t5-ft-billsum

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

• Loss: 2.2752

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: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	99	2.6250
No log	2.0	198	2.4587
No log	3.0	297	2.3865
No log	4.0	396	2.3431
No log	5.0	495	2.3226
2.7775	6.0	594	2.3019
2.7775	7.0	693	2.2882
2.7775	8.0	792	2.2802
2.7775	9.0	891	2.2764
2.7775	10.0	990	2.2752

Framework versions

• Transformers 4.17.0
• Pytorch 1.6.0
• Datasets 2.0.0
• Tokenizers 0.11.6