learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rougel	Rougelsum
No log	0	0	3.8357	0	12.0436	0.5990	0.4183	0.5993	0.5987	0.5987
No log	1	294	54.8148	0.0078	12.2489	0.3787	0.2747	0.3787	0.3793	0.3790
No log	2	588	2.6549	0.0156	16.8681	0.6213	0.3832	0.6213	0.6207	0.6210
No log	3	882	2.6569	0.0312	21.3233	0.6213	0.3832	0.6213	0.6207	0.6210
0.3104	4	1176	2.6704	0.0625	28.6613	0.6213	0.3832	0.6213	0.6207	0.6210
0.2261	5	1470	2.6547	0.125	32.9374	0.6213	0.3832	0.6213	0.6207	0.6210
0.3905	6	1764	2.6726	0.25	49.8449	0.6213	0.3832	0.6213	0.6207	0.6210
7.3579	7	2058	45.1944	0.5	73.3825	0.6213	0.3832	0.6213	0.6207	0.6210
2.6565	8.0	2352	2.6757	1.0	135.0485	0.6213	0.3832	0.6213	0.6207	0.6210
2.7641	9.0	2646	2.6898	1.0	128.4545	0.6213	0.3832	0.6213	0.6207	0.6210

contemmcm/399db4019217f37aa91f9ac055fdb8a5

399db4019217f37aa91f9ac055fdb8a5