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	0.7198	0	0.6321	0.4062	0.2889	0.4062	0.4062	0.4062
No log	1	19	0.7231	0.0078	1.2331	0.5469	0.3828	0.5469	0.5469	0.5469
No log	2	38	0.7711	0.0156	0.7152	0.3906	0.2809	0.3906	0.3906	0.3906
No log	3	57	0.6817	0.0312	0.7655	0.5312	0.3469	0.5312	0.5312	0.5312
No log	4	76	0.6857	0.0625	0.7978	0.5625	0.36	0.5625	0.5625	0.5625
No log	5	95	0.6904	0.125	0.7600	0.5312	0.4386	0.5312	0.5312	0.5312
0.0818	6	114	0.6868	0.25	0.8596	0.5625	0.36	0.5625	0.5625	0.5625
0.0818	7	133	0.7094	0.5	1.0670	0.4844	0.3727	0.4844	0.4844	0.4844

contemmcm/1bb2948ff4112395bf82c9d9a74a8ff7

1bb2948ff4112395bf82c9d9a74a8ff7