learning_rate: 0.0001
train_batch_size: 128
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 512
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
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
No log	0	0	3.8917
2.7225	0.6483	100	2.6803
1.6189	1.2917	200	1.5324
0.9914	1.9400	300	0.9894
0.8278	2.5835	400	0.9311
0.7646	3.2269	500	0.9649
0.7273	3.8752	600	0.9046
0.706	4.5186	700	0.8855
0.6927	5.1621	800	0.8959
0.6813	5.8104	900	0.8868
0.6719	6.4538	1000	0.8772
0.6683	7.0972	1100	0.8766
0.6584	7.7455	1200	0.8761
0.6592	8.3890	1300	0.8714
0.6567	9.0324	1400	0.8729
0.6512	9.6807	1500	0.8738