learning_rate: 3e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	60	1.9165	39.1847	20.771	35.3702	35.7857	18.3148
No log	2.0	120	1.8308	40.7152	21.7447	36.6752	37.1989	18.6296
No log	3.0	180	1.7769	40.7843	22.2581	36.3515	36.9362	18.7407
No log	4.0	240	1.7355	39.8099	21.8843	35.5563	36.0749	18.9444
No log	5.0	300	1.6971	41.3752	23.8678	36.8792	37.3489	18.7037
No log	6.0	360	1.6690	41.2441	23.4026	36.4348	37.067	18.9074
No log	7.0	420	1.6327	40.9744	23.6697	36.3964	36.9935	18.9074
No log	8.0	480	1.6214	41.3833	23.796	36.7591	37.4926	18.9815
1.7877	9.0	540	1.5955	40.9415	23.3711	36.2089	36.8672	18.7407
1.7877	10.0	600	1.5821	41.1759	23.362	36.5208	37.2207	18.7963
1.7877	11.0	660	1.5687	41.5582	23.575	36.4706	37.1927	18.9074
1.7877	12.0	720	1.5685	41.5293	23.2829	36.7273	37.468	18.8148
1.7877	13.0	780	1.5503	40.6781	21.9403	35.725	36.3384	18.9444
1.7877	14.0	840	1.5454	40.4918	22.3652	35.7063	36.3163	18.9815
1.7877	15.0	900	1.5364	41.6247	23.5637	36.9036	37.4561	18.8704
1.7877	16.0	960	1.5344	41.1763	23.2285	36.2463	36.6802	18.8704
1.3826	17.0	1020	1.5303	40.4807	21.8633	35.5338	36.2185	18.8519
1.3826	18.0	1080	1.5288	40.8854	22.6821	36.0638	36.8444	18.7778
1.3826	19.0	1140	1.5306	40.739	22.393	35.9189	36.4907	18.9815
1.3826	20.0	1200	1.5291	40.739	22.393	35.9189	36.4907	18.9815

imwizard/flanT5Base-riksIdentification-trained

flanT5Base-riksIdentification-trained