outout_model_29Jan26_FinetuneRealData

This model is a fine-tuned version of Eimhin03/outout_model on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5825
• Wer: 72.4051

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 1
• eval_batch_size: 1
• 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_warmup_steps: 200
• training_steps: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1170	4.0733	2000	2.3305	76.7089
0.0056	8.1466	4000	2.6266	76.2025
0.0013	12.2200	6000	2.5885	72.9114
0.0000	16.2933	8000	2.5777	72.6582
0.0000	20.3666	10000	2.5825	72.4051

Framework versions

• Transformers 5.0.1.dev0
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.2