learning_rate: 0.0001
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 2
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
1.103	0.2229	500	1.0905
1.0955	0.4458	1000	1.0865
1.0835	0.6687	1500	1.0834
1.0841	0.8916	2000	1.0814
1.0803	1.1141	2500	1.0802
1.0812	1.3370	3000	1.0788
1.0816	1.5599	3500	1.0781
1.0827	1.7828	4000	1.0784

mzizo4110/Summarization_Continue

Summarization_Continue