End of training
75c0d58
verified
-
attn_projector=orthogonal, attn_weight=5, extra_grad_stats=False, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
End of training
-
attn_projector=orthogonal, attn_weight=5, extra_grad_stats=True, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0
Training in progress, step 2475
