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: 0.1731
+- Loss: 0.1173
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0888        | 1.0   | 34   | 0.1520          |
-| 0.0672        | 2.0   | 68   | 0.1732          |
-| 0.0226        | 3.0   | 102  | 0.1731          |
+| 0.053         | 1.0   | 40   | 0.1124          |
+| 0.0331        | 2.0   | 80   | 0.1296          |
+| 0.0155        | 3.0   | 120  | 0.1173          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa68ee44fbe96b2770f3cd8c4fb3aad13fbf8e40e5578de9a85182d7e77db58
+oid sha256:35678f3eadec02fa4bf1b1727d9ed2b5b8b748a34b81105f0fe09981406e8710
 size 62969640

runs/Jan12_09-59-45_idc-training-gpu-compute-29/events.out.tfevents.1736675985.idc-training-gpu-compute-29.4160599.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18dc981f80b407a6d60d27c99f7e2c6c6195a44926884f3b2340a3da1bdd5725
+size 7955

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1920c2e5280d0eb25c5faff5c8f725bc527066e3568af80e12dc64fece68e81f
+oid sha256:85e1dd1062d0779e332d767d1fcb070f6c58eb13f6239428869442eebdd81bc5
 size 5560