output_model_shunyalabs_data_only_80000_steps

This model is a fine-tuned version of Eimhin03/output_model_shunyalabs_data_only_40000_steps on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8523
• Wer: 34.8988

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: 40000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0236	6.25	8000	0.9622	44.8087
0.0174	12.5	16000	0.9306	39.3147
0.0031	18.75	24000	0.9083	37.5277
0.0023	25.0	32000	0.8785	37.2471
0.0000	31.25	40000	0.8523	34.8988

Framework versions

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