| { | |
| "dataset": { | |
| "repo_id": "bridge_orig_1.0.0_lerobot", | |
| "root": null, | |
| "episodes": null, | |
| "image_transforms": { | |
| "enable": true, | |
| "max_num_transforms": 3, | |
| "random_order": false, | |
| "tfs": { | |
| "brightness": { | |
| "weight": 1.0, | |
| "type": "ColorJitter", | |
| "kwargs": { | |
| "brightness": [ | |
| 0.8, | |
| 1.2 | |
| ] | |
| } | |
| }, | |
| "contrast": { | |
| "weight": 1.0, | |
| "type": "ColorJitter", | |
| "kwargs": { | |
| "contrast": [ | |
| 0.8, | |
| 1.2 | |
| ] | |
| } | |
| }, | |
| "saturation": { | |
| "weight": 1.0, | |
| "type": "ColorJitter", | |
| "kwargs": { | |
| "saturation": [ | |
| 0.5, | |
| 1.5 | |
| ] | |
| } | |
| }, | |
| "hue": { | |
| "weight": 1.0, | |
| "type": "ColorJitter", | |
| "kwargs": { | |
| "hue": [ | |
| -0.05, | |
| 0.05 | |
| ] | |
| } | |
| }, | |
| "sharpness": { | |
| "weight": 1.0, | |
| "type": "SharpnessJitter", | |
| "kwargs": { | |
| "sharpness": [ | |
| 0.5, | |
| 1.5 | |
| ] | |
| } | |
| }, | |
| "crop_resize": { | |
| "weight": 1.0, | |
| "type": "RandomResizedCrop", | |
| "kwargs": { | |
| "size": [ | |
| 256, | |
| 256 | |
| ], | |
| "scale": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "ratio": [ | |
| 1.0, | |
| 1.0 | |
| ] | |
| } | |
| }, | |
| "rotate": { | |
| "weight": 1.0, | |
| "type": "RadomRotate", | |
| "kwargs": { | |
| "degrees": [ | |
| -5, | |
| 5 | |
| ] | |
| } | |
| } | |
| } | |
| }, | |
| "revision": null, | |
| "use_imagenet_stats": true, | |
| "video_backend": "torchcodec", | |
| "wrist_transforms": { | |
| "enable": true, | |
| "max_num_transforms": 3, | |
| "random_order": false, | |
| "tfs": { | |
| "brightness": { | |
| "weight": 1.0, | |
| "type": "ColorJitter", | |
| "kwargs": { | |
| "brightness": [ | |
| 0.8, | |
| 1.2 | |
| ] | |
| } | |
| }, | |
| "contrast": { | |
| "weight": 1.0, | |
| "type": "ColorJitter", | |
| "kwargs": { | |
| "contrast": [ | |
| 0.8, | |
| 1.2 | |
| ] | |
| } | |
| }, | |
| "saturation": { | |
| "weight": 1.0, | |
| "type": "ColorJitter", | |
| "kwargs": { | |
| "saturation": [ | |
| 0.5, | |
| 1.5 | |
| ] | |
| } | |
| }, | |
| "hue": { | |
| "weight": 1.0, | |
| "type": "ColorJitter", | |
| "kwargs": { | |
| "hue": [ | |
| -0.05, | |
| 0.05 | |
| ] | |
| } | |
| }, | |
| "sharpness": { | |
| "weight": 1.0, | |
| "type": "SharpnessJitter", | |
| "kwargs": { | |
| "sharpness": [ | |
| 0.5, | |
| 1.5 | |
| ] | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "env": null, | |
| "policy": { | |
| "type": "pi", | |
| "n_obs_steps": 1, | |
| "normalization_mapping": { | |
| "VISUAL": "IDENTITY", | |
| "STATE": "MEAN_STD", | |
| "ACTION": "MEAN_STD" | |
| }, | |
| "input_features": { | |
| "observation.images.image_0": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 256, | |
| 256 | |
| ] | |
| }, | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 8 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 7 | |
| ] | |
| } | |
| }, | |
| "device": "cpu", | |
| "use_amp": false, | |
| "chunk_size": 4, | |
| "n_action_steps": 4, | |
| "max_state_dim": 32, | |
| "max_action_dim": 32, | |
| "resize_imgs_with_padding": [ | |
| 224, | |
| 224 | |
| ], | |
| "empty_cameras": 0, | |
| "adapt_to_pi_aloha": false, | |
| "use_delta_joint_actions_aloha": false, | |
| "tokenizer_max_length": 48, | |
| "proj_width": 1024, | |
| "num_steps": 10, | |
| "use_cache": true, | |
| "attention_implementation": "eager", | |
| "freeze_vision_encoder": true, | |
| "train_expert_only": false, | |
| "train_state_proj": true, | |
| "optimizer_lr": 5e-05, | |
| "optimizer_betas": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "optimizer_eps": 1e-08, | |
| "optimizer_weight_decay": 1e-10, | |
| "scheduler_warmup_steps": 1000, | |
| "scheduler_decay_steps": 1600000, | |
| "scheduler_decay_lr": 2.5e-06, | |
| "paligemma_config": { | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "hidden_size": 2048, | |
| "ignore_index": -100, | |
| "image_token_index": 257152, | |
| "model_type": "paligemma", | |
| "pad_token_id": 0, | |
| "projection_dim": 2048, | |
| "text_config": { | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2048, | |
| "intermediate_size": 16384, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_image_tokens": 256, | |
| "num_key_value_heads": 1, | |
| "torch_dtype": "float32", | |
| "vocab_size": 257152 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.1", | |
| "vision_config": { | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 256, | |
| "patch_size": 14, | |
| "projection_dim": 2048, | |
| "projector_hidden_act": "gelu_fast", | |
| "vision_use_head": false | |
| }, | |
| "vocab_size": 257152 | |
| }, | |
| "gemma_expert_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "head_dim": 256, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.1", | |
| "use_cache": true, | |
| "vocab_size": 257152 | |
| } | |
| }, | |
| "output_dir": "outputs/pi0/2025-04-24/20-09-31_pi0_bridge_orig_1.0.0_lerobot_ck4_gpu8_lr5e-5_bs32_s1600k", | |
| "job_name": "pi0_bridge_orig_1.0.0_lerobot_ck4_gpu8_lr5e-5_bs32_s1600k", | |
| "resume": false, | |
| "seed": 42, | |
| "num_workers": 4, | |
| "batch_size": 32, | |
| "steps": 1600000, | |
| "eval_freq": 20000, | |
| "log_freq": 100, | |
| "save_checkpoint": true, | |
| "save_freq": 20000, | |
| "use_policy_training_preset": true, | |
| "optimizer": { | |
| "type": "adamw", | |
| "lr": 5e-05, | |
| "weight_decay": 1e-10, | |
| "grad_clip_norm": 10.0, | |
| "betas": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "eps": 1e-08 | |
| }, | |
| "scheduler": { | |
| "type": "cosine_decay_with_warmup", | |
| "num_warmup_steps": 1000, | |
| "num_decay_steps": 1600000, | |
| "peak_lr": 5e-05, | |
| "decay_lr": 2.5e-06 | |
| }, | |
| "eval": { | |
| "n_episodes": 50, | |
| "batch_size": 50, | |
| "use_async_envs": false | |
| }, | |
| "wandb": { | |
| "enable": true, | |
| "disable_artifact": true, | |
| "project": "ss2-o1", | |
| "entity": "qudelin", | |
| "notes": null, | |
| "run_id": null, | |
| "mode": null | |
| }, | |
| "policy_optimizer_lr": 5e-05, | |
| "checkpoints_total_limit": 0, | |
| "chunk_size": 4, | |
| "output_base": "pi0", | |
| "pretrained_paligemma_path": null, | |
| "freeze_vision_encoder": true, | |
| "attention_implementation": "eager", | |
| "empty_cameras": 0 | |
| } |