update model card README.md

README.md

@@ -14,13 +14,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 2.6923
+- eval_loss: 11.0473
 - eval_wer: 1.0
-- eval_runtime: 13.3697
-- eval_samples_per_second: 1.87
-- eval_steps_per_second: 0.299
-- epoch: 1.55
-- step: 169
+- eval_runtime: 3.3353
+- eval_samples_per_second: 2.399
+- eval_steps_per_second: 0.3
+- epoch: 3.12
+- step: 200
 
 ## Model description
 
@@ -39,14 +39,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
-- train_batch_size: 2
+- learning_rate: 0.5
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1
-- num_epochs: 10
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Framework versions