End of training

README.md

@@ -19,13 +19,11 @@ model-index:
     dataset:
       name: ASR Wolof Dataset
       type: IndabaxSenegal/asr-wolof-dataset
-      config: wo_sn
-      split: test
       args: 'config: wo, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 43.507061617297836
+      value: 52.95489047928865
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +33,8 @@ 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 ASR Wolof Dataset dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9866
-- Wer: 43.5071
+- Loss: 1.0929
+- Wer: 52.9549
 
 ## Model description
 
@@ -59,18 +57,20 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 3.0
+- lr_scheduler_type: cosine
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 1.1308        | 1.0   | 142  | 0.9861          | 43.7820 |
-| 0.6317        | 2.0   | 284  | 0.9646          | 43.4946 |
-| 0.4205        | 3.0   | 426  | 0.9866          | 43.5071 |
+| 0.1788        | 1.0   | 450  | 1.0593          | 54.4766 |
+| 0.1082        | 2.0   | 900  | 1.0710          | 53.9887 |
+| 0.0663        | 3.0   | 1350 | 1.0929          | 52.9549 |
 
 
 ### Framework versions

runs/Dec01_11-10-10_d08f9ecc9e77/events.out.tfevents.1733051419.d08f9ecc9e77.30.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ec440a5e643c270e6354211dde0531d11fae9700f912c47c40d43f9faab280
-size 13564
+oid sha256:663d9e27814e93075c63385cd53d217c86cdf96c06e9200e5dd72afb1539e692
+size 14236