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	1.6847	0	1.5042	0.2273	0.0883	0.2280	0.2280	0.2273
No log	1	178	1.4744	0.0078	2.5043	0.3430	0.1799	0.3438	0.3438	0.3430
No log	2	356	1.3236	0.0156	1.7831	0.4979	0.3396	0.4986	0.4986	0.4979
No log	3	534	1.1315	0.0312	1.8992	0.5114	0.3249	0.5114	0.5121	0.5114
No log	4	712	1.0243	0.0625	2.3969	0.6378	0.4864	0.6392	0.6385	0.6378
No log	5	890	0.8653	0.125	3.1190	0.6570	0.4593	0.6577	0.6577	0.6570
0.0671	6	1068	0.9167	0.25	4.5123	0.6776	0.5398	0.6783	0.6783	0.6776
0.7706	7	1246	0.7597	0.5	7.5424	0.7159	0.5701	0.7166	0.7159	0.7166
0.6373	8.0	1424	0.6951	1.0	13.6232	0.7259	0.7371	0.7266	0.7266	0.7266
0.603	9.0	1602	0.5889	1.0	13.3509	0.7699	0.8055	0.7706	0.7706	0.7706
0.5294	10.0	1780	0.6513	1.0	13.4181	0.7578	0.7974	0.7578	0.7578	0.7585
0.4812	11.0	1958	0.6771	1.0	13.6171	0.7479	0.7803	0.7479	0.7472	0.7479
0.3728	12.0	2136	0.6993	1.0	13.4518	0.7493	0.7976	0.7493	0.7493	0.75
0.3305	13.0	2314	0.7312	1.0	13.5041	0.7571	0.7977	0.7578	0.7578	0.7571

contemmcm/dc22db767834880b27c3b7580d7f0e11

dc22db767834880b27c3b7580d7f0e11