output_model_shunyalabs_data_only_40000_steps

This model is a fine-tuned version of Eimhin03/output_model_shunyalabs_data_only_20000_steps on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7551
• Wer: 33.1561

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: 20000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0570	3.9062	5000	0.8881	43.9374
0.0130	7.8125	10000	0.8320	40.3190
0.0015	11.7188	15000	0.7739	35.7407
0.0000	15.625	20000	0.7551	33.1561

Framework versions

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