{ "output_dir": "exps", "exp_name": "sit-xl-1-dinov2-b-enc8-ldm-only-e2e-vavae-0.5-4m", "logging_dir": "logs", "report_to": "wandb", "sampling_steps": 10000, "resume_step": 0, "continue_train_exp_dir": null, "wandb_history_path": null, "model": "SiT-XL/1", "num_classes": 1000, "encoder_depth": 8, "qk_norm": false, "fused_attn": true, "compile": true, "data_dir": "data", "resolution": 256, "batch_size": 256, "allow_tf32": true, "mixed_precision": "fp16", "epochs": 1400, "max_train_steps": 4000000, "checkpointing_steps": 50000, "gradient_accumulation_steps": 1, "learning_rate": 0.0001, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_weight_decay": 0.0, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "seed": 0, "num_workers": 4, "path_type": "linear", "prediction": "v", "cfg_prob": 0.1, "enc_type": "dinov2-vit-b", "proj_coeff": 0.5, "weighting": "uniform", "vae": "f16d32", "vae_latents_name": "e2e-vavae-400k", "vae_ckpt": "pretrained/e2e-vavae-400k/e2e-vavae-400k.pt" }