learning_rate: 5e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 7
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Meteor	Bertscore	Gen Len
3.8387	1.0	625	3.2061	0.1833	0.0287	0.1445	0.1445	0.1098	0.1257	19.8657
3.297	2.0	1250	2.9853	0.2064	0.0379	0.1618	0.1618	0.1256	0.154	19.4563
3.1871	3.0	1875	2.9210	0.2191	0.0412	0.1714	0.1714	0.1341	0.1731	19.3843
3.1439	4.0	2500	2.8890	0.2275	0.0448	0.1772	0.1772	0.1402	0.1815	19.4417
3.1128	5.0	3125	2.8696	0.2324	0.0461	0.1809	0.1809	0.1437	0.1873	19.49
3.0986	6.0	3750	2.8598	0.2353	0.0469	0.1828	0.1829	0.146	0.1909	19.5097
3.0899	7.0	4375	2.8569	0.2359	0.0473	0.1831	0.1832	0.1465	0.192	19.516

ace-aravind/xsum-summarization-t5-small

xsum-summarization-t5-small