learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
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
lr_scheduler_warmup_ratio: 0.06
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.4337	3.4	10	2.0532	0.2298	0.0574	0.1607	0.1608
1.1324	6.8	20	1.9706	0.3288	0.1234	0.2566	0.2569
0.6287	10.0	30	2.1180	0.3394	0.1291	0.2651	0.2653
0.3201	13.4	40	2.2383	0.3432	0.1293	0.2663	0.2663
0.1944	16.8	50	2.3291	0.3491	0.1324	0.2707	0.2705
0.1571	20.0	60	2.3595	0.3486	0.1302	0.2693	0.2693

taiypeo/bart-large-xsum-rouge-3-loss-differentiable-10-cnt-supervised

bart-large-xsum-rouge-3-loss-differentiable-10-cnt-supervised