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 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1946
+- Loss: 0.2334
 
 ## Model description
 
@@ -48,16 +48,18 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2346        | 1.0   | 491  | 0.2726          |
-| 0.1467        | 2.0   | 982  | 0.2088          |
-| 0.077         | 3.0   | 1473 | 0.1946          |
+| 0.244         | 1.0   | 491  | 0.2828          |
+| 0.1788        | 2.0   | 982  | 0.2497          |
+| 0.1169        | 3.0   | 1473 | 0.2181          |
+| 0.054         | 4.0   | 1964 | 0.2178          |
+| 0.0216        | 5.0   | 2455 | 0.2334          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfebfa627e68b3ee699432f42c32a07b67d59b8ac890e084b28dafe0147f5589
+oid sha256:631d28fe7139e48d48e40418e78f2712eaa405df76d197e4225de908ffbd8cbf
 size 62969640

runs/Nov18_07-15-32_ce79511cc19d/events.out.tfevents.1731914137.ce79511cc19d.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997d600ee6cec2f70f92c86c72763c09ff39cce9904e1adedfd3c16dc3d3cfe2
+size 28720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c08618e5ad05f3e7b727a98485c04a79fd28c5f8a60e10d975e97f9c294fce
+oid sha256:54771f0a43847bdf4ab2c1cf676f564019860272bd2b6045541781fdebc97d1a
 size 5496