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	33.2134	0	114.3879	0.0868	0.0608	0.0868	0.0868	0.0868
1.3265	1	17500	1.6095	0.0078	139.0626	0.9552	0.9557	0.9552	0.9553	0.9552
0.8681	2	35000	0.6767	0.0156	161.2543	0.9718	0.9719	0.9718	0.9718	0.9718
0.4877	3	52500	0.5717	0.0312	206.2159	0.9737	0.9738	0.9738	0.9737	0.9738
0.4475	4	70000	0.4402	0.0625	295.2759	0.9789	0.9790	0.9789	0.9789	0.9789
0.4207	5	87500	0.3562	0.125	477.2790	0.9839	0.9838	0.9839	0.9839	0.9839
0.3197	6	105000	0.3202	0.25	827.6861	0.9859	0.9859	0.9859	0.9859	0.9859
0.0018	7	122500	0.2840	0.5	1547.7098	0.9862	0.9862	0.9862	0.9862	0.9863
0.1548	8.0	140000	0.2411	1.0	2981.0301	0.9892	0.9892	0.9892	0.9892	0.9892
0.0722	9.0	157500	0.2792	1.0	2929.5555	0.9875	0.9875	0.9875	0.9875	0.9875
0.1158	10.0	175000	0.3076	1.0	2990.6640	0.9872	0.9872	0.9872	0.9872	0.9872
0.0746	11.0	192500	0.3949	1.0	3010.3513	0.9876	0.9876	0.9876	0.9876	0.9876
0.0389	12.0	210000	0.3947	1.0	2995.4803	0.9877	0.9878	0.9878	0.9877	0.9878

contemmcm/994afc0f90d06ff9ca02ed928e70e534

994afc0f90d06ff9ca02ed928e70e534