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	6.8133	0	3.6008	0.5342	0.4868	0.5342	0.5342	0.5347
No log	1	267	40.5906	0.0078	6.6616	0.6885	0.4078	0.6895	0.6885	0.6885
No log	2	534	6.1571	0.0156	15.8873	0.6885	0.4078	0.6895	0.6885	0.6885
No log	3	801	3.1608	0.0312	28.3234	0.3213	0.2589	0.3203	0.3213	0.3218
No log	4	1068	3.0131	0.0625	43.9222	0.6885	0.4078	0.6895	0.6885	0.6885
0.3567	5	1335	4.1273	0.125	67.4639	0.6240	0.5153	0.6240	0.6240	0.6240
2.9761	6	1602	2.5782	0.25	99.0117	0.6885	0.4078	0.6895	0.6885	0.6885
4.3065	7	1869	3.5554	0.5	143.9138	0.6885	0.4078	0.6895	0.6885	0.6885
2.5352	8.0	2136	3.0619	1.0	244.2800	0.3115	0.2375	0.3105	0.3115	0.3115
2.6081	9.0	2403	2.4858	1.0	242.8371	0.6885	0.4078	0.6895	0.6885	0.6885
2.597	10.0	2670	2.5125	1.0	242.3258	0.6885	0.4078	0.6895	0.6885	0.6885
2.5392	11.0	2937	2.5480	1.0	233.0938	0.6895	0.4111	0.6904	0.6895	0.6895
2.4674	12.0	3204	2.4747	1.0	240.1788	0.6875	0.4074	0.6885	0.6875	0.6875
2.3903	13.0	3471	2.7004	1.0	232.4674	0.6885	0.4078	0.6895	0.6885	0.6885
2.3017	14.0	3738	3.0116	1.0	247.9835	0.6885	0.4078	0.6895	0.6885	0.6885
1.9255	15.0	4005	3.2539	1.0	231.5395	0.6738	0.5067	0.6738	0.6738	0.6748
1.7593	16.0	4272	3.4725	1.0	241.1725	0.6846	0.4152	0.6855	0.6855	0.6846

contemmcm/887c886ce030fd10dce0bcc8b37b5407

887c886ce030fd10dce0bcc8b37b5407