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: 0.2475
+- Loss: 0.2463
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 17   | 0.3019          |
-| 0.502         | 2.0   | 34   | 0.2518          |
-| 0.1283        | 3.0   | 51   | 0.2475          |
+| No log        | 1.0   | 17   | 0.3043          |
+| 0.5022        | 2.0   | 34   | 0.2547          |
+| 0.1281        | 3.0   | 51   | 0.2463          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6f3d4c4f76dd31ca9c593c592c70b2ffa4a6f1e6f6dee455cbf673ca6397c29
+oid sha256:6e706e312e030a9a3f44bed2e9959edaf21fe4fa4d0c94934c72d5c9be2418e3
 size 63981160

runs/Feb14_05-00-33_idc-training-gpu-compute-03/events.out.tfevents.1739509234.idc-training-gpu-compute-03.616823.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db34c9a540dc70ec6cf788fc10b07bb78676bf8599a534acb29952da437ef4c
+size 7685

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d65e64359835bd5516875657fd88b4f4efc2fd4f81361ba920564d105fdf756
+oid sha256:745186093f3a08b4acb5e305dfc434d16fee9ebc7bdbdaea0c48405fa2c2cd87
 size 5624