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	3.3817	0	8.1722	0.6069	0.4096	0.6069	0.6063	0.6069
No log	1	294	8.0675	0.0078	9.0353	0.6054	0.4070	0.6057	0.6048	0.6051
No log	2	588	12.1118	0.0156	12.3209	0.3906	0.3098	0.3906	0.3909	0.3909
No log	3	882	3.3747	0.0312	15.5404	0.6213	0.3832	0.6213	0.6207	0.6210
0.1918	4	1176	2.8154	0.0625	22.6593	0.6213	0.3832	0.6213	0.6207	0.6210
0.2537	5	1470	2.6533	0.125	27.2402	0.6213	0.3832	0.6213	0.6207	0.6210
0.4038	6	1764	2.6687	0.25	36.7482	0.6213	0.3832	0.6213	0.6207	0.6210
2.8406	7	2058	2.6706	0.5	56.2651	0.6158	0.4532	0.6158	0.6155	0.6158
2.6455	8.0	2352	2.6670	1.0	94.8340	0.5968	0.5664	0.5965	0.5968	0.5965
2.6518	9.0	2646	2.6223	1.0	92.9978	0.6124	0.5852	0.6127	0.6124	0.6121
2.2339	10.0	2940	2.7200	1.0	94.3430	0.5968	0.5759	0.5965	0.5968	0.5965
1.9292	11.0	3234	2.7542	1.0	94.1464	0.6201	0.5887	0.6203	0.6207	0.6195
1.3051	12.0	3528	3.1854	1.0	97.2884	0.6330	0.6001	0.6330	0.6327	0.6324
0.76	13.0	3822	6.3280	1.0	100.4515	0.5794	0.5759	0.5795	0.5794	0.5794

contemmcm/e840358f2d7da6519c50dc7f3975ec30

e840358f2d7da6519c50dc7f3975ec30