my_awesome_billsum_model

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

Model description

More information needed

More information needed

More information needed

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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	133	5.5755	0.2491	0.0692	0.165	0.1651	16.6189
No log	2.0	266	5.4112	0.3096	0.0881	0.2061	0.206	17.0981
No log	3.0	399	5.3456	0.3484	0.1	0.2263	0.2265	17.8396
5.6693	4.0	532	5.2749	0.355	0.1081	0.2322	0.2323	17.7811
5.6693	5.0	665	5.1996	0.3662	0.1102	0.2374	0.2376	18.2943
5.6693	6.0	798	5.7658	0.3352	0.097	0.2194	0.2196	19.6679
5.6693	7.0	931	6.0595	0.2208	0.062	0.1555	0.1555	19.7245
5.8498	8.0	1064	6.0556	0.2137	0.0603	0.1514	0.1516	19.7226
5.8498	9.0	1197	6.0549	0.2087	0.059	0.1481	0.1482	19.734
5.8498	10.0	1330	6.0550	0.2087	0.0591	0.1479	0.1479	19.734
5.8498	11.0	1463	6.0550	0.2087	0.059	0.1478	0.1479	19.734
6.5293	12.0	1596	6.0550	0.2088	0.059	0.1479	0.148	19.7264
6.5293	13.0	1729	6.0549	0.2089	0.0591	0.1479	0.148	19.734
6.5293	14.0	1862	6.0548	0.2088	0.0591	0.1479	0.148	19.734
6.5293	15.0	1995	6.0546	0.2092	0.0592	0.148	0.148	19.734
6.5241	16.0	2128	6.0545	0.2087	0.059	0.1478	0.1479	19.734
6.5241	17.0	2261	6.0544	0.2088	0.0591	0.1479	0.148	19.734
6.5241	18.0	2394	6.0543	0.2075	0.0585	0.1472	0.1473	19.7264
6.5259	19.0	2527	6.0543	0.2075	0.0585	0.1472	0.1473	19.7264
6.5259	20.0	2660	6.0543	0.2075	0.0585	0.1472	0.1473	19.7264