Model save

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.36597792244551375
+      value: 0.3492782337956411
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mouseyy/result_data-1](https://huggingface.co/mouseyy/result_data-1) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2241
-- Wer: 0.3660
-- Cer: 0.1696
+- Loss: 0.2371
+- Wer: 0.3493
+- Cer: 0.1667
 
 ## Model description
 
@@ -54,7 +54,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5.0181182371213955e-05
+- learning_rate: 1.3065956368514577e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -64,12 +64,19 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 32
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 96
-- training_steps: 10
+- lr_scheduler_warmup_steps: 184
+- num_epochs: 5.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss | Wer    | Cer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
+| 0.1695        | 0.9099 | 1000 | 0.2457          | 0.3725 | 0.1714 |
+| 0.1502        | 1.8198 | 2000 | 0.2344          | 0.3640 | 0.1704 |
+| 0.1287        | 2.7298 | 3000 | 0.2321          | 0.3617 | 0.1691 |
+| 0.1248        | 3.6397 | 4000 | 0.2387          | 0.3561 | 0.1665 |
+| 0.1127        | 4.5496 | 5000 | 0.2371          | 0.3493 | 0.1667 |
 
 
 ### Framework versions