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: 0.0597
+- Loss: 0.3071
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 6    | 0.0471          |
-| No log        | 2.0   | 12   | 0.0582          |
-| No log        | 3.0   | 18   | 0.0597          |
+| No log        | 1.0   | 13   | 0.3046          |
+| 0.0396        | 2.0   | 26   | 0.2943          |
+| 0.0396        | 3.0   | 39   | 0.3071          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f063fbd962a1efa2b5fa2890281cfcf34782a27e874c55ae56b0b11a6487f9
+oid sha256:2cb3ded99bbe4ca65db29422a92c530cd44c9d5899ed527aa5efe668283a21d7
 size 62969640

runs/Jan12_20-31-49_idc-training-gpu-compute-29/events.out.tfevents.1736713919.idc-training-gpu-compute-29.67836.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cefde2c9af33097fe393e94aec3677a1dc698ca944e1f689f46298aff31ed5
+size 7334

runs/Jan12_20-31-49_idc-training-gpu-compute-29/events.out.tfevents.1736714015.idc-training-gpu-compute-29.67836.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a3e53c1e83c33769619621b7e6589d83e7ae48095f9caa9fef28b1c7abc23e
+size 7334

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8843a8c481a9cc9e1cdbb13ca872b158a04c5261aa9cf082c042c3ad582819c
+oid sha256:13a5b934ea675dd40e571e17787f4393f326f6f19193fca3b9be463cd7b80cea
 size 5560