End of training

README.md

@@ -21,8 +21,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the AIhub_foreign_dataset4 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0461
-- Cer: 38.7247
+- Loss: 0.9395
+- Cer: 48.1817
 
 ## Model description
 
@@ -41,12 +41,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 500
 - training_steps: 6000
 - mixed_precision_training: Native AMP
@@ -55,17 +55,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Cer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 1.1331        | 0.7299 | 1000 | 1.0860          | 51.9778 |
-| 1.0137        | 1.4599 | 2000 | 1.0169          | 52.3109 |
-| 0.6556        | 2.1898 | 3000 | 1.0076          | 46.6288 |
-| 0.7336        | 2.9197 | 4000 | 0.9763          | 44.7615 |
-| 0.5157        | 3.6496 | 5000 | 1.0181          | 40.7681 |
-| 0.3103        | 4.3796 | 6000 | 1.0461          | 38.7247 |
+| 1.0479        | 0.7299 | 1000 | 0.9942          | 53.5695 |
+| 0.983         | 1.4599 | 2000 | 0.9553          | 50.5824 |
+| 0.7329        | 2.1898 | 3000 | 0.9432          | 56.3785 |
+| 0.7979        | 2.9197 | 4000 | 0.9299          | 48.6001 |
+| 0.6956        | 3.6496 | 5000 | 0.9368          | 47.2723 |
+| 0.5971        | 4.3796 | 6000 | 0.9395          | 48.1817 |
 
 
 ### Framework versions
 
 - Transformers 4.51.0.dev0
 - Pytorch 2.6.0+cu124
-- Datasets 3.4.1
+- Datasets 3.5.0
 - Tokenizers 0.21.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9af9bcccc317ef9cb9577fff1fa7f2d30b6fae0c4df202b38d347f7e5a383a
+oid sha256:6ea36c228cebc740100e73f4a97f3a7fc887d3fb54eb9b97b31a60fec4836ba8
 size 290403936

runs/Mar28_15-51-54_f32a79138847/events.out.tfevents.1743177119.f32a79138847.1038.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab71ae114f048e243157b93cf9062f3bc35b7afcf43fa1a24adaec676473341
-size 58316
+oid sha256:f19411916e9d3b2f17019d1dd1838b2522ce7a7115abba660890c389486b4a33
+size 58670