update model card README.md

README.md

@@ -18,9 +18,9 @@ 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 MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - JA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.2691
-- Wer: 0.9960
-- Cer: 0.9555
+- Loss: 0.3316
+- Wer: 0.2564
+- Cer: 0.1218
 
 ## Model description
 
@@ -47,12 +47,24 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1000
-- num_epochs: 2.0
+- lr_scheduler_warmup_steps: 2000
+- num_epochs: 100.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step  | Validation Loss | Wer    | Cer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
+| 3.484         | 9.49  | 1500  | 1.1849          | 0.7543 | 0.4099 |
+| 1.3582        | 18.98 | 3000  | 0.4320          | 0.3489 | 0.1591 |
+| 1.1716        | 28.48 | 4500  | 0.3835          | 0.3175 | 0.1454 |
+| 1.0951        | 37.97 | 6000  | 0.3732          | 0.3033 | 0.1405 |
+| 1.04          | 47.47 | 7500  | 0.3485          | 0.2898 | 0.1360 |
+| 0.9768        | 56.96 | 9000  | 0.3386          | 0.2787 | 0.1309 |
+| 0.9129        | 66.45 | 10500 | 0.3363          | 0.2711 | 0.1272 |
+| 0.8614        | 75.94 | 12000 | 0.3386          | 0.2676 | 0.1260 |
+| 0.8092        | 85.44 | 13500 | 0.3356          | 0.2610 | 0.1240 |
+| 0.7658        | 94.93 | 15000 | 0.3316          | 0.2564 | 0.1218 |
 
 
 ### Framework versions