End of training

README.md

@@ -19,13 +19,6 @@ should probably proofread and complete it, then remove this comment. -->
 # Whisper medium Fa Yazdi - SRezaS
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Persian Yazdi Accent Custom Dataset dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.2664
-- eval_runtime: 19.2535
-- eval_samples_per_second: 3.116
-- eval_steps_per_second: 0.416
-- epoch: 13.0
-- step: 234
 
 ## Model description
 
@@ -52,10 +45,14 @@ The following hyperparameters were used during training:
 - total_train_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: 57
-- num_epochs: 20
+- lr_scheduler_warmup_steps: 40
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - PEFT 0.14.1.dev0