flan-t5-base-openie

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: 0.2502

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: 0.0003
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.6992	0.2216	500	0.5775
0.4807	0.4433	1000	0.4035
0.4021	0.6649	1500	0.3261
0.3681	0.8865	2000	0.2879
0.3256	1.1082	2500	0.2747
0.2796	1.3298	3000	0.2665
0.2769	1.5514	3500	0.2552
0.2709	1.7730	4000	0.2607
0.267	1.9947	4500	0.2494
0.2065	2.2163	5000	0.2641
0.1988	2.4379	5500	0.2551
0.2031	2.6596	6000	0.2519
0.1973	2.8812	6500	0.2502

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.4.2
• Tokenizers 0.22.1