diff --git a/trash_picking_cache/020000/pretrained_model/config.json b/trash_picking_cache/020000/pretrained_model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..df0d138639f0dee64b5abd0ba7d7606df907e3cd --- /dev/null +++ b/trash_picking_cache/020000/pretrained_model/config.json @@ -0,0 +1,69 @@ +{ + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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 +} \ No newline at end of file diff --git a/trash_picking_cache/020000/pretrained_model/model.safetensors b/trash_picking_cache/020000/pretrained_model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b796b2d0841339894b77ce22ca8196460e8797c --- /dev/null +++ b/trash_picking_cache/020000/pretrained_model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1006116557366e94083cc4bd0318a07993c170f6db5877ed06c67950cd35cd30 +size 206699736 diff --git a/trash_picking_cache/020000/pretrained_model/policy_postprocessor.json b/trash_picking_cache/020000/pretrained_model/policy_postprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..9ccb342474cecbf2bdbb034d27169a351ad96d2a --- /dev/null +++ b/trash_picking_cache/020000/pretrained_model/policy_postprocessor.json @@ -0,0 +1,32 @@ +{ + "name": "policy_postprocessor", + "steps": [ + { + "registry_name": "unnormalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors" + }, + { + "registry_name": "device_processor", + "config": { + "device": "cpu", + "float_dtype": null + } + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors b/trash_picking_cache/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/020000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/020000/pretrained_model/policy_preprocessor.json b/trash_picking_cache/020000/pretrained_model/policy_preprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..7d39638a64caf81ebb4e1d519ef769b085ee1523 --- /dev/null +++ b/trash_picking_cache/020000/pretrained_model/policy_preprocessor.json @@ -0,0 +1,64 @@ +{ + "name": "policy_preprocessor", + "steps": [ + { + "registry_name": "rename_observations_processor", + "config": { + "rename_map": {} + } + }, + { + "registry_name": "to_batch_processor", + "config": {} + }, + { + "registry_name": "device_processor", + "config": { + "device": "cuda", + "float_dtype": null + } + }, + { + "registry_name": "normalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + }, + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors" + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors b/trash_picking_cache/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/020000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/020000/pretrained_model/train_config.json b/trash_picking_cache/020000/pretrained_model/train_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f3f4ec3adb4a8d88d10c17994d18e954fe1b2b68 --- /dev/null +++ b/trash_picking_cache/020000/pretrained_model/train_config.json @@ -0,0 +1,176 @@ +{ + "dataset": { + "repo_id": "siyulw2025/minions001", + "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 + ] + } + } + } + }, + "revision": null, + "use_imagenet_stats": true, + "video_backend": "torchcodec", + "streaming": false + }, + "env": null, + "policy": { + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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/minions001", + "job_name": "trash_picking", + "resume": false, + "seed": 1000, + "num_workers": 4, + "batch_size": 1, + "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": false, + "disable_artifact": false, + "project": "lerobot", + "entity": null, + "notes": null, + "run_id": null, + "mode": null + } +} \ No newline at end of file diff --git a/trash_picking_cache/020000/training_state/optimizer_param_groups.json b/trash_picking_cache/020000/training_state/optimizer_param_groups.json new file mode 100644 index 0000000000000000000000000000000000000000..33506df097b87c64b2aa15765ab89706780c0dc0 --- /dev/null +++ b/trash_picking_cache/020000/training_state/optimizer_param_groups.json @@ -0,0 +1,191 @@ +[ + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 0, + 1, + 2, + 3, + 4, + 5, + 6, + 7, + 8, + 9, + 10, + 11, + 12, + 13, + 14, + 15, + 16, + 17, + 18, + 19, + 20, + 21, + 22, + 23, + 24, + 25, + 26, + 27, + 28, + 29, + 30, + 31, + 32, + 33, + 34, + 35, + 36, + 37, + 38, + 39, + 40, + 41, + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132 + ] + }, + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141, + 142, + 143, + 144, + 145, + 146, + 147, + 148, + 149, + 150, + 151, + 152 + ] + } +] \ No newline at end of file diff --git a/trash_picking_cache/020000/training_state/optimizer_state.safetensors b/trash_picking_cache/020000/training_state/optimizer_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f3c8001ede96c63a976cd1509db2e6d54fae094 --- /dev/null +++ b/trash_picking_cache/020000/training_state/optimizer_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21265bf4b106adf567558c9c9bc43e854d31ef50c6325ca3a1a07932a6f14736 +size 412817652 diff --git a/trash_picking_cache/020000/training_state/rng_state.safetensors b/trash_picking_cache/020000/training_state/rng_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..842b1960c96ab631b13eda0c36b89622f01c6438 --- /dev/null +++ b/trash_picking_cache/020000/training_state/rng_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf718f1bdfb1eeeec7e1e2bd4bf735eac73f90071d1ca60b51728a94a0d9cbb2 +size 15708 diff --git a/trash_picking_cache/020000/training_state/training_step.json b/trash_picking_cache/020000/training_state/training_step.json new file mode 100644 index 0000000000000000000000000000000000000000..dc9bb47026c5d5237ca6fc5dbff6020dd122ea05 --- /dev/null +++ b/trash_picking_cache/020000/training_state/training_step.json @@ -0,0 +1,3 @@ +{ + "step": 20000 +} \ No newline at end of file diff --git a/trash_picking_cache/040000/pretrained_model/config.json b/trash_picking_cache/040000/pretrained_model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..df0d138639f0dee64b5abd0ba7d7606df907e3cd --- /dev/null +++ b/trash_picking_cache/040000/pretrained_model/config.json @@ -0,0 +1,69 @@ +{ + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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 +} \ No newline at end of file diff --git a/trash_picking_cache/040000/pretrained_model/model.safetensors b/trash_picking_cache/040000/pretrained_model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f09dd2833b80f6cbba139bb8d32a5cbd1a6f4efa --- /dev/null +++ b/trash_picking_cache/040000/pretrained_model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5851011d160c7f390495a0f73981ba72d3e239d9b5e4fdd4f48c618f60eaa4f +size 206699736 diff --git a/trash_picking_cache/040000/pretrained_model/policy_postprocessor.json b/trash_picking_cache/040000/pretrained_model/policy_postprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..9ccb342474cecbf2bdbb034d27169a351ad96d2a --- /dev/null +++ b/trash_picking_cache/040000/pretrained_model/policy_postprocessor.json @@ -0,0 +1,32 @@ +{ + "name": "policy_postprocessor", + "steps": [ + { + "registry_name": "unnormalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors" + }, + { + "registry_name": "device_processor", + "config": { + "device": "cpu", + "float_dtype": null + } + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors b/trash_picking_cache/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/040000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/040000/pretrained_model/policy_preprocessor.json b/trash_picking_cache/040000/pretrained_model/policy_preprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..7d39638a64caf81ebb4e1d519ef769b085ee1523 --- /dev/null +++ b/trash_picking_cache/040000/pretrained_model/policy_preprocessor.json @@ -0,0 +1,64 @@ +{ + "name": "policy_preprocessor", + "steps": [ + { + "registry_name": "rename_observations_processor", + "config": { + "rename_map": {} + } + }, + { + "registry_name": "to_batch_processor", + "config": {} + }, + { + "registry_name": "device_processor", + "config": { + "device": "cuda", + "float_dtype": null + } + }, + { + "registry_name": "normalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + }, + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors" + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/040000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors b/trash_picking_cache/040000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/040000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/040000/pretrained_model/train_config.json b/trash_picking_cache/040000/pretrained_model/train_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f3f4ec3adb4a8d88d10c17994d18e954fe1b2b68 --- /dev/null +++ b/trash_picking_cache/040000/pretrained_model/train_config.json @@ -0,0 +1,176 @@ +{ + "dataset": { + "repo_id": "siyulw2025/minions001", + "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 + ] + } + } + } + }, + "revision": null, + "use_imagenet_stats": true, + "video_backend": "torchcodec", + "streaming": false + }, + "env": null, + "policy": { + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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/minions001", + "job_name": "trash_picking", + "resume": false, + "seed": 1000, + "num_workers": 4, + "batch_size": 1, + "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": false, + "disable_artifact": false, + "project": "lerobot", + "entity": null, + "notes": null, + "run_id": null, + "mode": null + } +} \ No newline at end of file diff --git a/trash_picking_cache/040000/training_state/optimizer_param_groups.json b/trash_picking_cache/040000/training_state/optimizer_param_groups.json new file mode 100644 index 0000000000000000000000000000000000000000..33506df097b87c64b2aa15765ab89706780c0dc0 --- /dev/null +++ b/trash_picking_cache/040000/training_state/optimizer_param_groups.json @@ -0,0 +1,191 @@ +[ + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 0, + 1, + 2, + 3, + 4, + 5, + 6, + 7, + 8, + 9, + 10, + 11, + 12, + 13, + 14, + 15, + 16, + 17, + 18, + 19, + 20, + 21, + 22, + 23, + 24, + 25, + 26, + 27, + 28, + 29, + 30, + 31, + 32, + 33, + 34, + 35, + 36, + 37, + 38, + 39, + 40, + 41, + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132 + ] + }, + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141, + 142, + 143, + 144, + 145, + 146, + 147, + 148, + 149, + 150, + 151, + 152 + ] + } +] \ No newline at end of file diff --git a/trash_picking_cache/040000/training_state/optimizer_state.safetensors b/trash_picking_cache/040000/training_state/optimizer_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cdbad6e84a3eac9abb8d5f1f4ac38a9e167e7fa4 --- /dev/null +++ b/trash_picking_cache/040000/training_state/optimizer_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ca84a67caaa3d7ab8baab5148afba9908c594edc7ed0be6f927bccbd34dfb17 +size 412817652 diff --git a/trash_picking_cache/040000/training_state/rng_state.safetensors b/trash_picking_cache/040000/training_state/rng_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2c57ea48e2868cb116edf31b1129219188a7a5b3 --- /dev/null +++ b/trash_picking_cache/040000/training_state/rng_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ea4422d6fc035e71ce8ce213c42aa304232e1f2550326cd04e5fd1283ab23c +size 15708 diff --git a/trash_picking_cache/040000/training_state/training_step.json b/trash_picking_cache/040000/training_state/training_step.json new file mode 100644 index 0000000000000000000000000000000000000000..fe40d8ff4312c7e5a8fba9bcc932a43a1384ba77 --- /dev/null +++ b/trash_picking_cache/040000/training_state/training_step.json @@ -0,0 +1,3 @@ +{ + "step": 40000 +} \ No newline at end of file diff --git a/trash_picking_cache/060000/pretrained_model/config.json b/trash_picking_cache/060000/pretrained_model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..df0d138639f0dee64b5abd0ba7d7606df907e3cd --- /dev/null +++ b/trash_picking_cache/060000/pretrained_model/config.json @@ -0,0 +1,69 @@ +{ + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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 +} \ No newline at end of file diff --git a/trash_picking_cache/060000/pretrained_model/model.safetensors b/trash_picking_cache/060000/pretrained_model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6fdd43170cd08b2ce114708c633f394522d497ff --- /dev/null +++ b/trash_picking_cache/060000/pretrained_model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e1d5aaa05bff51993d9c8dba642e45326cbd64c5d7fdc1e1f779e080c2390d +size 206699736 diff --git a/trash_picking_cache/060000/pretrained_model/policy_postprocessor.json b/trash_picking_cache/060000/pretrained_model/policy_postprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..9ccb342474cecbf2bdbb034d27169a351ad96d2a --- /dev/null +++ b/trash_picking_cache/060000/pretrained_model/policy_postprocessor.json @@ -0,0 +1,32 @@ +{ + "name": "policy_postprocessor", + "steps": [ + { + "registry_name": "unnormalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors" + }, + { + "registry_name": "device_processor", + "config": { + "device": "cpu", + "float_dtype": null + } + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/060000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors b/trash_picking_cache/060000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/060000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/060000/pretrained_model/policy_preprocessor.json b/trash_picking_cache/060000/pretrained_model/policy_preprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..7d39638a64caf81ebb4e1d519ef769b085ee1523 --- /dev/null +++ b/trash_picking_cache/060000/pretrained_model/policy_preprocessor.json @@ -0,0 +1,64 @@ +{ + "name": "policy_preprocessor", + "steps": [ + { + "registry_name": "rename_observations_processor", + "config": { + "rename_map": {} + } + }, + { + "registry_name": "to_batch_processor", + "config": {} + }, + { + "registry_name": "device_processor", + "config": { + "device": "cuda", + "float_dtype": null + } + }, + { + "registry_name": "normalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + }, + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors" + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/060000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors b/trash_picking_cache/060000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/060000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/060000/pretrained_model/train_config.json b/trash_picking_cache/060000/pretrained_model/train_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f3f4ec3adb4a8d88d10c17994d18e954fe1b2b68 --- /dev/null +++ b/trash_picking_cache/060000/pretrained_model/train_config.json @@ -0,0 +1,176 @@ +{ + "dataset": { + "repo_id": "siyulw2025/minions001", + "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 + ] + } + } + } + }, + "revision": null, + "use_imagenet_stats": true, + "video_backend": "torchcodec", + "streaming": false + }, + "env": null, + "policy": { + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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/minions001", + "job_name": "trash_picking", + "resume": false, + "seed": 1000, + "num_workers": 4, + "batch_size": 1, + "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": false, + "disable_artifact": false, + "project": "lerobot", + "entity": null, + "notes": null, + "run_id": null, + "mode": null + } +} \ No newline at end of file diff --git a/trash_picking_cache/060000/training_state/optimizer_param_groups.json b/trash_picking_cache/060000/training_state/optimizer_param_groups.json new file mode 100644 index 0000000000000000000000000000000000000000..33506df097b87c64b2aa15765ab89706780c0dc0 --- /dev/null +++ b/trash_picking_cache/060000/training_state/optimizer_param_groups.json @@ -0,0 +1,191 @@ +[ + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 0, + 1, + 2, + 3, + 4, + 5, + 6, + 7, + 8, + 9, + 10, + 11, + 12, + 13, + 14, + 15, + 16, + 17, + 18, + 19, + 20, + 21, + 22, + 23, + 24, + 25, + 26, + 27, + 28, + 29, + 30, + 31, + 32, + 33, + 34, + 35, + 36, + 37, + 38, + 39, + 40, + 41, + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132 + ] + }, + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141, + 142, + 143, + 144, + 145, + 146, + 147, + 148, + 149, + 150, + 151, + 152 + ] + } +] \ No newline at end of file diff --git a/trash_picking_cache/060000/training_state/optimizer_state.safetensors b/trash_picking_cache/060000/training_state/optimizer_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..71f6e845f87e5a823d45f9af347f898215426e6a --- /dev/null +++ b/trash_picking_cache/060000/training_state/optimizer_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c43d408b79b1eec09d2b0030c0d6881577f6d1a0fddf2f4f1ad48e3b9af3cac7 +size 412817652 diff --git a/trash_picking_cache/060000/training_state/rng_state.safetensors b/trash_picking_cache/060000/training_state/rng_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..685ff92a3d8ea434c9e5d4751a37f89eb8f5fbcf --- /dev/null +++ b/trash_picking_cache/060000/training_state/rng_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39810b9253b9b27d34d4e8c12db0f53da3fa1fec1068a89ae24b055d6b425e28 +size 15708 diff --git a/trash_picking_cache/060000/training_state/training_step.json b/trash_picking_cache/060000/training_state/training_step.json new file mode 100644 index 0000000000000000000000000000000000000000..d360b6037f1c8c2c85d38e951160eb02ace507dd --- /dev/null +++ b/trash_picking_cache/060000/training_state/training_step.json @@ -0,0 +1,3 @@ +{ + "step": 60000 +} \ No newline at end of file diff --git a/trash_picking_cache/080000/pretrained_model/config.json b/trash_picking_cache/080000/pretrained_model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..df0d138639f0dee64b5abd0ba7d7606df907e3cd --- /dev/null +++ b/trash_picking_cache/080000/pretrained_model/config.json @@ -0,0 +1,69 @@ +{ + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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 +} \ No newline at end of file diff --git a/trash_picking_cache/080000/pretrained_model/model.safetensors b/trash_picking_cache/080000/pretrained_model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c2ca4185847293b385279f9003c531bfbc70961 --- /dev/null +++ b/trash_picking_cache/080000/pretrained_model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bfb4a2f6268ee8b6af3555e44ef3c0ea68ad737260a4b827773aeae3c81e63f +size 206699736 diff --git a/trash_picking_cache/080000/pretrained_model/policy_postprocessor.json b/trash_picking_cache/080000/pretrained_model/policy_postprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..9ccb342474cecbf2bdbb034d27169a351ad96d2a --- /dev/null +++ b/trash_picking_cache/080000/pretrained_model/policy_postprocessor.json @@ -0,0 +1,32 @@ +{ + "name": "policy_postprocessor", + "steps": [ + { + "registry_name": "unnormalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors" + }, + { + "registry_name": "device_processor", + "config": { + "device": "cpu", + "float_dtype": null + } + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/080000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors b/trash_picking_cache/080000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/080000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/080000/pretrained_model/policy_preprocessor.json b/trash_picking_cache/080000/pretrained_model/policy_preprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..7d39638a64caf81ebb4e1d519ef769b085ee1523 --- /dev/null +++ b/trash_picking_cache/080000/pretrained_model/policy_preprocessor.json @@ -0,0 +1,64 @@ +{ + "name": "policy_preprocessor", + "steps": [ + { + "registry_name": "rename_observations_processor", + "config": { + "rename_map": {} + } + }, + { + "registry_name": "to_batch_processor", + "config": {} + }, + { + "registry_name": "device_processor", + "config": { + "device": "cuda", + "float_dtype": null + } + }, + { + "registry_name": "normalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + }, + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors" + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/080000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors b/trash_picking_cache/080000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/080000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/080000/pretrained_model/train_config.json b/trash_picking_cache/080000/pretrained_model/train_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f3f4ec3adb4a8d88d10c17994d18e954fe1b2b68 --- /dev/null +++ b/trash_picking_cache/080000/pretrained_model/train_config.json @@ -0,0 +1,176 @@ +{ + "dataset": { + "repo_id": "siyulw2025/minions001", + "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 + ] + } + } + } + }, + "revision": null, + "use_imagenet_stats": true, + "video_backend": "torchcodec", + "streaming": false + }, + "env": null, + "policy": { + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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/minions001", + "job_name": "trash_picking", + "resume": false, + "seed": 1000, + "num_workers": 4, + "batch_size": 1, + "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": false, + "disable_artifact": false, + "project": "lerobot", + "entity": null, + "notes": null, + "run_id": null, + "mode": null + } +} \ No newline at end of file diff --git a/trash_picking_cache/080000/training_state/optimizer_param_groups.json b/trash_picking_cache/080000/training_state/optimizer_param_groups.json new file mode 100644 index 0000000000000000000000000000000000000000..33506df097b87c64b2aa15765ab89706780c0dc0 --- /dev/null +++ b/trash_picking_cache/080000/training_state/optimizer_param_groups.json @@ -0,0 +1,191 @@ +[ + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 0, + 1, + 2, + 3, + 4, + 5, + 6, + 7, + 8, + 9, + 10, + 11, + 12, + 13, + 14, + 15, + 16, + 17, + 18, + 19, + 20, + 21, + 22, + 23, + 24, + 25, + 26, + 27, + 28, + 29, + 30, + 31, + 32, + 33, + 34, + 35, + 36, + 37, + 38, + 39, + 40, + 41, + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132 + ] + }, + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141, + 142, + 143, + 144, + 145, + 146, + 147, + 148, + 149, + 150, + 151, + 152 + ] + } +] \ No newline at end of file diff --git a/trash_picking_cache/080000/training_state/optimizer_state.safetensors b/trash_picking_cache/080000/training_state/optimizer_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ce3bacea092216f6d723f4e1b81752d93f987e7 --- /dev/null +++ b/trash_picking_cache/080000/training_state/optimizer_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe202eee8048e0d2c60f5ccc4fd439b44c9b0cbbfc5a412626765fc69b20b85 +size 412817652 diff --git a/trash_picking_cache/080000/training_state/rng_state.safetensors b/trash_picking_cache/080000/training_state/rng_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..accc98b06b4c08acb59e4b0fa9623fc00be25645 --- /dev/null +++ b/trash_picking_cache/080000/training_state/rng_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f61873e337b8f2ae0a067aa07ea6f1635fd67bd7497422edbffd8ddccfbd90 +size 15708 diff --git a/trash_picking_cache/080000/training_state/training_step.json b/trash_picking_cache/080000/training_state/training_step.json new file mode 100644 index 0000000000000000000000000000000000000000..384eace4ecc2a6cba352aa7cf27f04405b7319c3 --- /dev/null +++ b/trash_picking_cache/080000/training_state/training_step.json @@ -0,0 +1,3 @@ +{ + "step": 80000 +} \ No newline at end of file diff --git a/trash_picking_cache/100000/pretrained_model/config.json b/trash_picking_cache/100000/pretrained_model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..df0d138639f0dee64b5abd0ba7d7606df907e3cd --- /dev/null +++ b/trash_picking_cache/100000/pretrained_model/config.json @@ -0,0 +1,69 @@ +{ + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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 +} \ No newline at end of file diff --git a/trash_picking_cache/100000/pretrained_model/model.safetensors b/trash_picking_cache/100000/pretrained_model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e88e852d4ac62d30fb9fde2e60941dc4193a618a --- /dev/null +++ b/trash_picking_cache/100000/pretrained_model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8051aef401c6756053d8606c72491f602769f595b958c3b3d48ebae00fd9ea05 +size 206699736 diff --git a/trash_picking_cache/100000/pretrained_model/policy_postprocessor.json b/trash_picking_cache/100000/pretrained_model/policy_postprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..9ccb342474cecbf2bdbb034d27169a351ad96d2a --- /dev/null +++ b/trash_picking_cache/100000/pretrained_model/policy_postprocessor.json @@ -0,0 +1,32 @@ +{ + "name": "policy_postprocessor", + "steps": [ + { + "registry_name": "unnormalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors" + }, + { + "registry_name": "device_processor", + "config": { + "device": "cpu", + "float_dtype": null + } + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/100000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors b/trash_picking_cache/100000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/100000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/100000/pretrained_model/policy_preprocessor.json b/trash_picking_cache/100000/pretrained_model/policy_preprocessor.json new file mode 100644 index 0000000000000000000000000000000000000000..7d39638a64caf81ebb4e1d519ef769b085ee1523 --- /dev/null +++ b/trash_picking_cache/100000/pretrained_model/policy_preprocessor.json @@ -0,0 +1,64 @@ +{ + "name": "policy_preprocessor", + "steps": [ + { + "registry_name": "rename_observations_processor", + "config": { + "rename_map": {} + } + }, + { + "registry_name": "to_batch_processor", + "config": {} + }, + { + "registry_name": "device_processor", + "config": { + "device": "cuda", + "float_dtype": null + } + }, + { + "registry_name": "normalizer_processor", + "config": { + "eps": 1e-08, + "features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + }, + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "norm_map": { + "VISUAL": "MEAN_STD", + "STATE": "MEAN_STD", + "ACTION": "MEAN_STD" + } + }, + "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors" + } + ] +} \ No newline at end of file diff --git a/trash_picking_cache/100000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors b/trash_picking_cache/100000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de73d54593b8cecb12495aaea6a81e899f2b826d --- /dev/null +++ b/trash_picking_cache/100000/pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984d7923641cde3536b62f7fcee347ab4a2c5e24c09af3b8c4382083afb0172f +size 3748 diff --git a/trash_picking_cache/100000/pretrained_model/train_config.json b/trash_picking_cache/100000/pretrained_model/train_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f3f4ec3adb4a8d88d10c17994d18e954fe1b2b68 --- /dev/null +++ b/trash_picking_cache/100000/pretrained_model/train_config.json @@ -0,0 +1,176 @@ +{ + "dataset": { + "repo_id": "siyulw2025/minions001", + "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 + ] + } + } + } + }, + "revision": null, + "use_imagenet_stats": true, + "video_backend": "torchcodec", + "streaming": false + }, + "env": null, + "policy": { + "type": "act", + "n_obs_steps": 1, + "input_features": { + "observation.state": { + "type": "STATE", + "shape": [ + 6 + ] + }, + "observation.images.front": { + "type": "VISUAL", + "shape": [ + 3, + 1080, + 1920 + ] + }, + "observation.images.top": { + "type": "VISUAL", + "shape": [ + 3, + 720, + 1280 + ] + } + }, + "output_features": { + "action": { + "type": "ACTION", + "shape": [ + 6 + ] + } + }, + "device": "cuda", + "use_amp": false, + "push_to_hub": true, + "repo_id": "siyulw2025/trash_picking", + "private": null, + "tags": null, + "license": 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/minions001", + "job_name": "trash_picking", + "resume": false, + "seed": 1000, + "num_workers": 4, + "batch_size": 1, + "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": false, + "disable_artifact": false, + "project": "lerobot", + "entity": null, + "notes": null, + "run_id": null, + "mode": null + } +} \ No newline at end of file diff --git a/trash_picking_cache/100000/training_state/optimizer_param_groups.json b/trash_picking_cache/100000/training_state/optimizer_param_groups.json new file mode 100644 index 0000000000000000000000000000000000000000..33506df097b87c64b2aa15765ab89706780c0dc0 --- /dev/null +++ b/trash_picking_cache/100000/training_state/optimizer_param_groups.json @@ -0,0 +1,191 @@ +[ + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 0, + 1, + 2, + 3, + 4, + 5, + 6, + 7, + 8, + 9, + 10, + 11, + 12, + 13, + 14, + 15, + 16, + 17, + 18, + 19, + 20, + 21, + 22, + 23, + 24, + 25, + 26, + 27, + 28, + 29, + 30, + 31, + 32, + 33, + 34, + 35, + 36, + 37, + 38, + 39, + 40, + 41, + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132 + ] + }, + { + "lr": 1e-05, + "betas": [ + 0.9, + 0.999 + ], + "eps": 1e-08, + "weight_decay": 0.0001, + "amsgrad": false, + "maximize": false, + "foreach": null, + "capturable": false, + "differentiable": false, + "fused": null, + "decoupled_weight_decay": true, + "params": [ + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141, + 142, + 143, + 144, + 145, + 146, + 147, + 148, + 149, + 150, + 151, + 152 + ] + } +] \ No newline at end of file diff --git a/trash_picking_cache/100000/training_state/optimizer_state.safetensors b/trash_picking_cache/100000/training_state/optimizer_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13ac6b8ac60e36f348d56437dd516314022ba750 --- /dev/null +++ b/trash_picking_cache/100000/training_state/optimizer_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e13703c10ffb06cb4a7491668f6909bc5f6b0d433f3cbfa4bb4e813169f1bbe1 +size 412817652 diff --git a/trash_picking_cache/100000/training_state/rng_state.safetensors b/trash_picking_cache/100000/training_state/rng_state.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3791bb079f9fbe56b3d308364eb96ba365ff908 --- /dev/null +++ b/trash_picking_cache/100000/training_state/rng_state.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:720beb8b974a271d357d8f65249f1027023fa6bd244f466528045f4dffdc89a2 +size 15708 diff --git a/trash_picking_cache/100000/training_state/training_step.json b/trash_picking_cache/100000/training_state/training_step.json new file mode 100644 index 0000000000000000000000000000000000000000..8eb73c13d28bca88058c08796abbf931c3f9b012 --- /dev/null +++ b/trash_picking_cache/100000/training_state/training_step.json @@ -0,0 +1,3 @@ +{ + "step": 100000 +} \ No newline at end of file