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: 0.3054
+- Loss: 0.3041
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 14   | 0.3257          |
-| 0.3512        | 2.0   | 28   | 0.2991          |
-| 0.3512        | 3.0   | 42   | 0.3054          |
+| No log        | 1.0   | 14   | 0.3242          |
+| 0.3442        | 2.0   | 28   | 0.3016          |
+| 0.3442        | 3.0   | 42   | 0.3041          |
 
 
 ### Framework versions

adapter_config.json

@@ -22,7 +22,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ed01fabc54a33ce3b201cde57261e157417136b9aa0d6e0448d199c3f2297d
-size 7918280
+oid sha256:ca3177c0af5c4f8afd598fece03e3596c1c395da07272312632026de1932cc2f
+size 15782928

runs/Jan13_08-24-27_idc-training-gpu-compute-28/events.out.tfevents.1736756668.idc-training-gpu-compute-28.2762785.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91274965b36948bf78c7c8af91e51be2f34885dbc5de1ed2607ea44e01b69569
+size 7334

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c28ba6403b155eff86c50458837b9af889f3267f19a58b28fa16d8d28cbde193
+oid sha256:bceb99a37bd1a032f85310dfd951cf326f1649986dac3c0f989ae168235be527
 size 5560