End of training

README.md

@@ -16,10 +16,13 @@ model-index:
     dataset:
       name: Giga Speech
       type: OthmaneJ/distil-wav2vec2
+      config: xs
+      split: train
+      args: xs
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.46
+      value: 0.8881789137380192
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [OthmaneJ/distil-wav2vec2](https://huggingface.co/OthmaneJ/distil-wav2vec2) on the Giga Speech dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6843
-- Accuracy: 0.46
+- Loss: 0.4271
+- Accuracy: 0.8882
 
 ## Model description
 
@@ -62,10 +65,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.2474        | 1.0   | 113  | 2.1219          | 0.28     |
-| 2.1323        | 2.0   | 226  | 1.9120          | 0.28     |
-| 1.8539        | 3.0   | 339  | 1.7446          | 0.42     |
-| 1.831         | 4.0   | 452  | 1.6843          | 0.46     |
+| 1.4425        | 1.0   | 1057 | 1.3045          | 0.5399   |
+| 0.796         | 2.0   | 2114 | 0.8516          | 0.7284   |
+| 0.9685        | 3.0   | 3171 | 0.5054          | 0.8626   |
+| 0.5623        | 4.0   | 4228 | 0.4271          | 0.8882   |
 
 
 ### Framework versions