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: 0.0663
+- Loss: 0.0501
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0561        | 1.0   | 30   | 0.0532          |
-| 0.0346        | 2.0   | 60   | 0.0864          |
-| 0.0286        | 3.0   | 90   | 0.0663          |
+| 0.0561        | 1.0   | 30   | 0.0531          |
+| 0.0345        | 2.0   | 60   | 0.0975          |
+| 0.0269        | 3.0   | 90   | 0.0501          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1bbe1f0727d6b3bc7d8d26721ab7815bbe4a716ffaac2a9ef1f0a111c9091f1
+oid sha256:f35aecfd63e867d5bbf55d03fc2123e67e41bc610ce3e21a7d0f1155aaa66210
 size 62969640

runs/Jan11_11-55-21_idc-training-gpu-compute-27/events.out.tfevents.1736596521.idc-training-gpu-compute-27.3660830.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d9ee20a4b06147d3668e086e4efa442947d9ceafa17a34ca9b1b727fe92138
+size 7748

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b569685d9e561553b1a8429a2d4cbdcfbfc2f1befe4a54d57ef9677d9c765a40
+oid sha256:c3bb048c8f750be2fb31912e76eb57609974e939dd4051f1b81a7b4904450734
 size 5560