results

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: 2.2762

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use 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: 6

Training results

Training Loss	Epoch	Step	Validation Loss
2.4645	0.3559	100	2.3210
2.4822	0.7117	200	2.3128
2.4995	1.0676	300	2.3071
2.6056	1.4235	400	2.3002
2.4679	1.7794	500	2.2958
2.5161	2.1352	600	2.2915
2.4266	2.4911	700	2.2890
2.5262	2.8470	800	2.2863
2.503	3.2028	900	2.2839
2.4655	3.5587	1000	2.2821
2.4776	3.9146	1100	2.2803
2.5122	4.2705	1200	2.2788
2.4529	4.6263	1300	2.2777
2.4557	4.9822	1400	2.2768
2.4035	5.3381	1500	2.2763
2.3816	5.6940	1600	2.2762

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 2.16.0
• Tokenizers 0.20.3