Model save

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Heem2/Deepfake-audio-detection](https://huggingface.co/Heem2/Deepfake-audio-detection) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1666
-- Accuracy: 0.9897
-- Precision: 0.9912
-- Recall: 0.9882
-- F1: 0.9897
+- Loss: 0.0708
+- Accuracy: 0.9961
+- Precision: 0.9949
+- Recall: 0.9974
+- F1: 0.9961
 
 ## Model description
 
@@ -45,10 +45,10 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
-- gradient_accumulation_steps: 2
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 8
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
@@ -58,11 +58,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.1668        | 1.0   | 340  | 0.2081          | 0.9853   | 0.9853    | 0.9853 | 0.9853 |
-| 0.4339        | 2.0   | 680  | 0.2996          | 0.9809   | 0.9823    | 0.9794 | 0.9809 |
-| 0.0           | 3.0   | 1020 | 0.1666          | 0.9897   | 0.9912    | 0.9882 | 0.9897 |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.4204        | 1.0    | 388  | 0.5132          | 0.9691   | 0.9483    | 0.9923 | 0.9698 |
+| 0.5578        | 2.0    | 776  | 0.3286          | 0.9794   | 0.9697    | 0.9897 | 0.9796 |
+| 0.2106        | 3.0    | 1164 | 0.1348          | 0.9923   | 0.9923    | 0.9923 | 0.9923 |
+| 0.2262        | 4.0    | 1552 | 0.0624          | 0.9961   | 0.9923    | 1.0    | 0.9961 |
+| 0.0           | 4.9884 | 1935 | 0.0708          | 0.9961   | 0.9949    | 0.9974 | 0.9961 |
 
 
 ### Framework versions

logs/events.out.tfevents.1747905483.01ded4baac1e.35.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae2e918839a5f3bb1fe372747a1d5b97df31f22a3ac73b8d1c23b90b4c2a5c91
-size 41357
+oid sha256:9326c29a7d8e05f44590d0d11826b3ebaee789c2845fee7c37f55bc0ea26b819
+size 50201