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: 0.2604
+- Loss: 0.2733
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 14   | 0.3001          |
-| 0.6216        | 2.0   | 28   | 0.2617          |
-| 0.6216        | 3.0   | 42   | 0.2604          |
+| No log        | 1.0   | 9    | 0.5172          |
+| No log        | 2.0   | 18   | 0.2689          |
+| 0.4725        | 3.0   | 27   | 0.2733          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b152a461c7495d8b8094bf18051272879628f28c6c170f4f325a813da7b0c440
+oid sha256:0606e064347dde27ba72d66be96b657544063c41c04b9e32789e253a74ffd9d4
 size 252726072

runs/Jan20_20-21-03_idc-training-gpu-compute-30/events.out.tfevents.1737404464.idc-training-gpu-compute-30.1217904.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d684964ea770a58285182fb7b320bacb8798ff1124398fe9721a5c0276425532
+size 7320

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeecf8fa68eb8ed576a486b5dc2489f660d1ed90e0606e4cfb8880f614b1ab0f
+oid sha256:6d9c5c26e861cc9324b2b93618da76536f2cfda73e2f8d7c0bb0f305a7caf2ee
 size 5624