update model card README.md

README.md

@@ -14,7 +14,7 @@ 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: 3.2166
+- Loss: 3.1938
 - Wer: 1.0
 
 ## Model description
@@ -38,21 +38,21 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 45
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 300
-- num_epochs: 3
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer |
 |:-------------:|:-----:|:----:|:---------------:|:---:|
-| No log        | 0.98  | 300  | 3.6178          | 1.0 |
-| 9.0367        | 1.96  | 600  | 3.2166          | 1.0 |
-| 1658872299.52 | 2.94  | 900  | 3.2166          | 1.0 |
+| No log        | 0.61  | 300  | 3.1938          | 1.0 |
+| 15.6289       | 1.22  | 600  | 3.1938          | 1.0 |
+| 0.0           | 1.84  | 900  | 3.1938          | 1.0 |
 
 
 ### Framework versions