name-parser-pseudo-small

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0559
• Accuracy: 0.9783

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use adafactor and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 20000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1055	1.2797	2000	0.0850	0.9694
0.0839	2.5594	4000	0.0713	0.9743
0.0752	3.8390	6000	0.0649	0.9758
0.0698	5.1184	8000	0.0614	0.9767
0.0669	6.3981	10000	0.0592	0.9769
0.0646	7.6778	12000	0.0578	0.9778
0.0634	8.9574	14000	0.0569	0.9779
0.0622	10.2368	16000	0.0563	0.9782
0.062	11.5165	18000	0.0560	0.9783
0.0615	12.7962	20000	0.0559	0.9783

Framework versions

• Transformers 4.52.3
• Pytorch 2.7.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1