- attn_norm=None, attn_projector=mlp, attn_weight=25, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=mlp, attn_weight=25, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=mlp, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=mlp, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=None, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0004, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=None, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=None, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=None, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0004, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=mlp, attn_weight=25, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=mlp, attn_weight=25, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=mlp, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=2, warmup_ratio=0
- attn_norm=layernorm, attn_projector=mlp, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=layernorm, attn_projector=mlp, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=mlp, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=2, warmup_ratio=0
- attn_norm=layernorm, attn_projector=mlp, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=layernorm, attn_projector=mlp, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=25, learning_rate=0.0004, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=2, warmup_ratio=0
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0001, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=2, warmup_ratio=0
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0.2
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
- attn_norm=layernorm, attn_projector=orthogonal, attn_weight=5, learning_rate=0.0004, per_device_train_batch_size=4, warmup_ratio=0