End of training

README.md

@@ -20,7 +20,7 @@ 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 16.1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9520
+- Loss: 0.9259
 
 ## Model description
 
@@ -48,15 +48,16 @@ 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: 2
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.0115        | 1.0   | 2500 | 1.0421          |
-| 0.8407        | 2.0   | 5000 | 0.9520          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.0115        | 1.0   | 2500  | 1.0421          |
+| 0.7221        | 3.0   | 7500  | 0.9296          |
+| 0.5582        | 4.0   | 10000 | 0.9259          |
 
 
 ### Framework versions

runs/May10_07-15-34_a41953eec4b2/events.out.tfevents.1715325336.a41953eec4b2.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ed9ff560956865a42acba2697a30774435ab7420e20df358c0a7f1f5360a14
-size 48023
+oid sha256:75bedf5aaee9466f96d1843dfd3f6fd17f149a7fff84793cc80ec7d1b757faf7
+size 48648