Add files using upload-large-folder tool
Browse files- checkpoint-10000/config.json +64 -0
- checkpoint-10000/experiment_cfg/metadata.json +363 -0
- checkpoint-10000/model-00001-of-00002.safetensors +3 -0
- checkpoint-10000/model-00002-of-00002.safetensors +3 -0
- checkpoint-10000/model.safetensors.index.json +0 -0
- checkpoint-10000/optimizer.pt +3 -0
- checkpoint-10000/rng_state.pth +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/trainer_state.json +0 -0
- checkpoint-6000/config.json +64 -0
- checkpoint-6000/experiment_cfg/metadata.json +363 -0
- checkpoint-6000/model-00001-of-00002.safetensors +3 -0
- checkpoint-6000/model-00002-of-00002.safetensors +3 -0
- checkpoint-6000/model.safetensors.index.json +0 -0
- checkpoint-6000/rng_state.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/trainer_state.json +0 -0
- checkpoint-7000/config.json +64 -0
- checkpoint-7000/experiment_cfg/metadata.json +363 -0
- checkpoint-7000/model-00001-of-00002.safetensors +3 -0
- checkpoint-7000/model-00002-of-00002.safetensors +3 -0
- checkpoint-7000/model.safetensors.index.json +0 -0
- checkpoint-7000/optimizer.pt +3 -0
- checkpoint-7000/rng_state.pth +3 -0
- checkpoint-7000/scheduler.pt +3 -0
- checkpoint-7000/trainer_state.json +0 -0
- checkpoint-8000/config.json +64 -0
- checkpoint-8000/experiment_cfg/metadata.json +363 -0
- checkpoint-8000/model-00001-of-00002.safetensors +3 -0
- checkpoint-8000/model-00002-of-00002.safetensors +3 -0
- checkpoint-8000/model.safetensors.index.json +0 -0
- checkpoint-8000/optimizer.pt +3 -0
- checkpoint-8000/rng_state.pth +3 -0
- checkpoint-8000/scheduler.pt +3 -0
- checkpoint-8000/trainer_state.json +0 -0
- checkpoint-9000/config.json +64 -0
- checkpoint-9000/experiment_cfg/metadata.json +363 -0
- checkpoint-9000/model-00001-of-00002.safetensors +3 -0
- checkpoint-9000/model-00002-of-00002.safetensors +3 -0
- checkpoint-9000/model.safetensors.index.json +0 -0
- checkpoint-9000/rng_state.pth +3 -0
- checkpoint-9000/scheduler.pt +3 -0
- checkpoint-9000/trainer_state.json +0 -0
- config.json +64 -0
- experiment_cfg/metadata.json +363 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
checkpoint-10000/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_dim": 32,
|
| 3 |
+
"action_head_cfg": {
|
| 4 |
+
"action_dim": 32,
|
| 5 |
+
"action_horizon": 16,
|
| 6 |
+
"add_pos_embed": true,
|
| 7 |
+
"backbone_embedding_dim": 2048,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"cross_attention_dim": 2048,
|
| 11 |
+
"dropout": 0.2,
|
| 12 |
+
"final_dropout": true,
|
| 13 |
+
"interleave_self_attention": true,
|
| 14 |
+
"norm_type": "ada_norm",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_layers": 16,
|
| 17 |
+
"output_dim": 1024,
|
| 18 |
+
"positional_embeddings": null
|
| 19 |
+
},
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"max_action_dim": 32,
|
| 23 |
+
"max_state_dim": 64,
|
| 24 |
+
"model_dtype": "float32",
|
| 25 |
+
"noise_beta_alpha": 1.5,
|
| 26 |
+
"noise_beta_beta": 1.0,
|
| 27 |
+
"noise_s": 0.999,
|
| 28 |
+
"num_inference_timesteps": 4,
|
| 29 |
+
"num_target_vision_tokens": 32,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true,
|
| 33 |
+
"use_vlln": true,
|
| 34 |
+
"vl_self_attention_cfg": {
|
| 35 |
+
"attention_head_dim": 64,
|
| 36 |
+
"dropout": 0.2,
|
| 37 |
+
"final_dropout": true,
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_layers": 4,
|
| 40 |
+
"positional_embeddings": null
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"action_horizon": 16,
|
| 44 |
+
"architectures": [
|
| 45 |
+
"GR00T_N1_5"
|
| 46 |
+
],
|
| 47 |
+
"attn_implementation": null,
|
| 48 |
+
"backbone_cfg": {
|
| 49 |
+
"eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
|
| 50 |
+
"load_bf16": false,
|
| 51 |
+
"project_to_dim": null,
|
| 52 |
+
"reproject_vision": false,
|
| 53 |
+
"select_layer": 12,
|
| 54 |
+
"tune_llm": false,
|
| 55 |
+
"tune_visual": true,
|
| 56 |
+
"use_flash_attention": true
|
| 57 |
+
},
|
| 58 |
+
"compute_dtype": "bfloat16",
|
| 59 |
+
"hidden_size": 2048,
|
| 60 |
+
"model_dtype": "float32",
|
| 61 |
+
"model_type": "gr00t_n1_5",
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.51.3"
|
| 64 |
+
}
|
checkpoint-10000/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"white_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
-5.758017539978027,
|
| 8 |
+
45.33951950073242,
|
| 9 |
+
83.51254272460938,
|
| 10 |
+
98.8018798828125,
|
| 11 |
+
-3.8293497562408447
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-60.932945251464844,
|
| 15 |
+
-99.40953063964844,
|
| 16 |
+
-80.3763427734375,
|
| 17 |
+
30.851518630981445,
|
| 18 |
+
-58.36545944213867
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-41.30015563964844,
|
| 22 |
+
-59.61644744873047,
|
| 23 |
+
11.656304359436035,
|
| 24 |
+
92.30885314941406,
|
| 25 |
+
-48.28321838378906
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
12.557931900024414,
|
| 29 |
+
49.788997650146484,
|
| 30 |
+
33.65494918823242,
|
| 31 |
+
11.678942680358887,
|
| 32 |
+
12.509681701660156
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-60.71428680419922,
|
| 36 |
+
-99.40953063964844,
|
| 37 |
+
-61.021507263183594,
|
| 38 |
+
46.82926918029785,
|
| 39 |
+
-57.800052642822266
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
-6.778425693511963,
|
| 43 |
+
44.580345153808594,
|
| 44 |
+
48.11827850341797,
|
| 45 |
+
98.8018798828125,
|
| 46 |
+
-11.231045722961426
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"white_gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
34.37900161743164
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
1.7285531759262085
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
6.319039821624756
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
7.589016437530518
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
1.8565940856933594
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
30.34571075439453
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"blue_arm": {
|
| 70 |
+
"max": [
|
| 71 |
+
58.738216400146484,
|
| 72 |
+
18.63117790222168,
|
| 73 |
+
75.27173614501953,
|
| 74 |
+
99.04803466796875,
|
| 75 |
+
-4.080061435699463
|
| 76 |
+
],
|
| 77 |
+
"min": [
|
| 78 |
+
-16.533720016479492,
|
| 79 |
+
-99.070556640625,
|
| 80 |
+
-52.8079719543457,
|
| 81 |
+
66.85417938232422,
|
| 82 |
+
-58.48088455200195
|
| 83 |
+
],
|
| 84 |
+
"mean": [
|
| 85 |
+
22.58572769165039,
|
| 86 |
+
-46.04561233520508,
|
| 87 |
+
4.261409282684326,
|
| 88 |
+
95.5960922241211,
|
| 89 |
+
-31.681655883789062
|
| 90 |
+
],
|
| 91 |
+
"std": [
|
| 92 |
+
24.668598175048828,
|
| 93 |
+
42.83842086791992,
|
| 94 |
+
25.97476577758789,
|
| 95 |
+
6.019741535186768,
|
| 96 |
+
16.340681076049805
|
| 97 |
+
],
|
| 98 |
+
"q01": [
|
| 99 |
+
-16.316171646118164,
|
| 100 |
+
-98.90156555175781,
|
| 101 |
+
-47.55434799194336,
|
| 102 |
+
74.43184829711915,
|
| 103 |
+
-55.760841369628906
|
| 104 |
+
],
|
| 105 |
+
"q99": [
|
| 106 |
+
56.85279083251953,
|
| 107 |
+
17.78622817993164,
|
| 108 |
+
54.619564056396484,
|
| 109 |
+
99.04803466796875,
|
| 110 |
+
-4.285347938537598
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
"blue_gripper": {
|
| 114 |
+
"max": [
|
| 115 |
+
40.255374908447266
|
| 116 |
+
],
|
| 117 |
+
"min": [
|
| 118 |
+
1.0080645084381104
|
| 119 |
+
],
|
| 120 |
+
"mean": [
|
| 121 |
+
5.813619613647461
|
| 122 |
+
],
|
| 123 |
+
"std": [
|
| 124 |
+
9.993083000183105
|
| 125 |
+
],
|
| 126 |
+
"q01": [
|
| 127 |
+
1.0080645084381104
|
| 128 |
+
],
|
| 129 |
+
"q99": [
|
| 130 |
+
37.29838562011719
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"action": {
|
| 135 |
+
"white_arm": {
|
| 136 |
+
"max": [
|
| 137 |
+
-5.325443744659424,
|
| 138 |
+
44.7691650390625,
|
| 139 |
+
83.48375701904297,
|
| 140 |
+
100.0,
|
| 141 |
+
-3.3212246894836426
|
| 142 |
+
],
|
| 143 |
+
"min": [
|
| 144 |
+
-60.724853515625,
|
| 145 |
+
-100.0,
|
| 146 |
+
-83.21299743652344,
|
| 147 |
+
30.108932495117188,
|
| 148 |
+
-58.432796478271484
|
| 149 |
+
],
|
| 150 |
+
"mean": [
|
| 151 |
+
-41.21931457519531,
|
| 152 |
+
-60.167320251464844,
|
| 153 |
+
10.704584121704102,
|
| 154 |
+
92.57025146484375,
|
| 155 |
+
-48.337284088134766
|
| 156 |
+
],
|
| 157 |
+
"std": [
|
| 158 |
+
12.604560852050781,
|
| 159 |
+
49.407814025878906,
|
| 160 |
+
34.10797119140625,
|
| 161 |
+
12.075830459594727,
|
| 162 |
+
12.521093368530273
|
| 163 |
+
],
|
| 164 |
+
"q01": [
|
| 165 |
+
-60.502960205078125,
|
| 166 |
+
-99.83058166503906,
|
| 167 |
+
-63.963899002075195,
|
| 168 |
+
47.06405281066895,
|
| 169 |
+
-57.81006622314453
|
| 170 |
+
],
|
| 171 |
+
"q99": [
|
| 172 |
+
-6.804733753204346,
|
| 173 |
+
42.9783979797363,
|
| 174 |
+
47.743682861328125,
|
| 175 |
+
100.0,
|
| 176 |
+
-11.053450584411621
|
| 177 |
+
]
|
| 178 |
+
},
|
| 179 |
+
"white_gripper": {
|
| 180 |
+
"max": [
|
| 181 |
+
34.68433380126953
|
| 182 |
+
],
|
| 183 |
+
"min": [
|
| 184 |
+
1.3250194787979126
|
| 185 |
+
],
|
| 186 |
+
"mean": [
|
| 187 |
+
5.815976142883301
|
| 188 |
+
],
|
| 189 |
+
"std": [
|
| 190 |
+
7.803332805633545
|
| 191 |
+
],
|
| 192 |
+
"q01": [
|
| 193 |
+
1.6367887258529663
|
| 194 |
+
],
|
| 195 |
+
"q99": [
|
| 196 |
+
30.709274291992188
|
| 197 |
+
]
|
| 198 |
+
},
|
| 199 |
+
"blue_arm": {
|
| 200 |
+
"max": [
|
| 201 |
+
59.20177459716797,
|
| 202 |
+
18.235294342041016,
|
| 203 |
+
56.36856460571289,
|
| 204 |
+
99.4778060913086,
|
| 205 |
+
-3.9603960514068604
|
| 206 |
+
],
|
| 207 |
+
"min": [
|
| 208 |
+
-16.629711151123047,
|
| 209 |
+
-99.4117660522461,
|
| 210 |
+
-55.55555725097656,
|
| 211 |
+
65.97040557861328,
|
| 212 |
+
-58.780616760253906
|
| 213 |
+
],
|
| 214 |
+
"mean": [
|
| 215 |
+
22.72244644165039,
|
| 216 |
+
-46.86748123168945,
|
| 217 |
+
3.5456254482269287,
|
| 218 |
+
95.69131469726562,
|
| 219 |
+
-31.745248794555664
|
| 220 |
+
],
|
| 221 |
+
"std": [
|
| 222 |
+
24.648967742919922,
|
| 223 |
+
42.451499938964844,
|
| 224 |
+
26.123699188232422,
|
| 225 |
+
6.368340015411377,
|
| 226 |
+
16.331010818481445
|
| 227 |
+
],
|
| 228 |
+
"q01": [
|
| 229 |
+
-16.18625259399414,
|
| 230 |
+
-98.9916000366211,
|
| 231 |
+
-49.68383026123047,
|
| 232 |
+
73.62924194335938,
|
| 233 |
+
-55.549766540527344
|
| 234 |
+
],
|
| 235 |
+
"q99": [
|
| 236 |
+
57.058387756347656,
|
| 237 |
+
16.554622650146484,
|
| 238 |
+
52.93586349487305,
|
| 239 |
+
99.39077758789062,
|
| 240 |
+
-4.273058891296387
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
"blue_gripper": {
|
| 244 |
+
"max": [
|
| 245 |
+
40.44117736816406
|
| 246 |
+
],
|
| 247 |
+
"min": [
|
| 248 |
+
0.0
|
| 249 |
+
],
|
| 250 |
+
"mean": [
|
| 251 |
+
5.49310302734375
|
| 252 |
+
],
|
| 253 |
+
"std": [
|
| 254 |
+
10.243758201599121
|
| 255 |
+
],
|
| 256 |
+
"q01": [
|
| 257 |
+
0.898692786693573
|
| 258 |
+
],
|
| 259 |
+
"q99": [
|
| 260 |
+
37.33660125732422
|
| 261 |
+
]
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
+
"modalities": {
|
| 266 |
+
"video": {
|
| 267 |
+
"global_top": {
|
| 268 |
+
"resolution": [
|
| 269 |
+
1280,
|
| 270 |
+
720
|
| 271 |
+
],
|
| 272 |
+
"channels": 3,
|
| 273 |
+
"fps": 30.0
|
| 274 |
+
},
|
| 275 |
+
"white_front": {
|
| 276 |
+
"resolution": [
|
| 277 |
+
640,
|
| 278 |
+
480
|
| 279 |
+
],
|
| 280 |
+
"channels": 3,
|
| 281 |
+
"fps": 30.0
|
| 282 |
+
},
|
| 283 |
+
"blue_front": {
|
| 284 |
+
"resolution": [
|
| 285 |
+
640,
|
| 286 |
+
480
|
| 287 |
+
],
|
| 288 |
+
"channels": 3,
|
| 289 |
+
"fps": 30.0
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"state": {
|
| 293 |
+
"white_arm": {
|
| 294 |
+
"absolute": true,
|
| 295 |
+
"rotation_type": null,
|
| 296 |
+
"shape": [
|
| 297 |
+
5
|
| 298 |
+
],
|
| 299 |
+
"continuous": true
|
| 300 |
+
},
|
| 301 |
+
"white_gripper": {
|
| 302 |
+
"absolute": true,
|
| 303 |
+
"rotation_type": null,
|
| 304 |
+
"shape": [
|
| 305 |
+
1
|
| 306 |
+
],
|
| 307 |
+
"continuous": true
|
| 308 |
+
},
|
| 309 |
+
"blue_arm": {
|
| 310 |
+
"absolute": true,
|
| 311 |
+
"rotation_type": null,
|
| 312 |
+
"shape": [
|
| 313 |
+
5
|
| 314 |
+
],
|
| 315 |
+
"continuous": true
|
| 316 |
+
},
|
| 317 |
+
"blue_gripper": {
|
| 318 |
+
"absolute": true,
|
| 319 |
+
"rotation_type": null,
|
| 320 |
+
"shape": [
|
| 321 |
+
1
|
| 322 |
+
],
|
| 323 |
+
"continuous": true
|
| 324 |
+
}
|
| 325 |
+
},
|
| 326 |
+
"action": {
|
| 327 |
+
"white_arm": {
|
| 328 |
+
"absolute": true,
|
| 329 |
+
"rotation_type": null,
|
| 330 |
+
"shape": [
|
| 331 |
+
5
|
| 332 |
+
],
|
| 333 |
+
"continuous": true
|
| 334 |
+
},
|
| 335 |
+
"white_gripper": {
|
| 336 |
+
"absolute": true,
|
| 337 |
+
"rotation_type": null,
|
| 338 |
+
"shape": [
|
| 339 |
+
1
|
| 340 |
+
],
|
| 341 |
+
"continuous": true
|
| 342 |
+
},
|
| 343 |
+
"blue_arm": {
|
| 344 |
+
"absolute": true,
|
| 345 |
+
"rotation_type": null,
|
| 346 |
+
"shape": [
|
| 347 |
+
5
|
| 348 |
+
],
|
| 349 |
+
"continuous": true
|
| 350 |
+
},
|
| 351 |
+
"blue_gripper": {
|
| 352 |
+
"absolute": true,
|
| 353 |
+
"rotation_type": null,
|
| 354 |
+
"shape": [
|
| 355 |
+
1
|
| 356 |
+
],
|
| 357 |
+
"continuous": true
|
| 358 |
+
}
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"embodiment_tag": "new_embodiment"
|
| 362 |
+
}
|
| 363 |
+
}
|
checkpoint-10000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b
|
| 3 |
+
size 4999367032
|
checkpoint-10000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d7361d737dee4d886c5178e4a1d51f67b02d217892b13e46a09fce2ce62be80
|
| 3 |
+
size 2586705312
|
checkpoint-10000/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-10000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72241cc871ecdeb131b3eea0a9d40823df9aaaad8fcae3db212a8f4d3369a1a1
|
| 3 |
+
size 4147424698
|
checkpoint-10000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7569d97fb1a9c2fd53a28890407695d9eef0c559c9c90aebe7a5de42fdf5f27
|
| 3 |
+
size 14244
|
checkpoint-10000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07356cb668b8efc440ddb2f7f81f7da3152060e81d0229922fa3b30df3313f82
|
| 3 |
+
size 1064
|
checkpoint-10000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6000/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_dim": 32,
|
| 3 |
+
"action_head_cfg": {
|
| 4 |
+
"action_dim": 32,
|
| 5 |
+
"action_horizon": 16,
|
| 6 |
+
"add_pos_embed": true,
|
| 7 |
+
"backbone_embedding_dim": 2048,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"cross_attention_dim": 2048,
|
| 11 |
+
"dropout": 0.2,
|
| 12 |
+
"final_dropout": true,
|
| 13 |
+
"interleave_self_attention": true,
|
| 14 |
+
"norm_type": "ada_norm",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_layers": 16,
|
| 17 |
+
"output_dim": 1024,
|
| 18 |
+
"positional_embeddings": null
|
| 19 |
+
},
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"max_action_dim": 32,
|
| 23 |
+
"max_state_dim": 64,
|
| 24 |
+
"model_dtype": "float32",
|
| 25 |
+
"noise_beta_alpha": 1.5,
|
| 26 |
+
"noise_beta_beta": 1.0,
|
| 27 |
+
"noise_s": 0.999,
|
| 28 |
+
"num_inference_timesteps": 4,
|
| 29 |
+
"num_target_vision_tokens": 32,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true,
|
| 33 |
+
"use_vlln": true,
|
| 34 |
+
"vl_self_attention_cfg": {
|
| 35 |
+
"attention_head_dim": 64,
|
| 36 |
+
"dropout": 0.2,
|
| 37 |
+
"final_dropout": true,
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_layers": 4,
|
| 40 |
+
"positional_embeddings": null
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"action_horizon": 16,
|
| 44 |
+
"architectures": [
|
| 45 |
+
"GR00T_N1_5"
|
| 46 |
+
],
|
| 47 |
+
"attn_implementation": null,
|
| 48 |
+
"backbone_cfg": {
|
| 49 |
+
"eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
|
| 50 |
+
"load_bf16": false,
|
| 51 |
+
"project_to_dim": null,
|
| 52 |
+
"reproject_vision": false,
|
| 53 |
+
"select_layer": 12,
|
| 54 |
+
"tune_llm": false,
|
| 55 |
+
"tune_visual": true,
|
| 56 |
+
"use_flash_attention": true
|
| 57 |
+
},
|
| 58 |
+
"compute_dtype": "bfloat16",
|
| 59 |
+
"hidden_size": 2048,
|
| 60 |
+
"model_dtype": "float32",
|
| 61 |
+
"model_type": "gr00t_n1_5",
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.51.3"
|
| 64 |
+
}
|
checkpoint-6000/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"white_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
-5.758017539978027,
|
| 8 |
+
45.33951950073242,
|
| 9 |
+
83.51254272460938,
|
| 10 |
+
98.8018798828125,
|
| 11 |
+
-3.8293497562408447
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-60.932945251464844,
|
| 15 |
+
-99.40953063964844,
|
| 16 |
+
-80.3763427734375,
|
| 17 |
+
30.851518630981445,
|
| 18 |
+
-58.36545944213867
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-41.30015563964844,
|
| 22 |
+
-59.61644744873047,
|
| 23 |
+
11.656304359436035,
|
| 24 |
+
92.30885314941406,
|
| 25 |
+
-48.28321838378906
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
12.557931900024414,
|
| 29 |
+
49.788997650146484,
|
| 30 |
+
33.65494918823242,
|
| 31 |
+
11.678942680358887,
|
| 32 |
+
12.509681701660156
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-60.71428680419922,
|
| 36 |
+
-99.40953063964844,
|
| 37 |
+
-61.021507263183594,
|
| 38 |
+
46.82926918029785,
|
| 39 |
+
-57.800052642822266
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
-6.778425693511963,
|
| 43 |
+
44.580345153808594,
|
| 44 |
+
48.11827850341797,
|
| 45 |
+
98.8018798828125,
|
| 46 |
+
-11.231045722961426
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"white_gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
34.37900161743164
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
1.7285531759262085
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
6.319039821624756
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
7.589016437530518
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
1.8565940856933594
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
30.34571075439453
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"blue_arm": {
|
| 70 |
+
"max": [
|
| 71 |
+
58.738216400146484,
|
| 72 |
+
18.63117790222168,
|
| 73 |
+
75.27173614501953,
|
| 74 |
+
99.04803466796875,
|
| 75 |
+
-4.080061435699463
|
| 76 |
+
],
|
| 77 |
+
"min": [
|
| 78 |
+
-16.533720016479492,
|
| 79 |
+
-99.070556640625,
|
| 80 |
+
-52.8079719543457,
|
| 81 |
+
66.85417938232422,
|
| 82 |
+
-58.48088455200195
|
| 83 |
+
],
|
| 84 |
+
"mean": [
|
| 85 |
+
22.58572769165039,
|
| 86 |
+
-46.04561233520508,
|
| 87 |
+
4.261409282684326,
|
| 88 |
+
95.5960922241211,
|
| 89 |
+
-31.681655883789062
|
| 90 |
+
],
|
| 91 |
+
"std": [
|
| 92 |
+
24.668598175048828,
|
| 93 |
+
42.83842086791992,
|
| 94 |
+
25.97476577758789,
|
| 95 |
+
6.019741535186768,
|
| 96 |
+
16.340681076049805
|
| 97 |
+
],
|
| 98 |
+
"q01": [
|
| 99 |
+
-16.316171646118164,
|
| 100 |
+
-98.90156555175781,
|
| 101 |
+
-47.55434799194336,
|
| 102 |
+
74.43184829711915,
|
| 103 |
+
-55.760841369628906
|
| 104 |
+
],
|
| 105 |
+
"q99": [
|
| 106 |
+
56.85279083251953,
|
| 107 |
+
17.78622817993164,
|
| 108 |
+
54.619564056396484,
|
| 109 |
+
99.04803466796875,
|
| 110 |
+
-4.285347938537598
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
"blue_gripper": {
|
| 114 |
+
"max": [
|
| 115 |
+
40.255374908447266
|
| 116 |
+
],
|
| 117 |
+
"min": [
|
| 118 |
+
1.0080645084381104
|
| 119 |
+
],
|
| 120 |
+
"mean": [
|
| 121 |
+
5.813619613647461
|
| 122 |
+
],
|
| 123 |
+
"std": [
|
| 124 |
+
9.993083000183105
|
| 125 |
+
],
|
| 126 |
+
"q01": [
|
| 127 |
+
1.0080645084381104
|
| 128 |
+
],
|
| 129 |
+
"q99": [
|
| 130 |
+
37.29838562011719
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"action": {
|
| 135 |
+
"white_arm": {
|
| 136 |
+
"max": [
|
| 137 |
+
-5.325443744659424,
|
| 138 |
+
44.7691650390625,
|
| 139 |
+
83.48375701904297,
|
| 140 |
+
100.0,
|
| 141 |
+
-3.3212246894836426
|
| 142 |
+
],
|
| 143 |
+
"min": [
|
| 144 |
+
-60.724853515625,
|
| 145 |
+
-100.0,
|
| 146 |
+
-83.21299743652344,
|
| 147 |
+
30.108932495117188,
|
| 148 |
+
-58.432796478271484
|
| 149 |
+
],
|
| 150 |
+
"mean": [
|
| 151 |
+
-41.21931457519531,
|
| 152 |
+
-60.167320251464844,
|
| 153 |
+
10.704584121704102,
|
| 154 |
+
92.57025146484375,
|
| 155 |
+
-48.337284088134766
|
| 156 |
+
],
|
| 157 |
+
"std": [
|
| 158 |
+
12.604560852050781,
|
| 159 |
+
49.407814025878906,
|
| 160 |
+
34.10797119140625,
|
| 161 |
+
12.075830459594727,
|
| 162 |
+
12.521093368530273
|
| 163 |
+
],
|
| 164 |
+
"q01": [
|
| 165 |
+
-60.502960205078125,
|
| 166 |
+
-99.83058166503906,
|
| 167 |
+
-63.963899002075195,
|
| 168 |
+
47.06405281066895,
|
| 169 |
+
-57.81006622314453
|
| 170 |
+
],
|
| 171 |
+
"q99": [
|
| 172 |
+
-6.804733753204346,
|
| 173 |
+
42.9783979797363,
|
| 174 |
+
47.743682861328125,
|
| 175 |
+
100.0,
|
| 176 |
+
-11.053450584411621
|
| 177 |
+
]
|
| 178 |
+
},
|
| 179 |
+
"white_gripper": {
|
| 180 |
+
"max": [
|
| 181 |
+
34.68433380126953
|
| 182 |
+
],
|
| 183 |
+
"min": [
|
| 184 |
+
1.3250194787979126
|
| 185 |
+
],
|
| 186 |
+
"mean": [
|
| 187 |
+
5.815976142883301
|
| 188 |
+
],
|
| 189 |
+
"std": [
|
| 190 |
+
7.803332805633545
|
| 191 |
+
],
|
| 192 |
+
"q01": [
|
| 193 |
+
1.6367887258529663
|
| 194 |
+
],
|
| 195 |
+
"q99": [
|
| 196 |
+
30.709274291992188
|
| 197 |
+
]
|
| 198 |
+
},
|
| 199 |
+
"blue_arm": {
|
| 200 |
+
"max": [
|
| 201 |
+
59.20177459716797,
|
| 202 |
+
18.235294342041016,
|
| 203 |
+
56.36856460571289,
|
| 204 |
+
99.4778060913086,
|
| 205 |
+
-3.9603960514068604
|
| 206 |
+
],
|
| 207 |
+
"min": [
|
| 208 |
+
-16.629711151123047,
|
| 209 |
+
-99.4117660522461,
|
| 210 |
+
-55.55555725097656,
|
| 211 |
+
65.97040557861328,
|
| 212 |
+
-58.780616760253906
|
| 213 |
+
],
|
| 214 |
+
"mean": [
|
| 215 |
+
22.72244644165039,
|
| 216 |
+
-46.86748123168945,
|
| 217 |
+
3.5456254482269287,
|
| 218 |
+
95.69131469726562,
|
| 219 |
+
-31.745248794555664
|
| 220 |
+
],
|
| 221 |
+
"std": [
|
| 222 |
+
24.648967742919922,
|
| 223 |
+
42.451499938964844,
|
| 224 |
+
26.123699188232422,
|
| 225 |
+
6.368340015411377,
|
| 226 |
+
16.331010818481445
|
| 227 |
+
],
|
| 228 |
+
"q01": [
|
| 229 |
+
-16.18625259399414,
|
| 230 |
+
-98.9916000366211,
|
| 231 |
+
-49.68383026123047,
|
| 232 |
+
73.62924194335938,
|
| 233 |
+
-55.549766540527344
|
| 234 |
+
],
|
| 235 |
+
"q99": [
|
| 236 |
+
57.058387756347656,
|
| 237 |
+
16.554622650146484,
|
| 238 |
+
52.93586349487305,
|
| 239 |
+
99.39077758789062,
|
| 240 |
+
-4.273058891296387
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
"blue_gripper": {
|
| 244 |
+
"max": [
|
| 245 |
+
40.44117736816406
|
| 246 |
+
],
|
| 247 |
+
"min": [
|
| 248 |
+
0.0
|
| 249 |
+
],
|
| 250 |
+
"mean": [
|
| 251 |
+
5.49310302734375
|
| 252 |
+
],
|
| 253 |
+
"std": [
|
| 254 |
+
10.243758201599121
|
| 255 |
+
],
|
| 256 |
+
"q01": [
|
| 257 |
+
0.898692786693573
|
| 258 |
+
],
|
| 259 |
+
"q99": [
|
| 260 |
+
37.33660125732422
|
| 261 |
+
]
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
+
"modalities": {
|
| 266 |
+
"video": {
|
| 267 |
+
"global_top": {
|
| 268 |
+
"resolution": [
|
| 269 |
+
1280,
|
| 270 |
+
720
|
| 271 |
+
],
|
| 272 |
+
"channels": 3,
|
| 273 |
+
"fps": 30.0
|
| 274 |
+
},
|
| 275 |
+
"white_front": {
|
| 276 |
+
"resolution": [
|
| 277 |
+
640,
|
| 278 |
+
480
|
| 279 |
+
],
|
| 280 |
+
"channels": 3,
|
| 281 |
+
"fps": 30.0
|
| 282 |
+
},
|
| 283 |
+
"blue_front": {
|
| 284 |
+
"resolution": [
|
| 285 |
+
640,
|
| 286 |
+
480
|
| 287 |
+
],
|
| 288 |
+
"channels": 3,
|
| 289 |
+
"fps": 30.0
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"state": {
|
| 293 |
+
"white_arm": {
|
| 294 |
+
"absolute": true,
|
| 295 |
+
"rotation_type": null,
|
| 296 |
+
"shape": [
|
| 297 |
+
5
|
| 298 |
+
],
|
| 299 |
+
"continuous": true
|
| 300 |
+
},
|
| 301 |
+
"white_gripper": {
|
| 302 |
+
"absolute": true,
|
| 303 |
+
"rotation_type": null,
|
| 304 |
+
"shape": [
|
| 305 |
+
1
|
| 306 |
+
],
|
| 307 |
+
"continuous": true
|
| 308 |
+
},
|
| 309 |
+
"blue_arm": {
|
| 310 |
+
"absolute": true,
|
| 311 |
+
"rotation_type": null,
|
| 312 |
+
"shape": [
|
| 313 |
+
5
|
| 314 |
+
],
|
| 315 |
+
"continuous": true
|
| 316 |
+
},
|
| 317 |
+
"blue_gripper": {
|
| 318 |
+
"absolute": true,
|
| 319 |
+
"rotation_type": null,
|
| 320 |
+
"shape": [
|
| 321 |
+
1
|
| 322 |
+
],
|
| 323 |
+
"continuous": true
|
| 324 |
+
}
|
| 325 |
+
},
|
| 326 |
+
"action": {
|
| 327 |
+
"white_arm": {
|
| 328 |
+
"absolute": true,
|
| 329 |
+
"rotation_type": null,
|
| 330 |
+
"shape": [
|
| 331 |
+
5
|
| 332 |
+
],
|
| 333 |
+
"continuous": true
|
| 334 |
+
},
|
| 335 |
+
"white_gripper": {
|
| 336 |
+
"absolute": true,
|
| 337 |
+
"rotation_type": null,
|
| 338 |
+
"shape": [
|
| 339 |
+
1
|
| 340 |
+
],
|
| 341 |
+
"continuous": true
|
| 342 |
+
},
|
| 343 |
+
"blue_arm": {
|
| 344 |
+
"absolute": true,
|
| 345 |
+
"rotation_type": null,
|
| 346 |
+
"shape": [
|
| 347 |
+
5
|
| 348 |
+
],
|
| 349 |
+
"continuous": true
|
| 350 |
+
},
|
| 351 |
+
"blue_gripper": {
|
| 352 |
+
"absolute": true,
|
| 353 |
+
"rotation_type": null,
|
| 354 |
+
"shape": [
|
| 355 |
+
1
|
| 356 |
+
],
|
| 357 |
+
"continuous": true
|
| 358 |
+
}
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"embodiment_tag": "new_embodiment"
|
| 362 |
+
}
|
| 363 |
+
}
|
checkpoint-6000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b
|
| 3 |
+
size 4999367032
|
checkpoint-6000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:112b379253929192c1656abafbc6e7120d6790e81046efefa6a9e256e27c0390
|
| 3 |
+
size 2586705312
|
checkpoint-6000/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dd3956c0677fcb8cbd43983abbe9d31bfd5b78b336d06295973ea5b21b31b46
|
| 3 |
+
size 14244
|
checkpoint-6000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d6c0bf646ac78d188a2258804081d2e369772e8091e5395d9073771ec310aca
|
| 3 |
+
size 1064
|
checkpoint-6000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7000/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_dim": 32,
|
| 3 |
+
"action_head_cfg": {
|
| 4 |
+
"action_dim": 32,
|
| 5 |
+
"action_horizon": 16,
|
| 6 |
+
"add_pos_embed": true,
|
| 7 |
+
"backbone_embedding_dim": 2048,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"cross_attention_dim": 2048,
|
| 11 |
+
"dropout": 0.2,
|
| 12 |
+
"final_dropout": true,
|
| 13 |
+
"interleave_self_attention": true,
|
| 14 |
+
"norm_type": "ada_norm",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_layers": 16,
|
| 17 |
+
"output_dim": 1024,
|
| 18 |
+
"positional_embeddings": null
|
| 19 |
+
},
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"max_action_dim": 32,
|
| 23 |
+
"max_state_dim": 64,
|
| 24 |
+
"model_dtype": "float32",
|
| 25 |
+
"noise_beta_alpha": 1.5,
|
| 26 |
+
"noise_beta_beta": 1.0,
|
| 27 |
+
"noise_s": 0.999,
|
| 28 |
+
"num_inference_timesteps": 4,
|
| 29 |
+
"num_target_vision_tokens": 32,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true,
|
| 33 |
+
"use_vlln": true,
|
| 34 |
+
"vl_self_attention_cfg": {
|
| 35 |
+
"attention_head_dim": 64,
|
| 36 |
+
"dropout": 0.2,
|
| 37 |
+
"final_dropout": true,
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_layers": 4,
|
| 40 |
+
"positional_embeddings": null
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"action_horizon": 16,
|
| 44 |
+
"architectures": [
|
| 45 |
+
"GR00T_N1_5"
|
| 46 |
+
],
|
| 47 |
+
"attn_implementation": null,
|
| 48 |
+
"backbone_cfg": {
|
| 49 |
+
"eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
|
| 50 |
+
"load_bf16": false,
|
| 51 |
+
"project_to_dim": null,
|
| 52 |
+
"reproject_vision": false,
|
| 53 |
+
"select_layer": 12,
|
| 54 |
+
"tune_llm": false,
|
| 55 |
+
"tune_visual": true,
|
| 56 |
+
"use_flash_attention": true
|
| 57 |
+
},
|
| 58 |
+
"compute_dtype": "bfloat16",
|
| 59 |
+
"hidden_size": 2048,
|
| 60 |
+
"model_dtype": "float32",
|
| 61 |
+
"model_type": "gr00t_n1_5",
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.51.3"
|
| 64 |
+
}
|
checkpoint-7000/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"white_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
-5.758017539978027,
|
| 8 |
+
45.33951950073242,
|
| 9 |
+
83.51254272460938,
|
| 10 |
+
98.8018798828125,
|
| 11 |
+
-3.8293497562408447
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-60.932945251464844,
|
| 15 |
+
-99.40953063964844,
|
| 16 |
+
-80.3763427734375,
|
| 17 |
+
30.851518630981445,
|
| 18 |
+
-58.36545944213867
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-41.30015563964844,
|
| 22 |
+
-59.61644744873047,
|
| 23 |
+
11.656304359436035,
|
| 24 |
+
92.30885314941406,
|
| 25 |
+
-48.28321838378906
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
12.557931900024414,
|
| 29 |
+
49.788997650146484,
|
| 30 |
+
33.65494918823242,
|
| 31 |
+
11.678942680358887,
|
| 32 |
+
12.509681701660156
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-60.71428680419922,
|
| 36 |
+
-99.40953063964844,
|
| 37 |
+
-61.021507263183594,
|
| 38 |
+
46.82926918029785,
|
| 39 |
+
-57.800052642822266
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
-6.778425693511963,
|
| 43 |
+
44.580345153808594,
|
| 44 |
+
48.11827850341797,
|
| 45 |
+
98.8018798828125,
|
| 46 |
+
-11.231045722961426
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"white_gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
34.37900161743164
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
1.7285531759262085
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
6.319039821624756
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
7.589016437530518
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
1.8565940856933594
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
30.34571075439453
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"blue_arm": {
|
| 70 |
+
"max": [
|
| 71 |
+
58.738216400146484,
|
| 72 |
+
18.63117790222168,
|
| 73 |
+
75.27173614501953,
|
| 74 |
+
99.04803466796875,
|
| 75 |
+
-4.080061435699463
|
| 76 |
+
],
|
| 77 |
+
"min": [
|
| 78 |
+
-16.533720016479492,
|
| 79 |
+
-99.070556640625,
|
| 80 |
+
-52.8079719543457,
|
| 81 |
+
66.85417938232422,
|
| 82 |
+
-58.48088455200195
|
| 83 |
+
],
|
| 84 |
+
"mean": [
|
| 85 |
+
22.58572769165039,
|
| 86 |
+
-46.04561233520508,
|
| 87 |
+
4.261409282684326,
|
| 88 |
+
95.5960922241211,
|
| 89 |
+
-31.681655883789062
|
| 90 |
+
],
|
| 91 |
+
"std": [
|
| 92 |
+
24.668598175048828,
|
| 93 |
+
42.83842086791992,
|
| 94 |
+
25.97476577758789,
|
| 95 |
+
6.019741535186768,
|
| 96 |
+
16.340681076049805
|
| 97 |
+
],
|
| 98 |
+
"q01": [
|
| 99 |
+
-16.316171646118164,
|
| 100 |
+
-98.90156555175781,
|
| 101 |
+
-47.55434799194336,
|
| 102 |
+
74.43184829711915,
|
| 103 |
+
-55.760841369628906
|
| 104 |
+
],
|
| 105 |
+
"q99": [
|
| 106 |
+
56.85279083251953,
|
| 107 |
+
17.78622817993164,
|
| 108 |
+
54.619564056396484,
|
| 109 |
+
99.04803466796875,
|
| 110 |
+
-4.285347938537598
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
"blue_gripper": {
|
| 114 |
+
"max": [
|
| 115 |
+
40.255374908447266
|
| 116 |
+
],
|
| 117 |
+
"min": [
|
| 118 |
+
1.0080645084381104
|
| 119 |
+
],
|
| 120 |
+
"mean": [
|
| 121 |
+
5.813619613647461
|
| 122 |
+
],
|
| 123 |
+
"std": [
|
| 124 |
+
9.993083000183105
|
| 125 |
+
],
|
| 126 |
+
"q01": [
|
| 127 |
+
1.0080645084381104
|
| 128 |
+
],
|
| 129 |
+
"q99": [
|
| 130 |
+
37.29838562011719
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"action": {
|
| 135 |
+
"white_arm": {
|
| 136 |
+
"max": [
|
| 137 |
+
-5.325443744659424,
|
| 138 |
+
44.7691650390625,
|
| 139 |
+
83.48375701904297,
|
| 140 |
+
100.0,
|
| 141 |
+
-3.3212246894836426
|
| 142 |
+
],
|
| 143 |
+
"min": [
|
| 144 |
+
-60.724853515625,
|
| 145 |
+
-100.0,
|
| 146 |
+
-83.21299743652344,
|
| 147 |
+
30.108932495117188,
|
| 148 |
+
-58.432796478271484
|
| 149 |
+
],
|
| 150 |
+
"mean": [
|
| 151 |
+
-41.21931457519531,
|
| 152 |
+
-60.167320251464844,
|
| 153 |
+
10.704584121704102,
|
| 154 |
+
92.57025146484375,
|
| 155 |
+
-48.337284088134766
|
| 156 |
+
],
|
| 157 |
+
"std": [
|
| 158 |
+
12.604560852050781,
|
| 159 |
+
49.407814025878906,
|
| 160 |
+
34.10797119140625,
|
| 161 |
+
12.075830459594727,
|
| 162 |
+
12.521093368530273
|
| 163 |
+
],
|
| 164 |
+
"q01": [
|
| 165 |
+
-60.502960205078125,
|
| 166 |
+
-99.83058166503906,
|
| 167 |
+
-63.963899002075195,
|
| 168 |
+
47.06405281066895,
|
| 169 |
+
-57.81006622314453
|
| 170 |
+
],
|
| 171 |
+
"q99": [
|
| 172 |
+
-6.804733753204346,
|
| 173 |
+
42.9783979797363,
|
| 174 |
+
47.743682861328125,
|
| 175 |
+
100.0,
|
| 176 |
+
-11.053450584411621
|
| 177 |
+
]
|
| 178 |
+
},
|
| 179 |
+
"white_gripper": {
|
| 180 |
+
"max": [
|
| 181 |
+
34.68433380126953
|
| 182 |
+
],
|
| 183 |
+
"min": [
|
| 184 |
+
1.3250194787979126
|
| 185 |
+
],
|
| 186 |
+
"mean": [
|
| 187 |
+
5.815976142883301
|
| 188 |
+
],
|
| 189 |
+
"std": [
|
| 190 |
+
7.803332805633545
|
| 191 |
+
],
|
| 192 |
+
"q01": [
|
| 193 |
+
1.6367887258529663
|
| 194 |
+
],
|
| 195 |
+
"q99": [
|
| 196 |
+
30.709274291992188
|
| 197 |
+
]
|
| 198 |
+
},
|
| 199 |
+
"blue_arm": {
|
| 200 |
+
"max": [
|
| 201 |
+
59.20177459716797,
|
| 202 |
+
18.235294342041016,
|
| 203 |
+
56.36856460571289,
|
| 204 |
+
99.4778060913086,
|
| 205 |
+
-3.9603960514068604
|
| 206 |
+
],
|
| 207 |
+
"min": [
|
| 208 |
+
-16.629711151123047,
|
| 209 |
+
-99.4117660522461,
|
| 210 |
+
-55.55555725097656,
|
| 211 |
+
65.97040557861328,
|
| 212 |
+
-58.780616760253906
|
| 213 |
+
],
|
| 214 |
+
"mean": [
|
| 215 |
+
22.72244644165039,
|
| 216 |
+
-46.86748123168945,
|
| 217 |
+
3.5456254482269287,
|
| 218 |
+
95.69131469726562,
|
| 219 |
+
-31.745248794555664
|
| 220 |
+
],
|
| 221 |
+
"std": [
|
| 222 |
+
24.648967742919922,
|
| 223 |
+
42.451499938964844,
|
| 224 |
+
26.123699188232422,
|
| 225 |
+
6.368340015411377,
|
| 226 |
+
16.331010818481445
|
| 227 |
+
],
|
| 228 |
+
"q01": [
|
| 229 |
+
-16.18625259399414,
|
| 230 |
+
-98.9916000366211,
|
| 231 |
+
-49.68383026123047,
|
| 232 |
+
73.62924194335938,
|
| 233 |
+
-55.549766540527344
|
| 234 |
+
],
|
| 235 |
+
"q99": [
|
| 236 |
+
57.058387756347656,
|
| 237 |
+
16.554622650146484,
|
| 238 |
+
52.93586349487305,
|
| 239 |
+
99.39077758789062,
|
| 240 |
+
-4.273058891296387
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
"blue_gripper": {
|
| 244 |
+
"max": [
|
| 245 |
+
40.44117736816406
|
| 246 |
+
],
|
| 247 |
+
"min": [
|
| 248 |
+
0.0
|
| 249 |
+
],
|
| 250 |
+
"mean": [
|
| 251 |
+
5.49310302734375
|
| 252 |
+
],
|
| 253 |
+
"std": [
|
| 254 |
+
10.243758201599121
|
| 255 |
+
],
|
| 256 |
+
"q01": [
|
| 257 |
+
0.898692786693573
|
| 258 |
+
],
|
| 259 |
+
"q99": [
|
| 260 |
+
37.33660125732422
|
| 261 |
+
]
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
+
"modalities": {
|
| 266 |
+
"video": {
|
| 267 |
+
"global_top": {
|
| 268 |
+
"resolution": [
|
| 269 |
+
1280,
|
| 270 |
+
720
|
| 271 |
+
],
|
| 272 |
+
"channels": 3,
|
| 273 |
+
"fps": 30.0
|
| 274 |
+
},
|
| 275 |
+
"white_front": {
|
| 276 |
+
"resolution": [
|
| 277 |
+
640,
|
| 278 |
+
480
|
| 279 |
+
],
|
| 280 |
+
"channels": 3,
|
| 281 |
+
"fps": 30.0
|
| 282 |
+
},
|
| 283 |
+
"blue_front": {
|
| 284 |
+
"resolution": [
|
| 285 |
+
640,
|
| 286 |
+
480
|
| 287 |
+
],
|
| 288 |
+
"channels": 3,
|
| 289 |
+
"fps": 30.0
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"state": {
|
| 293 |
+
"white_arm": {
|
| 294 |
+
"absolute": true,
|
| 295 |
+
"rotation_type": null,
|
| 296 |
+
"shape": [
|
| 297 |
+
5
|
| 298 |
+
],
|
| 299 |
+
"continuous": true
|
| 300 |
+
},
|
| 301 |
+
"white_gripper": {
|
| 302 |
+
"absolute": true,
|
| 303 |
+
"rotation_type": null,
|
| 304 |
+
"shape": [
|
| 305 |
+
1
|
| 306 |
+
],
|
| 307 |
+
"continuous": true
|
| 308 |
+
},
|
| 309 |
+
"blue_arm": {
|
| 310 |
+
"absolute": true,
|
| 311 |
+
"rotation_type": null,
|
| 312 |
+
"shape": [
|
| 313 |
+
5
|
| 314 |
+
],
|
| 315 |
+
"continuous": true
|
| 316 |
+
},
|
| 317 |
+
"blue_gripper": {
|
| 318 |
+
"absolute": true,
|
| 319 |
+
"rotation_type": null,
|
| 320 |
+
"shape": [
|
| 321 |
+
1
|
| 322 |
+
],
|
| 323 |
+
"continuous": true
|
| 324 |
+
}
|
| 325 |
+
},
|
| 326 |
+
"action": {
|
| 327 |
+
"white_arm": {
|
| 328 |
+
"absolute": true,
|
| 329 |
+
"rotation_type": null,
|
| 330 |
+
"shape": [
|
| 331 |
+
5
|
| 332 |
+
],
|
| 333 |
+
"continuous": true
|
| 334 |
+
},
|
| 335 |
+
"white_gripper": {
|
| 336 |
+
"absolute": true,
|
| 337 |
+
"rotation_type": null,
|
| 338 |
+
"shape": [
|
| 339 |
+
1
|
| 340 |
+
],
|
| 341 |
+
"continuous": true
|
| 342 |
+
},
|
| 343 |
+
"blue_arm": {
|
| 344 |
+
"absolute": true,
|
| 345 |
+
"rotation_type": null,
|
| 346 |
+
"shape": [
|
| 347 |
+
5
|
| 348 |
+
],
|
| 349 |
+
"continuous": true
|
| 350 |
+
},
|
| 351 |
+
"blue_gripper": {
|
| 352 |
+
"absolute": true,
|
| 353 |
+
"rotation_type": null,
|
| 354 |
+
"shape": [
|
| 355 |
+
1
|
| 356 |
+
],
|
| 357 |
+
"continuous": true
|
| 358 |
+
}
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"embodiment_tag": "new_embodiment"
|
| 362 |
+
}
|
| 363 |
+
}
|
checkpoint-7000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b
|
| 3 |
+
size 4999367032
|
checkpoint-7000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c51aa3037e53ec7ecf50116c4b2fde9412cbc341c6fed6fff49fab755d3e44c
|
| 3 |
+
size 2586705312
|
checkpoint-7000/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-7000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc53abde01e7a4db1787b7e4a110648fdfb802226d2f42db3a04c1d0b31bad15
|
| 3 |
+
size 4147424698
|
checkpoint-7000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03f50eb6e86e953fd8b22049b00be02711915ec851ac6de5a01a81e456b6f4ce
|
| 3 |
+
size 14244
|
checkpoint-7000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45049460c0fa55fae34b1884c511d0c5cb5241d0d636fad92c82b0e0a657580e
|
| 3 |
+
size 1064
|
checkpoint-7000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8000/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_dim": 32,
|
| 3 |
+
"action_head_cfg": {
|
| 4 |
+
"action_dim": 32,
|
| 5 |
+
"action_horizon": 16,
|
| 6 |
+
"add_pos_embed": true,
|
| 7 |
+
"backbone_embedding_dim": 2048,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"cross_attention_dim": 2048,
|
| 11 |
+
"dropout": 0.2,
|
| 12 |
+
"final_dropout": true,
|
| 13 |
+
"interleave_self_attention": true,
|
| 14 |
+
"norm_type": "ada_norm",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_layers": 16,
|
| 17 |
+
"output_dim": 1024,
|
| 18 |
+
"positional_embeddings": null
|
| 19 |
+
},
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"max_action_dim": 32,
|
| 23 |
+
"max_state_dim": 64,
|
| 24 |
+
"model_dtype": "float32",
|
| 25 |
+
"noise_beta_alpha": 1.5,
|
| 26 |
+
"noise_beta_beta": 1.0,
|
| 27 |
+
"noise_s": 0.999,
|
| 28 |
+
"num_inference_timesteps": 4,
|
| 29 |
+
"num_target_vision_tokens": 32,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true,
|
| 33 |
+
"use_vlln": true,
|
| 34 |
+
"vl_self_attention_cfg": {
|
| 35 |
+
"attention_head_dim": 64,
|
| 36 |
+
"dropout": 0.2,
|
| 37 |
+
"final_dropout": true,
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_layers": 4,
|
| 40 |
+
"positional_embeddings": null
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"action_horizon": 16,
|
| 44 |
+
"architectures": [
|
| 45 |
+
"GR00T_N1_5"
|
| 46 |
+
],
|
| 47 |
+
"attn_implementation": null,
|
| 48 |
+
"backbone_cfg": {
|
| 49 |
+
"eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
|
| 50 |
+
"load_bf16": false,
|
| 51 |
+
"project_to_dim": null,
|
| 52 |
+
"reproject_vision": false,
|
| 53 |
+
"select_layer": 12,
|
| 54 |
+
"tune_llm": false,
|
| 55 |
+
"tune_visual": true,
|
| 56 |
+
"use_flash_attention": true
|
| 57 |
+
},
|
| 58 |
+
"compute_dtype": "bfloat16",
|
| 59 |
+
"hidden_size": 2048,
|
| 60 |
+
"model_dtype": "float32",
|
| 61 |
+
"model_type": "gr00t_n1_5",
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.51.3"
|
| 64 |
+
}
|
checkpoint-8000/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"white_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
-5.758017539978027,
|
| 8 |
+
45.33951950073242,
|
| 9 |
+
83.51254272460938,
|
| 10 |
+
98.8018798828125,
|
| 11 |
+
-3.8293497562408447
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-60.932945251464844,
|
| 15 |
+
-99.40953063964844,
|
| 16 |
+
-80.3763427734375,
|
| 17 |
+
30.851518630981445,
|
| 18 |
+
-58.36545944213867
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-41.30015563964844,
|
| 22 |
+
-59.61644744873047,
|
| 23 |
+
11.656304359436035,
|
| 24 |
+
92.30885314941406,
|
| 25 |
+
-48.28321838378906
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
12.557931900024414,
|
| 29 |
+
49.788997650146484,
|
| 30 |
+
33.65494918823242,
|
| 31 |
+
11.678942680358887,
|
| 32 |
+
12.509681701660156
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-60.71428680419922,
|
| 36 |
+
-99.40953063964844,
|
| 37 |
+
-61.021507263183594,
|
| 38 |
+
46.82926918029785,
|
| 39 |
+
-57.800052642822266
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
-6.778425693511963,
|
| 43 |
+
44.580345153808594,
|
| 44 |
+
48.11827850341797,
|
| 45 |
+
98.8018798828125,
|
| 46 |
+
-11.231045722961426
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"white_gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
34.37900161743164
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
1.7285531759262085
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
6.319039821624756
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
7.589016437530518
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
1.8565940856933594
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
30.34571075439453
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"blue_arm": {
|
| 70 |
+
"max": [
|
| 71 |
+
58.738216400146484,
|
| 72 |
+
18.63117790222168,
|
| 73 |
+
75.27173614501953,
|
| 74 |
+
99.04803466796875,
|
| 75 |
+
-4.080061435699463
|
| 76 |
+
],
|
| 77 |
+
"min": [
|
| 78 |
+
-16.533720016479492,
|
| 79 |
+
-99.070556640625,
|
| 80 |
+
-52.8079719543457,
|
| 81 |
+
66.85417938232422,
|
| 82 |
+
-58.48088455200195
|
| 83 |
+
],
|
| 84 |
+
"mean": [
|
| 85 |
+
22.58572769165039,
|
| 86 |
+
-46.04561233520508,
|
| 87 |
+
4.261409282684326,
|
| 88 |
+
95.5960922241211,
|
| 89 |
+
-31.681655883789062
|
| 90 |
+
],
|
| 91 |
+
"std": [
|
| 92 |
+
24.668598175048828,
|
| 93 |
+
42.83842086791992,
|
| 94 |
+
25.97476577758789,
|
| 95 |
+
6.019741535186768,
|
| 96 |
+
16.340681076049805
|
| 97 |
+
],
|
| 98 |
+
"q01": [
|
| 99 |
+
-16.316171646118164,
|
| 100 |
+
-98.90156555175781,
|
| 101 |
+
-47.55434799194336,
|
| 102 |
+
74.43184829711915,
|
| 103 |
+
-55.760841369628906
|
| 104 |
+
],
|
| 105 |
+
"q99": [
|
| 106 |
+
56.85279083251953,
|
| 107 |
+
17.78622817993164,
|
| 108 |
+
54.619564056396484,
|
| 109 |
+
99.04803466796875,
|
| 110 |
+
-4.285347938537598
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
"blue_gripper": {
|
| 114 |
+
"max": [
|
| 115 |
+
40.255374908447266
|
| 116 |
+
],
|
| 117 |
+
"min": [
|
| 118 |
+
1.0080645084381104
|
| 119 |
+
],
|
| 120 |
+
"mean": [
|
| 121 |
+
5.813619613647461
|
| 122 |
+
],
|
| 123 |
+
"std": [
|
| 124 |
+
9.993083000183105
|
| 125 |
+
],
|
| 126 |
+
"q01": [
|
| 127 |
+
1.0080645084381104
|
| 128 |
+
],
|
| 129 |
+
"q99": [
|
| 130 |
+
37.29838562011719
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"action": {
|
| 135 |
+
"white_arm": {
|
| 136 |
+
"max": [
|
| 137 |
+
-5.325443744659424,
|
| 138 |
+
44.7691650390625,
|
| 139 |
+
83.48375701904297,
|
| 140 |
+
100.0,
|
| 141 |
+
-3.3212246894836426
|
| 142 |
+
],
|
| 143 |
+
"min": [
|
| 144 |
+
-60.724853515625,
|
| 145 |
+
-100.0,
|
| 146 |
+
-83.21299743652344,
|
| 147 |
+
30.108932495117188,
|
| 148 |
+
-58.432796478271484
|
| 149 |
+
],
|
| 150 |
+
"mean": [
|
| 151 |
+
-41.21931457519531,
|
| 152 |
+
-60.167320251464844,
|
| 153 |
+
10.704584121704102,
|
| 154 |
+
92.57025146484375,
|
| 155 |
+
-48.337284088134766
|
| 156 |
+
],
|
| 157 |
+
"std": [
|
| 158 |
+
12.604560852050781,
|
| 159 |
+
49.407814025878906,
|
| 160 |
+
34.10797119140625,
|
| 161 |
+
12.075830459594727,
|
| 162 |
+
12.521093368530273
|
| 163 |
+
],
|
| 164 |
+
"q01": [
|
| 165 |
+
-60.502960205078125,
|
| 166 |
+
-99.83058166503906,
|
| 167 |
+
-63.963899002075195,
|
| 168 |
+
47.06405281066895,
|
| 169 |
+
-57.81006622314453
|
| 170 |
+
],
|
| 171 |
+
"q99": [
|
| 172 |
+
-6.804733753204346,
|
| 173 |
+
42.9783979797363,
|
| 174 |
+
47.743682861328125,
|
| 175 |
+
100.0,
|
| 176 |
+
-11.053450584411621
|
| 177 |
+
]
|
| 178 |
+
},
|
| 179 |
+
"white_gripper": {
|
| 180 |
+
"max": [
|
| 181 |
+
34.68433380126953
|
| 182 |
+
],
|
| 183 |
+
"min": [
|
| 184 |
+
1.3250194787979126
|
| 185 |
+
],
|
| 186 |
+
"mean": [
|
| 187 |
+
5.815976142883301
|
| 188 |
+
],
|
| 189 |
+
"std": [
|
| 190 |
+
7.803332805633545
|
| 191 |
+
],
|
| 192 |
+
"q01": [
|
| 193 |
+
1.6367887258529663
|
| 194 |
+
],
|
| 195 |
+
"q99": [
|
| 196 |
+
30.709274291992188
|
| 197 |
+
]
|
| 198 |
+
},
|
| 199 |
+
"blue_arm": {
|
| 200 |
+
"max": [
|
| 201 |
+
59.20177459716797,
|
| 202 |
+
18.235294342041016,
|
| 203 |
+
56.36856460571289,
|
| 204 |
+
99.4778060913086,
|
| 205 |
+
-3.9603960514068604
|
| 206 |
+
],
|
| 207 |
+
"min": [
|
| 208 |
+
-16.629711151123047,
|
| 209 |
+
-99.4117660522461,
|
| 210 |
+
-55.55555725097656,
|
| 211 |
+
65.97040557861328,
|
| 212 |
+
-58.780616760253906
|
| 213 |
+
],
|
| 214 |
+
"mean": [
|
| 215 |
+
22.72244644165039,
|
| 216 |
+
-46.86748123168945,
|
| 217 |
+
3.5456254482269287,
|
| 218 |
+
95.69131469726562,
|
| 219 |
+
-31.745248794555664
|
| 220 |
+
],
|
| 221 |
+
"std": [
|
| 222 |
+
24.648967742919922,
|
| 223 |
+
42.451499938964844,
|
| 224 |
+
26.123699188232422,
|
| 225 |
+
6.368340015411377,
|
| 226 |
+
16.331010818481445
|
| 227 |
+
],
|
| 228 |
+
"q01": [
|
| 229 |
+
-16.18625259399414,
|
| 230 |
+
-98.9916000366211,
|
| 231 |
+
-49.68383026123047,
|
| 232 |
+
73.62924194335938,
|
| 233 |
+
-55.549766540527344
|
| 234 |
+
],
|
| 235 |
+
"q99": [
|
| 236 |
+
57.058387756347656,
|
| 237 |
+
16.554622650146484,
|
| 238 |
+
52.93586349487305,
|
| 239 |
+
99.39077758789062,
|
| 240 |
+
-4.273058891296387
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
"blue_gripper": {
|
| 244 |
+
"max": [
|
| 245 |
+
40.44117736816406
|
| 246 |
+
],
|
| 247 |
+
"min": [
|
| 248 |
+
0.0
|
| 249 |
+
],
|
| 250 |
+
"mean": [
|
| 251 |
+
5.49310302734375
|
| 252 |
+
],
|
| 253 |
+
"std": [
|
| 254 |
+
10.243758201599121
|
| 255 |
+
],
|
| 256 |
+
"q01": [
|
| 257 |
+
0.898692786693573
|
| 258 |
+
],
|
| 259 |
+
"q99": [
|
| 260 |
+
37.33660125732422
|
| 261 |
+
]
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
+
"modalities": {
|
| 266 |
+
"video": {
|
| 267 |
+
"global_top": {
|
| 268 |
+
"resolution": [
|
| 269 |
+
1280,
|
| 270 |
+
720
|
| 271 |
+
],
|
| 272 |
+
"channels": 3,
|
| 273 |
+
"fps": 30.0
|
| 274 |
+
},
|
| 275 |
+
"white_front": {
|
| 276 |
+
"resolution": [
|
| 277 |
+
640,
|
| 278 |
+
480
|
| 279 |
+
],
|
| 280 |
+
"channels": 3,
|
| 281 |
+
"fps": 30.0
|
| 282 |
+
},
|
| 283 |
+
"blue_front": {
|
| 284 |
+
"resolution": [
|
| 285 |
+
640,
|
| 286 |
+
480
|
| 287 |
+
],
|
| 288 |
+
"channels": 3,
|
| 289 |
+
"fps": 30.0
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"state": {
|
| 293 |
+
"white_arm": {
|
| 294 |
+
"absolute": true,
|
| 295 |
+
"rotation_type": null,
|
| 296 |
+
"shape": [
|
| 297 |
+
5
|
| 298 |
+
],
|
| 299 |
+
"continuous": true
|
| 300 |
+
},
|
| 301 |
+
"white_gripper": {
|
| 302 |
+
"absolute": true,
|
| 303 |
+
"rotation_type": null,
|
| 304 |
+
"shape": [
|
| 305 |
+
1
|
| 306 |
+
],
|
| 307 |
+
"continuous": true
|
| 308 |
+
},
|
| 309 |
+
"blue_arm": {
|
| 310 |
+
"absolute": true,
|
| 311 |
+
"rotation_type": null,
|
| 312 |
+
"shape": [
|
| 313 |
+
5
|
| 314 |
+
],
|
| 315 |
+
"continuous": true
|
| 316 |
+
},
|
| 317 |
+
"blue_gripper": {
|
| 318 |
+
"absolute": true,
|
| 319 |
+
"rotation_type": null,
|
| 320 |
+
"shape": [
|
| 321 |
+
1
|
| 322 |
+
],
|
| 323 |
+
"continuous": true
|
| 324 |
+
}
|
| 325 |
+
},
|
| 326 |
+
"action": {
|
| 327 |
+
"white_arm": {
|
| 328 |
+
"absolute": true,
|
| 329 |
+
"rotation_type": null,
|
| 330 |
+
"shape": [
|
| 331 |
+
5
|
| 332 |
+
],
|
| 333 |
+
"continuous": true
|
| 334 |
+
},
|
| 335 |
+
"white_gripper": {
|
| 336 |
+
"absolute": true,
|
| 337 |
+
"rotation_type": null,
|
| 338 |
+
"shape": [
|
| 339 |
+
1
|
| 340 |
+
],
|
| 341 |
+
"continuous": true
|
| 342 |
+
},
|
| 343 |
+
"blue_arm": {
|
| 344 |
+
"absolute": true,
|
| 345 |
+
"rotation_type": null,
|
| 346 |
+
"shape": [
|
| 347 |
+
5
|
| 348 |
+
],
|
| 349 |
+
"continuous": true
|
| 350 |
+
},
|
| 351 |
+
"blue_gripper": {
|
| 352 |
+
"absolute": true,
|
| 353 |
+
"rotation_type": null,
|
| 354 |
+
"shape": [
|
| 355 |
+
1
|
| 356 |
+
],
|
| 357 |
+
"continuous": true
|
| 358 |
+
}
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"embodiment_tag": "new_embodiment"
|
| 362 |
+
}
|
| 363 |
+
}
|
checkpoint-8000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b
|
| 3 |
+
size 4999367032
|
checkpoint-8000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e146799ee2f93ed5f2c4faefbeff2f536c9ec6d6c7f4caaade3a907f95edf6d9
|
| 3 |
+
size 2586705312
|
checkpoint-8000/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21d4b11936d8b20d5d0d8d84916bd932d4329746e4e848925bfeb1ef509edecd
|
| 3 |
+
size 4147424698
|
checkpoint-8000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64649f886d30ad1e56b60fafe3bdfe279d780c9464ccc56b95e99f02728a003d
|
| 3 |
+
size 14244
|
checkpoint-8000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00739e77892b3b90e07da5aa63424b8c4adff832abcfc91f97c4f8838af650db
|
| 3 |
+
size 1064
|
checkpoint-8000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-9000/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_dim": 32,
|
| 3 |
+
"action_head_cfg": {
|
| 4 |
+
"action_dim": 32,
|
| 5 |
+
"action_horizon": 16,
|
| 6 |
+
"add_pos_embed": true,
|
| 7 |
+
"backbone_embedding_dim": 2048,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"cross_attention_dim": 2048,
|
| 11 |
+
"dropout": 0.2,
|
| 12 |
+
"final_dropout": true,
|
| 13 |
+
"interleave_self_attention": true,
|
| 14 |
+
"norm_type": "ada_norm",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_layers": 16,
|
| 17 |
+
"output_dim": 1024,
|
| 18 |
+
"positional_embeddings": null
|
| 19 |
+
},
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"max_action_dim": 32,
|
| 23 |
+
"max_state_dim": 64,
|
| 24 |
+
"model_dtype": "float32",
|
| 25 |
+
"noise_beta_alpha": 1.5,
|
| 26 |
+
"noise_beta_beta": 1.0,
|
| 27 |
+
"noise_s": 0.999,
|
| 28 |
+
"num_inference_timesteps": 4,
|
| 29 |
+
"num_target_vision_tokens": 32,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true,
|
| 33 |
+
"use_vlln": true,
|
| 34 |
+
"vl_self_attention_cfg": {
|
| 35 |
+
"attention_head_dim": 64,
|
| 36 |
+
"dropout": 0.2,
|
| 37 |
+
"final_dropout": true,
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_layers": 4,
|
| 40 |
+
"positional_embeddings": null
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"action_horizon": 16,
|
| 44 |
+
"architectures": [
|
| 45 |
+
"GR00T_N1_5"
|
| 46 |
+
],
|
| 47 |
+
"attn_implementation": null,
|
| 48 |
+
"backbone_cfg": {
|
| 49 |
+
"eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
|
| 50 |
+
"load_bf16": false,
|
| 51 |
+
"project_to_dim": null,
|
| 52 |
+
"reproject_vision": false,
|
| 53 |
+
"select_layer": 12,
|
| 54 |
+
"tune_llm": false,
|
| 55 |
+
"tune_visual": true,
|
| 56 |
+
"use_flash_attention": true
|
| 57 |
+
},
|
| 58 |
+
"compute_dtype": "bfloat16",
|
| 59 |
+
"hidden_size": 2048,
|
| 60 |
+
"model_dtype": "float32",
|
| 61 |
+
"model_type": "gr00t_n1_5",
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.51.3"
|
| 64 |
+
}
|
checkpoint-9000/experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"white_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
-5.758017539978027,
|
| 8 |
+
45.33951950073242,
|
| 9 |
+
83.51254272460938,
|
| 10 |
+
98.8018798828125,
|
| 11 |
+
-3.8293497562408447
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-60.932945251464844,
|
| 15 |
+
-99.40953063964844,
|
| 16 |
+
-80.3763427734375,
|
| 17 |
+
30.851518630981445,
|
| 18 |
+
-58.36545944213867
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-41.30015563964844,
|
| 22 |
+
-59.61644744873047,
|
| 23 |
+
11.656304359436035,
|
| 24 |
+
92.30885314941406,
|
| 25 |
+
-48.28321838378906
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
12.557931900024414,
|
| 29 |
+
49.788997650146484,
|
| 30 |
+
33.65494918823242,
|
| 31 |
+
11.678942680358887,
|
| 32 |
+
12.509681701660156
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-60.71428680419922,
|
| 36 |
+
-99.40953063964844,
|
| 37 |
+
-61.021507263183594,
|
| 38 |
+
46.82926918029785,
|
| 39 |
+
-57.800052642822266
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
-6.778425693511963,
|
| 43 |
+
44.580345153808594,
|
| 44 |
+
48.11827850341797,
|
| 45 |
+
98.8018798828125,
|
| 46 |
+
-11.231045722961426
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"white_gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
34.37900161743164
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
1.7285531759262085
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
6.319039821624756
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
7.589016437530518
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
1.8565940856933594
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
30.34571075439453
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"blue_arm": {
|
| 70 |
+
"max": [
|
| 71 |
+
58.738216400146484,
|
| 72 |
+
18.63117790222168,
|
| 73 |
+
75.27173614501953,
|
| 74 |
+
99.04803466796875,
|
| 75 |
+
-4.080061435699463
|
| 76 |
+
],
|
| 77 |
+
"min": [
|
| 78 |
+
-16.533720016479492,
|
| 79 |
+
-99.070556640625,
|
| 80 |
+
-52.8079719543457,
|
| 81 |
+
66.85417938232422,
|
| 82 |
+
-58.48088455200195
|
| 83 |
+
],
|
| 84 |
+
"mean": [
|
| 85 |
+
22.58572769165039,
|
| 86 |
+
-46.04561233520508,
|
| 87 |
+
4.261409282684326,
|
| 88 |
+
95.5960922241211,
|
| 89 |
+
-31.681655883789062
|
| 90 |
+
],
|
| 91 |
+
"std": [
|
| 92 |
+
24.668598175048828,
|
| 93 |
+
42.83842086791992,
|
| 94 |
+
25.97476577758789,
|
| 95 |
+
6.019741535186768,
|
| 96 |
+
16.340681076049805
|
| 97 |
+
],
|
| 98 |
+
"q01": [
|
| 99 |
+
-16.316171646118164,
|
| 100 |
+
-98.90156555175781,
|
| 101 |
+
-47.55434799194336,
|
| 102 |
+
74.43184829711915,
|
| 103 |
+
-55.760841369628906
|
| 104 |
+
],
|
| 105 |
+
"q99": [
|
| 106 |
+
56.85279083251953,
|
| 107 |
+
17.78622817993164,
|
| 108 |
+
54.619564056396484,
|
| 109 |
+
99.04803466796875,
|
| 110 |
+
-4.285347938537598
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
"blue_gripper": {
|
| 114 |
+
"max": [
|
| 115 |
+
40.255374908447266
|
| 116 |
+
],
|
| 117 |
+
"min": [
|
| 118 |
+
1.0080645084381104
|
| 119 |
+
],
|
| 120 |
+
"mean": [
|
| 121 |
+
5.813619613647461
|
| 122 |
+
],
|
| 123 |
+
"std": [
|
| 124 |
+
9.993083000183105
|
| 125 |
+
],
|
| 126 |
+
"q01": [
|
| 127 |
+
1.0080645084381104
|
| 128 |
+
],
|
| 129 |
+
"q99": [
|
| 130 |
+
37.29838562011719
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"action": {
|
| 135 |
+
"white_arm": {
|
| 136 |
+
"max": [
|
| 137 |
+
-5.325443744659424,
|
| 138 |
+
44.7691650390625,
|
| 139 |
+
83.48375701904297,
|
| 140 |
+
100.0,
|
| 141 |
+
-3.3212246894836426
|
| 142 |
+
],
|
| 143 |
+
"min": [
|
| 144 |
+
-60.724853515625,
|
| 145 |
+
-100.0,
|
| 146 |
+
-83.21299743652344,
|
| 147 |
+
30.108932495117188,
|
| 148 |
+
-58.432796478271484
|
| 149 |
+
],
|
| 150 |
+
"mean": [
|
| 151 |
+
-41.21931457519531,
|
| 152 |
+
-60.167320251464844,
|
| 153 |
+
10.704584121704102,
|
| 154 |
+
92.57025146484375,
|
| 155 |
+
-48.337284088134766
|
| 156 |
+
],
|
| 157 |
+
"std": [
|
| 158 |
+
12.604560852050781,
|
| 159 |
+
49.407814025878906,
|
| 160 |
+
34.10797119140625,
|
| 161 |
+
12.075830459594727,
|
| 162 |
+
12.521093368530273
|
| 163 |
+
],
|
| 164 |
+
"q01": [
|
| 165 |
+
-60.502960205078125,
|
| 166 |
+
-99.83058166503906,
|
| 167 |
+
-63.963899002075195,
|
| 168 |
+
47.06405281066895,
|
| 169 |
+
-57.81006622314453
|
| 170 |
+
],
|
| 171 |
+
"q99": [
|
| 172 |
+
-6.804733753204346,
|
| 173 |
+
42.9783979797363,
|
| 174 |
+
47.743682861328125,
|
| 175 |
+
100.0,
|
| 176 |
+
-11.053450584411621
|
| 177 |
+
]
|
| 178 |
+
},
|
| 179 |
+
"white_gripper": {
|
| 180 |
+
"max": [
|
| 181 |
+
34.68433380126953
|
| 182 |
+
],
|
| 183 |
+
"min": [
|
| 184 |
+
1.3250194787979126
|
| 185 |
+
],
|
| 186 |
+
"mean": [
|
| 187 |
+
5.815976142883301
|
| 188 |
+
],
|
| 189 |
+
"std": [
|
| 190 |
+
7.803332805633545
|
| 191 |
+
],
|
| 192 |
+
"q01": [
|
| 193 |
+
1.6367887258529663
|
| 194 |
+
],
|
| 195 |
+
"q99": [
|
| 196 |
+
30.709274291992188
|
| 197 |
+
]
|
| 198 |
+
},
|
| 199 |
+
"blue_arm": {
|
| 200 |
+
"max": [
|
| 201 |
+
59.20177459716797,
|
| 202 |
+
18.235294342041016,
|
| 203 |
+
56.36856460571289,
|
| 204 |
+
99.4778060913086,
|
| 205 |
+
-3.9603960514068604
|
| 206 |
+
],
|
| 207 |
+
"min": [
|
| 208 |
+
-16.629711151123047,
|
| 209 |
+
-99.4117660522461,
|
| 210 |
+
-55.55555725097656,
|
| 211 |
+
65.97040557861328,
|
| 212 |
+
-58.780616760253906
|
| 213 |
+
],
|
| 214 |
+
"mean": [
|
| 215 |
+
22.72244644165039,
|
| 216 |
+
-46.86748123168945,
|
| 217 |
+
3.5456254482269287,
|
| 218 |
+
95.69131469726562,
|
| 219 |
+
-31.745248794555664
|
| 220 |
+
],
|
| 221 |
+
"std": [
|
| 222 |
+
24.648967742919922,
|
| 223 |
+
42.451499938964844,
|
| 224 |
+
26.123699188232422,
|
| 225 |
+
6.368340015411377,
|
| 226 |
+
16.331010818481445
|
| 227 |
+
],
|
| 228 |
+
"q01": [
|
| 229 |
+
-16.18625259399414,
|
| 230 |
+
-98.9916000366211,
|
| 231 |
+
-49.68383026123047,
|
| 232 |
+
73.62924194335938,
|
| 233 |
+
-55.549766540527344
|
| 234 |
+
],
|
| 235 |
+
"q99": [
|
| 236 |
+
57.058387756347656,
|
| 237 |
+
16.554622650146484,
|
| 238 |
+
52.93586349487305,
|
| 239 |
+
99.39077758789062,
|
| 240 |
+
-4.273058891296387
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
"blue_gripper": {
|
| 244 |
+
"max": [
|
| 245 |
+
40.44117736816406
|
| 246 |
+
],
|
| 247 |
+
"min": [
|
| 248 |
+
0.0
|
| 249 |
+
],
|
| 250 |
+
"mean": [
|
| 251 |
+
5.49310302734375
|
| 252 |
+
],
|
| 253 |
+
"std": [
|
| 254 |
+
10.243758201599121
|
| 255 |
+
],
|
| 256 |
+
"q01": [
|
| 257 |
+
0.898692786693573
|
| 258 |
+
],
|
| 259 |
+
"q99": [
|
| 260 |
+
37.33660125732422
|
| 261 |
+
]
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
+
"modalities": {
|
| 266 |
+
"video": {
|
| 267 |
+
"global_top": {
|
| 268 |
+
"resolution": [
|
| 269 |
+
1280,
|
| 270 |
+
720
|
| 271 |
+
],
|
| 272 |
+
"channels": 3,
|
| 273 |
+
"fps": 30.0
|
| 274 |
+
},
|
| 275 |
+
"white_front": {
|
| 276 |
+
"resolution": [
|
| 277 |
+
640,
|
| 278 |
+
480
|
| 279 |
+
],
|
| 280 |
+
"channels": 3,
|
| 281 |
+
"fps": 30.0
|
| 282 |
+
},
|
| 283 |
+
"blue_front": {
|
| 284 |
+
"resolution": [
|
| 285 |
+
640,
|
| 286 |
+
480
|
| 287 |
+
],
|
| 288 |
+
"channels": 3,
|
| 289 |
+
"fps": 30.0
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"state": {
|
| 293 |
+
"white_arm": {
|
| 294 |
+
"absolute": true,
|
| 295 |
+
"rotation_type": null,
|
| 296 |
+
"shape": [
|
| 297 |
+
5
|
| 298 |
+
],
|
| 299 |
+
"continuous": true
|
| 300 |
+
},
|
| 301 |
+
"white_gripper": {
|
| 302 |
+
"absolute": true,
|
| 303 |
+
"rotation_type": null,
|
| 304 |
+
"shape": [
|
| 305 |
+
1
|
| 306 |
+
],
|
| 307 |
+
"continuous": true
|
| 308 |
+
},
|
| 309 |
+
"blue_arm": {
|
| 310 |
+
"absolute": true,
|
| 311 |
+
"rotation_type": null,
|
| 312 |
+
"shape": [
|
| 313 |
+
5
|
| 314 |
+
],
|
| 315 |
+
"continuous": true
|
| 316 |
+
},
|
| 317 |
+
"blue_gripper": {
|
| 318 |
+
"absolute": true,
|
| 319 |
+
"rotation_type": null,
|
| 320 |
+
"shape": [
|
| 321 |
+
1
|
| 322 |
+
],
|
| 323 |
+
"continuous": true
|
| 324 |
+
}
|
| 325 |
+
},
|
| 326 |
+
"action": {
|
| 327 |
+
"white_arm": {
|
| 328 |
+
"absolute": true,
|
| 329 |
+
"rotation_type": null,
|
| 330 |
+
"shape": [
|
| 331 |
+
5
|
| 332 |
+
],
|
| 333 |
+
"continuous": true
|
| 334 |
+
},
|
| 335 |
+
"white_gripper": {
|
| 336 |
+
"absolute": true,
|
| 337 |
+
"rotation_type": null,
|
| 338 |
+
"shape": [
|
| 339 |
+
1
|
| 340 |
+
],
|
| 341 |
+
"continuous": true
|
| 342 |
+
},
|
| 343 |
+
"blue_arm": {
|
| 344 |
+
"absolute": true,
|
| 345 |
+
"rotation_type": null,
|
| 346 |
+
"shape": [
|
| 347 |
+
5
|
| 348 |
+
],
|
| 349 |
+
"continuous": true
|
| 350 |
+
},
|
| 351 |
+
"blue_gripper": {
|
| 352 |
+
"absolute": true,
|
| 353 |
+
"rotation_type": null,
|
| 354 |
+
"shape": [
|
| 355 |
+
1
|
| 356 |
+
],
|
| 357 |
+
"continuous": true
|
| 358 |
+
}
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"embodiment_tag": "new_embodiment"
|
| 362 |
+
}
|
| 363 |
+
}
|
checkpoint-9000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b
|
| 3 |
+
size 4999367032
|
checkpoint-9000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5e191587830d672979ff2cb7c2b1d79cb7c2870d48fd0f195cd10de0cafbe06
|
| 3 |
+
size 2586705312
|
checkpoint-9000/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-9000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7061b9c1256b30e7c4fcef7e10b60e2605f8b61975cd3c8992e74a7ad6f1466
|
| 3 |
+
size 14244
|
checkpoint-9000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c26823aa5685497db4fe82a648513d12cb6c26d9be110887b197c10fe3a44ac
|
| 3 |
+
size 1064
|
checkpoint-9000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_dim": 32,
|
| 3 |
+
"action_head_cfg": {
|
| 4 |
+
"action_dim": 32,
|
| 5 |
+
"action_horizon": 16,
|
| 6 |
+
"add_pos_embed": true,
|
| 7 |
+
"backbone_embedding_dim": 2048,
|
| 8 |
+
"diffusion_model_cfg": {
|
| 9 |
+
"attention_head_dim": 48,
|
| 10 |
+
"cross_attention_dim": 2048,
|
| 11 |
+
"dropout": 0.2,
|
| 12 |
+
"final_dropout": true,
|
| 13 |
+
"interleave_self_attention": true,
|
| 14 |
+
"norm_type": "ada_norm",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_layers": 16,
|
| 17 |
+
"output_dim": 1024,
|
| 18 |
+
"positional_embeddings": null
|
| 19 |
+
},
|
| 20 |
+
"hidden_size": 1024,
|
| 21 |
+
"input_embedding_dim": 1536,
|
| 22 |
+
"max_action_dim": 32,
|
| 23 |
+
"max_state_dim": 64,
|
| 24 |
+
"model_dtype": "float32",
|
| 25 |
+
"noise_beta_alpha": 1.5,
|
| 26 |
+
"noise_beta_beta": 1.0,
|
| 27 |
+
"noise_s": 0.999,
|
| 28 |
+
"num_inference_timesteps": 4,
|
| 29 |
+
"num_target_vision_tokens": 32,
|
| 30 |
+
"num_timestep_buckets": 1000,
|
| 31 |
+
"tune_diffusion_model": true,
|
| 32 |
+
"tune_projector": true,
|
| 33 |
+
"use_vlln": true,
|
| 34 |
+
"vl_self_attention_cfg": {
|
| 35 |
+
"attention_head_dim": 64,
|
| 36 |
+
"dropout": 0.2,
|
| 37 |
+
"final_dropout": true,
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_layers": 4,
|
| 40 |
+
"positional_embeddings": null
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"action_horizon": 16,
|
| 44 |
+
"architectures": [
|
| 45 |
+
"GR00T_N1_5"
|
| 46 |
+
],
|
| 47 |
+
"attn_implementation": null,
|
| 48 |
+
"backbone_cfg": {
|
| 49 |
+
"eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
|
| 50 |
+
"load_bf16": false,
|
| 51 |
+
"project_to_dim": null,
|
| 52 |
+
"reproject_vision": false,
|
| 53 |
+
"select_layer": 12,
|
| 54 |
+
"tune_llm": false,
|
| 55 |
+
"tune_visual": true,
|
| 56 |
+
"use_flash_attention": true
|
| 57 |
+
},
|
| 58 |
+
"compute_dtype": "bfloat16",
|
| 59 |
+
"hidden_size": 2048,
|
| 60 |
+
"model_dtype": "float32",
|
| 61 |
+
"model_type": "gr00t_n1_5",
|
| 62 |
+
"torch_dtype": "bfloat16",
|
| 63 |
+
"transformers_version": "4.51.3"
|
| 64 |
+
}
|
experiment_cfg/metadata.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"statistics": {
|
| 4 |
+
"state": {
|
| 5 |
+
"white_arm": {
|
| 6 |
+
"max": [
|
| 7 |
+
-5.758017539978027,
|
| 8 |
+
45.33951950073242,
|
| 9 |
+
83.51254272460938,
|
| 10 |
+
98.8018798828125,
|
| 11 |
+
-3.8293497562408447
|
| 12 |
+
],
|
| 13 |
+
"min": [
|
| 14 |
+
-60.932945251464844,
|
| 15 |
+
-99.40953063964844,
|
| 16 |
+
-80.3763427734375,
|
| 17 |
+
30.851518630981445,
|
| 18 |
+
-58.36545944213867
|
| 19 |
+
],
|
| 20 |
+
"mean": [
|
| 21 |
+
-41.30015563964844,
|
| 22 |
+
-59.61644744873047,
|
| 23 |
+
11.656304359436035,
|
| 24 |
+
92.30885314941406,
|
| 25 |
+
-48.28321838378906
|
| 26 |
+
],
|
| 27 |
+
"std": [
|
| 28 |
+
12.557931900024414,
|
| 29 |
+
49.788997650146484,
|
| 30 |
+
33.65494918823242,
|
| 31 |
+
11.678942680358887,
|
| 32 |
+
12.509681701660156
|
| 33 |
+
],
|
| 34 |
+
"q01": [
|
| 35 |
+
-60.71428680419922,
|
| 36 |
+
-99.40953063964844,
|
| 37 |
+
-61.021507263183594,
|
| 38 |
+
46.82926918029785,
|
| 39 |
+
-57.800052642822266
|
| 40 |
+
],
|
| 41 |
+
"q99": [
|
| 42 |
+
-6.778425693511963,
|
| 43 |
+
44.580345153808594,
|
| 44 |
+
48.11827850341797,
|
| 45 |
+
98.8018798828125,
|
| 46 |
+
-11.231045722961426
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"white_gripper": {
|
| 50 |
+
"max": [
|
| 51 |
+
34.37900161743164
|
| 52 |
+
],
|
| 53 |
+
"min": [
|
| 54 |
+
1.7285531759262085
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
6.319039821624756
|
| 58 |
+
],
|
| 59 |
+
"std": [
|
| 60 |
+
7.589016437530518
|
| 61 |
+
],
|
| 62 |
+
"q01": [
|
| 63 |
+
1.8565940856933594
|
| 64 |
+
],
|
| 65 |
+
"q99": [
|
| 66 |
+
30.34571075439453
|
| 67 |
+
]
|
| 68 |
+
},
|
| 69 |
+
"blue_arm": {
|
| 70 |
+
"max": [
|
| 71 |
+
58.738216400146484,
|
| 72 |
+
18.63117790222168,
|
| 73 |
+
75.27173614501953,
|
| 74 |
+
99.04803466796875,
|
| 75 |
+
-4.080061435699463
|
| 76 |
+
],
|
| 77 |
+
"min": [
|
| 78 |
+
-16.533720016479492,
|
| 79 |
+
-99.070556640625,
|
| 80 |
+
-52.8079719543457,
|
| 81 |
+
66.85417938232422,
|
| 82 |
+
-58.48088455200195
|
| 83 |
+
],
|
| 84 |
+
"mean": [
|
| 85 |
+
22.58572769165039,
|
| 86 |
+
-46.04561233520508,
|
| 87 |
+
4.261409282684326,
|
| 88 |
+
95.5960922241211,
|
| 89 |
+
-31.681655883789062
|
| 90 |
+
],
|
| 91 |
+
"std": [
|
| 92 |
+
24.668598175048828,
|
| 93 |
+
42.83842086791992,
|
| 94 |
+
25.97476577758789,
|
| 95 |
+
6.019741535186768,
|
| 96 |
+
16.340681076049805
|
| 97 |
+
],
|
| 98 |
+
"q01": [
|
| 99 |
+
-16.316171646118164,
|
| 100 |
+
-98.90156555175781,
|
| 101 |
+
-47.55434799194336,
|
| 102 |
+
74.43184829711915,
|
| 103 |
+
-55.760841369628906
|
| 104 |
+
],
|
| 105 |
+
"q99": [
|
| 106 |
+
56.85279083251953,
|
| 107 |
+
17.78622817993164,
|
| 108 |
+
54.619564056396484,
|
| 109 |
+
99.04803466796875,
|
| 110 |
+
-4.285347938537598
|
| 111 |
+
]
|
| 112 |
+
},
|
| 113 |
+
"blue_gripper": {
|
| 114 |
+
"max": [
|
| 115 |
+
40.255374908447266
|
| 116 |
+
],
|
| 117 |
+
"min": [
|
| 118 |
+
1.0080645084381104
|
| 119 |
+
],
|
| 120 |
+
"mean": [
|
| 121 |
+
5.813619613647461
|
| 122 |
+
],
|
| 123 |
+
"std": [
|
| 124 |
+
9.993083000183105
|
| 125 |
+
],
|
| 126 |
+
"q01": [
|
| 127 |
+
1.0080645084381104
|
| 128 |
+
],
|
| 129 |
+
"q99": [
|
| 130 |
+
37.29838562011719
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
},
|
| 134 |
+
"action": {
|
| 135 |
+
"white_arm": {
|
| 136 |
+
"max": [
|
| 137 |
+
-5.325443744659424,
|
| 138 |
+
44.7691650390625,
|
| 139 |
+
83.48375701904297,
|
| 140 |
+
100.0,
|
| 141 |
+
-3.3212246894836426
|
| 142 |
+
],
|
| 143 |
+
"min": [
|
| 144 |
+
-60.724853515625,
|
| 145 |
+
-100.0,
|
| 146 |
+
-83.21299743652344,
|
| 147 |
+
30.108932495117188,
|
| 148 |
+
-58.432796478271484
|
| 149 |
+
],
|
| 150 |
+
"mean": [
|
| 151 |
+
-41.21931457519531,
|
| 152 |
+
-60.167320251464844,
|
| 153 |
+
10.704584121704102,
|
| 154 |
+
92.57025146484375,
|
| 155 |
+
-48.337284088134766
|
| 156 |
+
],
|
| 157 |
+
"std": [
|
| 158 |
+
12.604560852050781,
|
| 159 |
+
49.407814025878906,
|
| 160 |
+
34.10797119140625,
|
| 161 |
+
12.075830459594727,
|
| 162 |
+
12.521093368530273
|
| 163 |
+
],
|
| 164 |
+
"q01": [
|
| 165 |
+
-60.502960205078125,
|
| 166 |
+
-99.83058166503906,
|
| 167 |
+
-63.963899002075195,
|
| 168 |
+
47.06405281066895,
|
| 169 |
+
-57.81006622314453
|
| 170 |
+
],
|
| 171 |
+
"q99": [
|
| 172 |
+
-6.804733753204346,
|
| 173 |
+
42.9783979797363,
|
| 174 |
+
47.743682861328125,
|
| 175 |
+
100.0,
|
| 176 |
+
-11.053450584411621
|
| 177 |
+
]
|
| 178 |
+
},
|
| 179 |
+
"white_gripper": {
|
| 180 |
+
"max": [
|
| 181 |
+
34.68433380126953
|
| 182 |
+
],
|
| 183 |
+
"min": [
|
| 184 |
+
1.3250194787979126
|
| 185 |
+
],
|
| 186 |
+
"mean": [
|
| 187 |
+
5.815976142883301
|
| 188 |
+
],
|
| 189 |
+
"std": [
|
| 190 |
+
7.803332805633545
|
| 191 |
+
],
|
| 192 |
+
"q01": [
|
| 193 |
+
1.6367887258529663
|
| 194 |
+
],
|
| 195 |
+
"q99": [
|
| 196 |
+
30.709274291992188
|
| 197 |
+
]
|
| 198 |
+
},
|
| 199 |
+
"blue_arm": {
|
| 200 |
+
"max": [
|
| 201 |
+
59.20177459716797,
|
| 202 |
+
18.235294342041016,
|
| 203 |
+
56.36856460571289,
|
| 204 |
+
99.4778060913086,
|
| 205 |
+
-3.9603960514068604
|
| 206 |
+
],
|
| 207 |
+
"min": [
|
| 208 |
+
-16.629711151123047,
|
| 209 |
+
-99.4117660522461,
|
| 210 |
+
-55.55555725097656,
|
| 211 |
+
65.97040557861328,
|
| 212 |
+
-58.780616760253906
|
| 213 |
+
],
|
| 214 |
+
"mean": [
|
| 215 |
+
22.72244644165039,
|
| 216 |
+
-46.86748123168945,
|
| 217 |
+
3.5456254482269287,
|
| 218 |
+
95.69131469726562,
|
| 219 |
+
-31.745248794555664
|
| 220 |
+
],
|
| 221 |
+
"std": [
|
| 222 |
+
24.648967742919922,
|
| 223 |
+
42.451499938964844,
|
| 224 |
+
26.123699188232422,
|
| 225 |
+
6.368340015411377,
|
| 226 |
+
16.331010818481445
|
| 227 |
+
],
|
| 228 |
+
"q01": [
|
| 229 |
+
-16.18625259399414,
|
| 230 |
+
-98.9916000366211,
|
| 231 |
+
-49.68383026123047,
|
| 232 |
+
73.62924194335938,
|
| 233 |
+
-55.549766540527344
|
| 234 |
+
],
|
| 235 |
+
"q99": [
|
| 236 |
+
57.058387756347656,
|
| 237 |
+
16.554622650146484,
|
| 238 |
+
52.93586349487305,
|
| 239 |
+
99.39077758789062,
|
| 240 |
+
-4.273058891296387
|
| 241 |
+
]
|
| 242 |
+
},
|
| 243 |
+
"blue_gripper": {
|
| 244 |
+
"max": [
|
| 245 |
+
40.44117736816406
|
| 246 |
+
],
|
| 247 |
+
"min": [
|
| 248 |
+
0.0
|
| 249 |
+
],
|
| 250 |
+
"mean": [
|
| 251 |
+
5.49310302734375
|
| 252 |
+
],
|
| 253 |
+
"std": [
|
| 254 |
+
10.243758201599121
|
| 255 |
+
],
|
| 256 |
+
"q01": [
|
| 257 |
+
0.898692786693573
|
| 258 |
+
],
|
| 259 |
+
"q99": [
|
| 260 |
+
37.33660125732422
|
| 261 |
+
]
|
| 262 |
+
}
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
+
"modalities": {
|
| 266 |
+
"video": {
|
| 267 |
+
"global_top": {
|
| 268 |
+
"resolution": [
|
| 269 |
+
1280,
|
| 270 |
+
720
|
| 271 |
+
],
|
| 272 |
+
"channels": 3,
|
| 273 |
+
"fps": 30.0
|
| 274 |
+
},
|
| 275 |
+
"white_front": {
|
| 276 |
+
"resolution": [
|
| 277 |
+
640,
|
| 278 |
+
480
|
| 279 |
+
],
|
| 280 |
+
"channels": 3,
|
| 281 |
+
"fps": 30.0
|
| 282 |
+
},
|
| 283 |
+
"blue_front": {
|
| 284 |
+
"resolution": [
|
| 285 |
+
640,
|
| 286 |
+
480
|
| 287 |
+
],
|
| 288 |
+
"channels": 3,
|
| 289 |
+
"fps": 30.0
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"state": {
|
| 293 |
+
"white_arm": {
|
| 294 |
+
"absolute": true,
|
| 295 |
+
"rotation_type": null,
|
| 296 |
+
"shape": [
|
| 297 |
+
5
|
| 298 |
+
],
|
| 299 |
+
"continuous": true
|
| 300 |
+
},
|
| 301 |
+
"white_gripper": {
|
| 302 |
+
"absolute": true,
|
| 303 |
+
"rotation_type": null,
|
| 304 |
+
"shape": [
|
| 305 |
+
1
|
| 306 |
+
],
|
| 307 |
+
"continuous": true
|
| 308 |
+
},
|
| 309 |
+
"blue_arm": {
|
| 310 |
+
"absolute": true,
|
| 311 |
+
"rotation_type": null,
|
| 312 |
+
"shape": [
|
| 313 |
+
5
|
| 314 |
+
],
|
| 315 |
+
"continuous": true
|
| 316 |
+
},
|
| 317 |
+
"blue_gripper": {
|
| 318 |
+
"absolute": true,
|
| 319 |
+
"rotation_type": null,
|
| 320 |
+
"shape": [
|
| 321 |
+
1
|
| 322 |
+
],
|
| 323 |
+
"continuous": true
|
| 324 |
+
}
|
| 325 |
+
},
|
| 326 |
+
"action": {
|
| 327 |
+
"white_arm": {
|
| 328 |
+
"absolute": true,
|
| 329 |
+
"rotation_type": null,
|
| 330 |
+
"shape": [
|
| 331 |
+
5
|
| 332 |
+
],
|
| 333 |
+
"continuous": true
|
| 334 |
+
},
|
| 335 |
+
"white_gripper": {
|
| 336 |
+
"absolute": true,
|
| 337 |
+
"rotation_type": null,
|
| 338 |
+
"shape": [
|
| 339 |
+
1
|
| 340 |
+
],
|
| 341 |
+
"continuous": true
|
| 342 |
+
},
|
| 343 |
+
"blue_arm": {
|
| 344 |
+
"absolute": true,
|
| 345 |
+
"rotation_type": null,
|
| 346 |
+
"shape": [
|
| 347 |
+
5
|
| 348 |
+
],
|
| 349 |
+
"continuous": true
|
| 350 |
+
},
|
| 351 |
+
"blue_gripper": {
|
| 352 |
+
"absolute": true,
|
| 353 |
+
"rotation_type": null,
|
| 354 |
+
"shape": [
|
| 355 |
+
1
|
| 356 |
+
],
|
| 357 |
+
"continuous": true
|
| 358 |
+
}
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"embodiment_tag": "new_embodiment"
|
| 362 |
+
}
|
| 363 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b
|
| 3 |
+
size 4999367032
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d7361d737dee4d886c5178e4a1d51f67b02d217892b13e46a09fce2ce62be80
|
| 3 |
+
size 2586705312
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbcf85b1f2fca3472ecf16882a45472b8428adac3f1e4f50ff21c43e4ca0a828
|
| 3 |
+
size 5304
|