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 [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: 0.4442
+- Loss: 0.0448
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 14   | 0.5178          |
-| 0.5309        | 2.0   | 28   | 0.4394          |
-| 0.5309        | 3.0   | 42   | 0.4442          |
+| 0.3183        | 1.0   | 93   | 0.1889          |
+| 0.1722        | 2.0   | 186  | 0.0798          |
+| 0.0646        | 3.0   | 279  | 0.0448          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4f198a005172af78b715fc7609c917c17f60779c8d36163b7b1bd91b8a1fc9
+oid sha256:330b0deef567a3c5e84f5ddeb0ddc1873cab1b8e6c885f251ff14d0c53cb1999
 size 62969640

runs/Jan12_21-22-07_idc-training-gpu-compute-29/events.out.tfevents.1736716931.idc-training-gpu-compute-29.67836.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb55b5ac74a599a0c9b39eac29ac0d6dc26f12d3299a36b21495cfd0ae1b887
+size 9451

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb6496d6069e97a053086ac1d615cca14debadad79e97a4540d7aafec81f60c
+oid sha256:96cddbe564a908355773da38c9f10c24f91bb3397194ca228af02847aa167837
 size 5560