End of training

README.md

@@ -20,7 +20,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 62.548565318125114
+      value: 60.82338264124042
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,8 +30,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 6.1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5656
-- Wer: 62.5486
+- Loss: 1.6083
+- Wer: 60.8234
 
 ## Model description
 
@@ -57,16 +57,19 @@ 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: 50
-- training_steps: 300
+- training_steps: 600
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.8838        | 6.6667  | 100  | 1.6662          | 71.3171 |
-| 0.0976        | 13.3333 | 200  | 1.5559          | 63.6036 |
-| 0.023         | 20.0    | 300  | 1.5656          | 62.5486 |
+| 0.8626        | 6.6667  | 100  | 1.6526          | 70.6755 |
+| 0.0473        | 13.3333 | 200  | 1.5418          | 62.1244 |
+| 0.0054        | 20.0    | 300  | 1.5761          | 61.4971 |
+| 0.0031        | 26.6667 | 400  | 1.5958          | 61.0872 |
+| 0.0024        | 33.3333 | 500  | 1.6048          | 60.8198 |
+| 0.0021        | 40.0    | 600  | 1.6083          | 60.8234 |
 
 
 ### Framework versions

runs/May30_11-22-15_a100gpu5/events.out.tfevents.1717060964.a100gpu5.2126245.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0931cea699a1bcc024b52e2cd786f51fd18a9184212efd4fe45e8da65e768213
-size 12214
+oid sha256:a438ca645523776973bf0a1d228da9eb5163c2f24d343bccfebe3f1bc8914417
+size 13730