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: 0.0448
+- Loss: 0.2527
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3183        | 1.0   | 93   | 0.1889          |
-| 0.1722        | 2.0   | 186  | 0.0798          |
-| 0.0646        | 3.0   | 279  | 0.0448          |
+| No log        | 1.0   | 14   | 0.2889          |
+| 0.3887        | 2.0   | 28   | 0.2657          |
+| 0.3887        | 3.0   | 42   | 0.2527          |
 
 
 ### 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,
@@ -22,7 +22,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 1,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330b0deef567a3c5e84f5ddeb0ddc1873cab1b8e6c885f251ff14d0c53cb1999
-size 62969640
+oid sha256:d44947e8fdacb1e39798ae11866a40821b208c94d43b13d2b6dc6e069d8d03f2
+size 2019712

runs/Jan13_08-00-46_idc-training-gpu-compute-28/events.out.tfevents.1736755250.idc-training-gpu-compute-28.2762785.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e284f071873bc167cc3e5a89c84ec1a1e8ed4d3580eace384f76b4aeaab75b40
+size 7334

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96cddbe564a908355773da38c9f10c24f91bb3397194ca228af02847aa167837
+oid sha256:9854da27843dc5145a200398daa528930d81c766d747b3e1a37e868f930b415b
 size 5560