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: 0.2975
+- Loss: 0.2969
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 11   | 0.3707          |
-| No log        | 2.0   | 22   | 0.3098          |
-| 0.4103        | 3.0   | 33   | 0.2975          |
+| No log        | 1.0   | 11   | 0.3708          |
+| No log        | 2.0   | 22   | 0.3088          |
+| 0.4103        | 3.0   | 33   | 0.2969          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80801ab1b42e53fbac7c5877b68b513b46b6b9a042e45e1bb69f305ec8e87d15
+oid sha256:c86a3386418f670eae04ea1420b5474f0916490cca14ee3c8a63cd53baeda4f7
 size 3030912

runs/Feb08_13-51-29_idc-training-gpu-compute-04/events.out.tfevents.1739022690.idc-training-gpu-compute-04.365005.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250e9a6b98cc521f3093191001155a828e7c1c322fe82457eca32ecd366c2b88
+size 7472

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c7d7685a3af87b9430d837437eb71512ccdb12f58b46a7a6588699cf08e543
+oid sha256:d302f0da3b39b2775c8e3744479103c3a41eca2162a0b05c765fb549b3f61edf
 size 5624