End of training

README.md

@@ -3,24 +3,24 @@ library_name: peft
 language:
 - ne
 license: apache-2.0
-base_model: kiranpantha/whisper-large-v3-nepali
+base_model: openai/whisper-large-v3
 tags:
 - generated_from_trainer
 datasets:
 - kiranpantha/OpenSLR54-Balanced-Nepali
 model-index:
-- name: kiranpantha/whisper-large-v3-nepali
+- name: openai/whisper-large-v3
   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. -->
 
-# kiranpantha/whisper-large-v3-nepali
+# openai/whisper-large-v3
 
-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.
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the OpenSLR54 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2607
+- Loss: 0.4484
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 14   | 0.3010          |
-| 0.6238        | 2.0   | 28   | 0.2616          |
-| 0.6238        | 3.0   | 42   | 0.2607          |
+| No log        | 1.0   | 9    | 0.8309          |
+| No log        | 2.0   | 18   | 0.5090          |
+| 0.7788        | 3.0   | 27   | 0.4484          |
 
 
 ### 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": "kiranpantha/whisper-large-v3-nepali",
+  "base_model_name_or_path": "openai/whisper-large-v3",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -22,7 +22,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 1,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e55552c0b1528d9b95c4ce5c4d7d1a5b294c846d3f32cc78a902310c9d8039
-size 251714264
+oid sha256:8befda75e7cadfee9a272bd557411746890caa36d67065b2511d5937def1d1ef
+size 2019712

runs/Jan13_21-59-49_idc-training-gpu-compute-28/events.out.tfevents.1736805589.idc-training-gpu-compute-28.2829836.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d72eaf9d3e42ad18718f1c63c4da01580dc10198d07d2a64b7022f56c7af59
+size 7338

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca07731aa088aa339117b077e80ec3665fb8ae49bc0329da9326342e23f9a7b4
+oid sha256:fec6401d58b04118051d3ab761ca63763206e19120e36e2bf52460d677bf3a37
 size 5560