learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
3.5827	1.6667	5	2.9897	0.1514	0.0141	0.1163	0.1163
2.9585	3.3333	10	2.5352	0.1528	0.0152	0.1176	0.1176
2.3352	5.0	15	2.3523	0.168	0.0254	0.1304	0.1304
2.0399	6.6667	20	2.2857	0.1881	0.0372	0.1464	0.1464
1.5424	8.3333	25	2.2634	0.2007	0.0439	0.1564	0.1562
1.6209	10.0	30	2.2610	0.2079	0.0485	0.1632	0.1631
1.3376	11.6667	35	2.2648	0.2105	0.0497	0.1652	0.1651
1.2973	13.3333	40	2.2727	0.2133	0.052	0.1675	0.1674
1.1125	15.0	45	2.2819	0.2172	0.0539	0.1707	0.1708
1.129	16.6667	50	2.2901	0.2194	0.0546	0.1727	0.1728
1.1407	18.3333	55	2.2952	0.2217	0.0563	0.174	0.174
1.0031	20.0	60	2.2974	0.2222	0.0562	0.1744	0.1743

taiypeo/bart-base-xsum-sentence-paraphrased-10-cnt-supervised-basic

bart-base-xsum-sentence-paraphrased-10-cnt-supervised-basic