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-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4459
+- Loss: 0.3917
 
 ## Model description
 
@@ -45,16 +45,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
-- num_epochs: 2
+- lr_scheduler_warmup_ratio: 0.06
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.425         | 1.0   | 3111 | 0.5223          |
-| 0.2723        | 2.0   | 6222 | 0.4459          |
+| 0.6127        | 1.0   | 1550 | 0.5854          |
+| 0.4298        | 2.0   | 3100 | 0.4626          |
+| 0.2312        | 3.0   | 4650 | 0.4104          |
+| 0.1511        | 4.0   | 6200 | 0.3917          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749a31f6cedf76643337586c8949375ed1b8c44fff704b5721e2ac7391215e32
+oid sha256:02b2d33977e57d5694c328a35bf25fc859c56b9b3b0cd0bb027aeae83febb3f1
 size 19548472

runs/Apr18_17-07-07_d9df666dc796/events.out.tfevents.1713460031.d9df666dc796.25.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ec06c0f5af315e3d36dce93d669eb573a453c805ca900c43847367ce9011f6
-size 56879
+oid sha256:4c6212c0eb7ebccc0c8077b3bb249da3463c152f8fc8d0964a2aeda2af7eea05
+size 59192