update model card README.md

README.md

@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice_12_0 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.4396
-- eval_wer: 0.3150
-- eval_runtime: 213.145
-- eval_samples_per_second: 14.492
-- eval_steps_per_second: 1.816
-- epoch: 21.85
-- step: 2600
+- eval_loss: 0.2882
+- eval_wer: 0.2424
+- eval_runtime: 211.4996
+- eval_samples_per_second: 14.605
+- eval_steps_per_second: 1.83
+- epoch: 14.71
+- step: 1750
 
 ## Model description
 
@@ -41,7 +41,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -50,7 +50,7 @@ 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: 500
-- num_epochs: 30
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Framework versions