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: 0.1063
+- Loss: 0.0965
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3962        | 1.0   | 25   | 0.4612          |
-| 0.1542        | 2.0   | 50   | 0.4570          |
-| 0.1596        | 3.0   | 75   | 0.1063          |
+| 0.3962        | 1.0   | 25   | 0.4430          |
+| 0.2137        | 2.0   | 50   | 0.2027          |
+| 0.0565        | 3.0   | 75   | 0.0965          |
 
 
 ### 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:dcb43faa6991d92e7ac8bd1f27d5610da5ca1e834f9a92aaa3c33cb63160e967
+oid sha256:b0f5b083e3b647d6b081f5724e225d5b859ab3704305c7d66d3ba3a85229eb9b
 size 4997168

runs/Feb10_19-59-29_idc-training-gpu-compute-03/events.out.tfevents.1739217570.idc-training-gpu-compute-03.368456.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6882f9b782aa4e83f8e38f0dd4262f3b23a0c2dc12a423c8234fa706ff22ab3c
+size 7895

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd60951e8accd4a81e182984b686b1885a932333f1913670f5e1cfa2796e020
+oid sha256:bf07234808c50c3c24948c516456b76db395347cbabd13a23faa6b340e681097
 size 5624