learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 64
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 32
total_eval_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 354
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel
2.5418	1.0	710	2.2551	0.4149	0.2004	0.3759
2.4178	2.0	1420	2.1667	0.4213	0.2039	0.3811
2.2870	3.0	2130	2.1339	0.4203	0.205	0.3811
2.2201	4.0	2840	2.1188	0.4253	0.2087	0.3853
2.1824	5.0	3550	2.1135	0.4234	0.2083	0.3836

narwhalsilent/satire-sft-t5_training_full_vanilla

satire-sft-t5_training_full_vanilla