Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- 010000/pretrained_model/config.json +69 -0
- 010000/pretrained_model/model.safetensors +3 -0
- 010000/pretrained_model/train_config.json +175 -0
- 010000/training_state/optimizer_param_groups.json +191 -0
- 010000/training_state/optimizer_state.safetensors +3 -0
- 010000/training_state/rng_state.safetensors +3 -0
- 010000/training_state/training_step.json +3 -0
- 020000/pretrained_model/config.json +69 -0
- 020000/pretrained_model/model.safetensors +3 -0
- 020000/pretrained_model/train_config.json +175 -0
- 020000/training_state/optimizer_param_groups.json +191 -0
- 020000/training_state/optimizer_state.safetensors +3 -0
- 020000/training_state/rng_state.safetensors +3 -0
- 020000/training_state/training_step.json +3 -0
- 030000/pretrained_model/config.json +69 -0
- 030000/pretrained_model/model.safetensors +3 -0
- 030000/pretrained_model/train_config.json +175 -0
- 030000/training_state/optimizer_param_groups.json +191 -0
- 030000/training_state/optimizer_state.safetensors +3 -0
- 030000/training_state/rng_state.safetensors +3 -0
- 030000/training_state/training_step.json +3 -0
- 040000/pretrained_model/config.json +69 -0
- 040000/pretrained_model/model.safetensors +3 -0
- 040000/pretrained_model/train_config.json +175 -0
- 040000/training_state/optimizer_param_groups.json +191 -0
- 040000/training_state/optimizer_state.safetensors +3 -0
- 040000/training_state/rng_state.safetensors +3 -0
- 040000/training_state/training_step.json +3 -0
- 050000/pretrained_model/config.json +69 -0
- 050000/pretrained_model/model.safetensors +3 -0
- 050000/pretrained_model/train_config.json +175 -0
- 050000/training_state/optimizer_param_groups.json +191 -0
- 050000/training_state/optimizer_state.safetensors +3 -0
- 050000/training_state/rng_state.safetensors +3 -0
- 050000/training_state/training_step.json +3 -0
- 060000/pretrained_model/config.json +69 -0
- 060000/pretrained_model/model.safetensors +3 -0
- 060000/pretrained_model/train_config.json +175 -0
- 060000/training_state/optimizer_param_groups.json +191 -0
- 060000/training_state/optimizer_state.safetensors +3 -0
- 060000/training_state/rng_state.safetensors +3 -0
- 060000/training_state/training_step.json +3 -0
- 070000/pretrained_model/config.json +69 -0
- 070000/pretrained_model/model.safetensors +3 -0
- 070000/pretrained_model/train_config.json +175 -0
- 070000/training_state/optimizer_param_groups.json +191 -0
- 070000/training_state/optimizer_state.safetensors +3 -0
- 070000/training_state/rng_state.safetensors +3 -0
- 070000/training_state/training_step.json +3 -0
- 080000/pretrained_model/config.json +69 -0
010000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"normalization_mapping": {
|
| 5 |
+
"VISUAL": "MEAN_STD",
|
| 6 |
+
"STATE": "MEAN_STD",
|
| 7 |
+
"ACTION": "MEAN_STD"
|
| 8 |
+
},
|
| 9 |
+
"input_features": {
|
| 10 |
+
"observation.state": {
|
| 11 |
+
"type": "STATE",
|
| 12 |
+
"shape": [
|
| 13 |
+
6
|
| 14 |
+
]
|
| 15 |
+
},
|
| 16 |
+
"observation.images.front": {
|
| 17 |
+
"type": "VISUAL",
|
| 18 |
+
"shape": [
|
| 19 |
+
3,
|
| 20 |
+
480,
|
| 21 |
+
640
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"observation.images.overhead": {
|
| 25 |
+
"type": "VISUAL",
|
| 26 |
+
"shape": [
|
| 27 |
+
3,
|
| 28 |
+
480,
|
| 29 |
+
640
|
| 30 |
+
]
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"output_features": {
|
| 34 |
+
"action": {
|
| 35 |
+
"type": "ACTION",
|
| 36 |
+
"shape": [
|
| 37 |
+
6
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"device": "cuda",
|
| 42 |
+
"use_amp": false,
|
| 43 |
+
"push_to_hub": true,
|
| 44 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 45 |
+
"private": null,
|
| 46 |
+
"tags": null,
|
| 47 |
+
"license": null,
|
| 48 |
+
"chunk_size": 100,
|
| 49 |
+
"n_action_steps": 100,
|
| 50 |
+
"vision_backbone": "resnet18",
|
| 51 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 52 |
+
"replace_final_stride_with_dilation": false,
|
| 53 |
+
"pre_norm": false,
|
| 54 |
+
"dim_model": 512,
|
| 55 |
+
"n_heads": 8,
|
| 56 |
+
"dim_feedforward": 3200,
|
| 57 |
+
"feedforward_activation": "relu",
|
| 58 |
+
"n_encoder_layers": 4,
|
| 59 |
+
"n_decoder_layers": 1,
|
| 60 |
+
"use_vae": true,
|
| 61 |
+
"latent_dim": 32,
|
| 62 |
+
"n_vae_encoder_layers": 4,
|
| 63 |
+
"temporal_ensemble_coeff": null,
|
| 64 |
+
"dropout": 0.1,
|
| 65 |
+
"kl_weight": 10.0,
|
| 66 |
+
"optimizer_lr": 1e-05,
|
| 67 |
+
"optimizer_weight_decay": 0.0001,
|
| 68 |
+
"optimizer_lr_backbone": 1e-05
|
| 69 |
+
}
|
010000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46afed9d7fe03c2bbeaa683ae00d15f4e55569fec3ddf4069744facd6d4db3ff
|
| 3 |
+
size 206701072
|
010000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "dleon23/record-so101_2",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": false,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"revision": null,
|
| 64 |
+
"use_imagenet_stats": true,
|
| 65 |
+
"video_backend": "torchcodec"
|
| 66 |
+
},
|
| 67 |
+
"env": null,
|
| 68 |
+
"policy": {
|
| 69 |
+
"type": "act",
|
| 70 |
+
"n_obs_steps": 1,
|
| 71 |
+
"normalization_mapping": {
|
| 72 |
+
"VISUAL": "MEAN_STD",
|
| 73 |
+
"STATE": "MEAN_STD",
|
| 74 |
+
"ACTION": "MEAN_STD"
|
| 75 |
+
},
|
| 76 |
+
"input_features": {
|
| 77 |
+
"observation.state": {
|
| 78 |
+
"type": "STATE",
|
| 79 |
+
"shape": [
|
| 80 |
+
6
|
| 81 |
+
]
|
| 82 |
+
},
|
| 83 |
+
"observation.images.front": {
|
| 84 |
+
"type": "VISUAL",
|
| 85 |
+
"shape": [
|
| 86 |
+
3,
|
| 87 |
+
480,
|
| 88 |
+
640
|
| 89 |
+
]
|
| 90 |
+
},
|
| 91 |
+
"observation.images.overhead": {
|
| 92 |
+
"type": "VISUAL",
|
| 93 |
+
"shape": [
|
| 94 |
+
3,
|
| 95 |
+
480,
|
| 96 |
+
640
|
| 97 |
+
]
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"output_features": {
|
| 101 |
+
"action": {
|
| 102 |
+
"type": "ACTION",
|
| 103 |
+
"shape": [
|
| 104 |
+
6
|
| 105 |
+
]
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"device": "cuda",
|
| 109 |
+
"use_amp": false,
|
| 110 |
+
"push_to_hub": true,
|
| 111 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 112 |
+
"private": null,
|
| 113 |
+
"tags": null,
|
| 114 |
+
"license": null,
|
| 115 |
+
"chunk_size": 100,
|
| 116 |
+
"n_action_steps": 100,
|
| 117 |
+
"vision_backbone": "resnet18",
|
| 118 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 119 |
+
"replace_final_stride_with_dilation": false,
|
| 120 |
+
"pre_norm": false,
|
| 121 |
+
"dim_model": 512,
|
| 122 |
+
"n_heads": 8,
|
| 123 |
+
"dim_feedforward": 3200,
|
| 124 |
+
"feedforward_activation": "relu",
|
| 125 |
+
"n_encoder_layers": 4,
|
| 126 |
+
"n_decoder_layers": 1,
|
| 127 |
+
"use_vae": true,
|
| 128 |
+
"latent_dim": 32,
|
| 129 |
+
"n_vae_encoder_layers": 4,
|
| 130 |
+
"temporal_ensemble_coeff": null,
|
| 131 |
+
"dropout": 0.1,
|
| 132 |
+
"kl_weight": 10.0,
|
| 133 |
+
"optimizer_lr": 1e-05,
|
| 134 |
+
"optimizer_weight_decay": 0.0001,
|
| 135 |
+
"optimizer_lr_backbone": 1e-05
|
| 136 |
+
},
|
| 137 |
+
"output_dir": "outputs/train/pick_box_so101",
|
| 138 |
+
"job_name": "so101_act_training",
|
| 139 |
+
"resume": false,
|
| 140 |
+
"seed": 1000,
|
| 141 |
+
"num_workers": 4,
|
| 142 |
+
"batch_size": 8,
|
| 143 |
+
"steps": 100000,
|
| 144 |
+
"eval_freq": 20000,
|
| 145 |
+
"log_freq": 200,
|
| 146 |
+
"save_checkpoint": true,
|
| 147 |
+
"save_freq": 10000,
|
| 148 |
+
"use_policy_training_preset": true,
|
| 149 |
+
"optimizer": {
|
| 150 |
+
"type": "adamw",
|
| 151 |
+
"lr": 1e-05,
|
| 152 |
+
"weight_decay": 0.0001,
|
| 153 |
+
"grad_clip_norm": 10.0,
|
| 154 |
+
"betas": [
|
| 155 |
+
0.9,
|
| 156 |
+
0.999
|
| 157 |
+
],
|
| 158 |
+
"eps": 1e-08
|
| 159 |
+
},
|
| 160 |
+
"scheduler": null,
|
| 161 |
+
"eval": {
|
| 162 |
+
"n_episodes": 50,
|
| 163 |
+
"batch_size": 50,
|
| 164 |
+
"use_async_envs": false
|
| 165 |
+
},
|
| 166 |
+
"wandb": {
|
| 167 |
+
"enable": true,
|
| 168 |
+
"disable_artifact": false,
|
| 169 |
+
"project": "lerobot",
|
| 170 |
+
"entity": null,
|
| 171 |
+
"notes": null,
|
| 172 |
+
"run_id": "9kt9ehbs",
|
| 173 |
+
"mode": null
|
| 174 |
+
}
|
| 175 |
+
}
|
010000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 1e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 0.0001,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"params": [
|
| 18 |
+
0,
|
| 19 |
+
1,
|
| 20 |
+
2,
|
| 21 |
+
3,
|
| 22 |
+
4,
|
| 23 |
+
5,
|
| 24 |
+
6,
|
| 25 |
+
7,
|
| 26 |
+
8,
|
| 27 |
+
9,
|
| 28 |
+
10,
|
| 29 |
+
11,
|
| 30 |
+
12,
|
| 31 |
+
13,
|
| 32 |
+
14,
|
| 33 |
+
15,
|
| 34 |
+
16,
|
| 35 |
+
17,
|
| 36 |
+
18,
|
| 37 |
+
19,
|
| 38 |
+
20,
|
| 39 |
+
21,
|
| 40 |
+
22,
|
| 41 |
+
23,
|
| 42 |
+
24,
|
| 43 |
+
25,
|
| 44 |
+
26,
|
| 45 |
+
27,
|
| 46 |
+
28,
|
| 47 |
+
29,
|
| 48 |
+
30,
|
| 49 |
+
31,
|
| 50 |
+
32,
|
| 51 |
+
33,
|
| 52 |
+
34,
|
| 53 |
+
35,
|
| 54 |
+
36,
|
| 55 |
+
37,
|
| 56 |
+
38,
|
| 57 |
+
39,
|
| 58 |
+
40,
|
| 59 |
+
41,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
47,
|
| 66 |
+
48,
|
| 67 |
+
49,
|
| 68 |
+
50,
|
| 69 |
+
51,
|
| 70 |
+
52,
|
| 71 |
+
53,
|
| 72 |
+
54,
|
| 73 |
+
55,
|
| 74 |
+
56,
|
| 75 |
+
57,
|
| 76 |
+
58,
|
| 77 |
+
59,
|
| 78 |
+
60,
|
| 79 |
+
61,
|
| 80 |
+
62,
|
| 81 |
+
63,
|
| 82 |
+
64,
|
| 83 |
+
65,
|
| 84 |
+
66,
|
| 85 |
+
67,
|
| 86 |
+
68,
|
| 87 |
+
69,
|
| 88 |
+
70,
|
| 89 |
+
71,
|
| 90 |
+
72,
|
| 91 |
+
73,
|
| 92 |
+
74,
|
| 93 |
+
75,
|
| 94 |
+
76,
|
| 95 |
+
77,
|
| 96 |
+
78,
|
| 97 |
+
79,
|
| 98 |
+
80,
|
| 99 |
+
81,
|
| 100 |
+
82,
|
| 101 |
+
83,
|
| 102 |
+
84,
|
| 103 |
+
85,
|
| 104 |
+
86,
|
| 105 |
+
87,
|
| 106 |
+
88,
|
| 107 |
+
89,
|
| 108 |
+
90,
|
| 109 |
+
91,
|
| 110 |
+
92,
|
| 111 |
+
93,
|
| 112 |
+
94,
|
| 113 |
+
95,
|
| 114 |
+
96,
|
| 115 |
+
97,
|
| 116 |
+
98,
|
| 117 |
+
99,
|
| 118 |
+
100,
|
| 119 |
+
101,
|
| 120 |
+
102,
|
| 121 |
+
103,
|
| 122 |
+
104,
|
| 123 |
+
105,
|
| 124 |
+
106,
|
| 125 |
+
107,
|
| 126 |
+
108,
|
| 127 |
+
109,
|
| 128 |
+
110,
|
| 129 |
+
111,
|
| 130 |
+
112,
|
| 131 |
+
113,
|
| 132 |
+
114,
|
| 133 |
+
115,
|
| 134 |
+
116,
|
| 135 |
+
117,
|
| 136 |
+
118,
|
| 137 |
+
119,
|
| 138 |
+
120,
|
| 139 |
+
121,
|
| 140 |
+
122,
|
| 141 |
+
123,
|
| 142 |
+
124,
|
| 143 |
+
125,
|
| 144 |
+
126,
|
| 145 |
+
127,
|
| 146 |
+
128,
|
| 147 |
+
129,
|
| 148 |
+
130,
|
| 149 |
+
131,
|
| 150 |
+
132
|
| 151 |
+
]
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"lr": 1e-05,
|
| 155 |
+
"betas": [
|
| 156 |
+
0.9,
|
| 157 |
+
0.999
|
| 158 |
+
],
|
| 159 |
+
"eps": 1e-08,
|
| 160 |
+
"weight_decay": 0.0001,
|
| 161 |
+
"amsgrad": false,
|
| 162 |
+
"maximize": false,
|
| 163 |
+
"foreach": null,
|
| 164 |
+
"capturable": false,
|
| 165 |
+
"differentiable": false,
|
| 166 |
+
"fused": null,
|
| 167 |
+
"decoupled_weight_decay": true,
|
| 168 |
+
"params": [
|
| 169 |
+
133,
|
| 170 |
+
134,
|
| 171 |
+
135,
|
| 172 |
+
136,
|
| 173 |
+
137,
|
| 174 |
+
138,
|
| 175 |
+
139,
|
| 176 |
+
140,
|
| 177 |
+
141,
|
| 178 |
+
142,
|
| 179 |
+
143,
|
| 180 |
+
144,
|
| 181 |
+
145,
|
| 182 |
+
146,
|
| 183 |
+
147,
|
| 184 |
+
148,
|
| 185 |
+
149,
|
| 186 |
+
150,
|
| 187 |
+
151,
|
| 188 |
+
152
|
| 189 |
+
]
|
| 190 |
+
}
|
| 191 |
+
]
|
010000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf99006bb78a2530b7f4ee2a58b43627ce046e01d1313871c9e6f7a5ff256374
|
| 3 |
+
size 412817652
|
010000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3d0691d6427a3f97159169401844e4cec54a3eb17c77335b1e11da17cf167c4
|
| 3 |
+
size 15708
|
010000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 10000
|
| 3 |
+
}
|
020000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"normalization_mapping": {
|
| 5 |
+
"VISUAL": "MEAN_STD",
|
| 6 |
+
"STATE": "MEAN_STD",
|
| 7 |
+
"ACTION": "MEAN_STD"
|
| 8 |
+
},
|
| 9 |
+
"input_features": {
|
| 10 |
+
"observation.state": {
|
| 11 |
+
"type": "STATE",
|
| 12 |
+
"shape": [
|
| 13 |
+
6
|
| 14 |
+
]
|
| 15 |
+
},
|
| 16 |
+
"observation.images.front": {
|
| 17 |
+
"type": "VISUAL",
|
| 18 |
+
"shape": [
|
| 19 |
+
3,
|
| 20 |
+
480,
|
| 21 |
+
640
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"observation.images.overhead": {
|
| 25 |
+
"type": "VISUAL",
|
| 26 |
+
"shape": [
|
| 27 |
+
3,
|
| 28 |
+
480,
|
| 29 |
+
640
|
| 30 |
+
]
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"output_features": {
|
| 34 |
+
"action": {
|
| 35 |
+
"type": "ACTION",
|
| 36 |
+
"shape": [
|
| 37 |
+
6
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"device": "cuda",
|
| 42 |
+
"use_amp": false,
|
| 43 |
+
"push_to_hub": true,
|
| 44 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 45 |
+
"private": null,
|
| 46 |
+
"tags": null,
|
| 47 |
+
"license": null,
|
| 48 |
+
"chunk_size": 100,
|
| 49 |
+
"n_action_steps": 100,
|
| 50 |
+
"vision_backbone": "resnet18",
|
| 51 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 52 |
+
"replace_final_stride_with_dilation": false,
|
| 53 |
+
"pre_norm": false,
|
| 54 |
+
"dim_model": 512,
|
| 55 |
+
"n_heads": 8,
|
| 56 |
+
"dim_feedforward": 3200,
|
| 57 |
+
"feedforward_activation": "relu",
|
| 58 |
+
"n_encoder_layers": 4,
|
| 59 |
+
"n_decoder_layers": 1,
|
| 60 |
+
"use_vae": true,
|
| 61 |
+
"latent_dim": 32,
|
| 62 |
+
"n_vae_encoder_layers": 4,
|
| 63 |
+
"temporal_ensemble_coeff": null,
|
| 64 |
+
"dropout": 0.1,
|
| 65 |
+
"kl_weight": 10.0,
|
| 66 |
+
"optimizer_lr": 1e-05,
|
| 67 |
+
"optimizer_weight_decay": 0.0001,
|
| 68 |
+
"optimizer_lr_backbone": 1e-05
|
| 69 |
+
}
|
020000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bac6eafcf463aa9eb6511e1a82ac88bdf5c5a5f8e666110dba06c63eee602f48
|
| 3 |
+
size 206701072
|
020000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "dleon23/record-so101_2",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": false,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"revision": null,
|
| 64 |
+
"use_imagenet_stats": true,
|
| 65 |
+
"video_backend": "torchcodec"
|
| 66 |
+
},
|
| 67 |
+
"env": null,
|
| 68 |
+
"policy": {
|
| 69 |
+
"type": "act",
|
| 70 |
+
"n_obs_steps": 1,
|
| 71 |
+
"normalization_mapping": {
|
| 72 |
+
"VISUAL": "MEAN_STD",
|
| 73 |
+
"STATE": "MEAN_STD",
|
| 74 |
+
"ACTION": "MEAN_STD"
|
| 75 |
+
},
|
| 76 |
+
"input_features": {
|
| 77 |
+
"observation.state": {
|
| 78 |
+
"type": "STATE",
|
| 79 |
+
"shape": [
|
| 80 |
+
6
|
| 81 |
+
]
|
| 82 |
+
},
|
| 83 |
+
"observation.images.front": {
|
| 84 |
+
"type": "VISUAL",
|
| 85 |
+
"shape": [
|
| 86 |
+
3,
|
| 87 |
+
480,
|
| 88 |
+
640
|
| 89 |
+
]
|
| 90 |
+
},
|
| 91 |
+
"observation.images.overhead": {
|
| 92 |
+
"type": "VISUAL",
|
| 93 |
+
"shape": [
|
| 94 |
+
3,
|
| 95 |
+
480,
|
| 96 |
+
640
|
| 97 |
+
]
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"output_features": {
|
| 101 |
+
"action": {
|
| 102 |
+
"type": "ACTION",
|
| 103 |
+
"shape": [
|
| 104 |
+
6
|
| 105 |
+
]
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"device": "cuda",
|
| 109 |
+
"use_amp": false,
|
| 110 |
+
"push_to_hub": true,
|
| 111 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 112 |
+
"private": null,
|
| 113 |
+
"tags": null,
|
| 114 |
+
"license": null,
|
| 115 |
+
"chunk_size": 100,
|
| 116 |
+
"n_action_steps": 100,
|
| 117 |
+
"vision_backbone": "resnet18",
|
| 118 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 119 |
+
"replace_final_stride_with_dilation": false,
|
| 120 |
+
"pre_norm": false,
|
| 121 |
+
"dim_model": 512,
|
| 122 |
+
"n_heads": 8,
|
| 123 |
+
"dim_feedforward": 3200,
|
| 124 |
+
"feedforward_activation": "relu",
|
| 125 |
+
"n_encoder_layers": 4,
|
| 126 |
+
"n_decoder_layers": 1,
|
| 127 |
+
"use_vae": true,
|
| 128 |
+
"latent_dim": 32,
|
| 129 |
+
"n_vae_encoder_layers": 4,
|
| 130 |
+
"temporal_ensemble_coeff": null,
|
| 131 |
+
"dropout": 0.1,
|
| 132 |
+
"kl_weight": 10.0,
|
| 133 |
+
"optimizer_lr": 1e-05,
|
| 134 |
+
"optimizer_weight_decay": 0.0001,
|
| 135 |
+
"optimizer_lr_backbone": 1e-05
|
| 136 |
+
},
|
| 137 |
+
"output_dir": "outputs/train/pick_box_so101",
|
| 138 |
+
"job_name": "so101_act_training",
|
| 139 |
+
"resume": false,
|
| 140 |
+
"seed": 1000,
|
| 141 |
+
"num_workers": 4,
|
| 142 |
+
"batch_size": 8,
|
| 143 |
+
"steps": 100000,
|
| 144 |
+
"eval_freq": 20000,
|
| 145 |
+
"log_freq": 200,
|
| 146 |
+
"save_checkpoint": true,
|
| 147 |
+
"save_freq": 10000,
|
| 148 |
+
"use_policy_training_preset": true,
|
| 149 |
+
"optimizer": {
|
| 150 |
+
"type": "adamw",
|
| 151 |
+
"lr": 1e-05,
|
| 152 |
+
"weight_decay": 0.0001,
|
| 153 |
+
"grad_clip_norm": 10.0,
|
| 154 |
+
"betas": [
|
| 155 |
+
0.9,
|
| 156 |
+
0.999
|
| 157 |
+
],
|
| 158 |
+
"eps": 1e-08
|
| 159 |
+
},
|
| 160 |
+
"scheduler": null,
|
| 161 |
+
"eval": {
|
| 162 |
+
"n_episodes": 50,
|
| 163 |
+
"batch_size": 50,
|
| 164 |
+
"use_async_envs": false
|
| 165 |
+
},
|
| 166 |
+
"wandb": {
|
| 167 |
+
"enable": true,
|
| 168 |
+
"disable_artifact": false,
|
| 169 |
+
"project": "lerobot",
|
| 170 |
+
"entity": null,
|
| 171 |
+
"notes": null,
|
| 172 |
+
"run_id": "9kt9ehbs",
|
| 173 |
+
"mode": null
|
| 174 |
+
}
|
| 175 |
+
}
|
020000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 1e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 0.0001,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"params": [
|
| 18 |
+
0,
|
| 19 |
+
1,
|
| 20 |
+
2,
|
| 21 |
+
3,
|
| 22 |
+
4,
|
| 23 |
+
5,
|
| 24 |
+
6,
|
| 25 |
+
7,
|
| 26 |
+
8,
|
| 27 |
+
9,
|
| 28 |
+
10,
|
| 29 |
+
11,
|
| 30 |
+
12,
|
| 31 |
+
13,
|
| 32 |
+
14,
|
| 33 |
+
15,
|
| 34 |
+
16,
|
| 35 |
+
17,
|
| 36 |
+
18,
|
| 37 |
+
19,
|
| 38 |
+
20,
|
| 39 |
+
21,
|
| 40 |
+
22,
|
| 41 |
+
23,
|
| 42 |
+
24,
|
| 43 |
+
25,
|
| 44 |
+
26,
|
| 45 |
+
27,
|
| 46 |
+
28,
|
| 47 |
+
29,
|
| 48 |
+
30,
|
| 49 |
+
31,
|
| 50 |
+
32,
|
| 51 |
+
33,
|
| 52 |
+
34,
|
| 53 |
+
35,
|
| 54 |
+
36,
|
| 55 |
+
37,
|
| 56 |
+
38,
|
| 57 |
+
39,
|
| 58 |
+
40,
|
| 59 |
+
41,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
47,
|
| 66 |
+
48,
|
| 67 |
+
49,
|
| 68 |
+
50,
|
| 69 |
+
51,
|
| 70 |
+
52,
|
| 71 |
+
53,
|
| 72 |
+
54,
|
| 73 |
+
55,
|
| 74 |
+
56,
|
| 75 |
+
57,
|
| 76 |
+
58,
|
| 77 |
+
59,
|
| 78 |
+
60,
|
| 79 |
+
61,
|
| 80 |
+
62,
|
| 81 |
+
63,
|
| 82 |
+
64,
|
| 83 |
+
65,
|
| 84 |
+
66,
|
| 85 |
+
67,
|
| 86 |
+
68,
|
| 87 |
+
69,
|
| 88 |
+
70,
|
| 89 |
+
71,
|
| 90 |
+
72,
|
| 91 |
+
73,
|
| 92 |
+
74,
|
| 93 |
+
75,
|
| 94 |
+
76,
|
| 95 |
+
77,
|
| 96 |
+
78,
|
| 97 |
+
79,
|
| 98 |
+
80,
|
| 99 |
+
81,
|
| 100 |
+
82,
|
| 101 |
+
83,
|
| 102 |
+
84,
|
| 103 |
+
85,
|
| 104 |
+
86,
|
| 105 |
+
87,
|
| 106 |
+
88,
|
| 107 |
+
89,
|
| 108 |
+
90,
|
| 109 |
+
91,
|
| 110 |
+
92,
|
| 111 |
+
93,
|
| 112 |
+
94,
|
| 113 |
+
95,
|
| 114 |
+
96,
|
| 115 |
+
97,
|
| 116 |
+
98,
|
| 117 |
+
99,
|
| 118 |
+
100,
|
| 119 |
+
101,
|
| 120 |
+
102,
|
| 121 |
+
103,
|
| 122 |
+
104,
|
| 123 |
+
105,
|
| 124 |
+
106,
|
| 125 |
+
107,
|
| 126 |
+
108,
|
| 127 |
+
109,
|
| 128 |
+
110,
|
| 129 |
+
111,
|
| 130 |
+
112,
|
| 131 |
+
113,
|
| 132 |
+
114,
|
| 133 |
+
115,
|
| 134 |
+
116,
|
| 135 |
+
117,
|
| 136 |
+
118,
|
| 137 |
+
119,
|
| 138 |
+
120,
|
| 139 |
+
121,
|
| 140 |
+
122,
|
| 141 |
+
123,
|
| 142 |
+
124,
|
| 143 |
+
125,
|
| 144 |
+
126,
|
| 145 |
+
127,
|
| 146 |
+
128,
|
| 147 |
+
129,
|
| 148 |
+
130,
|
| 149 |
+
131,
|
| 150 |
+
132
|
| 151 |
+
]
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"lr": 1e-05,
|
| 155 |
+
"betas": [
|
| 156 |
+
0.9,
|
| 157 |
+
0.999
|
| 158 |
+
],
|
| 159 |
+
"eps": 1e-08,
|
| 160 |
+
"weight_decay": 0.0001,
|
| 161 |
+
"amsgrad": false,
|
| 162 |
+
"maximize": false,
|
| 163 |
+
"foreach": null,
|
| 164 |
+
"capturable": false,
|
| 165 |
+
"differentiable": false,
|
| 166 |
+
"fused": null,
|
| 167 |
+
"decoupled_weight_decay": true,
|
| 168 |
+
"params": [
|
| 169 |
+
133,
|
| 170 |
+
134,
|
| 171 |
+
135,
|
| 172 |
+
136,
|
| 173 |
+
137,
|
| 174 |
+
138,
|
| 175 |
+
139,
|
| 176 |
+
140,
|
| 177 |
+
141,
|
| 178 |
+
142,
|
| 179 |
+
143,
|
| 180 |
+
144,
|
| 181 |
+
145,
|
| 182 |
+
146,
|
| 183 |
+
147,
|
| 184 |
+
148,
|
| 185 |
+
149,
|
| 186 |
+
150,
|
| 187 |
+
151,
|
| 188 |
+
152
|
| 189 |
+
]
|
| 190 |
+
}
|
| 191 |
+
]
|
020000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a12fae4863b2ad38aa9e5b25eed7ce5a99681a6d83a8d88d909d5759115b87af
|
| 3 |
+
size 412817652
|
020000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:768ecdb672822a1d80cd449a6288c56ec9d65ce66601b5d78ebe742403a59a19
|
| 3 |
+
size 15708
|
020000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 20000
|
| 3 |
+
}
|
030000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"normalization_mapping": {
|
| 5 |
+
"VISUAL": "MEAN_STD",
|
| 6 |
+
"STATE": "MEAN_STD",
|
| 7 |
+
"ACTION": "MEAN_STD"
|
| 8 |
+
},
|
| 9 |
+
"input_features": {
|
| 10 |
+
"observation.state": {
|
| 11 |
+
"type": "STATE",
|
| 12 |
+
"shape": [
|
| 13 |
+
6
|
| 14 |
+
]
|
| 15 |
+
},
|
| 16 |
+
"observation.images.front": {
|
| 17 |
+
"type": "VISUAL",
|
| 18 |
+
"shape": [
|
| 19 |
+
3,
|
| 20 |
+
480,
|
| 21 |
+
640
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"observation.images.overhead": {
|
| 25 |
+
"type": "VISUAL",
|
| 26 |
+
"shape": [
|
| 27 |
+
3,
|
| 28 |
+
480,
|
| 29 |
+
640
|
| 30 |
+
]
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"output_features": {
|
| 34 |
+
"action": {
|
| 35 |
+
"type": "ACTION",
|
| 36 |
+
"shape": [
|
| 37 |
+
6
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"device": "cuda",
|
| 42 |
+
"use_amp": false,
|
| 43 |
+
"push_to_hub": true,
|
| 44 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 45 |
+
"private": null,
|
| 46 |
+
"tags": null,
|
| 47 |
+
"license": null,
|
| 48 |
+
"chunk_size": 100,
|
| 49 |
+
"n_action_steps": 100,
|
| 50 |
+
"vision_backbone": "resnet18",
|
| 51 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 52 |
+
"replace_final_stride_with_dilation": false,
|
| 53 |
+
"pre_norm": false,
|
| 54 |
+
"dim_model": 512,
|
| 55 |
+
"n_heads": 8,
|
| 56 |
+
"dim_feedforward": 3200,
|
| 57 |
+
"feedforward_activation": "relu",
|
| 58 |
+
"n_encoder_layers": 4,
|
| 59 |
+
"n_decoder_layers": 1,
|
| 60 |
+
"use_vae": true,
|
| 61 |
+
"latent_dim": 32,
|
| 62 |
+
"n_vae_encoder_layers": 4,
|
| 63 |
+
"temporal_ensemble_coeff": null,
|
| 64 |
+
"dropout": 0.1,
|
| 65 |
+
"kl_weight": 10.0,
|
| 66 |
+
"optimizer_lr": 1e-05,
|
| 67 |
+
"optimizer_weight_decay": 0.0001,
|
| 68 |
+
"optimizer_lr_backbone": 1e-05
|
| 69 |
+
}
|
030000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9af9b437303fe171ee51b60c8f3f29a8598705dd7e1498d2f93611e0be65dbe1
|
| 3 |
+
size 206701072
|
030000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "dleon23/record-so101_2",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": false,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"revision": null,
|
| 64 |
+
"use_imagenet_stats": true,
|
| 65 |
+
"video_backend": "torchcodec"
|
| 66 |
+
},
|
| 67 |
+
"env": null,
|
| 68 |
+
"policy": {
|
| 69 |
+
"type": "act",
|
| 70 |
+
"n_obs_steps": 1,
|
| 71 |
+
"normalization_mapping": {
|
| 72 |
+
"VISUAL": "MEAN_STD",
|
| 73 |
+
"STATE": "MEAN_STD",
|
| 74 |
+
"ACTION": "MEAN_STD"
|
| 75 |
+
},
|
| 76 |
+
"input_features": {
|
| 77 |
+
"observation.state": {
|
| 78 |
+
"type": "STATE",
|
| 79 |
+
"shape": [
|
| 80 |
+
6
|
| 81 |
+
]
|
| 82 |
+
},
|
| 83 |
+
"observation.images.front": {
|
| 84 |
+
"type": "VISUAL",
|
| 85 |
+
"shape": [
|
| 86 |
+
3,
|
| 87 |
+
480,
|
| 88 |
+
640
|
| 89 |
+
]
|
| 90 |
+
},
|
| 91 |
+
"observation.images.overhead": {
|
| 92 |
+
"type": "VISUAL",
|
| 93 |
+
"shape": [
|
| 94 |
+
3,
|
| 95 |
+
480,
|
| 96 |
+
640
|
| 97 |
+
]
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"output_features": {
|
| 101 |
+
"action": {
|
| 102 |
+
"type": "ACTION",
|
| 103 |
+
"shape": [
|
| 104 |
+
6
|
| 105 |
+
]
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"device": "cuda",
|
| 109 |
+
"use_amp": false,
|
| 110 |
+
"push_to_hub": true,
|
| 111 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 112 |
+
"private": null,
|
| 113 |
+
"tags": null,
|
| 114 |
+
"license": null,
|
| 115 |
+
"chunk_size": 100,
|
| 116 |
+
"n_action_steps": 100,
|
| 117 |
+
"vision_backbone": "resnet18",
|
| 118 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 119 |
+
"replace_final_stride_with_dilation": false,
|
| 120 |
+
"pre_norm": false,
|
| 121 |
+
"dim_model": 512,
|
| 122 |
+
"n_heads": 8,
|
| 123 |
+
"dim_feedforward": 3200,
|
| 124 |
+
"feedforward_activation": "relu",
|
| 125 |
+
"n_encoder_layers": 4,
|
| 126 |
+
"n_decoder_layers": 1,
|
| 127 |
+
"use_vae": true,
|
| 128 |
+
"latent_dim": 32,
|
| 129 |
+
"n_vae_encoder_layers": 4,
|
| 130 |
+
"temporal_ensemble_coeff": null,
|
| 131 |
+
"dropout": 0.1,
|
| 132 |
+
"kl_weight": 10.0,
|
| 133 |
+
"optimizer_lr": 1e-05,
|
| 134 |
+
"optimizer_weight_decay": 0.0001,
|
| 135 |
+
"optimizer_lr_backbone": 1e-05
|
| 136 |
+
},
|
| 137 |
+
"output_dir": "outputs/train/pick_box_so101",
|
| 138 |
+
"job_name": "so101_act_training",
|
| 139 |
+
"resume": false,
|
| 140 |
+
"seed": 1000,
|
| 141 |
+
"num_workers": 4,
|
| 142 |
+
"batch_size": 8,
|
| 143 |
+
"steps": 100000,
|
| 144 |
+
"eval_freq": 20000,
|
| 145 |
+
"log_freq": 200,
|
| 146 |
+
"save_checkpoint": true,
|
| 147 |
+
"save_freq": 10000,
|
| 148 |
+
"use_policy_training_preset": true,
|
| 149 |
+
"optimizer": {
|
| 150 |
+
"type": "adamw",
|
| 151 |
+
"lr": 1e-05,
|
| 152 |
+
"weight_decay": 0.0001,
|
| 153 |
+
"grad_clip_norm": 10.0,
|
| 154 |
+
"betas": [
|
| 155 |
+
0.9,
|
| 156 |
+
0.999
|
| 157 |
+
],
|
| 158 |
+
"eps": 1e-08
|
| 159 |
+
},
|
| 160 |
+
"scheduler": null,
|
| 161 |
+
"eval": {
|
| 162 |
+
"n_episodes": 50,
|
| 163 |
+
"batch_size": 50,
|
| 164 |
+
"use_async_envs": false
|
| 165 |
+
},
|
| 166 |
+
"wandb": {
|
| 167 |
+
"enable": true,
|
| 168 |
+
"disable_artifact": false,
|
| 169 |
+
"project": "lerobot",
|
| 170 |
+
"entity": null,
|
| 171 |
+
"notes": null,
|
| 172 |
+
"run_id": "9kt9ehbs",
|
| 173 |
+
"mode": null
|
| 174 |
+
}
|
| 175 |
+
}
|
030000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 1e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 0.0001,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"params": [
|
| 18 |
+
0,
|
| 19 |
+
1,
|
| 20 |
+
2,
|
| 21 |
+
3,
|
| 22 |
+
4,
|
| 23 |
+
5,
|
| 24 |
+
6,
|
| 25 |
+
7,
|
| 26 |
+
8,
|
| 27 |
+
9,
|
| 28 |
+
10,
|
| 29 |
+
11,
|
| 30 |
+
12,
|
| 31 |
+
13,
|
| 32 |
+
14,
|
| 33 |
+
15,
|
| 34 |
+
16,
|
| 35 |
+
17,
|
| 36 |
+
18,
|
| 37 |
+
19,
|
| 38 |
+
20,
|
| 39 |
+
21,
|
| 40 |
+
22,
|
| 41 |
+
23,
|
| 42 |
+
24,
|
| 43 |
+
25,
|
| 44 |
+
26,
|
| 45 |
+
27,
|
| 46 |
+
28,
|
| 47 |
+
29,
|
| 48 |
+
30,
|
| 49 |
+
31,
|
| 50 |
+
32,
|
| 51 |
+
33,
|
| 52 |
+
34,
|
| 53 |
+
35,
|
| 54 |
+
36,
|
| 55 |
+
37,
|
| 56 |
+
38,
|
| 57 |
+
39,
|
| 58 |
+
40,
|
| 59 |
+
41,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
47,
|
| 66 |
+
48,
|
| 67 |
+
49,
|
| 68 |
+
50,
|
| 69 |
+
51,
|
| 70 |
+
52,
|
| 71 |
+
53,
|
| 72 |
+
54,
|
| 73 |
+
55,
|
| 74 |
+
56,
|
| 75 |
+
57,
|
| 76 |
+
58,
|
| 77 |
+
59,
|
| 78 |
+
60,
|
| 79 |
+
61,
|
| 80 |
+
62,
|
| 81 |
+
63,
|
| 82 |
+
64,
|
| 83 |
+
65,
|
| 84 |
+
66,
|
| 85 |
+
67,
|
| 86 |
+
68,
|
| 87 |
+
69,
|
| 88 |
+
70,
|
| 89 |
+
71,
|
| 90 |
+
72,
|
| 91 |
+
73,
|
| 92 |
+
74,
|
| 93 |
+
75,
|
| 94 |
+
76,
|
| 95 |
+
77,
|
| 96 |
+
78,
|
| 97 |
+
79,
|
| 98 |
+
80,
|
| 99 |
+
81,
|
| 100 |
+
82,
|
| 101 |
+
83,
|
| 102 |
+
84,
|
| 103 |
+
85,
|
| 104 |
+
86,
|
| 105 |
+
87,
|
| 106 |
+
88,
|
| 107 |
+
89,
|
| 108 |
+
90,
|
| 109 |
+
91,
|
| 110 |
+
92,
|
| 111 |
+
93,
|
| 112 |
+
94,
|
| 113 |
+
95,
|
| 114 |
+
96,
|
| 115 |
+
97,
|
| 116 |
+
98,
|
| 117 |
+
99,
|
| 118 |
+
100,
|
| 119 |
+
101,
|
| 120 |
+
102,
|
| 121 |
+
103,
|
| 122 |
+
104,
|
| 123 |
+
105,
|
| 124 |
+
106,
|
| 125 |
+
107,
|
| 126 |
+
108,
|
| 127 |
+
109,
|
| 128 |
+
110,
|
| 129 |
+
111,
|
| 130 |
+
112,
|
| 131 |
+
113,
|
| 132 |
+
114,
|
| 133 |
+
115,
|
| 134 |
+
116,
|
| 135 |
+
117,
|
| 136 |
+
118,
|
| 137 |
+
119,
|
| 138 |
+
120,
|
| 139 |
+
121,
|
| 140 |
+
122,
|
| 141 |
+
123,
|
| 142 |
+
124,
|
| 143 |
+
125,
|
| 144 |
+
126,
|
| 145 |
+
127,
|
| 146 |
+
128,
|
| 147 |
+
129,
|
| 148 |
+
130,
|
| 149 |
+
131,
|
| 150 |
+
132
|
| 151 |
+
]
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"lr": 1e-05,
|
| 155 |
+
"betas": [
|
| 156 |
+
0.9,
|
| 157 |
+
0.999
|
| 158 |
+
],
|
| 159 |
+
"eps": 1e-08,
|
| 160 |
+
"weight_decay": 0.0001,
|
| 161 |
+
"amsgrad": false,
|
| 162 |
+
"maximize": false,
|
| 163 |
+
"foreach": null,
|
| 164 |
+
"capturable": false,
|
| 165 |
+
"differentiable": false,
|
| 166 |
+
"fused": null,
|
| 167 |
+
"decoupled_weight_decay": true,
|
| 168 |
+
"params": [
|
| 169 |
+
133,
|
| 170 |
+
134,
|
| 171 |
+
135,
|
| 172 |
+
136,
|
| 173 |
+
137,
|
| 174 |
+
138,
|
| 175 |
+
139,
|
| 176 |
+
140,
|
| 177 |
+
141,
|
| 178 |
+
142,
|
| 179 |
+
143,
|
| 180 |
+
144,
|
| 181 |
+
145,
|
| 182 |
+
146,
|
| 183 |
+
147,
|
| 184 |
+
148,
|
| 185 |
+
149,
|
| 186 |
+
150,
|
| 187 |
+
151,
|
| 188 |
+
152
|
| 189 |
+
]
|
| 190 |
+
}
|
| 191 |
+
]
|
030000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fec93322503a4429614093e75e97d6c426c6c1654e64532af8c0ec9b57be988c
|
| 3 |
+
size 412817652
|
030000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98fbcc832a7f24eabdeabbf4411a9e3213621e86c39967d0e3bbc9c0f110aa38
|
| 3 |
+
size 15708
|
030000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 30000
|
| 3 |
+
}
|
040000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"normalization_mapping": {
|
| 5 |
+
"VISUAL": "MEAN_STD",
|
| 6 |
+
"STATE": "MEAN_STD",
|
| 7 |
+
"ACTION": "MEAN_STD"
|
| 8 |
+
},
|
| 9 |
+
"input_features": {
|
| 10 |
+
"observation.state": {
|
| 11 |
+
"type": "STATE",
|
| 12 |
+
"shape": [
|
| 13 |
+
6
|
| 14 |
+
]
|
| 15 |
+
},
|
| 16 |
+
"observation.images.front": {
|
| 17 |
+
"type": "VISUAL",
|
| 18 |
+
"shape": [
|
| 19 |
+
3,
|
| 20 |
+
480,
|
| 21 |
+
640
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"observation.images.overhead": {
|
| 25 |
+
"type": "VISUAL",
|
| 26 |
+
"shape": [
|
| 27 |
+
3,
|
| 28 |
+
480,
|
| 29 |
+
640
|
| 30 |
+
]
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"output_features": {
|
| 34 |
+
"action": {
|
| 35 |
+
"type": "ACTION",
|
| 36 |
+
"shape": [
|
| 37 |
+
6
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"device": "cuda",
|
| 42 |
+
"use_amp": false,
|
| 43 |
+
"push_to_hub": true,
|
| 44 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 45 |
+
"private": null,
|
| 46 |
+
"tags": null,
|
| 47 |
+
"license": null,
|
| 48 |
+
"chunk_size": 100,
|
| 49 |
+
"n_action_steps": 100,
|
| 50 |
+
"vision_backbone": "resnet18",
|
| 51 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 52 |
+
"replace_final_stride_with_dilation": false,
|
| 53 |
+
"pre_norm": false,
|
| 54 |
+
"dim_model": 512,
|
| 55 |
+
"n_heads": 8,
|
| 56 |
+
"dim_feedforward": 3200,
|
| 57 |
+
"feedforward_activation": "relu",
|
| 58 |
+
"n_encoder_layers": 4,
|
| 59 |
+
"n_decoder_layers": 1,
|
| 60 |
+
"use_vae": true,
|
| 61 |
+
"latent_dim": 32,
|
| 62 |
+
"n_vae_encoder_layers": 4,
|
| 63 |
+
"temporal_ensemble_coeff": null,
|
| 64 |
+
"dropout": 0.1,
|
| 65 |
+
"kl_weight": 10.0,
|
| 66 |
+
"optimizer_lr": 1e-05,
|
| 67 |
+
"optimizer_weight_decay": 0.0001,
|
| 68 |
+
"optimizer_lr_backbone": 1e-05
|
| 69 |
+
}
|
040000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bed5083a191f335159e438ef18723f4591350f196fe9425b7e142d1b62d1bde8
|
| 3 |
+
size 206701072
|
040000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "dleon23/record-so101_2",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": false,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"revision": null,
|
| 64 |
+
"use_imagenet_stats": true,
|
| 65 |
+
"video_backend": "torchcodec"
|
| 66 |
+
},
|
| 67 |
+
"env": null,
|
| 68 |
+
"policy": {
|
| 69 |
+
"type": "act",
|
| 70 |
+
"n_obs_steps": 1,
|
| 71 |
+
"normalization_mapping": {
|
| 72 |
+
"VISUAL": "MEAN_STD",
|
| 73 |
+
"STATE": "MEAN_STD",
|
| 74 |
+
"ACTION": "MEAN_STD"
|
| 75 |
+
},
|
| 76 |
+
"input_features": {
|
| 77 |
+
"observation.state": {
|
| 78 |
+
"type": "STATE",
|
| 79 |
+
"shape": [
|
| 80 |
+
6
|
| 81 |
+
]
|
| 82 |
+
},
|
| 83 |
+
"observation.images.front": {
|
| 84 |
+
"type": "VISUAL",
|
| 85 |
+
"shape": [
|
| 86 |
+
3,
|
| 87 |
+
480,
|
| 88 |
+
640
|
| 89 |
+
]
|
| 90 |
+
},
|
| 91 |
+
"observation.images.overhead": {
|
| 92 |
+
"type": "VISUAL",
|
| 93 |
+
"shape": [
|
| 94 |
+
3,
|
| 95 |
+
480,
|
| 96 |
+
640
|
| 97 |
+
]
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"output_features": {
|
| 101 |
+
"action": {
|
| 102 |
+
"type": "ACTION",
|
| 103 |
+
"shape": [
|
| 104 |
+
6
|
| 105 |
+
]
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"device": "cuda",
|
| 109 |
+
"use_amp": false,
|
| 110 |
+
"push_to_hub": true,
|
| 111 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 112 |
+
"private": null,
|
| 113 |
+
"tags": null,
|
| 114 |
+
"license": null,
|
| 115 |
+
"chunk_size": 100,
|
| 116 |
+
"n_action_steps": 100,
|
| 117 |
+
"vision_backbone": "resnet18",
|
| 118 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 119 |
+
"replace_final_stride_with_dilation": false,
|
| 120 |
+
"pre_norm": false,
|
| 121 |
+
"dim_model": 512,
|
| 122 |
+
"n_heads": 8,
|
| 123 |
+
"dim_feedforward": 3200,
|
| 124 |
+
"feedforward_activation": "relu",
|
| 125 |
+
"n_encoder_layers": 4,
|
| 126 |
+
"n_decoder_layers": 1,
|
| 127 |
+
"use_vae": true,
|
| 128 |
+
"latent_dim": 32,
|
| 129 |
+
"n_vae_encoder_layers": 4,
|
| 130 |
+
"temporal_ensemble_coeff": null,
|
| 131 |
+
"dropout": 0.1,
|
| 132 |
+
"kl_weight": 10.0,
|
| 133 |
+
"optimizer_lr": 1e-05,
|
| 134 |
+
"optimizer_weight_decay": 0.0001,
|
| 135 |
+
"optimizer_lr_backbone": 1e-05
|
| 136 |
+
},
|
| 137 |
+
"output_dir": "outputs/train/pick_box_so101",
|
| 138 |
+
"job_name": "so101_act_training",
|
| 139 |
+
"resume": false,
|
| 140 |
+
"seed": 1000,
|
| 141 |
+
"num_workers": 4,
|
| 142 |
+
"batch_size": 8,
|
| 143 |
+
"steps": 100000,
|
| 144 |
+
"eval_freq": 20000,
|
| 145 |
+
"log_freq": 200,
|
| 146 |
+
"save_checkpoint": true,
|
| 147 |
+
"save_freq": 10000,
|
| 148 |
+
"use_policy_training_preset": true,
|
| 149 |
+
"optimizer": {
|
| 150 |
+
"type": "adamw",
|
| 151 |
+
"lr": 1e-05,
|
| 152 |
+
"weight_decay": 0.0001,
|
| 153 |
+
"grad_clip_norm": 10.0,
|
| 154 |
+
"betas": [
|
| 155 |
+
0.9,
|
| 156 |
+
0.999
|
| 157 |
+
],
|
| 158 |
+
"eps": 1e-08
|
| 159 |
+
},
|
| 160 |
+
"scheduler": null,
|
| 161 |
+
"eval": {
|
| 162 |
+
"n_episodes": 50,
|
| 163 |
+
"batch_size": 50,
|
| 164 |
+
"use_async_envs": false
|
| 165 |
+
},
|
| 166 |
+
"wandb": {
|
| 167 |
+
"enable": true,
|
| 168 |
+
"disable_artifact": false,
|
| 169 |
+
"project": "lerobot",
|
| 170 |
+
"entity": null,
|
| 171 |
+
"notes": null,
|
| 172 |
+
"run_id": "9kt9ehbs",
|
| 173 |
+
"mode": null
|
| 174 |
+
}
|
| 175 |
+
}
|
040000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 1e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 0.0001,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"params": [
|
| 18 |
+
0,
|
| 19 |
+
1,
|
| 20 |
+
2,
|
| 21 |
+
3,
|
| 22 |
+
4,
|
| 23 |
+
5,
|
| 24 |
+
6,
|
| 25 |
+
7,
|
| 26 |
+
8,
|
| 27 |
+
9,
|
| 28 |
+
10,
|
| 29 |
+
11,
|
| 30 |
+
12,
|
| 31 |
+
13,
|
| 32 |
+
14,
|
| 33 |
+
15,
|
| 34 |
+
16,
|
| 35 |
+
17,
|
| 36 |
+
18,
|
| 37 |
+
19,
|
| 38 |
+
20,
|
| 39 |
+
21,
|
| 40 |
+
22,
|
| 41 |
+
23,
|
| 42 |
+
24,
|
| 43 |
+
25,
|
| 44 |
+
26,
|
| 45 |
+
27,
|
| 46 |
+
28,
|
| 47 |
+
29,
|
| 48 |
+
30,
|
| 49 |
+
31,
|
| 50 |
+
32,
|
| 51 |
+
33,
|
| 52 |
+
34,
|
| 53 |
+
35,
|
| 54 |
+
36,
|
| 55 |
+
37,
|
| 56 |
+
38,
|
| 57 |
+
39,
|
| 58 |
+
40,
|
| 59 |
+
41,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
47,
|
| 66 |
+
48,
|
| 67 |
+
49,
|
| 68 |
+
50,
|
| 69 |
+
51,
|
| 70 |
+
52,
|
| 71 |
+
53,
|
| 72 |
+
54,
|
| 73 |
+
55,
|
| 74 |
+
56,
|
| 75 |
+
57,
|
| 76 |
+
58,
|
| 77 |
+
59,
|
| 78 |
+
60,
|
| 79 |
+
61,
|
| 80 |
+
62,
|
| 81 |
+
63,
|
| 82 |
+
64,
|
| 83 |
+
65,
|
| 84 |
+
66,
|
| 85 |
+
67,
|
| 86 |
+
68,
|
| 87 |
+
69,
|
| 88 |
+
70,
|
| 89 |
+
71,
|
| 90 |
+
72,
|
| 91 |
+
73,
|
| 92 |
+
74,
|
| 93 |
+
75,
|
| 94 |
+
76,
|
| 95 |
+
77,
|
| 96 |
+
78,
|
| 97 |
+
79,
|
| 98 |
+
80,
|
| 99 |
+
81,
|
| 100 |
+
82,
|
| 101 |
+
83,
|
| 102 |
+
84,
|
| 103 |
+
85,
|
| 104 |
+
86,
|
| 105 |
+
87,
|
| 106 |
+
88,
|
| 107 |
+
89,
|
| 108 |
+
90,
|
| 109 |
+
91,
|
| 110 |
+
92,
|
| 111 |
+
93,
|
| 112 |
+
94,
|
| 113 |
+
95,
|
| 114 |
+
96,
|
| 115 |
+
97,
|
| 116 |
+
98,
|
| 117 |
+
99,
|
| 118 |
+
100,
|
| 119 |
+
101,
|
| 120 |
+
102,
|
| 121 |
+
103,
|
| 122 |
+
104,
|
| 123 |
+
105,
|
| 124 |
+
106,
|
| 125 |
+
107,
|
| 126 |
+
108,
|
| 127 |
+
109,
|
| 128 |
+
110,
|
| 129 |
+
111,
|
| 130 |
+
112,
|
| 131 |
+
113,
|
| 132 |
+
114,
|
| 133 |
+
115,
|
| 134 |
+
116,
|
| 135 |
+
117,
|
| 136 |
+
118,
|
| 137 |
+
119,
|
| 138 |
+
120,
|
| 139 |
+
121,
|
| 140 |
+
122,
|
| 141 |
+
123,
|
| 142 |
+
124,
|
| 143 |
+
125,
|
| 144 |
+
126,
|
| 145 |
+
127,
|
| 146 |
+
128,
|
| 147 |
+
129,
|
| 148 |
+
130,
|
| 149 |
+
131,
|
| 150 |
+
132
|
| 151 |
+
]
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"lr": 1e-05,
|
| 155 |
+
"betas": [
|
| 156 |
+
0.9,
|
| 157 |
+
0.999
|
| 158 |
+
],
|
| 159 |
+
"eps": 1e-08,
|
| 160 |
+
"weight_decay": 0.0001,
|
| 161 |
+
"amsgrad": false,
|
| 162 |
+
"maximize": false,
|
| 163 |
+
"foreach": null,
|
| 164 |
+
"capturable": false,
|
| 165 |
+
"differentiable": false,
|
| 166 |
+
"fused": null,
|
| 167 |
+
"decoupled_weight_decay": true,
|
| 168 |
+
"params": [
|
| 169 |
+
133,
|
| 170 |
+
134,
|
| 171 |
+
135,
|
| 172 |
+
136,
|
| 173 |
+
137,
|
| 174 |
+
138,
|
| 175 |
+
139,
|
| 176 |
+
140,
|
| 177 |
+
141,
|
| 178 |
+
142,
|
| 179 |
+
143,
|
| 180 |
+
144,
|
| 181 |
+
145,
|
| 182 |
+
146,
|
| 183 |
+
147,
|
| 184 |
+
148,
|
| 185 |
+
149,
|
| 186 |
+
150,
|
| 187 |
+
151,
|
| 188 |
+
152
|
| 189 |
+
]
|
| 190 |
+
}
|
| 191 |
+
]
|
040000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:255e3a5fb191d92fcfb2986d3712b37a948a6955f7b64b820601b508b1c4aec7
|
| 3 |
+
size 412817652
|
040000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ceb57137f62f31f898e6d7cc6b9d4305b7d51e93eb506e3d708ad8497f00fd6
|
| 3 |
+
size 15708
|
040000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 40000
|
| 3 |
+
}
|
050000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"normalization_mapping": {
|
| 5 |
+
"VISUAL": "MEAN_STD",
|
| 6 |
+
"STATE": "MEAN_STD",
|
| 7 |
+
"ACTION": "MEAN_STD"
|
| 8 |
+
},
|
| 9 |
+
"input_features": {
|
| 10 |
+
"observation.state": {
|
| 11 |
+
"type": "STATE",
|
| 12 |
+
"shape": [
|
| 13 |
+
6
|
| 14 |
+
]
|
| 15 |
+
},
|
| 16 |
+
"observation.images.front": {
|
| 17 |
+
"type": "VISUAL",
|
| 18 |
+
"shape": [
|
| 19 |
+
3,
|
| 20 |
+
480,
|
| 21 |
+
640
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"observation.images.overhead": {
|
| 25 |
+
"type": "VISUAL",
|
| 26 |
+
"shape": [
|
| 27 |
+
3,
|
| 28 |
+
480,
|
| 29 |
+
640
|
| 30 |
+
]
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"output_features": {
|
| 34 |
+
"action": {
|
| 35 |
+
"type": "ACTION",
|
| 36 |
+
"shape": [
|
| 37 |
+
6
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"device": "cuda",
|
| 42 |
+
"use_amp": false,
|
| 43 |
+
"push_to_hub": true,
|
| 44 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 45 |
+
"private": null,
|
| 46 |
+
"tags": null,
|
| 47 |
+
"license": null,
|
| 48 |
+
"chunk_size": 100,
|
| 49 |
+
"n_action_steps": 100,
|
| 50 |
+
"vision_backbone": "resnet18",
|
| 51 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 52 |
+
"replace_final_stride_with_dilation": false,
|
| 53 |
+
"pre_norm": false,
|
| 54 |
+
"dim_model": 512,
|
| 55 |
+
"n_heads": 8,
|
| 56 |
+
"dim_feedforward": 3200,
|
| 57 |
+
"feedforward_activation": "relu",
|
| 58 |
+
"n_encoder_layers": 4,
|
| 59 |
+
"n_decoder_layers": 1,
|
| 60 |
+
"use_vae": true,
|
| 61 |
+
"latent_dim": 32,
|
| 62 |
+
"n_vae_encoder_layers": 4,
|
| 63 |
+
"temporal_ensemble_coeff": null,
|
| 64 |
+
"dropout": 0.1,
|
| 65 |
+
"kl_weight": 10.0,
|
| 66 |
+
"optimizer_lr": 1e-05,
|
| 67 |
+
"optimizer_weight_decay": 0.0001,
|
| 68 |
+
"optimizer_lr_backbone": 1e-05
|
| 69 |
+
}
|
050000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9afbc709a84dc2038bb7b38425ec63a91a6240102b696aec5393b94ce62620a7
|
| 3 |
+
size 206701072
|
050000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "dleon23/record-so101_2",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": false,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"revision": null,
|
| 64 |
+
"use_imagenet_stats": true,
|
| 65 |
+
"video_backend": "torchcodec"
|
| 66 |
+
},
|
| 67 |
+
"env": null,
|
| 68 |
+
"policy": {
|
| 69 |
+
"type": "act",
|
| 70 |
+
"n_obs_steps": 1,
|
| 71 |
+
"normalization_mapping": {
|
| 72 |
+
"VISUAL": "MEAN_STD",
|
| 73 |
+
"STATE": "MEAN_STD",
|
| 74 |
+
"ACTION": "MEAN_STD"
|
| 75 |
+
},
|
| 76 |
+
"input_features": {
|
| 77 |
+
"observation.state": {
|
| 78 |
+
"type": "STATE",
|
| 79 |
+
"shape": [
|
| 80 |
+
6
|
| 81 |
+
]
|
| 82 |
+
},
|
| 83 |
+
"observation.images.front": {
|
| 84 |
+
"type": "VISUAL",
|
| 85 |
+
"shape": [
|
| 86 |
+
3,
|
| 87 |
+
480,
|
| 88 |
+
640
|
| 89 |
+
]
|
| 90 |
+
},
|
| 91 |
+
"observation.images.overhead": {
|
| 92 |
+
"type": "VISUAL",
|
| 93 |
+
"shape": [
|
| 94 |
+
3,
|
| 95 |
+
480,
|
| 96 |
+
640
|
| 97 |
+
]
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"output_features": {
|
| 101 |
+
"action": {
|
| 102 |
+
"type": "ACTION",
|
| 103 |
+
"shape": [
|
| 104 |
+
6
|
| 105 |
+
]
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"device": "cuda",
|
| 109 |
+
"use_amp": false,
|
| 110 |
+
"push_to_hub": true,
|
| 111 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 112 |
+
"private": null,
|
| 113 |
+
"tags": null,
|
| 114 |
+
"license": null,
|
| 115 |
+
"chunk_size": 100,
|
| 116 |
+
"n_action_steps": 100,
|
| 117 |
+
"vision_backbone": "resnet18",
|
| 118 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 119 |
+
"replace_final_stride_with_dilation": false,
|
| 120 |
+
"pre_norm": false,
|
| 121 |
+
"dim_model": 512,
|
| 122 |
+
"n_heads": 8,
|
| 123 |
+
"dim_feedforward": 3200,
|
| 124 |
+
"feedforward_activation": "relu",
|
| 125 |
+
"n_encoder_layers": 4,
|
| 126 |
+
"n_decoder_layers": 1,
|
| 127 |
+
"use_vae": true,
|
| 128 |
+
"latent_dim": 32,
|
| 129 |
+
"n_vae_encoder_layers": 4,
|
| 130 |
+
"temporal_ensemble_coeff": null,
|
| 131 |
+
"dropout": 0.1,
|
| 132 |
+
"kl_weight": 10.0,
|
| 133 |
+
"optimizer_lr": 1e-05,
|
| 134 |
+
"optimizer_weight_decay": 0.0001,
|
| 135 |
+
"optimizer_lr_backbone": 1e-05
|
| 136 |
+
},
|
| 137 |
+
"output_dir": "outputs/train/pick_box_so101",
|
| 138 |
+
"job_name": "so101_act_training",
|
| 139 |
+
"resume": false,
|
| 140 |
+
"seed": 1000,
|
| 141 |
+
"num_workers": 4,
|
| 142 |
+
"batch_size": 8,
|
| 143 |
+
"steps": 100000,
|
| 144 |
+
"eval_freq": 20000,
|
| 145 |
+
"log_freq": 200,
|
| 146 |
+
"save_checkpoint": true,
|
| 147 |
+
"save_freq": 10000,
|
| 148 |
+
"use_policy_training_preset": true,
|
| 149 |
+
"optimizer": {
|
| 150 |
+
"type": "adamw",
|
| 151 |
+
"lr": 1e-05,
|
| 152 |
+
"weight_decay": 0.0001,
|
| 153 |
+
"grad_clip_norm": 10.0,
|
| 154 |
+
"betas": [
|
| 155 |
+
0.9,
|
| 156 |
+
0.999
|
| 157 |
+
],
|
| 158 |
+
"eps": 1e-08
|
| 159 |
+
},
|
| 160 |
+
"scheduler": null,
|
| 161 |
+
"eval": {
|
| 162 |
+
"n_episodes": 50,
|
| 163 |
+
"batch_size": 50,
|
| 164 |
+
"use_async_envs": false
|
| 165 |
+
},
|
| 166 |
+
"wandb": {
|
| 167 |
+
"enable": true,
|
| 168 |
+
"disable_artifact": false,
|
| 169 |
+
"project": "lerobot",
|
| 170 |
+
"entity": null,
|
| 171 |
+
"notes": null,
|
| 172 |
+
"run_id": "9kt9ehbs",
|
| 173 |
+
"mode": null
|
| 174 |
+
}
|
| 175 |
+
}
|
050000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 1e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 0.0001,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"params": [
|
| 18 |
+
0,
|
| 19 |
+
1,
|
| 20 |
+
2,
|
| 21 |
+
3,
|
| 22 |
+
4,
|
| 23 |
+
5,
|
| 24 |
+
6,
|
| 25 |
+
7,
|
| 26 |
+
8,
|
| 27 |
+
9,
|
| 28 |
+
10,
|
| 29 |
+
11,
|
| 30 |
+
12,
|
| 31 |
+
13,
|
| 32 |
+
14,
|
| 33 |
+
15,
|
| 34 |
+
16,
|
| 35 |
+
17,
|
| 36 |
+
18,
|
| 37 |
+
19,
|
| 38 |
+
20,
|
| 39 |
+
21,
|
| 40 |
+
22,
|
| 41 |
+
23,
|
| 42 |
+
24,
|
| 43 |
+
25,
|
| 44 |
+
26,
|
| 45 |
+
27,
|
| 46 |
+
28,
|
| 47 |
+
29,
|
| 48 |
+
30,
|
| 49 |
+
31,
|
| 50 |
+
32,
|
| 51 |
+
33,
|
| 52 |
+
34,
|
| 53 |
+
35,
|
| 54 |
+
36,
|
| 55 |
+
37,
|
| 56 |
+
38,
|
| 57 |
+
39,
|
| 58 |
+
40,
|
| 59 |
+
41,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
47,
|
| 66 |
+
48,
|
| 67 |
+
49,
|
| 68 |
+
50,
|
| 69 |
+
51,
|
| 70 |
+
52,
|
| 71 |
+
53,
|
| 72 |
+
54,
|
| 73 |
+
55,
|
| 74 |
+
56,
|
| 75 |
+
57,
|
| 76 |
+
58,
|
| 77 |
+
59,
|
| 78 |
+
60,
|
| 79 |
+
61,
|
| 80 |
+
62,
|
| 81 |
+
63,
|
| 82 |
+
64,
|
| 83 |
+
65,
|
| 84 |
+
66,
|
| 85 |
+
67,
|
| 86 |
+
68,
|
| 87 |
+
69,
|
| 88 |
+
70,
|
| 89 |
+
71,
|
| 90 |
+
72,
|
| 91 |
+
73,
|
| 92 |
+
74,
|
| 93 |
+
75,
|
| 94 |
+
76,
|
| 95 |
+
77,
|
| 96 |
+
78,
|
| 97 |
+
79,
|
| 98 |
+
80,
|
| 99 |
+
81,
|
| 100 |
+
82,
|
| 101 |
+
83,
|
| 102 |
+
84,
|
| 103 |
+
85,
|
| 104 |
+
86,
|
| 105 |
+
87,
|
| 106 |
+
88,
|
| 107 |
+
89,
|
| 108 |
+
90,
|
| 109 |
+
91,
|
| 110 |
+
92,
|
| 111 |
+
93,
|
| 112 |
+
94,
|
| 113 |
+
95,
|
| 114 |
+
96,
|
| 115 |
+
97,
|
| 116 |
+
98,
|
| 117 |
+
99,
|
| 118 |
+
100,
|
| 119 |
+
101,
|
| 120 |
+
102,
|
| 121 |
+
103,
|
| 122 |
+
104,
|
| 123 |
+
105,
|
| 124 |
+
106,
|
| 125 |
+
107,
|
| 126 |
+
108,
|
| 127 |
+
109,
|
| 128 |
+
110,
|
| 129 |
+
111,
|
| 130 |
+
112,
|
| 131 |
+
113,
|
| 132 |
+
114,
|
| 133 |
+
115,
|
| 134 |
+
116,
|
| 135 |
+
117,
|
| 136 |
+
118,
|
| 137 |
+
119,
|
| 138 |
+
120,
|
| 139 |
+
121,
|
| 140 |
+
122,
|
| 141 |
+
123,
|
| 142 |
+
124,
|
| 143 |
+
125,
|
| 144 |
+
126,
|
| 145 |
+
127,
|
| 146 |
+
128,
|
| 147 |
+
129,
|
| 148 |
+
130,
|
| 149 |
+
131,
|
| 150 |
+
132
|
| 151 |
+
]
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"lr": 1e-05,
|
| 155 |
+
"betas": [
|
| 156 |
+
0.9,
|
| 157 |
+
0.999
|
| 158 |
+
],
|
| 159 |
+
"eps": 1e-08,
|
| 160 |
+
"weight_decay": 0.0001,
|
| 161 |
+
"amsgrad": false,
|
| 162 |
+
"maximize": false,
|
| 163 |
+
"foreach": null,
|
| 164 |
+
"capturable": false,
|
| 165 |
+
"differentiable": false,
|
| 166 |
+
"fused": null,
|
| 167 |
+
"decoupled_weight_decay": true,
|
| 168 |
+
"params": [
|
| 169 |
+
133,
|
| 170 |
+
134,
|
| 171 |
+
135,
|
| 172 |
+
136,
|
| 173 |
+
137,
|
| 174 |
+
138,
|
| 175 |
+
139,
|
| 176 |
+
140,
|
| 177 |
+
141,
|
| 178 |
+
142,
|
| 179 |
+
143,
|
| 180 |
+
144,
|
| 181 |
+
145,
|
| 182 |
+
146,
|
| 183 |
+
147,
|
| 184 |
+
148,
|
| 185 |
+
149,
|
| 186 |
+
150,
|
| 187 |
+
151,
|
| 188 |
+
152
|
| 189 |
+
]
|
| 190 |
+
}
|
| 191 |
+
]
|
050000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bbbcee40ae5119a6528717489637257ba6b20bb3cb1dd40b71ab42dfd0134f6
|
| 3 |
+
size 412817652
|
050000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ccf7cdabf2451ac71f2950e7af632a111d678baf76c36d2313e977d947d85d
|
| 3 |
+
size 15708
|
050000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 50000
|
| 3 |
+
}
|
060000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"normalization_mapping": {
|
| 5 |
+
"VISUAL": "MEAN_STD",
|
| 6 |
+
"STATE": "MEAN_STD",
|
| 7 |
+
"ACTION": "MEAN_STD"
|
| 8 |
+
},
|
| 9 |
+
"input_features": {
|
| 10 |
+
"observation.state": {
|
| 11 |
+
"type": "STATE",
|
| 12 |
+
"shape": [
|
| 13 |
+
6
|
| 14 |
+
]
|
| 15 |
+
},
|
| 16 |
+
"observation.images.front": {
|
| 17 |
+
"type": "VISUAL",
|
| 18 |
+
"shape": [
|
| 19 |
+
3,
|
| 20 |
+
480,
|
| 21 |
+
640
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"observation.images.overhead": {
|
| 25 |
+
"type": "VISUAL",
|
| 26 |
+
"shape": [
|
| 27 |
+
3,
|
| 28 |
+
480,
|
| 29 |
+
640
|
| 30 |
+
]
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"output_features": {
|
| 34 |
+
"action": {
|
| 35 |
+
"type": "ACTION",
|
| 36 |
+
"shape": [
|
| 37 |
+
6
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"device": "cuda",
|
| 42 |
+
"use_amp": false,
|
| 43 |
+
"push_to_hub": true,
|
| 44 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 45 |
+
"private": null,
|
| 46 |
+
"tags": null,
|
| 47 |
+
"license": null,
|
| 48 |
+
"chunk_size": 100,
|
| 49 |
+
"n_action_steps": 100,
|
| 50 |
+
"vision_backbone": "resnet18",
|
| 51 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 52 |
+
"replace_final_stride_with_dilation": false,
|
| 53 |
+
"pre_norm": false,
|
| 54 |
+
"dim_model": 512,
|
| 55 |
+
"n_heads": 8,
|
| 56 |
+
"dim_feedforward": 3200,
|
| 57 |
+
"feedforward_activation": "relu",
|
| 58 |
+
"n_encoder_layers": 4,
|
| 59 |
+
"n_decoder_layers": 1,
|
| 60 |
+
"use_vae": true,
|
| 61 |
+
"latent_dim": 32,
|
| 62 |
+
"n_vae_encoder_layers": 4,
|
| 63 |
+
"temporal_ensemble_coeff": null,
|
| 64 |
+
"dropout": 0.1,
|
| 65 |
+
"kl_weight": 10.0,
|
| 66 |
+
"optimizer_lr": 1e-05,
|
| 67 |
+
"optimizer_weight_decay": 0.0001,
|
| 68 |
+
"optimizer_lr_backbone": 1e-05
|
| 69 |
+
}
|
060000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74de157dd3a29ef0c7ef3f5ae8413e0394d1a550238bcb8bb0e97b9c850344e6
|
| 3 |
+
size 206701072
|
060000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "dleon23/record-so101_2",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": false,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"revision": null,
|
| 64 |
+
"use_imagenet_stats": true,
|
| 65 |
+
"video_backend": "torchcodec"
|
| 66 |
+
},
|
| 67 |
+
"env": null,
|
| 68 |
+
"policy": {
|
| 69 |
+
"type": "act",
|
| 70 |
+
"n_obs_steps": 1,
|
| 71 |
+
"normalization_mapping": {
|
| 72 |
+
"VISUAL": "MEAN_STD",
|
| 73 |
+
"STATE": "MEAN_STD",
|
| 74 |
+
"ACTION": "MEAN_STD"
|
| 75 |
+
},
|
| 76 |
+
"input_features": {
|
| 77 |
+
"observation.state": {
|
| 78 |
+
"type": "STATE",
|
| 79 |
+
"shape": [
|
| 80 |
+
6
|
| 81 |
+
]
|
| 82 |
+
},
|
| 83 |
+
"observation.images.front": {
|
| 84 |
+
"type": "VISUAL",
|
| 85 |
+
"shape": [
|
| 86 |
+
3,
|
| 87 |
+
480,
|
| 88 |
+
640
|
| 89 |
+
]
|
| 90 |
+
},
|
| 91 |
+
"observation.images.overhead": {
|
| 92 |
+
"type": "VISUAL",
|
| 93 |
+
"shape": [
|
| 94 |
+
3,
|
| 95 |
+
480,
|
| 96 |
+
640
|
| 97 |
+
]
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"output_features": {
|
| 101 |
+
"action": {
|
| 102 |
+
"type": "ACTION",
|
| 103 |
+
"shape": [
|
| 104 |
+
6
|
| 105 |
+
]
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"device": "cuda",
|
| 109 |
+
"use_amp": false,
|
| 110 |
+
"push_to_hub": true,
|
| 111 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 112 |
+
"private": null,
|
| 113 |
+
"tags": null,
|
| 114 |
+
"license": null,
|
| 115 |
+
"chunk_size": 100,
|
| 116 |
+
"n_action_steps": 100,
|
| 117 |
+
"vision_backbone": "resnet18",
|
| 118 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 119 |
+
"replace_final_stride_with_dilation": false,
|
| 120 |
+
"pre_norm": false,
|
| 121 |
+
"dim_model": 512,
|
| 122 |
+
"n_heads": 8,
|
| 123 |
+
"dim_feedforward": 3200,
|
| 124 |
+
"feedforward_activation": "relu",
|
| 125 |
+
"n_encoder_layers": 4,
|
| 126 |
+
"n_decoder_layers": 1,
|
| 127 |
+
"use_vae": true,
|
| 128 |
+
"latent_dim": 32,
|
| 129 |
+
"n_vae_encoder_layers": 4,
|
| 130 |
+
"temporal_ensemble_coeff": null,
|
| 131 |
+
"dropout": 0.1,
|
| 132 |
+
"kl_weight": 10.0,
|
| 133 |
+
"optimizer_lr": 1e-05,
|
| 134 |
+
"optimizer_weight_decay": 0.0001,
|
| 135 |
+
"optimizer_lr_backbone": 1e-05
|
| 136 |
+
},
|
| 137 |
+
"output_dir": "outputs/train/pick_box_so101",
|
| 138 |
+
"job_name": "so101_act_training",
|
| 139 |
+
"resume": false,
|
| 140 |
+
"seed": 1000,
|
| 141 |
+
"num_workers": 4,
|
| 142 |
+
"batch_size": 8,
|
| 143 |
+
"steps": 100000,
|
| 144 |
+
"eval_freq": 20000,
|
| 145 |
+
"log_freq": 200,
|
| 146 |
+
"save_checkpoint": true,
|
| 147 |
+
"save_freq": 10000,
|
| 148 |
+
"use_policy_training_preset": true,
|
| 149 |
+
"optimizer": {
|
| 150 |
+
"type": "adamw",
|
| 151 |
+
"lr": 1e-05,
|
| 152 |
+
"weight_decay": 0.0001,
|
| 153 |
+
"grad_clip_norm": 10.0,
|
| 154 |
+
"betas": [
|
| 155 |
+
0.9,
|
| 156 |
+
0.999
|
| 157 |
+
],
|
| 158 |
+
"eps": 1e-08
|
| 159 |
+
},
|
| 160 |
+
"scheduler": null,
|
| 161 |
+
"eval": {
|
| 162 |
+
"n_episodes": 50,
|
| 163 |
+
"batch_size": 50,
|
| 164 |
+
"use_async_envs": false
|
| 165 |
+
},
|
| 166 |
+
"wandb": {
|
| 167 |
+
"enable": true,
|
| 168 |
+
"disable_artifact": false,
|
| 169 |
+
"project": "lerobot",
|
| 170 |
+
"entity": null,
|
| 171 |
+
"notes": null,
|
| 172 |
+
"run_id": "9kt9ehbs",
|
| 173 |
+
"mode": null
|
| 174 |
+
}
|
| 175 |
+
}
|
060000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 1e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 0.0001,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"params": [
|
| 18 |
+
0,
|
| 19 |
+
1,
|
| 20 |
+
2,
|
| 21 |
+
3,
|
| 22 |
+
4,
|
| 23 |
+
5,
|
| 24 |
+
6,
|
| 25 |
+
7,
|
| 26 |
+
8,
|
| 27 |
+
9,
|
| 28 |
+
10,
|
| 29 |
+
11,
|
| 30 |
+
12,
|
| 31 |
+
13,
|
| 32 |
+
14,
|
| 33 |
+
15,
|
| 34 |
+
16,
|
| 35 |
+
17,
|
| 36 |
+
18,
|
| 37 |
+
19,
|
| 38 |
+
20,
|
| 39 |
+
21,
|
| 40 |
+
22,
|
| 41 |
+
23,
|
| 42 |
+
24,
|
| 43 |
+
25,
|
| 44 |
+
26,
|
| 45 |
+
27,
|
| 46 |
+
28,
|
| 47 |
+
29,
|
| 48 |
+
30,
|
| 49 |
+
31,
|
| 50 |
+
32,
|
| 51 |
+
33,
|
| 52 |
+
34,
|
| 53 |
+
35,
|
| 54 |
+
36,
|
| 55 |
+
37,
|
| 56 |
+
38,
|
| 57 |
+
39,
|
| 58 |
+
40,
|
| 59 |
+
41,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
47,
|
| 66 |
+
48,
|
| 67 |
+
49,
|
| 68 |
+
50,
|
| 69 |
+
51,
|
| 70 |
+
52,
|
| 71 |
+
53,
|
| 72 |
+
54,
|
| 73 |
+
55,
|
| 74 |
+
56,
|
| 75 |
+
57,
|
| 76 |
+
58,
|
| 77 |
+
59,
|
| 78 |
+
60,
|
| 79 |
+
61,
|
| 80 |
+
62,
|
| 81 |
+
63,
|
| 82 |
+
64,
|
| 83 |
+
65,
|
| 84 |
+
66,
|
| 85 |
+
67,
|
| 86 |
+
68,
|
| 87 |
+
69,
|
| 88 |
+
70,
|
| 89 |
+
71,
|
| 90 |
+
72,
|
| 91 |
+
73,
|
| 92 |
+
74,
|
| 93 |
+
75,
|
| 94 |
+
76,
|
| 95 |
+
77,
|
| 96 |
+
78,
|
| 97 |
+
79,
|
| 98 |
+
80,
|
| 99 |
+
81,
|
| 100 |
+
82,
|
| 101 |
+
83,
|
| 102 |
+
84,
|
| 103 |
+
85,
|
| 104 |
+
86,
|
| 105 |
+
87,
|
| 106 |
+
88,
|
| 107 |
+
89,
|
| 108 |
+
90,
|
| 109 |
+
91,
|
| 110 |
+
92,
|
| 111 |
+
93,
|
| 112 |
+
94,
|
| 113 |
+
95,
|
| 114 |
+
96,
|
| 115 |
+
97,
|
| 116 |
+
98,
|
| 117 |
+
99,
|
| 118 |
+
100,
|
| 119 |
+
101,
|
| 120 |
+
102,
|
| 121 |
+
103,
|
| 122 |
+
104,
|
| 123 |
+
105,
|
| 124 |
+
106,
|
| 125 |
+
107,
|
| 126 |
+
108,
|
| 127 |
+
109,
|
| 128 |
+
110,
|
| 129 |
+
111,
|
| 130 |
+
112,
|
| 131 |
+
113,
|
| 132 |
+
114,
|
| 133 |
+
115,
|
| 134 |
+
116,
|
| 135 |
+
117,
|
| 136 |
+
118,
|
| 137 |
+
119,
|
| 138 |
+
120,
|
| 139 |
+
121,
|
| 140 |
+
122,
|
| 141 |
+
123,
|
| 142 |
+
124,
|
| 143 |
+
125,
|
| 144 |
+
126,
|
| 145 |
+
127,
|
| 146 |
+
128,
|
| 147 |
+
129,
|
| 148 |
+
130,
|
| 149 |
+
131,
|
| 150 |
+
132
|
| 151 |
+
]
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"lr": 1e-05,
|
| 155 |
+
"betas": [
|
| 156 |
+
0.9,
|
| 157 |
+
0.999
|
| 158 |
+
],
|
| 159 |
+
"eps": 1e-08,
|
| 160 |
+
"weight_decay": 0.0001,
|
| 161 |
+
"amsgrad": false,
|
| 162 |
+
"maximize": false,
|
| 163 |
+
"foreach": null,
|
| 164 |
+
"capturable": false,
|
| 165 |
+
"differentiable": false,
|
| 166 |
+
"fused": null,
|
| 167 |
+
"decoupled_weight_decay": true,
|
| 168 |
+
"params": [
|
| 169 |
+
133,
|
| 170 |
+
134,
|
| 171 |
+
135,
|
| 172 |
+
136,
|
| 173 |
+
137,
|
| 174 |
+
138,
|
| 175 |
+
139,
|
| 176 |
+
140,
|
| 177 |
+
141,
|
| 178 |
+
142,
|
| 179 |
+
143,
|
| 180 |
+
144,
|
| 181 |
+
145,
|
| 182 |
+
146,
|
| 183 |
+
147,
|
| 184 |
+
148,
|
| 185 |
+
149,
|
| 186 |
+
150,
|
| 187 |
+
151,
|
| 188 |
+
152
|
| 189 |
+
]
|
| 190 |
+
}
|
| 191 |
+
]
|
060000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:695be2f930aa81f2c1a4c731b2772dda7847f54b2985d0d2da92ad7446dc4033
|
| 3 |
+
size 412817652
|
060000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:059e1d97e8ee218ef08f9695c23b4282aee134090d7946c91d71fa6619aa13ec
|
| 3 |
+
size 15708
|
060000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 60000
|
| 3 |
+
}
|
070000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"normalization_mapping": {
|
| 5 |
+
"VISUAL": "MEAN_STD",
|
| 6 |
+
"STATE": "MEAN_STD",
|
| 7 |
+
"ACTION": "MEAN_STD"
|
| 8 |
+
},
|
| 9 |
+
"input_features": {
|
| 10 |
+
"observation.state": {
|
| 11 |
+
"type": "STATE",
|
| 12 |
+
"shape": [
|
| 13 |
+
6
|
| 14 |
+
]
|
| 15 |
+
},
|
| 16 |
+
"observation.images.front": {
|
| 17 |
+
"type": "VISUAL",
|
| 18 |
+
"shape": [
|
| 19 |
+
3,
|
| 20 |
+
480,
|
| 21 |
+
640
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"observation.images.overhead": {
|
| 25 |
+
"type": "VISUAL",
|
| 26 |
+
"shape": [
|
| 27 |
+
3,
|
| 28 |
+
480,
|
| 29 |
+
640
|
| 30 |
+
]
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"output_features": {
|
| 34 |
+
"action": {
|
| 35 |
+
"type": "ACTION",
|
| 36 |
+
"shape": [
|
| 37 |
+
6
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"device": "cuda",
|
| 42 |
+
"use_amp": false,
|
| 43 |
+
"push_to_hub": true,
|
| 44 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 45 |
+
"private": null,
|
| 46 |
+
"tags": null,
|
| 47 |
+
"license": null,
|
| 48 |
+
"chunk_size": 100,
|
| 49 |
+
"n_action_steps": 100,
|
| 50 |
+
"vision_backbone": "resnet18",
|
| 51 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 52 |
+
"replace_final_stride_with_dilation": false,
|
| 53 |
+
"pre_norm": false,
|
| 54 |
+
"dim_model": 512,
|
| 55 |
+
"n_heads": 8,
|
| 56 |
+
"dim_feedforward": 3200,
|
| 57 |
+
"feedforward_activation": "relu",
|
| 58 |
+
"n_encoder_layers": 4,
|
| 59 |
+
"n_decoder_layers": 1,
|
| 60 |
+
"use_vae": true,
|
| 61 |
+
"latent_dim": 32,
|
| 62 |
+
"n_vae_encoder_layers": 4,
|
| 63 |
+
"temporal_ensemble_coeff": null,
|
| 64 |
+
"dropout": 0.1,
|
| 65 |
+
"kl_weight": 10.0,
|
| 66 |
+
"optimizer_lr": 1e-05,
|
| 67 |
+
"optimizer_weight_decay": 0.0001,
|
| 68 |
+
"optimizer_lr_backbone": 1e-05
|
| 69 |
+
}
|
070000/pretrained_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5beb56f3f5e51ca2032677bff40f8a4879fa567ff89ed74f569e5bbc0a90fa35
|
| 3 |
+
size 206701072
|
070000/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "dleon23/record-so101_2",
|
| 4 |
+
"root": null,
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": false,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"revision": null,
|
| 64 |
+
"use_imagenet_stats": true,
|
| 65 |
+
"video_backend": "torchcodec"
|
| 66 |
+
},
|
| 67 |
+
"env": null,
|
| 68 |
+
"policy": {
|
| 69 |
+
"type": "act",
|
| 70 |
+
"n_obs_steps": 1,
|
| 71 |
+
"normalization_mapping": {
|
| 72 |
+
"VISUAL": "MEAN_STD",
|
| 73 |
+
"STATE": "MEAN_STD",
|
| 74 |
+
"ACTION": "MEAN_STD"
|
| 75 |
+
},
|
| 76 |
+
"input_features": {
|
| 77 |
+
"observation.state": {
|
| 78 |
+
"type": "STATE",
|
| 79 |
+
"shape": [
|
| 80 |
+
6
|
| 81 |
+
]
|
| 82 |
+
},
|
| 83 |
+
"observation.images.front": {
|
| 84 |
+
"type": "VISUAL",
|
| 85 |
+
"shape": [
|
| 86 |
+
3,
|
| 87 |
+
480,
|
| 88 |
+
640
|
| 89 |
+
]
|
| 90 |
+
},
|
| 91 |
+
"observation.images.overhead": {
|
| 92 |
+
"type": "VISUAL",
|
| 93 |
+
"shape": [
|
| 94 |
+
3,
|
| 95 |
+
480,
|
| 96 |
+
640
|
| 97 |
+
]
|
| 98 |
+
}
|
| 99 |
+
},
|
| 100 |
+
"output_features": {
|
| 101 |
+
"action": {
|
| 102 |
+
"type": "ACTION",
|
| 103 |
+
"shape": [
|
| 104 |
+
6
|
| 105 |
+
]
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
"device": "cuda",
|
| 109 |
+
"use_amp": false,
|
| 110 |
+
"push_to_hub": true,
|
| 111 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 112 |
+
"private": null,
|
| 113 |
+
"tags": null,
|
| 114 |
+
"license": null,
|
| 115 |
+
"chunk_size": 100,
|
| 116 |
+
"n_action_steps": 100,
|
| 117 |
+
"vision_backbone": "resnet18",
|
| 118 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 119 |
+
"replace_final_stride_with_dilation": false,
|
| 120 |
+
"pre_norm": false,
|
| 121 |
+
"dim_model": 512,
|
| 122 |
+
"n_heads": 8,
|
| 123 |
+
"dim_feedforward": 3200,
|
| 124 |
+
"feedforward_activation": "relu",
|
| 125 |
+
"n_encoder_layers": 4,
|
| 126 |
+
"n_decoder_layers": 1,
|
| 127 |
+
"use_vae": true,
|
| 128 |
+
"latent_dim": 32,
|
| 129 |
+
"n_vae_encoder_layers": 4,
|
| 130 |
+
"temporal_ensemble_coeff": null,
|
| 131 |
+
"dropout": 0.1,
|
| 132 |
+
"kl_weight": 10.0,
|
| 133 |
+
"optimizer_lr": 1e-05,
|
| 134 |
+
"optimizer_weight_decay": 0.0001,
|
| 135 |
+
"optimizer_lr_backbone": 1e-05
|
| 136 |
+
},
|
| 137 |
+
"output_dir": "outputs/train/pick_box_so101",
|
| 138 |
+
"job_name": "so101_act_training",
|
| 139 |
+
"resume": false,
|
| 140 |
+
"seed": 1000,
|
| 141 |
+
"num_workers": 4,
|
| 142 |
+
"batch_size": 8,
|
| 143 |
+
"steps": 100000,
|
| 144 |
+
"eval_freq": 20000,
|
| 145 |
+
"log_freq": 200,
|
| 146 |
+
"save_checkpoint": true,
|
| 147 |
+
"save_freq": 10000,
|
| 148 |
+
"use_policy_training_preset": true,
|
| 149 |
+
"optimizer": {
|
| 150 |
+
"type": "adamw",
|
| 151 |
+
"lr": 1e-05,
|
| 152 |
+
"weight_decay": 0.0001,
|
| 153 |
+
"grad_clip_norm": 10.0,
|
| 154 |
+
"betas": [
|
| 155 |
+
0.9,
|
| 156 |
+
0.999
|
| 157 |
+
],
|
| 158 |
+
"eps": 1e-08
|
| 159 |
+
},
|
| 160 |
+
"scheduler": null,
|
| 161 |
+
"eval": {
|
| 162 |
+
"n_episodes": 50,
|
| 163 |
+
"batch_size": 50,
|
| 164 |
+
"use_async_envs": false
|
| 165 |
+
},
|
| 166 |
+
"wandb": {
|
| 167 |
+
"enable": true,
|
| 168 |
+
"disable_artifact": false,
|
| 169 |
+
"project": "lerobot",
|
| 170 |
+
"entity": null,
|
| 171 |
+
"notes": null,
|
| 172 |
+
"run_id": "9kt9ehbs",
|
| 173 |
+
"mode": null
|
| 174 |
+
}
|
| 175 |
+
}
|
070000/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 1e-05,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 0.0001,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"params": [
|
| 18 |
+
0,
|
| 19 |
+
1,
|
| 20 |
+
2,
|
| 21 |
+
3,
|
| 22 |
+
4,
|
| 23 |
+
5,
|
| 24 |
+
6,
|
| 25 |
+
7,
|
| 26 |
+
8,
|
| 27 |
+
9,
|
| 28 |
+
10,
|
| 29 |
+
11,
|
| 30 |
+
12,
|
| 31 |
+
13,
|
| 32 |
+
14,
|
| 33 |
+
15,
|
| 34 |
+
16,
|
| 35 |
+
17,
|
| 36 |
+
18,
|
| 37 |
+
19,
|
| 38 |
+
20,
|
| 39 |
+
21,
|
| 40 |
+
22,
|
| 41 |
+
23,
|
| 42 |
+
24,
|
| 43 |
+
25,
|
| 44 |
+
26,
|
| 45 |
+
27,
|
| 46 |
+
28,
|
| 47 |
+
29,
|
| 48 |
+
30,
|
| 49 |
+
31,
|
| 50 |
+
32,
|
| 51 |
+
33,
|
| 52 |
+
34,
|
| 53 |
+
35,
|
| 54 |
+
36,
|
| 55 |
+
37,
|
| 56 |
+
38,
|
| 57 |
+
39,
|
| 58 |
+
40,
|
| 59 |
+
41,
|
| 60 |
+
42,
|
| 61 |
+
43,
|
| 62 |
+
44,
|
| 63 |
+
45,
|
| 64 |
+
46,
|
| 65 |
+
47,
|
| 66 |
+
48,
|
| 67 |
+
49,
|
| 68 |
+
50,
|
| 69 |
+
51,
|
| 70 |
+
52,
|
| 71 |
+
53,
|
| 72 |
+
54,
|
| 73 |
+
55,
|
| 74 |
+
56,
|
| 75 |
+
57,
|
| 76 |
+
58,
|
| 77 |
+
59,
|
| 78 |
+
60,
|
| 79 |
+
61,
|
| 80 |
+
62,
|
| 81 |
+
63,
|
| 82 |
+
64,
|
| 83 |
+
65,
|
| 84 |
+
66,
|
| 85 |
+
67,
|
| 86 |
+
68,
|
| 87 |
+
69,
|
| 88 |
+
70,
|
| 89 |
+
71,
|
| 90 |
+
72,
|
| 91 |
+
73,
|
| 92 |
+
74,
|
| 93 |
+
75,
|
| 94 |
+
76,
|
| 95 |
+
77,
|
| 96 |
+
78,
|
| 97 |
+
79,
|
| 98 |
+
80,
|
| 99 |
+
81,
|
| 100 |
+
82,
|
| 101 |
+
83,
|
| 102 |
+
84,
|
| 103 |
+
85,
|
| 104 |
+
86,
|
| 105 |
+
87,
|
| 106 |
+
88,
|
| 107 |
+
89,
|
| 108 |
+
90,
|
| 109 |
+
91,
|
| 110 |
+
92,
|
| 111 |
+
93,
|
| 112 |
+
94,
|
| 113 |
+
95,
|
| 114 |
+
96,
|
| 115 |
+
97,
|
| 116 |
+
98,
|
| 117 |
+
99,
|
| 118 |
+
100,
|
| 119 |
+
101,
|
| 120 |
+
102,
|
| 121 |
+
103,
|
| 122 |
+
104,
|
| 123 |
+
105,
|
| 124 |
+
106,
|
| 125 |
+
107,
|
| 126 |
+
108,
|
| 127 |
+
109,
|
| 128 |
+
110,
|
| 129 |
+
111,
|
| 130 |
+
112,
|
| 131 |
+
113,
|
| 132 |
+
114,
|
| 133 |
+
115,
|
| 134 |
+
116,
|
| 135 |
+
117,
|
| 136 |
+
118,
|
| 137 |
+
119,
|
| 138 |
+
120,
|
| 139 |
+
121,
|
| 140 |
+
122,
|
| 141 |
+
123,
|
| 142 |
+
124,
|
| 143 |
+
125,
|
| 144 |
+
126,
|
| 145 |
+
127,
|
| 146 |
+
128,
|
| 147 |
+
129,
|
| 148 |
+
130,
|
| 149 |
+
131,
|
| 150 |
+
132
|
| 151 |
+
]
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"lr": 1e-05,
|
| 155 |
+
"betas": [
|
| 156 |
+
0.9,
|
| 157 |
+
0.999
|
| 158 |
+
],
|
| 159 |
+
"eps": 1e-08,
|
| 160 |
+
"weight_decay": 0.0001,
|
| 161 |
+
"amsgrad": false,
|
| 162 |
+
"maximize": false,
|
| 163 |
+
"foreach": null,
|
| 164 |
+
"capturable": false,
|
| 165 |
+
"differentiable": false,
|
| 166 |
+
"fused": null,
|
| 167 |
+
"decoupled_weight_decay": true,
|
| 168 |
+
"params": [
|
| 169 |
+
133,
|
| 170 |
+
134,
|
| 171 |
+
135,
|
| 172 |
+
136,
|
| 173 |
+
137,
|
| 174 |
+
138,
|
| 175 |
+
139,
|
| 176 |
+
140,
|
| 177 |
+
141,
|
| 178 |
+
142,
|
| 179 |
+
143,
|
| 180 |
+
144,
|
| 181 |
+
145,
|
| 182 |
+
146,
|
| 183 |
+
147,
|
| 184 |
+
148,
|
| 185 |
+
149,
|
| 186 |
+
150,
|
| 187 |
+
151,
|
| 188 |
+
152
|
| 189 |
+
]
|
| 190 |
+
}
|
| 191 |
+
]
|
070000/training_state/optimizer_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:609ecdc4042b2c477328a74342c70e33197480f291010ae48b61c2924e3b45e7
|
| 3 |
+
size 412817652
|
070000/training_state/rng_state.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db31228beba2beb06a502fcc4a331f6338eaa8b11d5023fd48fbfbf8bdd7fbfe
|
| 3 |
+
size 15708
|
070000/training_state/training_step.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 70000
|
| 3 |
+
}
|
080000/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "act",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"normalization_mapping": {
|
| 5 |
+
"VISUAL": "MEAN_STD",
|
| 6 |
+
"STATE": "MEAN_STD",
|
| 7 |
+
"ACTION": "MEAN_STD"
|
| 8 |
+
},
|
| 9 |
+
"input_features": {
|
| 10 |
+
"observation.state": {
|
| 11 |
+
"type": "STATE",
|
| 12 |
+
"shape": [
|
| 13 |
+
6
|
| 14 |
+
]
|
| 15 |
+
},
|
| 16 |
+
"observation.images.front": {
|
| 17 |
+
"type": "VISUAL",
|
| 18 |
+
"shape": [
|
| 19 |
+
3,
|
| 20 |
+
480,
|
| 21 |
+
640
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"observation.images.overhead": {
|
| 25 |
+
"type": "VISUAL",
|
| 26 |
+
"shape": [
|
| 27 |
+
3,
|
| 28 |
+
480,
|
| 29 |
+
640
|
| 30 |
+
]
|
| 31 |
+
}
|
| 32 |
+
},
|
| 33 |
+
"output_features": {
|
| 34 |
+
"action": {
|
| 35 |
+
"type": "ACTION",
|
| 36 |
+
"shape": [
|
| 37 |
+
6
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"device": "cuda",
|
| 42 |
+
"use_amp": false,
|
| 43 |
+
"push_to_hub": true,
|
| 44 |
+
"repo_id": "dleon23/so101_pick_box",
|
| 45 |
+
"private": null,
|
| 46 |
+
"tags": null,
|
| 47 |
+
"license": null,
|
| 48 |
+
"chunk_size": 100,
|
| 49 |
+
"n_action_steps": 100,
|
| 50 |
+
"vision_backbone": "resnet18",
|
| 51 |
+
"pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
|
| 52 |
+
"replace_final_stride_with_dilation": false,
|
| 53 |
+
"pre_norm": false,
|
| 54 |
+
"dim_model": 512,
|
| 55 |
+
"n_heads": 8,
|
| 56 |
+
"dim_feedforward": 3200,
|
| 57 |
+
"feedforward_activation": "relu",
|
| 58 |
+
"n_encoder_layers": 4,
|
| 59 |
+
"n_decoder_layers": 1,
|
| 60 |
+
"use_vae": true,
|
| 61 |
+
"latent_dim": 32,
|
| 62 |
+
"n_vae_encoder_layers": 4,
|
| 63 |
+
"temporal_ensemble_coeff": null,
|
| 64 |
+
"dropout": 0.1,
|
| 65 |
+
"kl_weight": 10.0,
|
| 66 |
+
"optimizer_lr": 1e-05,
|
| 67 |
+
"optimizer_weight_decay": 0.0001,
|
| 68 |
+
"optimizer_lr_backbone": 1e-05
|
| 69 |
+
}
|