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: 0.5229
+- Loss: 0.2964
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 6    | 1.2723          |
-| No log        | 2.0   | 12   | 0.6589          |
-| No log        | 3.0   | 18   | 0.5229          |
+| No log        | 1.0   | 14   | 0.6624          |
+| 0.9184        | 2.0   | 28   | 0.3761          |
+| 0.9184        | 3.0   | 42   | 0.2964          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73618523cad8a7daff2b6eaf2417fcf65aaed1097ef6ba4ff693e46394203bd
+oid sha256:09e9d2b1ea01f289536cf7bfc4b7a5fdd0c1f6e648360ac2e56458db3c132fe2
 size 3986008

runs/Jan14_22-03-03_idc-training-gpu-compute-27/events.out.tfevents.1736892184.idc-training-gpu-compute-27.657637.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a53d3deb677957071105b2ffcda2553fcbfd0f2550fce776a37d05d280ae7b
+size 7318

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380157d3bbcfa9d45a65a9af2270c0fca87f275cbbaf88ce501bd120f8c79046
+oid sha256:b21515d0854cc5207bdb1d52312aebc874265a234703d8a6433176ef092b8e2c
 size 5624