model-test-v1

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.061946902654867256
+      value: 0.09734513274336283
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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 minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6623
-- Accuracy: 0.0619
+- Loss: 2.6471
+- Accuracy: 0.0973
 
 ## Model description
 
@@ -56,30 +56,21 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
-- 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: 10
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 0.8   | 3    | 2.6362          | 0.0796   |
-| No log        | 1.87  | 7    | 2.6456          | 0.0708   |
-| 2.6357        | 2.93  | 11   | 2.6502          | 0.0796   |
-| 2.6357        | 4.0   | 15   | 2.6498          | 0.0885   |
-| 2.6357        | 4.8   | 18   | 2.6459          | 0.0973   |
-| 2.6234        | 5.87  | 22   | 2.6601          | 0.0619   |
-| 2.6234        | 6.93  | 26   | 2.6624          | 0.0796   |
-| 2.621         | 8.0   | 30   | 2.6623          | 0.0619   |
+| No log        | 1.0   | 15   | 2.6423          | 0.0531   |
+| No log        | 2.0   | 30   | 2.6471          | 0.0973   |
 
 
 ### Framework versions
 
-- Transformers 4.33.1
+- Transformers 4.33.2
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.5
 - Tokenizers 0.13.3