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	1.5962	0	2.8454	0.2599	0.1001	0.2599	0.2599	0.2592
No log	1	178	1.5405	0.0078	4.1446	0.3068	0.1548	0.3068	0.3075	0.3061
No log	2	356	1.5057	0.0156	4.8043	0.4318	0.2290	0.4318	0.4325	0.4318
No log	3	534	1.1937	0.0312	6.2565	0.4865	0.3042	0.4865	0.4858	0.4865
No log	4	712	1.0637	0.0625	8.1109	0.6300	0.4908	0.6300	0.6300	0.6307
No log	5	890	0.9300	0.125	11.6363	0.6534	0.4633	0.6541	0.6548	0.6534
0.0685	6	1068	0.7826	0.25	14.8630	0.7031	0.5703	0.7038	0.7031	0.7038
0.7148	7	1246	0.6820	0.5	23.2347	0.7443	0.5830	0.7457	0.7450	0.7443
0.553	8.0	1424	0.6457	1.0	38.9396	0.7578	0.7506	0.7578	0.7578	0.7578
0.4288	9.0	1602	0.6601	1.0	37.2185	0.7713	0.7710	0.7720	0.7720	0.7706
0.2815	10.0	1780	0.7299	1.0	37.8961	0.7507	0.7925	0.7507	0.7507	0.7507
0.1955	11.0	1958	0.9711	1.0	37.6824	0.7692	0.8077	0.7699	0.7692	0.7692
0.1563	12.0	2136	1.1040	1.0	38.2415	0.7443	0.7917	0.7450	0.7443	0.7447

contemmcm/6cb716c2d567ac28cc6c5bd79d88fb88

6cb716c2d567ac28cc6c5bd79d88fb88