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	0.7234	0	14.0293	0.3860	0.3075	0.3862	0.3860	0.3862
0.578	1	11370	0.4660	0.0078	18.0289	0.7744	0.7598	0.7744	0.7744	0.7743
0.4441	2	22740	0.4300	0.0156	19.3506	0.7981	0.7787	0.7980	0.7980	0.7981
0.4302	3	34110	0.4161	0.0312	24.6922	0.8020	0.7746	0.8020	0.8020	0.8020
0.372	4	45480	0.3825	0.0625	36.2419	0.8296	0.8149	0.8295	0.8295	0.8297
0.3646	5	56850	0.3344	0.125	58.1879	0.8482	0.8374	0.8483	0.8481	0.8483
0.3284	6	68220	0.3172	0.25	103.0408	0.8592	0.8508	0.8591	0.8592	0.8592
0.2833	7	79590	0.2920	0.5	193.8019	0.8702	0.8635	0.8702	0.8702	0.8701
0.2889	8.0	90960	0.2779	1.0	372.6897	0.8778	0.8673	0.8778	0.8778	0.8778
0.242	9.0	102330	0.2661	1.0	369.8296	0.8847	0.8782	0.8846	0.8847	0.8848
0.2001	10.0	113700	0.2843	1.0	369.6368	0.8890	0.8808	0.8889	0.8891	0.8891
0.1826	11.0	125070	0.2967	1.0	377.0188	0.8941	0.8872	0.8942	0.8941	0.8941
0.1554	12.0	136440	0.2850	1.0	372.0233	0.8962	0.8889	0.8962	0.8963	0.8962
0.1705	13.0	147810	0.2798	1.0	372.7546	0.8976	0.8905	0.8976	0.8976	0.8976

contemmcm/f06174b8b83d892cad19bfd9c4064d83

f06174b8b83d892cad19bfd9c4064d83