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	3.0343	0	1.2218	0.5625	0.5333	0.5625	0.5625	0.5625
No log	1	19	10.9727	0.0078	1.2521	0.5625	0.36	0.5625	0.5625	0.5625
No log	2	38	4.2301	0.0156	4.2410	0.5312	0.3469	0.5312	0.5312	0.5312
No log	3	57	6.4789	0.0312	6.2611	0.4375	0.3043	0.4375	0.4375	0.4375
No log	4	76	4.5024	0.0625	7.8373	0.5	0.3592	0.5	0.5	0.5
No log	5	95	5.1913	0.125	8.5188	0.4062	0.2889	0.4062	0.4062	0.4062
0.5535	6	114	2.8407	0.25	10.4607	0.5156	0.3402	0.5156	0.5156	0.5156
0.5535	7	133	3.1844	0.5	11.2334	0.4375	0.3043	0.4375	0.4375	0.4375
2.3392	8.0	152	2.8088	1.0	17.3577	0.4375	0.3263	0.4375	0.4375	0.4375
2.3392	9.0	171	2.7628	1.0	18.0285	0.5625	0.36	0.5625	0.5625	0.5625
2.3392	10.0	190	2.8635	1.0	17.8232	0.5625	0.36	0.5625	0.5625	0.5625
2.9673	11.0	209	2.8484	1.0	17.3111	0.4062	0.3420	0.4062	0.4062	0.4062
2.9673	12.0	228	2.7981	1.0	17.6545	0.5625	0.36	0.5625	0.5625	0.5625
2.9673	13.0	247	2.7714	1.0	17.8993	0.5625	0.36	0.5625	0.5625	0.5625

contemmcm/03b3c6b33980db7f3d9f996e2e2aa880

03b3c6b33980db7f3d9f996e2e2aa880