update model card README.md

README.md

@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the librispeech_asr dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.6846
-- Wer: 1.9630
+- Loss: 4.9983
+- Wer: 1.9518
 
 ## Model description
 
@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
@@ -51,9 +51,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 4.5471        | 0.28  | 500  | 5.5816          | 1.9376 |
-| 4.6377        | 0.56  | 1000 | 5.0728          | 1.9178 |
-| 4.5932        | 0.84  | 1500 | 4.6846          | 1.9630 |
+| 4.4011        | 0.56  | 500  | 4.9983          | 1.9518 |
 
 
 ### Framework versions