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:
-- eval_loss: 0.5961
-- eval_per: 0.2501
-- eval_runtime: 774.0848
-- eval_samples_per_second: 20.906
-- eval_steps_per_second: 20.906
-- epoch: 0.1630
-- step: 3000
+- Loss: nan
+- Per: 1.0
 
 ## Model description
 
@@ -52,6 +47,15 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 300
 - training_steps: 10000
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Per    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.6277        | 0.1630 | 3000 | 0.5961          | 0.2501 |
+| 0.0           | 0.3259 | 6000 | nan             | 1.0    |
+| 0.0           | 0.4889 | 9000 | nan             | 1.0    |
+
+
 ### Framework versions
 
 - Transformers 4.57.0