learning_rate: 0.0003
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use 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: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
1.8753	0.6061	200	0.9023
1.7196	1.2121	400	0.8306
1.6462	1.8182	600	0.8004
1.5884	2.4242	800	0.7781
1.5744	3.0303	1000	0.7645
1.5188	3.6364	1200	0.7548
1.442	4.2424	1400	0.7489
1.4986	4.8485	1600	0.7440

treysarkar/phi2derma

phi2derma