flan-t5-base-text_answering_T5

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: 0.3074
• Accuracy: 0.7464
• Precision: 0.7462
• Recall: 0.7464
• F1: 0.7462

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-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.3367	1.0	276	0.3063	0.6775	0.6812	0.6775	0.6732
0.3135	2.0	552	0.2994	0.6902	0.6952	0.6902	0.6856
0.2987	3.0	828	0.2941	0.7228	0.7227	0.7228	0.7224
0.2829	4.0	1104	0.2971	0.7391	0.739	0.7391	0.739
0.2853	5.0	1380	0.2997	0.7391	0.7391	0.7391	0.7391
0.2781	6.0	1656	0.3120	0.7373	0.7372	0.7373	0.737
0.2751	7.0	1932	0.3100	0.7464	0.7463	0.7464	0.7463
0.2735	8.0	2208	0.3073	0.7464	0.7463	0.7464	0.7463
0.2763	9.0	2484	0.3055	0.7446	0.7444	0.7446	0.7444
0.269	10.0	2760	0.3069	0.7446	0.7444	0.7446	0.7443
0.2674	11.0	3036	0.3077	0.7446	0.7444	0.7446	0.7443
0.2608	12.0	3312	0.3074	0.7464	0.7462	0.7464	0.7462

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1