pal_team_tfq_generation

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

• Loss: 1.8807
• Rouge1: 0.3793
• Rouge2: 0.1737
• Rougel: 0.3534
• Rougelsum: 0.3535
• Gen Len: 12.7453

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: 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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.4543	1.0	1179	2.0285	0.3608	0.1524	0.3326	0.3326	12.3572
2.2496	2.0	2358	1.9305	0.3706	0.163	0.343	0.3432	12.7278
2.1221	3.0	3537	1.8922	0.3779	0.1725	0.3516	0.3519	12.6859
2.1428	4.0	4716	1.8807	0.3793	0.1737	0.3534	0.3535	12.7453

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0