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: 0.3456
+- Loss: 0.2959
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 14   | 0.4116          |
-| 0.6016        | 2.0   | 28   | 0.3558          |
-| 0.6016        | 3.0   | 42   | 0.3456          |
+| No log        | 1.0   | 6    | 0.9539          |
+| No log        | 2.0   | 12   | 0.5069          |
+| No log        | 3.0   | 18   | 0.2959          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9787332b37f0f973f9fa89da34d2cbdeeebd830a48abef2cc13a6c16b63c841b
+oid sha256:8bba8c10013a36c841ac718054d03b7b8b2b41895f2d02ee9d311906aa8fca00
 size 3986008

runs/Jan14_21-00-29_idc-training-gpu-compute-27/events.out.tfevents.1736888429.idc-training-gpu-compute-27.657637.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0975c09619f59e692ce2c38950902e0a37128e04dd4c4c276eea49fafd1ccd
+size 7111

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7d8eadd2cfe5ded5f4738cff182a2017b35442638158bb64bbd4e8c1cd7cde
+oid sha256:7d7dfea1a2a503162af88b82cd73297ca61f135852a5e731b71629df1328c5ab
 size 5624