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: 0.2405
+- Loss: 0.4650
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3595        | 1.0   | 25   | 0.1547          |
-| 0.1059        | 2.0   | 50   | 0.1212          |
-| 0.2275        | 3.0   | 75   | 0.2405          |
+| 0.3595        | 1.0   | 25   | 0.1553          |
+| 0.1059        | 2.0   | 50   | 0.1218          |
+| 0.1272        | 3.0   | 75   | 0.4650          |
 
 
 ### Framework versions

adapter_config.json

@@ -26,8 +26,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60f294293ff4035c5c7c3630447fc53c31f85aef639e88a44daf51ffa24dea6
+oid sha256:f84b3846675ee39acd1e0ea73a3cd17ec952be8a6375b57d2b621a014e600d8e
 size 8929448

runs/Feb10_20-18-07_idc-training-gpu-compute-03/events.out.tfevents.1739218687.idc-training-gpu-compute-03.368456.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83375d7c5219d943df901b485e8379d202f11e793b6939e1882f606c0ca12e4
+size 7895

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c99513a5559a699754608ccd4ef344661f1a78a42ab6d2b75075c55e8c5d0b6
+oid sha256:f24b5878c3bcae0a3b2d9089d128f37525509224ec8a2a81428b5e3f9733eca0
 size 5624