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: 0.4378
+- Loss: 0.3456
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 9    | 0.8709          |
-| No log        | 2.0   | 18   | 0.4782          |
-| 0.7485        | 3.0   | 27   | 0.4378          |
+| No log        | 1.0   | 14   | 0.4116          |
+| 0.6016        | 2.0   | 28   | 0.3558          |
+| 0.6016        | 3.0   | 42   | 0.3456          |
 
 
 ### Framework versions

adapter_config.json

@@ -26,7 +26,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj"
+    "q_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:a55feb2ee4c03f4567ef523d7aaff4079fca307c5f918581fff816eecd5034a3
-size 1992920
+oid sha256:9787332b37f0f973f9fa89da34d2cbdeeebd830a48abef2cc13a6c16b63c841b
+size 3986008

runs/Jan14_20-56-35_idc-training-gpu-compute-27/events.out.tfevents.1736888195.idc-training-gpu-compute-27.657637.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a05f9328087052400fa8173f0626a9d6356210695f53611b0899799ac45938b
+size 7318

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bfadf57adddac8b77750e366bacd19e5ad80ad89ebdb1512e59a51b7b3de8b8
-size 5560
+oid sha256:3b7d8eadd2cfe5ded5f4738cff182a2017b35442638158bb64bbd4e8c1cd7cde
+size 5624