learning_rate: 5e-06
train_batch_size: 1
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 64
total_train_batch_size: 64
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
lr_scheduler_warmup_ratio: 0.05
training_steps: 300

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6944	0.08	25	0.6598	0.584
0.7264	0.16	50	0.7157	0.568
0.6153	0.24	75	0.6331	0.642
0.6774	0.32	100	0.5896	0.658
0.5579	0.4	125	0.5685	0.694
0.5981	0.48	150	0.5802	0.702
0.5214	0.56	175	0.6180	0.688
0.5363	0.64	200	0.6699	0.668
0.5309	0.72	225	0.5933	0.694
0.5541	0.8	250	0.5949	0.7
0.5562	0.88	275	0.5978	0.698
0.5539	0.96	300	0.5965	0.7

mehuldamani/orm-hotpot-v2-final-correctness

orm-hotpot-v2-final-correctness