update model card README.md

README.md

@@ -18,8 +18,8 @@ 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: 2.6391
-- Accuracy: 0.0885
+- Loss: 2.6359
+- Accuracy: 0.0619
 
 ## Model description
 
@@ -47,25 +47,27 @@ 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: 100
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 3.2283        | 11.53 | 35   | 2.6432          | 0.1062   |
-| 3.4248        | 23.27 | 70   | 2.6394          | 0.0973   |
-| 3.4245        | 34.8  | 105  | 2.6404          | 0.0442   |
-| 3.2245        | 46.53 | 140  | 2.6405          | 0.0531   |
-| 3.2287        | 58.27 | 175  | 2.6416          | 0.0796   |
-| 3.2289        | 69.8  | 210  | 2.6424          | 0.0973   |
-| 3.2252        | 81.53 | 245  | 2.6396          | 0.1062   |
-| 3.424         | 93.27 | 280  | 2.6391          | 0.0885   |
+| No log        | 0.8   | 3    | 2.6579          | 0.0796   |
+| No log        | 1.8   | 6    | 2.6500          | 0.0796   |
+| No log        | 2.8   | 9    | 2.6507          | 0.0708   |
+| 3.2239        | 3.8   | 12   | 2.6486          | 0.0708   |
+| 3.2239        | 4.8   | 15   | 2.6410          | 0.1150   |
+| 3.2239        | 5.8   | 18   | 2.6365          | 0.0973   |
+| 3.2191        | 6.8   | 21   | 2.6367          | 0.0885   |
+| 3.2191        | 7.8   | 24   | 2.6379          | 0.0708   |
+| 3.2191        | 8.8   | 27   | 2.6353          | 0.0796   |
+| 3.2232        | 9.8   | 30   | 2.6359          | 0.0619   |
 
 
 ### Framework versions
 
-- Transformers 4.11.3
-- Pytorch 1.13.1
-- Datasets 2.15.0
-- Tokenizers 0.10.3
+- Transformers 4.26.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.13.3