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: 0.1305
+- Loss: 0.1301
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4471        | 1.0   | 25   | 0.1432          |
-| 0.12          | 2.0   | 50   | 0.1250          |
-| 0.0651        | 3.0   | 75   | 0.1305          |
+| 0.4472        | 1.0   | 25   | 0.1430          |
+| 0.1198        | 2.0   | 50   | 0.1253          |
+| 0.0651        | 3.0   | 75   | 0.1301          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1270f39d36c65a2668aa475723e62a3e0008218c5af1bda32446700d1ad9b9bc
+oid sha256:a9c6f572af29c087dde009759122028fdb53b9e63d9dd4d8890657d6ce2de070
 size 3030912

runs/Feb08_13-53-33_idc-training-gpu-compute-04/events.out.tfevents.1739022814.idc-training-gpu-compute-04.365005.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e466b7c9b0a86a556a0eb4b7e694e6a8e3f60a3d14232c9960df174a936ced3
+size 7895

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5efc52a8c86916ddbd0ec2c4c67fc6a1e3731c3152092d0c9b6000a23531a64
+oid sha256:a8e6bcb791789b58827fdfe628d936a5a9ce6c8235b04a6d09682fd88490cb98
 size 5624