Model save

README.md

@@ -3,7 +3,6 @@ library_name: transformers
 license: apache-2.0
 base_model: facebook/wav2vec2-base
 tags:
-- audio-classification
 - generated_from_trainer
 datasets:
 - superb
@@ -24,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8245072080023537
+      value: 0.9811709326272433
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +33,8 @@ 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 superb dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8823
-- Accuracy: 0.8245
+- Loss: 0.1243
+- Accuracy: 0.9812
 
 ## Model description
 
@@ -63,18 +62,23 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 5.0
+- num_epochs: 10.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.7728        | 1.0   | 100  | 1.7271          | 0.6209   |
-| 1.3042        | 2.0   | 200  | 1.2065          | 0.6493   |
-| 1.1086        | 3.0   | 300  | 0.9967          | 0.6936   |
-| 0.967         | 4.0   | 400  | 0.9590          | 0.7930   |
-| 0.8801        | 5.0   | 500  | 0.8823          | 0.8245   |
+| 1.8178        | 1.0   | 100  | 1.7386          | 0.6209   |
+| 1.3138        | 2.0   | 200  | 1.1779          | 0.6511   |
+| 0.9632        | 3.0   | 300  | 0.8326          | 0.8679   |
+| 0.499         | 4.0   | 400  | 0.3697          | 0.9725   |
+| 0.3191        | 5.0   | 500  | 0.2240          | 0.9760   |
+| 0.242         | 6.0   | 600  | 0.1709          | 0.9793   |
+| 0.2144        | 7.0   | 700  | 0.1460          | 0.9806   |
+| 0.1977        | 8.0   | 800  | 0.1344          | 0.9800   |
+| 0.1742        | 9.0   | 900  | 0.1282          | 0.9797   |
+| 0.1867        | 10.0  | 1000 | 0.1243          | 0.9812   |
 
 
 ### Framework versions