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: 0.7224
+- Loss: 0.4834
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 14   | 0.6883          |
-| 0.9469        | 2.0   | 28   | 0.4438          |
-| 0.9469        | 3.0   | 42   | 0.7224          |
+| No log        | 1.0   | 14   | 0.8504          |
+| 0.897         | 2.0   | 28   | 0.5416          |
+| 0.897         | 3.0   | 42   | 0.4834          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f65b70d8e1f6b16eb349fc6a70fb61fdb9ab1eb52f7ed481aab8cb49bceb80f
+oid sha256:a1261d557158cae386fe95ad0e98118778ac8ee2c26e27b4748f61bea0fd0e93
 size 1992920

runs/Jan14_21-25-33_idc-training-gpu-compute-27/events.out.tfevents.1736889934.idc-training-gpu-compute-27.657637.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350d5fbf61bd5dccd763ff6f3b43a039d1e62b01e22e2c6e3a218aa6dc1b7bce
+size 7311

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776d2d02531deb4f359b2a68e4b9574f2619ed9e6794b34fe774064c4b815e79
+oid sha256:987c84c4d8032dd37e05745662f244e35a6404c934bc0b0357cc6d50595434c9
 size 5560