outout_model_29Jan26_FinetuneRealData_time_11_10

This model is a fine-tuned version of Eimhin03/outout_model_29Jan26_FinetuneRealData on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8577
• Wer: 44.0703

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.5827	0.4883	1250	1.5260	65.6328
1.1912	0.9766	2500	1.1241	52.1636
0.3742	1.4648	3750	0.9686	47.4376
0.5058	1.9531	5000	0.8577	44.0703

Framework versions

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