End of training

README.md

@@ -5,22 +5,9 @@ tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_6_1
-metrics:
-- wer
 model-index:
 - name: Whisper Small Frisian 1h
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 6.1
-      type: mozilla-foundation/common_voice_6_1
-      args: 'config: frisian, split: test'
-    metrics:
-    - name: Wer
-      type: wer
-      value: 63.251646334880704
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,8 +17,13 @@ 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 6.1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0076
-- Wer: 63.2516
+- eval_loss: 0.9050
+- eval_wer: 43.8389
+- eval_runtime: 596.14
+- eval_samples_per_second: 5.066
+- eval_steps_per_second: 0.634
+- epoch: 7.8652
+- step: 700
 
 ## Model description
 
@@ -50,30 +42,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-06
-- train_batch_size: 16
+- learning_rate: 3e-06
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- training_steps: 1000
+- lr_scheduler_warmup_steps: 50
+- training_steps: 1500
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch   | Step | Validation Loss | Wer     |
-|:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 2.4337        | 4.4444  | 200  | 2.4123          | 86.6566 |
-| 1.2587        | 8.8889  | 400  | 1.4507          | 74.9685 |
-| 0.6617        | 13.3333 | 600  | 1.1118          | 66.6991 |
-| 0.4265        | 17.7778 | 800  | 1.0242          | 63.8850 |
-| 0.3419        | 22.2222 | 1000 | 1.0076          | 63.2516 |
-
-
 ### Framework versions
 
 - Transformers 4.40.1
-- Pytorch 2.2.2+cu121
+- Pytorch 2.3.0+cu121
 - Datasets 2.19.0
 - Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5bc0676f035c7e824aa8062e15f0262c6b89180d0eda5af6e45588471c3ee1e
+oid sha256:a9e858458b048bfcf05a4a66e21a629a89e092dabb94eb98f69a7bbefaadf3b7
 size 966995080

runs/May30_18-37-59_a100gpu5/events.out.tfevents.1717087087.a100gpu5.2302632.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221cbef948beb2ce9da86ca2fe4d6d29e6a29ffd3ccecded36d6afc6a1c4c340
-size 12212
+oid sha256:8260750af0094e35c9e747f569f8c1077016b74c9d5d7e6f9e3d7b356d21e0d9
+size 15380