output_model_shunyalabs_data_base_model_80k

This model is a fine-tuned version of Eimhin03/output_model_shunyalabs_data_base_model_40k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7143
• Wer: 28.1790

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: 1e-06
• 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: 500
• training_steps: 40000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0115	3.9062	5000	0.7443	33.5696
0.0005	7.8125	10000	0.7308	32.5358
0.0001	11.7188	15000	0.7250	30.6897
0.0001	15.625	20000	0.7200	29.7297
0.0000	19.5312	25000	0.7167	28.9765
0.0000	23.4375	30000	0.7153	28.4005
0.0000	27.3438	35000	0.7145	28.1199
0.0000	31.25	40000	0.7143	28.1790

Framework versions

• Transformers 5.0.0
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2