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	1.6877	0	1.1516	0.2408	0.0930	0.2408	0.2408	0.2408
No log	1	178	1.4572	0.0078	1.3273	0.4119	0.2730	0.4126	0.4126	0.4112
No log	2	356	1.3424	0.0156	1.2503	0.4624	0.2968	0.4631	0.4631	0.4616
No log	3	534	1.0930	0.0312	1.2713	0.6328	0.5020	0.6335	0.6328	0.6328
No log	4	712	0.8348	0.0625	1.5452	0.6875	0.5035	0.6882	0.6875	0.6875
No log	5	890	0.7604	0.125	1.8696	0.7081	0.5430	0.7088	0.7088	0.7088
0.0579	6	1068	0.6835	0.25	2.6009	0.7195	0.5746	0.7202	0.7195	0.7195
0.6188	7	1246	0.6388	0.5	4.0470	0.7479	0.7277	0.7493	0.7479	0.7479
0.5303	8.0	1424	0.5805	1.0	7.1521	0.7741	0.7829	0.7741	0.7749	0.7741
0.4377	9.0	1602	0.5852	1.0	6.9961	0.7685	0.8004	0.7692	0.7692	0.7692
0.3168	10.0	1780	0.7057	1.0	6.9122	0.7564	0.7953	0.7571	0.7564	0.7571
0.2304	11.0	1958	0.7780	1.0	6.9348	0.7685	0.8075	0.7685	0.7685	0.7685
0.1476	12.0	2136	0.8697	1.0	6.9310	0.7614	0.7976	0.7614	0.7617	0.7614

contemmcm/764e9c16bd5e36e8d38a1d3a71d4f337

764e9c16bd5e36e8d38a1d3a71d4f337