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: 0.4576
+- Loss: 0.2975
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 6    | 0.9838          |
-| No log        | 2.0   | 12   | 0.5705          |
-| No log        | 3.0   | 18   | 0.4576          |
+| No log        | 1.0   | 6    | 0.7001          |
+| No log        | 2.0   | 12   | 0.3407          |
+| No log        | 3.0   | 18   | 0.2975          |
 
 
 ### Framework versions

adapter_config.json

@@ -15,7 +15,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d549d62ecdc962e4f16884b755196529347f64208c6268a1d931e570c8a5ec8e
+oid sha256:bb719581ae8d4569b7c02c26d24f99207966f2e57edce20f97bed952224d6224
 size 62969640

runs/Jan28_19-37-31_idc-training-gpu-compute-29/events.out.tfevents.1738093051.idc-training-gpu-compute-29.3660861.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b61374be276b1b423fdf8052403e7bfc4d9d5ec55aeb958d20ca1792df81d1
+size 7226

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86bb318011a41e1ad8664d3578748f9c7e985afdd4fb3d06a251328239e93741
+oid sha256:75cbf809a14bc47a0ab18e0c7a4f6d3ea3ad3359d5d851084142ec5944ccd012
 size 5624