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: 0.9810238305383936
+      value: 0.9814651368049426
 ---
 
 <!-- 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: 0.0855
-- Accuracy: 0.9810
+- Loss: 0.0982
+- Accuracy: 0.9815
 
 ## Model description
 
@@ -70,11 +69,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.487         | 1.0    | 400  | 0.3713          | 0.9701   |
-| 0.1701        | 2.0    | 800  | 0.1345          | 0.9748   |
-| 0.1905        | 3.0    | 1200 | 0.1007          | 0.9785   |
-| 0.1365        | 4.0    | 1600 | 0.0850          | 0.9809   |
-| 0.1317        | 4.9894 | 1995 | 0.0855          | 0.9810   |
+| 0.8747        | 1.0    | 400  | 0.8067          | 0.9341   |
+| 0.2332        | 2.0    | 800  | 0.1779          | 0.9746   |
+| 0.217         | 3.0    | 1200 | 0.1263          | 0.9766   |
+| 0.1529        | 4.0    | 1600 | 0.1045          | 0.9806   |
+| 0.15          | 4.9894 | 1995 | 0.0982          | 0.9815   |
 
 
 ### Framework versions

runs/Apr08_16-30-28_cs-Precision-7960-Tower/events.out.tfevents.1744144232.cs-Precision-7960-Tower.26085.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03d6957bc24eaee5cf8fd149e078be363f71bd7d82242f2f802e91ed12b32c6
-size 50564
+oid sha256:1fd7d5bc9dffb9e5dba9ccc671990195bff0686bf608380b9a69ba296066b27a
+size 51241