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: 3.1398
-- eval_accuracy: 0.0208
-- eval_f1: 0.0136
-- eval_runtime: 5.2008
-- eval_samples_per_second: 9.229
-- eval_steps_per_second: 1.154
-- epoch: 1.78
-- step: 4
+- Loss: 3.1508
+- Accuracy: 0.0208
+- F1: 0.0130
 
 ## 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        | 0.89  | 2    | 3.1398          | 0.0208   | 0.0136 |
+| No log        | 1.78  | 4    | 3.1398          | 0.0208   | 0.0136 |
+| No log        | 2.67  | 6    | 3.1508          | 0.0208   | 0.0130 |
+
+
 ### Framework versions
 
 - Transformers 4.36.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60cb4236c1ea5fab34e72896db2f9b5089d9cc9b48b84cc0bcec7d95375449a2
+oid sha256:523795cf6572943d87a044b258516ddafd9e849d9799f442b08bb4b771f48a59
 size 378323956