my_awesome_billsum_model

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

• Loss: 2.5044
• Rouge1: 0.3792
• Rouge2: 0.1352
• Rougel: 0.2397
• Rougelsum: 0.2396
• Gen Len: 120.504

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
No log	1.0	62	2.7945	0.3671	0.1263	0.2355	0.2353	108.9919
No log	2.0	124	2.5845	0.3779	0.1309	0.2372	0.2371	117.7258
No log	3.0	186	2.5210	0.3797	0.1369	0.2398	0.2396	120.3508
No log	4.0	248	2.5044	0.3792	0.1352	0.2397	0.2396	120.504

Framework versions

• Transformers 5.18.0
• Pytorch 2.11.0+cu130
• Datasets 4.8.5
• Tokenizers 0.23.2