flan-t5-base

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1770

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-05
• train_batch_size: 4
• 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
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.1657	1.0	25	0.1833
0.1693	2.0	50	0.1824
0.1676	3.0	75	0.1814
0.1446	4.0	100	0.1807
0.132	5.0	125	0.1800
0.1373	6.0	150	0.1794
0.139	7.0	175	0.1789
0.1406	8.0	200	0.1785
0.1357	9.0	225	0.1779
0.1529	10.0	250	0.1776
0.1575	11.0	275	0.1773
0.1374	12.0	300	0.1771
0.1485	13.0	325	0.1770
0.176	14.0	350	0.1770
0.1539	15.0	375	0.1770

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0