learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
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: 1

Training Loss	Epoch	Step	Validation Loss
0.0856	0.0714	50	0.0800
0.0673	0.1428	100	0.0686
0.0722	0.2142	150	0.0625
0.0506	0.2856	200	0.0613
0.0480	0.3570	250	0.0549
0.0426	0.4283	300	0.0536
0.0520	0.4997	350	0.0523
0.0446	0.5711	400	0.0502
0.0586	0.6425	450	0.0477
0.0502	0.7139	500	0.0477
0.0474	0.7853	550	0.0475
0.0456	0.8567	600	0.0471
0.0491	0.9281	650	0.0466
0.0563	0.9995	700	0.0466
0.0563	1.0	701	0.0466

cs-552-2026-MMRF/safety_model

2xwildguard