End of training

README.md

@@ -3,24 +3,24 @@ library_name: peft
 language:
 - ne
 license: apache-2.0
-base_model: openai/whisper-large-v3
+base_model: kiranpantha/whisper-large-v3-nepali
 tags:
 - generated_from_trainer
 datasets:
 - kiranpantha/OpenSLR54-Balanced-Nepali
 model-index:
-- name: openai/whisper-large-v3
+- name: kiranpantha/whisper-large-v3-nepali
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# openai/whisper-large-v3
+# kiranpantha/whisper-large-v3-nepali
 
-This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the OpenSLR54 dataset.
+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: 0.4484
+- Loss: 0.2897
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 9    | 0.8309          |
-| No log        | 2.0   | 18   | 0.5090          |
-| 0.7788        | 3.0   | 27   | 0.4484          |
+| No log        | 1.0   | 9    | 0.6282          |
+| No log        | 2.0   | 18   | 0.2886          |
+| 0.5645        | 3.0   | 27   | 0.2897          |
 
 
 ### Framework versions

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "WhisperForConditionalGeneration",
     "parent_library": "transformers.models.whisper.modeling_whisper"
   },
-  "base_model_name_or_path": "openai/whisper-large-v3",
+  "base_model_name_or_path": "kiranpantha/whisper-large-v3-nepali",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8befda75e7cadfee9a272bd557411746890caa36d67065b2511d5937def1d1ef
+oid sha256:84018a579adb6a873829ad9c605ed1aa2e9261f737dcc43007674e0c4e410568
 size 2019712

runs/Jan13_22-06-44_idc-training-gpu-compute-28/events.out.tfevents.1736806005.idc-training-gpu-compute-28.2829836.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22234e0d402bc97c5773387fc74d1f913a30bc85729a5eb05744fcf519299c8d
+size 7331

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec6401d58b04118051d3ab761ca63763206e19120e36e2bf52460d677bf3a37
+oid sha256:f198064ce77937711e98d41a1ea6ee5f6c75146d535d1231edecc5c9e6f20f43
 size 5560