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 [kiranpantha/whisper-large-v3-nepali](https://huggingface.co/kiranpantha/whisper-large-v3-nepali) on the OpenSLR54 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3704
+- Loss: 0.5229
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 14   | 0.7019          |
-| 0.7842        | 2.0   | 28   | 0.4426          |
-| 0.7842        | 3.0   | 42   | 0.3704          |
+| No log        | 1.0   | 6    | 1.2723          |
+| No log        | 2.0   | 12   | 0.6589          |
+| No log        | 3.0   | 18   | 0.5229          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a177eb690ab48e23f9e4cc78432202ad49b018d24c07ac1c7296626fe003d579
+oid sha256:c73618523cad8a7daff2b6eaf2417fcf65aaed1097ef6ba4ff693e46394203bd
 size 3986008

runs/Jan14_22-00-04_idc-training-gpu-compute-27/events.out.tfevents.1736892005.idc-training-gpu-compute-27.657637.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9327c66a76deeb635130a1fd1b734ae375f4d62ef608acbf655b250a33656aaa
+size 7111

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c84b4314bb1ada5d3872d975ad9f4a8bbe110b0ade267ebcc7f48f1dc6875d4
+oid sha256:380157d3bbcfa9d45a65a9af2270c0fca87f275cbbaf88ce501bd120f8c79046
 size 5624