End of training

README.md

@@ -16,13 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- epoch: 0.3259
-- eval_loss: 0.4649
-- eval_per: 0.2070
-- eval_runtime: 803.6436
-- eval_samples_per_second: 20.137
-- eval_steps_per_second: 20.137
-- step: 6000
+- Loss: 0.4084
+- Per: 0.1818
 
 ## Model description
 
@@ -53,6 +48,15 @@ The following hyperparameters were used during training:
 - training_steps: 10000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Per    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.6277        | 0.1630 | 3000 | 0.5961          | 0.2501 |
+| 0.445         | 0.3259 | 6000 | 0.4649          | 0.2070 |
+| 0.3751        | 0.4889 | 9000 | 0.4084          | 0.1818 |
+
+
 ### Framework versions
 
 - Transformers 4.57.0