End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 33.76623376623377
+      value: 46.930342384887844
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6251
-- Wer Ortho: 33.9914
-- Wer: 33.7662
+- Loss: 1.8863
+- Wer Ortho: 46.9463
+- Wer: 46.9303
 
 ## Model description
 
@@ -53,10 +53,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
+- gradient_accumulation_steps: 24
+- total_train_batch_size: 384
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
@@ -64,9 +66,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.0007        | 8.93  | 500  | 0.6251          | 33.9914   | 33.7662 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
+| 0.0           | 428.57 | 500  | 1.8863          | 46.9463   | 46.9303 |
 
 
 ### Framework versions