Model save

README.md

@@ -3,8 +3,6 @@ license: apache-2.0
 base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: small-deepfake
   results: []
@@ -16,9 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
 # small-deepfake
 
 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:
-- Loss: 0.8395
-- Accuracy: 0.3
 
 ## Model description
 
@@ -46,16 +41,13 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 4
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.8   | 2    | 0.7376          | 0.3      |
-| No log        | 2.0   | 5    | 0.7560          | 0.3      |
-| No log        | 2.8   | 7    | 0.8433          | 0.3      |
-| No log        | 3.2   | 8    | 0.8395          | 0.3      |
+| No log        | 0.8   | 2    | 0.7285          | 0.35     |
 
 
 ### Framework versions