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: 0.3201
+- Loss: 0.3247
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 14   | 0.3427          |
-| 0.4967        | 2.0   | 28   | 0.3090          |
-| 0.4967        | 3.0   | 42   | 0.3201          |
+| No log        | 1.0   | 14   | 0.5482          |
+| 0.5968        | 2.0   | 28   | 0.3352          |
+| 0.5968        | 3.0   | 42   | 0.3247          |
 
 
 ### Framework versions

adapter_config.json

@@ -15,7 +15,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "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 sha256:5041e1ed78538f954e427b95442e75217f0f8248ae0ca8f41be608cc59f749bc
+oid sha256:057600e8d761b55d83392a0879f22ec652b989bc0a6ca5ce77ad39518247bd1c
 size 62969640

runs/Jan28_19-26-37_idc-training-gpu-compute-29/events.out.tfevents.1738092398.idc-training-gpu-compute-29.3660861.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b47f4b509497f6adc32ee1fff6beda2a419349e58fd702938b04e00a60ba00
+size 7433

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0906b9a125a3fd0402e2815eeb58841ca445b351341a7a373a08e70d03dfb339
+oid sha256:2549017a2f24b3a58ab365cd052d59dbcdc9b69bfe8853f135369cc5ed20e8ce
 size 5624