tc-huang's picture
Upload policy weights, train config and readme
3328f3c verified
{
"dataset": {
"repo_id": "lerobot/aloha_sim_insertion_human",
"root": null,
"episodes": null,
"image_transforms": {
"enable": false,
"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
]
}
},
"affine": {
"weight": 1.0,
"type": "RandomAffine",
"kwargs": {
"degrees": [
-5.0,
5.0
],
"translate": [
0.05,
0.05
]
}
}
}
},
"revision": null,
"use_imagenet_stats": true,
"video_backend": "torchcodec",
"streaming": false
},
"env": {
"type": "aloha",
"task": "AlohaInsertion-v0",
"fps": 50,
"features": {
"action": {
"type": "ACTION",
"shape": [
14
]
},
"agent_pos": {
"type": "STATE",
"shape": [
14
]
},
"pixels/top": {
"type": "VISUAL",
"shape": [
480,
640,
3
]
}
},
"features_map": {
"action": "action",
"agent_pos": "observation.state",
"top": "observation.image.top",
"pixels/top": "observation.images.top"
},
"max_parallel_tasks": 1,
"disable_env_checker": true,
"episode_length": 400,
"obs_type": "pixels_agent_pos",
"observation_height": 480,
"observation_width": 640,
"render_mode": "rgb_array"
},
"policy": {
"type": "act",
"n_obs_steps": 1,
"input_features": {
"observation.images.top": {
"type": "VISUAL",
"shape": [
3,
480,
640
]
},
"observation.state": {
"type": "STATE",
"shape": [
14
]
}
},
"output_features": {
"action": {
"type": "ACTION",
"shape": [
14
]
}
},
"device": "cuda",
"use_amp": false,
"push_to_hub": true,
"repo_id": "tc-huang/act_aloha_insertion_rtx4090_compiled_test_1",
"private": null,
"tags": null,
"license": null,
"pretrained_path": null,
"chunk_size": 100,
"n_action_steps": 100,
"normalization_mapping": {
"VISUAL": "MEAN_STD",
"STATE": "MEAN_STD",
"ACTION": "MEAN_STD"
},
"vision_backbone": "resnet18",
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
"replace_final_stride_with_dilation": false,
"pre_norm": false,
"dim_model": 512,
"n_heads": 8,
"dim_feedforward": 3200,
"feedforward_activation": "relu",
"n_encoder_layers": 4,
"n_decoder_layers": 1,
"use_vae": true,
"latent_dim": 32,
"n_vae_encoder_layers": 4,
"temporal_ensemble_coeff": null,
"dropout": 0.1,
"kl_weight": 10.0,
"optimizer_lr": 1e-05,
"optimizer_weight_decay": 0.0001,
"optimizer_lr_backbone": 1e-05
},
"output_dir": "outputs/train/act_aloha_insertion_rtx4090_compiled_test_1",
"job_name": "aloha_act",
"resume": false,
"seed": 1000,
"num_workers": 4,
"batch_size": 8,
"steps": 100000,
"eval_freq": 20000,
"log_freq": 200,
"save_checkpoint": true,
"save_freq": 20000,
"use_policy_training_preset": true,
"optimizer": {
"type": "adamw",
"lr": 1e-05,
"weight_decay": 0.0001,
"grad_clip_norm": 10.0,
"betas": [
0.9,
0.999
],
"eps": 1e-08
},
"scheduler": null,
"eval": {
"n_episodes": 50,
"batch_size": 50,
"use_async_envs": false
},
"wandb": {
"enable": true,
"disable_artifact": false,
"project": "lerobot",
"entity": null,
"notes": null,
"run_id": "89bms185",
"mode": null
},
"checkpoint_path": null,
"rename_map": {}
}