juniorjukeko/audio-class-minds14

README.md

@@ -8,7 +8,7 @@ datasets:
 metrics:
 - accuracy
 model-index:
-- name: audio_classification
+- name: audio-class-minds14
   results:
   - task:
       name: Audio Classification
@@ -22,18 +22,18 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.05309734513274336
+      value: 0.061946902654867256
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# audio_classification
+# audio-class-minds14
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6493
-- Accuracy: 0.0531
+- Loss: 2.6413
+- Accuracy: 0.0619
 
 ## Model description
 
@@ -52,29 +52,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 5e-05
 - train_batch_size: 32
 - eval_batch_size: 32
-- seed: 42
+- seed: 143
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.8   | 3    | 2.6374          | 0.1150   |
-| No log        | 1.87  | 7    | 2.6436          | 0.0531   |
-| No log        | 2.4   | 9    | 2.6493          | 0.0531   |
+| No log        | 0.8   | 3    | 2.6388          | 0.0531   |
+| No log        | 1.87  | 7    | 2.6363          | 0.0442   |
+| 2.6298        | 2.93  | 11   | 2.6413          | 0.0619   |
+| 2.6298        | 4.0   | 15   | 2.6417          | 0.0531   |
+| 2.6298        | 4.8   | 18   | 2.6425          | 0.0354   |
+| 2.6296        | 5.87  | 22   | 2.6412          | 0.0354   |
+| 2.6296        | 6.93  | 26   | 2.6427          | 0.0531   |
+| 2.6175        | 8.0   | 30   | 2.6425          | 0.0442   |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
+- Transformers 4.33.2
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
 - Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05518d2226258c5ba9452674b8f98ab8b1f3d2fb41f33c7bd5acc91f5cf7ef01
+oid sha256:7ba6a8565275ff84ed2dded28159811b23c9e03598db0ade1330303f1510f511
 size 378362729