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	0.7221	0	4.0115	0.5048	0.3416	0.5046	0.5046	0.5044
No log	1	3273	0.4753	0.0078	6.2258	0.7871	0.7834	0.7869	0.7868	0.7875
0.0091	2	6546	0.3686	0.0156	8.3708	0.8386	0.8353	0.8386	0.8386	0.8386
0.3873	3	9819	0.2283	0.0312	12.7594	0.9204	0.9204	0.9204	0.9202	0.9204
0.2796	4	13092	0.2260	0.0625	21.0479	0.9175	0.9175	0.9175	0.9176	0.9176
0.2356	5	16365	0.1960	0.125	38.0719	0.9267	0.9266	0.9268	0.9267	0.9267
0.2192	6	19638	0.2178	0.25	70.9393	0.9226	0.9226	0.9230	0.9224	0.9228
0.19	7	22911	0.1886	0.5	153.8451	0.9278	0.9277	0.9278	0.9279	0.9278
0.1771	8.0	26184	0.1892	1.0	308.0908	0.9263	0.9263	0.9263	0.9263	0.9265
0.0974	9.0	29457	0.2689	1.0	307.7917	0.9187	0.9187	0.9187	0.9186	0.9189
0.0794	10.0	32730	0.2984	1.0	303.5691	0.9197	0.9196	0.9199	0.9195	0.9197
0.1164	11.0	36003	0.3848	1.0	307.6984	0.9088	0.9087	0.9088	0.9088	0.9088

contemmcm/848717d1bb6dcb417941b32247e995ac

848717d1bb6dcb417941b32247e995ac