results

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

• Loss: 1.6431

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: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.534	1.0	1408	2.2057
2.3375	2.0	2816	2.0560
2.1977	3.0	4224	1.9526
2.1173	4.0	5632	1.8788
2.0417	5.0	7040	1.8221
1.9958	6.0	8448	1.7791
1.959	7.0	9856	1.7447
1.9224	8.0	11264	1.7189
1.8799	9.0	12672	1.6962
1.8579	10.0	14080	1.6794
1.8582	11.0	15488	1.6661
1.8309	12.0	16896	1.6547
1.8176	13.0	18304	1.6483
1.8193	14.0	19712	1.6439
1.8114	15.0	21120	1.6431

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1