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	0.7010	0	4.0038	0.4824	0.4155	0.4822	0.4825	0.4824
No log	1	3273	0.6997	0.0078	5.9706	0.5149	0.4646	0.5149	0.5143	0.5149
0.0113	2	6546	0.7108	0.0156	7.4290	0.5057	0.3359	0.5053	0.5057	0.5056
0.7127	3	9819	0.7127	0.0312	10.5526	0.4943	0.3308	0.4947	0.4943	0.4944
0.7007	4	13092	0.6932	0.0625	17.0746	0.5057	0.3359	0.5053	0.5057	0.5056
0.6991	5	16365	0.7012	0.125	29.8681	0.5057	0.3359	0.5053	0.5057	0.5056
0.6957	6	19638	0.6936	0.25	55.5806	0.4943	0.3308	0.4947	0.4943	0.4944
0.6962	7	22911	0.6960	0.5	108.9770	0.4943	0.3308	0.4947	0.4943	0.4944
0.6935	8.0	26184	0.6934	1.0	215.7032	0.4943	0.3308	0.4947	0.4943	0.4944

contemmcm/64f1aeb3dcfd40ad2c7298f590919c10

64f1aeb3dcfd40ad2c7298f590919c10