End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.6882143267793492
+      value: 0.6113372427273772
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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 common_voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8092
-- Wer: 0.6882
+- Loss: 1.0444
+- Wer: 0.6113
 
 ## Model description
 
@@ -53,23 +53,32 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 16
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
+- 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: 300
-- num_epochs: 10
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 5.5231        | 3.33  | 200  | 2.9353          | 1.0000 |
-| 2.1315        | 6.67  | 400  | 1.0531          | 0.8513 |
-| 0.5451        | 10.0  | 600  | 0.8092          | 0.6882 |
+| 5.5551        | 1.67  | 200  | 2.9315          | 1.0    |
+| 2.7259        | 3.33  | 400  | 1.6133          | 0.9592 |
+| 1.1027        | 5.0   | 600  | 0.9823          | 0.8117 |
+| 0.5978        | 6.67  | 800  | 0.9360          | 0.7384 |
+| 0.4142        | 8.33  | 1000 | 0.9242          | 0.6867 |
+| 0.3098        | 10.0  | 1200 | 0.9829          | 0.6749 |
+| 0.2511        | 11.67 | 1400 | 1.0105          | 0.6674 |
+| 0.2181        | 13.33 | 1600 | 1.0412          | 0.6524 |
+| 0.1765        | 15.0  | 1800 | 1.0473          | 0.6415 |
+| 0.1602        | 16.67 | 2000 | 1.0681          | 0.6256 |
+| 0.1415        | 18.33 | 2200 | 1.0362          | 0.6107 |
+| 0.1311        | 20.0  | 2400 | 1.0444          | 0.6113 |
 
 
 ### Framework versions