my_awesome_billsum_model_12

This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6167
• Rouge1: 0.9635
• Rouge2: 0.8396
• Rougel: 0.8914
• Rougelsum: 0.8919
• Gen Len: 5.1042

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: 16
• eval_batch_size: 16
• 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	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	12	2.0578	0.4077	0.2938	0.3916	0.3923	17.6458
No log	2.0	24	1.5690	0.4152	0.2977	0.4017	0.4017	17.3125
No log	3.0	36	1.1237	0.47	0.3505	0.4472	0.4469	15.4792
No log	4.0	48	0.8172	0.7763	0.6588	0.7333	0.7354	8.8542
No log	5.0	60	0.6854	0.9174	0.7868	0.8455	0.8454	6.0833
No log	6.0	72	0.6514	0.9635	0.8396	0.8914	0.8919	5.1042
No log	7.0	84	0.6364	0.9635	0.8396	0.8914	0.8919	5.1042
No log	8.0	96	0.6261	0.9635	0.8396	0.8914	0.8919	5.1042
No log	9.0	108	0.6202	0.9635	0.8396	0.8914	0.8919	5.1042
No log	10.0	120	0.6167	0.9635	0.8396	0.8914	0.8919	5.1042

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1