Eimhin03/outout_model_EUBookShop_data_only_76000_steps

outout_model_EUBookShop_data_only_more_training

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

• Loss: 0.1065
• Wer: 7.6083

Trained for 76000 steps total

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: 2
• eval_batch_size: 4
• 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: 56000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3486	0.2643	8000	0.3053	18.8961
0.2431	0.5286	16000	0.2307	15.5896
0.2082	0.7928	24000	0.1936	13.1886
0.0841	1.0571	32000	0.1665	11.6163
0.0907	1.3214	40000	0.1434	9.4768
0.0896	1.5857	48000	0.1184	8.6716
0.0555	1.8500	56000	0.1065	7.6083

Framework versions

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