wav2vec2-attempt2

README.md

@@ -3,6 +3,9 @@ license: apache-2.0
 base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
 model-index:
 - name: wav2vec2-attempt2
   results: []
@@ -15,14 +18,9 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 3.1368
-- eval_accuracy: 0.0222
-- eval_f1: 0.0060
-- eval_runtime: 4.7781
-- eval_samples_per_second: 9.418
-- eval_steps_per_second: 1.046
-- epoch: 1.92
-- step: 4
+- Loss: 3.1415
+- Accuracy: 0.0444
+- F1: 0.0063
 
 ## Model description
 
@@ -53,6 +51,15 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 0.96  | 2    | 3.1368          | 0.0222   | 0.0060 |
+| No log        | 1.92  | 4    | 3.1368          | 0.0222   | 0.0060 |
+| No log        | 2.88  | 6    | 3.1415          | 0.0444   | 0.0063 |
+
+
 ### Framework versions
 
 - Transformers 4.36.2