End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 0.33250529508668253
+      value: 0.25583766963888815
 ---
 
 <!-- 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-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2213
-- Wer: 0.3325
+- Loss: 0.2072
+- Wer: 0.2558
 
 ## Model description
 
@@ -61,20 +61,21 @@ 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_steps: 500
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.6259        | 0.85  | 400  | 0.6826          | 0.8552 |
-| 0.344         | 1.7   | 800  | 0.2798          | 0.4271 |
-| 0.1695        | 2.56  | 1200 | 0.2213          | 0.3325 |
+| 0.2423        | 1.28  | 600  | 0.2974          | 0.4100 |
+| 0.1685        | 2.56  | 1200 | 0.2354          | 0.3337 |
+| 0.107         | 3.83  | 1800 | 0.2234          | 0.2835 |
+| 0.0684        | 5.11  | 2400 | 0.2072          | 0.2558 |
 
 
 ### Framework versions
 
-- Transformers 4.32.0
+- Transformers 4.32.1
 - Pytorch 2.0.1+cu118
 - Datasets 2.14.4
 - Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ee4343104ed79614751f8ac9a5f18dbf54b791c683657610c3f147d120e8a48
+oid sha256:3f1a447a750a6c97201a69116b57556a946e8f5c86b6250e18e77d9e72dd79c8
 size 1262033069