learning_rate: 5.6e-05
train_batch_size: 8
eval_batch_size: 8
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: 4

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.5613	0.499	499	2.5247	42.9693	23.0702	38.0214	38.0551	15.1225
2.7006	0.998	998	2.3682	43.4559	23.4682	38.3135	38.3676	15.0435
2.0314	1.4970	1497	2.3936	43.6633	23.9315	38.625	38.6834	15.5975
1.982	1.996	1996	2.3585	43.9906	23.635	38.656	38.6946	16.5285
1.6361	2.495	2495	2.4054	44.3992	23.9348	39.1448	39.2071	16.0925
1.6261	2.9940	2994	2.3747	44.0552	23.9472	38.9413	38.9995	16.045
1.3756	3.493	3493	2.4233	44.5154	24.2567	39.1726	39.2081	16.366
1.3683	3.992	3992	2.4261	44.6882	24.3496	39.2746	39.3072	16.271

Mug3n24/bart-base-finetune-finetuned-research-papers-XX

bart-base-finetune-finetuned-research-papers-XX