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: 0.3012
+- Loss: 0.2974
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 6    | 0.7010          |
-| No log        | 2.0   | 12   | 0.3403          |
-| No log        | 3.0   | 18   | 0.3012          |
+| No log        | 1.0   | 6    | 0.6970          |
+| No log        | 2.0   | 12   | 0.3391          |
+| No log        | 3.0   | 18   | 0.2974          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6931ca7da6fe5f6d9b05fef200a4a80e967c5e3634eb8b0ac6218500184c9b7e
+oid sha256:ad1f15f079dcbf338b9985bd7264aca94fe71d8035563b65ea4fd71f8cc3438a
 size 63981160

runs/Jan29_05-05-26_idc-training-gpu-compute-29/events.out.tfevents.1738127126.idc-training-gpu-compute-29.3730264.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12191fbe5696b0e1ea710dcecfa390ca8a0bfac1ae02782bab457ecb48246e8c
+size 7229

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c29bb130cb6650b6f3ef10dfb0583d6b5348b126516a52513517cd2dd6f9e8d
+oid sha256:50be145d595189139fe6864ce36533bfa71928c1641385531025d926f4127916
 size 5624