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: 0.2733
+- Loss: 0.2929
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 9    | 0.5172          |
-| No log        | 2.0   | 18   | 0.2689          |
-| 0.4725        | 3.0   | 27   | 0.2733          |
+| No log        | 1.0   | 14   | 0.4751          |
+| 0.6466        | 2.0   | 28   | 0.3004          |
+| 0.6466        | 3.0   | 42   | 0.2929          |
 
 
 ### Framework versions

adapter_config.json

@@ -22,12 +22,11 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 1,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_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 sha256:0606e064347dde27ba72d66be96b657544063c41c04b9e32789e253a74ffd9d4
-size 252726072
+oid sha256:f0e0beaeb107e9497c13a3b45eadaad9c06717740b09e91c6b6ee1184acff560
+size 1515264

runs/Jan20_20-44-03_idc-training-gpu-compute-30/events.out.tfevents.1737405844.idc-training-gpu-compute-30.1217904.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181029f900c13f19e484ca3904f673477d245bccaea6487016d7eaf195cfa83b
+size 7311

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9c5c26e861cc9324b2b93618da76536f2cfda73e2f8d7c0bb0f305a7caf2ee
-size 5624
+oid sha256:cb8c1374b54b9afd9b21e0eae5900790297eb84eedb2fff0e7361223f188f482
+size 5560