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: 0.2485
+- Loss: 0.2904
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 17   | 0.3037          |
-| 0.5059        | 2.0   | 34   | 0.2533          |
-| 0.1359        | 3.0   | 51   | 0.2485          |
+| No log        | 1.0   | 17   | 0.3111          |
+| 0.5051        | 2.0   | 34   | 0.4765          |
+| 0.3134        | 3.0   | 51   | 0.2904          |
 
 
 ### Framework versions

adapter_config.json

@@ -26,9 +26,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "k_proj",
     "c_attn",
-    "k_proj"
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7173ce0c14fc48a2608079aa53891de5fbaf5dcac839f5e2f4b668c33146d3ce
+oid sha256:9eb7128d523c165d0b3260e49264453322c88ce61a6ec6128dbd08c892b22f7f
 size 62969640

runs/Feb10_16-31-55_idc-training-gpu-compute-03/events.out.tfevents.1739205116.idc-training-gpu-compute-03.350171.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3483e6180a11e16a81d2cf5fe26001c70d88c8293e49f0f28b422453aab6d1a
+size 7685

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fdbb8494d2af0ac347b70190adfc0e591ba37b43906d64194f99399093b2bc5
+oid sha256:f134bc709848f59f469ba69ee3b38df9764d4e3c0ccdfeefbad4ec694d1a473d
 size 5624