 | 100  | 0.3963          | 8.7513 |
-| 0.9541        | 0.1147 | 200  | 0.3768          | 8.1268 |
-| 0.8591        | 0.1721 | 300  | 0.3602          | 7.8067 |
-| 0.7881        | 0.2294 | 400  | 0.3562          | 8.0760 |
-| 0.8192        | 0.2868 | 500  | 0.3492          | 8.0760 |
+| 1.3968        | 0.0991 | 100  | 0.3683          | 8.4273 |
+| 1.061         | 0.1982 | 200  | 0.3611          | 8.5093 |
+| 1.0374        | 0.2973 | 300  | 0.3500          | 8.1463 |
+| 0.9825        | 0.3964 | 400  | 0.3458          | 7.9394 |
+| 0.9185        | 0.4955 | 500  | 0.3309          | 7.5608 |
 
 
 ### Framework versions
 
 - Transformers 4.44.0
 - Pytorch 2.3.1+cu121
-- Datasets 2.20.0
+- Datasets 2.21.0
 - Tokenizers 0.19.1