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: 0.2826
+- Loss: 0.4502
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 9    | 0.5909          |
-| No log        | 2.0   | 18   | 0.2857          |
-| 0.4917        | 3.0   | 27   | 0.2826          |
+| No log        | 1.0   | 14   | 0.7278          |
+| 0.8225        | 2.0   | 28   | 0.5067          |
+| 0.8225        | 3.0   | 42   | 0.4502          |
 
 
 ### Framework versions

adapter_config.json

@@ -26,7 +26,7 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj"
+    "q_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003dd89aba354dd0593abe111bdad1d3b96ea26bca444a99d09b6a5afbe20abb
+oid sha256:794a56f651eeaf9ca72d8d05ab1a5df40fa4714086f17df2f92a25e9e374db26
 size 1992920

runs/Jan14_20-39-25_idc-training-gpu-compute-27/events.out.tfevents.1736887166.idc-training-gpu-compute-27.657637.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14aafb4d5edd30c1d0dc79491dc58023448eb4cbf86ed99edd9aacc1a3d1eff2
+size 7311

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74323d2e111ffe7f2a636629967dca9f14ea13e6de4f661e3408c49ba160f83c
+oid sha256:0624e09d6333c00b0309371e93abfa9e1d13c3cdf0335b95a4aaf11e30f187d5
 size 5560