End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 56.672545561434454
+      value: 44.135490394337715
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7402
-- Wer Ortho: 58.1904
-- Wer: 56.6725
+- Loss: 1.4342
+- Wer Ortho: 46.8432
+- Wer: 44.1355
 
 ## Model description
 
@@ -54,15 +54,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
+- learning_rate: 5e-05
+- train_batch_size: 32
 - eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 32
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- total_train_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant_with_warmup
-- lr_scheduler_warmup_steps: 50
+- lr_scheduler_warmup_steps: 100
 - training_steps: 450
 - mixed_precision_training: Native AMP
 
@@ -70,12 +70,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Wer Ortho | Wer     |
 |:-------------:|:-------:|:----:|:---------------:|:---------:|:-------:|
-| 0.0001        | 32.1481 | 450  | 2.7402          | 58.1904   | 56.6725 |
+| 0.0039        | 64.2857 | 450  | 1.4342          | 46.8432   | 44.1355 |
 
 
 ### Framework versions
 
-- Transformers 4.50.0
-- Pytorch 2.6.0+cu124
-- Datasets 3.4.1
-- Tokenizers 0.21.1
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.3.1
+- Tokenizers 0.21.0

generation_config.json

@@ -258,5 +258,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.50.0"
+  "transformers_version": "4.47.0"
 }