Upload folder using huggingface_hub
Browse files- checkpoint-60000/config.json +70 -0
- checkpoint-60000/embodiment_id.json +11 -0
- checkpoint-60000/latest +1 -0
- checkpoint-60000/model-00001-of-00002.safetensors +3 -0
- checkpoint-60000/model-00002-of-00002.safetensors +3 -0
- checkpoint-60000/model.safetensors.index.json +0 -0
- checkpoint-60000/processor_config.json +923 -0
- checkpoint-60000/rng_state_0.pth +3 -0
- checkpoint-60000/rng_state_1.pth +3 -0
- checkpoint-60000/scheduler.pt +3 -0
- checkpoint-60000/statistics.json +0 -0
- checkpoint-60000/trainer_state.json +0 -0
- checkpoint-60000/training_args.bin +3 -0
- checkpoint-60000/zero_to_fp32.py +760 -0
- config.json +70 -0
- experiment_cfg/dataset_statistics.json +317 -0
- experiment_cfg/final_model_config.json +53 -0
- experiment_cfg/final_processor_config.json +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- processor/embodiment_id.json +11 -0
- processor/processor_config.json +923 -0
- processor/statistics.json +0 -0
- training_args.bin +3 -0
checkpoint-60000/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_horizon": 50,
|
| 3 |
+
"add_pos_embed": true,
|
| 4 |
+
"apply_sincos_state_encoding": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Gr00tN1d6"
|
| 7 |
+
],
|
| 8 |
+
"attn_dropout": 0.2,
|
| 9 |
+
"attn_implementation": null,
|
| 10 |
+
"backbone_embedding_dim": 2048,
|
| 11 |
+
"backbone_model_type": "eagle",
|
| 12 |
+
"backbone_trainable_params_fp32": true,
|
| 13 |
+
"collator_overwrite_image_inputs": false,
|
| 14 |
+
"color_jitter_params": {
|
| 15 |
+
"brightness": 0.1,
|
| 16 |
+
"contrast": 0.1,
|
| 17 |
+
"hue": 0.1,
|
| 18 |
+
"saturation": 0.1
|
| 19 |
+
},
|
| 20 |
+
"crop_fraction": 0.95,
|
| 21 |
+
"diffusion_model_cfg": {
|
| 22 |
+
"attention_head_dim": 48,
|
| 23 |
+
"dropout": 0.2,
|
| 24 |
+
"final_dropout": true,
|
| 25 |
+
"interleave_self_attention": true,
|
| 26 |
+
"norm_type": "ada_norm",
|
| 27 |
+
"num_attention_heads": 32,
|
| 28 |
+
"num_layers": 32,
|
| 29 |
+
"output_dim": 1024,
|
| 30 |
+
"positional_embeddings": null
|
| 31 |
+
},
|
| 32 |
+
"eagle_collator": true,
|
| 33 |
+
"formalize_language": true,
|
| 34 |
+
"gemma_collator": false,
|
| 35 |
+
"hidden_size": 1024,
|
| 36 |
+
"image_crop_size": null,
|
| 37 |
+
"image_target_size": null,
|
| 38 |
+
"input_embedding_dim": 1536,
|
| 39 |
+
"load_bf16": true,
|
| 40 |
+
"max_action_dim": 128,
|
| 41 |
+
"max_num_embodiments": 32,
|
| 42 |
+
"max_seq_len": 1024,
|
| 43 |
+
"max_state_dim": 128,
|
| 44 |
+
"model_dtype": "bfloat16",
|
| 45 |
+
"model_name": "nvidia/Eagle-Block2A-2B-v2",
|
| 46 |
+
"model_type": "Gr00tN1d6",
|
| 47 |
+
"noise_beta_alpha": 1.5,
|
| 48 |
+
"noise_beta_beta": 1.0,
|
| 49 |
+
"noise_s": 0.999,
|
| 50 |
+
"num_inference_timesteps": 4,
|
| 51 |
+
"num_timestep_buckets": 1000,
|
| 52 |
+
"random_rotation_angle": null,
|
| 53 |
+
"reproject_vision": false,
|
| 54 |
+
"select_layer": 16,
|
| 55 |
+
"shortest_image_edge": 256,
|
| 56 |
+
"state_dropout_prob": 0.0,
|
| 57 |
+
"torch_dtype": "bfloat16",
|
| 58 |
+
"transformers_version": "4.51.3",
|
| 59 |
+
"tune_diffusion_model": true,
|
| 60 |
+
"tune_llm": false,
|
| 61 |
+
"tune_projector": true,
|
| 62 |
+
"tune_top_llm_layers": 4,
|
| 63 |
+
"tune_visual": false,
|
| 64 |
+
"tune_vlln": true,
|
| 65 |
+
"use_albumentations_transforms": true,
|
| 66 |
+
"use_alternate_vl_dit": true,
|
| 67 |
+
"use_flash_attention": true,
|
| 68 |
+
"use_relative_action": true,
|
| 69 |
+
"use_vlln": true
|
| 70 |
+
}
|
checkpoint-60000/embodiment_id.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"robocasa_panda_omron": 13,
|
| 3 |
+
"gr1": 20,
|
| 4 |
+
"behavior_r1_pro": 24,
|
| 5 |
+
"unitree_g1": 8,
|
| 6 |
+
"oxe_google": 0,
|
| 7 |
+
"oxe_widowx": 1,
|
| 8 |
+
"libero_panda": 2,
|
| 9 |
+
"oxe_droid": 16,
|
| 10 |
+
"new_embodiment": 10
|
| 11 |
+
}
|
checkpoint-60000/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step60000
|
checkpoint-60000/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fd3f824fb806d8bcd6c308b99c9fb3bc02ab201cf161343b452a60beb361255
|
| 3 |
+
size 4991091456
|
checkpoint-60000/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bb5cc1c97053e21fded718b9138232709488ac911d0116d4c346f299662ba3b
|
| 3 |
+
size 1582283096
|
checkpoint-60000/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-60000/processor_config.json
ADDED
|
@@ -0,0 +1,923 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"processor_class": "Gr00tN1d6Processor",
|
| 3 |
+
"processor_kwargs": {
|
| 4 |
+
"modality_configs": {
|
| 5 |
+
"behavior_r1_pro": {
|
| 6 |
+
"video": {
|
| 7 |
+
"delta_indices": [
|
| 8 |
+
0
|
| 9 |
+
],
|
| 10 |
+
"modality_keys": [
|
| 11 |
+
"observation.images.rgb.head_256_256",
|
| 12 |
+
"observation.images.rgb.left_wrist_256_256",
|
| 13 |
+
"observation.images.rgb.right_wrist_256_256"
|
| 14 |
+
],
|
| 15 |
+
"sin_cos_embedding_keys": null,
|
| 16 |
+
"mean_std_embedding_keys": null,
|
| 17 |
+
"action_configs": null
|
| 18 |
+
},
|
| 19 |
+
"state": {
|
| 20 |
+
"delta_indices": [
|
| 21 |
+
0
|
| 22 |
+
],
|
| 23 |
+
"modality_keys": [
|
| 24 |
+
"robot_pos",
|
| 25 |
+
"robot_ori_cos",
|
| 26 |
+
"robot_ori_sin",
|
| 27 |
+
"robot_2d_ori",
|
| 28 |
+
"robot_2d_ori_cos",
|
| 29 |
+
"robot_2d_ori_sin",
|
| 30 |
+
"robot_lin_vel",
|
| 31 |
+
"robot_ang_vel",
|
| 32 |
+
"arm_left_qpos",
|
| 33 |
+
"arm_left_qpos_sin",
|
| 34 |
+
"arm_left_qpos_cos",
|
| 35 |
+
"eef_left_pos",
|
| 36 |
+
"eef_left_quat",
|
| 37 |
+
"gripper_left_qpos",
|
| 38 |
+
"arm_right_qpos",
|
| 39 |
+
"arm_right_qpos_sin",
|
| 40 |
+
"arm_right_qpos_cos",
|
| 41 |
+
"eef_right_pos",
|
| 42 |
+
"eef_right_quat",
|
| 43 |
+
"gripper_right_qpos",
|
| 44 |
+
"trunk_qpos"
|
| 45 |
+
],
|
| 46 |
+
"sin_cos_embedding_keys": null,
|
| 47 |
+
"mean_std_embedding_keys": null,
|
| 48 |
+
"action_configs": null
|
| 49 |
+
},
|
| 50 |
+
"action": {
|
| 51 |
+
"delta_indices": [
|
| 52 |
+
0,
|
| 53 |
+
1,
|
| 54 |
+
2,
|
| 55 |
+
3,
|
| 56 |
+
4,
|
| 57 |
+
5,
|
| 58 |
+
6,
|
| 59 |
+
7,
|
| 60 |
+
8,
|
| 61 |
+
9,
|
| 62 |
+
10,
|
| 63 |
+
11,
|
| 64 |
+
12,
|
| 65 |
+
13,
|
| 66 |
+
14,
|
| 67 |
+
15,
|
| 68 |
+
16,
|
| 69 |
+
17,
|
| 70 |
+
18,
|
| 71 |
+
19,
|
| 72 |
+
20,
|
| 73 |
+
21,
|
| 74 |
+
22,
|
| 75 |
+
23,
|
| 76 |
+
24,
|
| 77 |
+
25,
|
| 78 |
+
26,
|
| 79 |
+
27,
|
| 80 |
+
28,
|
| 81 |
+
29,
|
| 82 |
+
30,
|
| 83 |
+
31
|
| 84 |
+
],
|
| 85 |
+
"modality_keys": [
|
| 86 |
+
"base",
|
| 87 |
+
"torso",
|
| 88 |
+
"left_arm",
|
| 89 |
+
"left_gripper",
|
| 90 |
+
"right_arm",
|
| 91 |
+
"right_gripper"
|
| 92 |
+
],
|
| 93 |
+
"sin_cos_embedding_keys": null,
|
| 94 |
+
"mean_std_embedding_keys": null,
|
| 95 |
+
"action_configs": [
|
| 96 |
+
{
|
| 97 |
+
"rep": "ABSOLUTE",
|
| 98 |
+
"type": "NON_EEF",
|
| 99 |
+
"format": "DEFAULT",
|
| 100 |
+
"state_key": null
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"rep": "RELATIVE",
|
| 104 |
+
"type": "NON_EEF",
|
| 105 |
+
"format": "DEFAULT",
|
| 106 |
+
"state_key": "trunk_qpos"
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"rep": "RELATIVE",
|
| 110 |
+
"type": "NON_EEF",
|
| 111 |
+
"format": "DEFAULT",
|
| 112 |
+
"state_key": "arm_left_qpos"
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"rep": "ABSOLUTE",
|
| 116 |
+
"type": "NON_EEF",
|
| 117 |
+
"format": "DEFAULT",
|
| 118 |
+
"state_key": null
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"rep": "RELATIVE",
|
| 122 |
+
"type": "NON_EEF",
|
| 123 |
+
"format": "DEFAULT",
|
| 124 |
+
"state_key": "arm_right_qpos"
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"rep": "ABSOLUTE",
|
| 128 |
+
"type": "NON_EEF",
|
| 129 |
+
"format": "DEFAULT",
|
| 130 |
+
"state_key": null
|
| 131 |
+
}
|
| 132 |
+
]
|
| 133 |
+
},
|
| 134 |
+
"language": {
|
| 135 |
+
"delta_indices": [
|
| 136 |
+
0
|
| 137 |
+
],
|
| 138 |
+
"modality_keys": [
|
| 139 |
+
"annotation.human.coarse_action"
|
| 140 |
+
],
|
| 141 |
+
"sin_cos_embedding_keys": null,
|
| 142 |
+
"mean_std_embedding_keys": null,
|
| 143 |
+
"action_configs": null
|
| 144 |
+
}
|
| 145 |
+
},
|
| 146 |
+
"gr1": {
|
| 147 |
+
"video": {
|
| 148 |
+
"delta_indices": [
|
| 149 |
+
0
|
| 150 |
+
],
|
| 151 |
+
"modality_keys": [
|
| 152 |
+
"ego_view_bg_crop_pad_res256_freq20"
|
| 153 |
+
],
|
| 154 |
+
"sin_cos_embedding_keys": null,
|
| 155 |
+
"mean_std_embedding_keys": null,
|
| 156 |
+
"action_configs": null
|
| 157 |
+
},
|
| 158 |
+
"state": {
|
| 159 |
+
"delta_indices": [
|
| 160 |
+
0
|
| 161 |
+
],
|
| 162 |
+
"modality_keys": [
|
| 163 |
+
"left_arm",
|
| 164 |
+
"right_arm",
|
| 165 |
+
"left_hand",
|
| 166 |
+
"right_hand",
|
| 167 |
+
"waist"
|
| 168 |
+
],
|
| 169 |
+
"sin_cos_embedding_keys": [
|
| 170 |
+
"left_arm",
|
| 171 |
+
"right_arm",
|
| 172 |
+
"left_hand",
|
| 173 |
+
"right_hand",
|
| 174 |
+
"waist"
|
| 175 |
+
],
|
| 176 |
+
"mean_std_embedding_keys": null,
|
| 177 |
+
"action_configs": null
|
| 178 |
+
},
|
| 179 |
+
"action": {
|
| 180 |
+
"delta_indices": [
|
| 181 |
+
0,
|
| 182 |
+
1,
|
| 183 |
+
2,
|
| 184 |
+
3,
|
| 185 |
+
4,
|
| 186 |
+
5,
|
| 187 |
+
6,
|
| 188 |
+
7,
|
| 189 |
+
8,
|
| 190 |
+
9,
|
| 191 |
+
10,
|
| 192 |
+
11,
|
| 193 |
+
12,
|
| 194 |
+
13,
|
| 195 |
+
14,
|
| 196 |
+
15
|
| 197 |
+
],
|
| 198 |
+
"modality_keys": [
|
| 199 |
+
"left_arm",
|
| 200 |
+
"right_arm",
|
| 201 |
+
"left_hand",
|
| 202 |
+
"right_hand",
|
| 203 |
+
"waist"
|
| 204 |
+
],
|
| 205 |
+
"sin_cos_embedding_keys": null,
|
| 206 |
+
"mean_std_embedding_keys": null,
|
| 207 |
+
"action_configs": [
|
| 208 |
+
{
|
| 209 |
+
"rep": "RELATIVE",
|
| 210 |
+
"type": "NON_EEF",
|
| 211 |
+
"format": "DEFAULT",
|
| 212 |
+
"state_key": null
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"rep": "RELATIVE",
|
| 216 |
+
"type": "NON_EEF",
|
| 217 |
+
"format": "DEFAULT",
|
| 218 |
+
"state_key": null
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"rep": "RELATIVE",
|
| 222 |
+
"type": "NON_EEF",
|
| 223 |
+
"format": "DEFAULT",
|
| 224 |
+
"state_key": null
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"rep": "RELATIVE",
|
| 228 |
+
"type": "NON_EEF",
|
| 229 |
+
"format": "DEFAULT",
|
| 230 |
+
"state_key": null
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"rep": "ABSOLUTE",
|
| 234 |
+
"type": "NON_EEF",
|
| 235 |
+
"format": "DEFAULT",
|
| 236 |
+
"state_key": null
|
| 237 |
+
}
|
| 238 |
+
]
|
| 239 |
+
},
|
| 240 |
+
"language": {
|
| 241 |
+
"delta_indices": [
|
| 242 |
+
0
|
| 243 |
+
],
|
| 244 |
+
"modality_keys": [
|
| 245 |
+
"task"
|
| 246 |
+
],
|
| 247 |
+
"sin_cos_embedding_keys": null,
|
| 248 |
+
"mean_std_embedding_keys": null,
|
| 249 |
+
"action_configs": null
|
| 250 |
+
}
|
| 251 |
+
},
|
| 252 |
+
"robocasa_panda_omron": {
|
| 253 |
+
"video": {
|
| 254 |
+
"delta_indices": [
|
| 255 |
+
0
|
| 256 |
+
],
|
| 257 |
+
"modality_keys": [
|
| 258 |
+
"robot0_eye_in_hand",
|
| 259 |
+
"robot0_agentview_left",
|
| 260 |
+
"robot0_agentview_right"
|
| 261 |
+
],
|
| 262 |
+
"sin_cos_embedding_keys": null,
|
| 263 |
+
"mean_std_embedding_keys": null,
|
| 264 |
+
"action_configs": null
|
| 265 |
+
},
|
| 266 |
+
"state": {
|
| 267 |
+
"delta_indices": [
|
| 268 |
+
0
|
| 269 |
+
],
|
| 270 |
+
"modality_keys": [
|
| 271 |
+
"base_position",
|
| 272 |
+
"base_rotation",
|
| 273 |
+
"end_effector_position_relative",
|
| 274 |
+
"end_effector_rotation_relative",
|
| 275 |
+
"gripper_qpos"
|
| 276 |
+
],
|
| 277 |
+
"sin_cos_embedding_keys": null,
|
| 278 |
+
"mean_std_embedding_keys": null,
|
| 279 |
+
"action_configs": null
|
| 280 |
+
},
|
| 281 |
+
"action": {
|
| 282 |
+
"delta_indices": [
|
| 283 |
+
0,
|
| 284 |
+
1,
|
| 285 |
+
2,
|
| 286 |
+
3,
|
| 287 |
+
4,
|
| 288 |
+
5,
|
| 289 |
+
6,
|
| 290 |
+
7,
|
| 291 |
+
8,
|
| 292 |
+
9,
|
| 293 |
+
10,
|
| 294 |
+
11,
|
| 295 |
+
12,
|
| 296 |
+
13,
|
| 297 |
+
14,
|
| 298 |
+
15
|
| 299 |
+
],
|
| 300 |
+
"modality_keys": [
|
| 301 |
+
"base_motion",
|
| 302 |
+
"control_mode",
|
| 303 |
+
"end_effector_position",
|
| 304 |
+
"end_effector_rotation",
|
| 305 |
+
"gripper_close"
|
| 306 |
+
],
|
| 307 |
+
"sin_cos_embedding_keys": null,
|
| 308 |
+
"mean_std_embedding_keys": null,
|
| 309 |
+
"action_configs": [
|
| 310 |
+
{
|
| 311 |
+
"rep": "ABSOLUTE",
|
| 312 |
+
"type": "NON_EEF",
|
| 313 |
+
"format": "DEFAULT",
|
| 314 |
+
"state_key": null
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"rep": "ABSOLUTE",
|
| 318 |
+
"type": "NON_EEF",
|
| 319 |
+
"format": "DEFAULT",
|
| 320 |
+
"state_key": null
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"rep": "ABSOLUTE",
|
| 324 |
+
"type": "EEF",
|
| 325 |
+
"format": "DEFAULT",
|
| 326 |
+
"state_key": null
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"rep": "ABSOLUTE",
|
| 330 |
+
"type": "EEF",
|
| 331 |
+
"format": "DEFAULT",
|
| 332 |
+
"state_key": null
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"rep": "ABSOLUTE",
|
| 336 |
+
"type": "NON_EEF",
|
| 337 |
+
"format": "DEFAULT",
|
| 338 |
+
"state_key": null
|
| 339 |
+
}
|
| 340 |
+
]
|
| 341 |
+
},
|
| 342 |
+
"language": {
|
| 343 |
+
"delta_indices": [
|
| 344 |
+
0
|
| 345 |
+
],
|
| 346 |
+
"modality_keys": [
|
| 347 |
+
"task"
|
| 348 |
+
],
|
| 349 |
+
"sin_cos_embedding_keys": null,
|
| 350 |
+
"mean_std_embedding_keys": null,
|
| 351 |
+
"action_configs": null
|
| 352 |
+
}
|
| 353 |
+
},
|
| 354 |
+
"unitree_g1": {
|
| 355 |
+
"video": {
|
| 356 |
+
"delta_indices": [
|
| 357 |
+
0
|
| 358 |
+
],
|
| 359 |
+
"modality_keys": [
|
| 360 |
+
"ego_view"
|
| 361 |
+
],
|
| 362 |
+
"sin_cos_embedding_keys": null,
|
| 363 |
+
"mean_std_embedding_keys": null,
|
| 364 |
+
"action_configs": null
|
| 365 |
+
},
|
| 366 |
+
"state": {
|
| 367 |
+
"delta_indices": [
|
| 368 |
+
0
|
| 369 |
+
],
|
| 370 |
+
"modality_keys": [
|
| 371 |
+
"left_leg",
|
| 372 |
+
"right_leg",
|
| 373 |
+
"waist",
|
| 374 |
+
"left_arm",
|
| 375 |
+
"right_arm",
|
| 376 |
+
"left_hand",
|
| 377 |
+
"right_hand"
|
| 378 |
+
],
|
| 379 |
+
"sin_cos_embedding_keys": null,
|
| 380 |
+
"mean_std_embedding_keys": null,
|
| 381 |
+
"action_configs": null
|
| 382 |
+
},
|
| 383 |
+
"action": {
|
| 384 |
+
"delta_indices": [
|
| 385 |
+
0,
|
| 386 |
+
1,
|
| 387 |
+
2,
|
| 388 |
+
3,
|
| 389 |
+
4,
|
| 390 |
+
5,
|
| 391 |
+
6,
|
| 392 |
+
7,
|
| 393 |
+
8,
|
| 394 |
+
9,
|
| 395 |
+
10,
|
| 396 |
+
11,
|
| 397 |
+
12,
|
| 398 |
+
13,
|
| 399 |
+
14,
|
| 400 |
+
15,
|
| 401 |
+
16,
|
| 402 |
+
17,
|
| 403 |
+
18,
|
| 404 |
+
19,
|
| 405 |
+
20,
|
| 406 |
+
21,
|
| 407 |
+
22,
|
| 408 |
+
23,
|
| 409 |
+
24,
|
| 410 |
+
25,
|
| 411 |
+
26,
|
| 412 |
+
27,
|
| 413 |
+
28,
|
| 414 |
+
29
|
| 415 |
+
],
|
| 416 |
+
"modality_keys": [
|
| 417 |
+
"left_arm",
|
| 418 |
+
"right_arm",
|
| 419 |
+
"left_hand",
|
| 420 |
+
"right_hand",
|
| 421 |
+
"waist",
|
| 422 |
+
"base_height_command",
|
| 423 |
+
"navigate_command"
|
| 424 |
+
],
|
| 425 |
+
"sin_cos_embedding_keys": null,
|
| 426 |
+
"mean_std_embedding_keys": null,
|
| 427 |
+
"action_configs": [
|
| 428 |
+
{
|
| 429 |
+
"rep": "RELATIVE",
|
| 430 |
+
"type": "NON_EEF",
|
| 431 |
+
"format": "DEFAULT",
|
| 432 |
+
"state_key": null
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"rep": "RELATIVE",
|
| 436 |
+
"type": "NON_EEF",
|
| 437 |
+
"format": "DEFAULT",
|
| 438 |
+
"state_key": null
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"rep": "ABSOLUTE",
|
| 442 |
+
"type": "NON_EEF",
|
| 443 |
+
"format": "DEFAULT",
|
| 444 |
+
"state_key": null
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"rep": "ABSOLUTE",
|
| 448 |
+
"type": "NON_EEF",
|
| 449 |
+
"format": "DEFAULT",
|
| 450 |
+
"state_key": null
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"rep": "ABSOLUTE",
|
| 454 |
+
"type": "NON_EEF",
|
| 455 |
+
"format": "DEFAULT",
|
| 456 |
+
"state_key": null
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"rep": "ABSOLUTE",
|
| 460 |
+
"type": "NON_EEF",
|
| 461 |
+
"format": "DEFAULT",
|
| 462 |
+
"state_key": null
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"rep": "ABSOLUTE",
|
| 466 |
+
"type": "NON_EEF",
|
| 467 |
+
"format": "DEFAULT",
|
| 468 |
+
"state_key": null
|
| 469 |
+
}
|
| 470 |
+
]
|
| 471 |
+
},
|
| 472 |
+
"language": {
|
| 473 |
+
"delta_indices": [
|
| 474 |
+
0
|
| 475 |
+
],
|
| 476 |
+
"modality_keys": [
|
| 477 |
+
"annotation.human.task_description"
|
| 478 |
+
],
|
| 479 |
+
"sin_cos_embedding_keys": null,
|
| 480 |
+
"mean_std_embedding_keys": null,
|
| 481 |
+
"action_configs": null
|
| 482 |
+
}
|
| 483 |
+
},
|
| 484 |
+
"libero_panda": {
|
| 485 |
+
"video": {
|
| 486 |
+
"delta_indices": [
|
| 487 |
+
0
|
| 488 |
+
],
|
| 489 |
+
"modality_keys": [
|
| 490 |
+
"image",
|
| 491 |
+
"wrist_image"
|
| 492 |
+
],
|
| 493 |
+
"sin_cos_embedding_keys": null,
|
| 494 |
+
"mean_std_embedding_keys": null,
|
| 495 |
+
"action_configs": null
|
| 496 |
+
},
|
| 497 |
+
"state": {
|
| 498 |
+
"delta_indices": [
|
| 499 |
+
0
|
| 500 |
+
],
|
| 501 |
+
"modality_keys": [
|
| 502 |
+
"x",
|
| 503 |
+
"y",
|
| 504 |
+
"z",
|
| 505 |
+
"roll",
|
| 506 |
+
"pitch",
|
| 507 |
+
"yaw",
|
| 508 |
+
"gripper"
|
| 509 |
+
],
|
| 510 |
+
"sin_cos_embedding_keys": null,
|
| 511 |
+
"mean_std_embedding_keys": null,
|
| 512 |
+
"action_configs": null
|
| 513 |
+
},
|
| 514 |
+
"action": {
|
| 515 |
+
"delta_indices": [
|
| 516 |
+
0,
|
| 517 |
+
1,
|
| 518 |
+
2,
|
| 519 |
+
3,
|
| 520 |
+
4,
|
| 521 |
+
5,
|
| 522 |
+
6,
|
| 523 |
+
7,
|
| 524 |
+
8,
|
| 525 |
+
9,
|
| 526 |
+
10,
|
| 527 |
+
11,
|
| 528 |
+
12,
|
| 529 |
+
13,
|
| 530 |
+
14,
|
| 531 |
+
15
|
| 532 |
+
],
|
| 533 |
+
"modality_keys": [
|
| 534 |
+
"x",
|
| 535 |
+
"y",
|
| 536 |
+
"z",
|
| 537 |
+
"roll",
|
| 538 |
+
"pitch",
|
| 539 |
+
"yaw",
|
| 540 |
+
"gripper"
|
| 541 |
+
],
|
| 542 |
+
"sin_cos_embedding_keys": null,
|
| 543 |
+
"mean_std_embedding_keys": null,
|
| 544 |
+
"action_configs": null
|
| 545 |
+
},
|
| 546 |
+
"language": {
|
| 547 |
+
"delta_indices": [
|
| 548 |
+
0
|
| 549 |
+
],
|
| 550 |
+
"modality_keys": [
|
| 551 |
+
"annotation.human.action.task_description"
|
| 552 |
+
],
|
| 553 |
+
"sin_cos_embedding_keys": null,
|
| 554 |
+
"mean_std_embedding_keys": null,
|
| 555 |
+
"action_configs": null
|
| 556 |
+
}
|
| 557 |
+
},
|
| 558 |
+
"oxe_widowx": {
|
| 559 |
+
"video": {
|
| 560 |
+
"delta_indices": [
|
| 561 |
+
0
|
| 562 |
+
],
|
| 563 |
+
"modality_keys": [
|
| 564 |
+
"image_0"
|
| 565 |
+
],
|
| 566 |
+
"sin_cos_embedding_keys": null,
|
| 567 |
+
"mean_std_embedding_keys": null,
|
| 568 |
+
"action_configs": null
|
| 569 |
+
},
|
| 570 |
+
"state": {
|
| 571 |
+
"delta_indices": [
|
| 572 |
+
0
|
| 573 |
+
],
|
| 574 |
+
"modality_keys": [
|
| 575 |
+
"x",
|
| 576 |
+
"y",
|
| 577 |
+
"z",
|
| 578 |
+
"roll",
|
| 579 |
+
"pitch",
|
| 580 |
+
"yaw",
|
| 581 |
+
"pad",
|
| 582 |
+
"gripper"
|
| 583 |
+
],
|
| 584 |
+
"sin_cos_embedding_keys": null,
|
| 585 |
+
"mean_std_embedding_keys": null,
|
| 586 |
+
"action_configs": null
|
| 587 |
+
},
|
| 588 |
+
"action": {
|
| 589 |
+
"delta_indices": [
|
| 590 |
+
0,
|
| 591 |
+
1,
|
| 592 |
+
2,
|
| 593 |
+
3,
|
| 594 |
+
4,
|
| 595 |
+
5,
|
| 596 |
+
6,
|
| 597 |
+
7
|
| 598 |
+
],
|
| 599 |
+
"modality_keys": [
|
| 600 |
+
"x",
|
| 601 |
+
"y",
|
| 602 |
+
"z",
|
| 603 |
+
"roll",
|
| 604 |
+
"pitch",
|
| 605 |
+
"yaw",
|
| 606 |
+
"gripper"
|
| 607 |
+
],
|
| 608 |
+
"sin_cos_embedding_keys": null,
|
| 609 |
+
"mean_std_embedding_keys": [
|
| 610 |
+
"x",
|
| 611 |
+
"y",
|
| 612 |
+
"z",
|
| 613 |
+
"roll",
|
| 614 |
+
"pitch",
|
| 615 |
+
"yaw"
|
| 616 |
+
],
|
| 617 |
+
"action_configs": null
|
| 618 |
+
},
|
| 619 |
+
"language": {
|
| 620 |
+
"delta_indices": [
|
| 621 |
+
0
|
| 622 |
+
],
|
| 623 |
+
"modality_keys": [
|
| 624 |
+
"annotation.human.action.task_description"
|
| 625 |
+
],
|
| 626 |
+
"sin_cos_embedding_keys": null,
|
| 627 |
+
"mean_std_embedding_keys": null,
|
| 628 |
+
"action_configs": null
|
| 629 |
+
}
|
| 630 |
+
},
|
| 631 |
+
"oxe_google": {
|
| 632 |
+
"video": {
|
| 633 |
+
"delta_indices": [
|
| 634 |
+
0
|
| 635 |
+
],
|
| 636 |
+
"modality_keys": [
|
| 637 |
+
"image"
|
| 638 |
+
],
|
| 639 |
+
"sin_cos_embedding_keys": null,
|
| 640 |
+
"mean_std_embedding_keys": null,
|
| 641 |
+
"action_configs": null
|
| 642 |
+
},
|
| 643 |
+
"state": {
|
| 644 |
+
"delta_indices": [
|
| 645 |
+
0
|
| 646 |
+
],
|
| 647 |
+
"modality_keys": [
|
| 648 |
+
"x",
|
| 649 |
+
"y",
|
| 650 |
+
"z",
|
| 651 |
+
"rx",
|
| 652 |
+
"ry",
|
| 653 |
+
"rz",
|
| 654 |
+
"rw",
|
| 655 |
+
"gripper"
|
| 656 |
+
],
|
| 657 |
+
"sin_cos_embedding_keys": null,
|
| 658 |
+
"mean_std_embedding_keys": null,
|
| 659 |
+
"action_configs": null
|
| 660 |
+
},
|
| 661 |
+
"action": {
|
| 662 |
+
"delta_indices": [
|
| 663 |
+
0,
|
| 664 |
+
1,
|
| 665 |
+
2,
|
| 666 |
+
3,
|
| 667 |
+
4,
|
| 668 |
+
5,
|
| 669 |
+
6,
|
| 670 |
+
7
|
| 671 |
+
],
|
| 672 |
+
"modality_keys": [
|
| 673 |
+
"x",
|
| 674 |
+
"y",
|
| 675 |
+
"z",
|
| 676 |
+
"roll",
|
| 677 |
+
"pitch",
|
| 678 |
+
"yaw",
|
| 679 |
+
"gripper"
|
| 680 |
+
],
|
| 681 |
+
"sin_cos_embedding_keys": null,
|
| 682 |
+
"mean_std_embedding_keys": [
|
| 683 |
+
"x",
|
| 684 |
+
"y",
|
| 685 |
+
"z",
|
| 686 |
+
"roll",
|
| 687 |
+
"pitch",
|
| 688 |
+
"yaw"
|
| 689 |
+
],
|
| 690 |
+
"action_configs": null
|
| 691 |
+
},
|
| 692 |
+
"language": {
|
| 693 |
+
"delta_indices": [
|
| 694 |
+
0
|
| 695 |
+
],
|
| 696 |
+
"modality_keys": [
|
| 697 |
+
"annotation.human.action.task_description"
|
| 698 |
+
],
|
| 699 |
+
"sin_cos_embedding_keys": null,
|
| 700 |
+
"mean_std_embedding_keys": null,
|
| 701 |
+
"action_configs": null
|
| 702 |
+
}
|
| 703 |
+
},
|
| 704 |
+
"oxe_droid": {
|
| 705 |
+
"video": {
|
| 706 |
+
"delta_indices": [
|
| 707 |
+
0
|
| 708 |
+
],
|
| 709 |
+
"modality_keys": [
|
| 710 |
+
"exterior_image_1_left",
|
| 711 |
+
"wrist_image_left"
|
| 712 |
+
],
|
| 713 |
+
"sin_cos_embedding_keys": null,
|
| 714 |
+
"mean_std_embedding_keys": null,
|
| 715 |
+
"action_configs": null
|
| 716 |
+
},
|
| 717 |
+
"state": {
|
| 718 |
+
"delta_indices": [
|
| 719 |
+
0
|
| 720 |
+
],
|
| 721 |
+
"modality_keys": [
|
| 722 |
+
"joint_position",
|
| 723 |
+
"gripper_position"
|
| 724 |
+
],
|
| 725 |
+
"sin_cos_embedding_keys": null,
|
| 726 |
+
"mean_std_embedding_keys": null,
|
| 727 |
+
"action_configs": null
|
| 728 |
+
},
|
| 729 |
+
"action": {
|
| 730 |
+
"delta_indices": [
|
| 731 |
+
0,
|
| 732 |
+
1,
|
| 733 |
+
2,
|
| 734 |
+
3,
|
| 735 |
+
4,
|
| 736 |
+
5,
|
| 737 |
+
6,
|
| 738 |
+
7,
|
| 739 |
+
8,
|
| 740 |
+
9,
|
| 741 |
+
10,
|
| 742 |
+
11,
|
| 743 |
+
12,
|
| 744 |
+
13,
|
| 745 |
+
14,
|
| 746 |
+
15,
|
| 747 |
+
16,
|
| 748 |
+
17,
|
| 749 |
+
18,
|
| 750 |
+
19,
|
| 751 |
+
20,
|
| 752 |
+
21,
|
| 753 |
+
22,
|
| 754 |
+
23,
|
| 755 |
+
24,
|
| 756 |
+
25,
|
| 757 |
+
26,
|
| 758 |
+
27,
|
| 759 |
+
28,
|
| 760 |
+
29,
|
| 761 |
+
30,
|
| 762 |
+
31
|
| 763 |
+
],
|
| 764 |
+
"modality_keys": [
|
| 765 |
+
"joint_position",
|
| 766 |
+
"gripper_position"
|
| 767 |
+
],
|
| 768 |
+
"sin_cos_embedding_keys": null,
|
| 769 |
+
"mean_std_embedding_keys": null,
|
| 770 |
+
"action_configs": [
|
| 771 |
+
{
|
| 772 |
+
"rep": "RELATIVE",
|
| 773 |
+
"type": "NON_EEF",
|
| 774 |
+
"format": "DEFAULT",
|
| 775 |
+
"state_key": null
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"rep": "ABSOLUTE",
|
| 779 |
+
"type": "NON_EEF",
|
| 780 |
+
"format": "DEFAULT",
|
| 781 |
+
"state_key": null
|
| 782 |
+
}
|
| 783 |
+
]
|
| 784 |
+
},
|
| 785 |
+
"language": {
|
| 786 |
+
"delta_indices": [
|
| 787 |
+
0
|
| 788 |
+
],
|
| 789 |
+
"modality_keys": [
|
| 790 |
+
"annotation.language.language_instruction"
|
| 791 |
+
],
|
| 792 |
+
"sin_cos_embedding_keys": null,
|
| 793 |
+
"mean_std_embedding_keys": null,
|
| 794 |
+
"action_configs": null
|
| 795 |
+
}
|
| 796 |
+
},
|
| 797 |
+
"new_embodiment": {
|
| 798 |
+
"video": {
|
| 799 |
+
"delta_indices": [
|
| 800 |
+
0
|
| 801 |
+
],
|
| 802 |
+
"modality_keys": [
|
| 803 |
+
"robot0_eye_in_hand",
|
| 804 |
+
"robot0_agentview_left",
|
| 805 |
+
"robot0_agentview_right"
|
| 806 |
+
],
|
| 807 |
+
"sin_cos_embedding_keys": null,
|
| 808 |
+
"mean_std_embedding_keys": null,
|
| 809 |
+
"action_configs": null
|
| 810 |
+
},
|
| 811 |
+
"state": {
|
| 812 |
+
"delta_indices": [
|
| 813 |
+
0
|
| 814 |
+
],
|
| 815 |
+
"modality_keys": [
|
| 816 |
+
"base_position",
|
| 817 |
+
"base_rotation",
|
| 818 |
+
"end_effector_position_relative",
|
| 819 |
+
"end_effector_rotation_relative",
|
| 820 |
+
"gripper_qpos"
|
| 821 |
+
],
|
| 822 |
+
"sin_cos_embedding_keys": null,
|
| 823 |
+
"mean_std_embedding_keys": null,
|
| 824 |
+
"action_configs": null
|
| 825 |
+
},
|
| 826 |
+
"action": {
|
| 827 |
+
"delta_indices": [
|
| 828 |
+
0,
|
| 829 |
+
1,
|
| 830 |
+
2,
|
| 831 |
+
3,
|
| 832 |
+
4,
|
| 833 |
+
5,
|
| 834 |
+
6,
|
| 835 |
+
7,
|
| 836 |
+
8,
|
| 837 |
+
9,
|
| 838 |
+
10,
|
| 839 |
+
11,
|
| 840 |
+
12,
|
| 841 |
+
13,
|
| 842 |
+
14,
|
| 843 |
+
15
|
| 844 |
+
],
|
| 845 |
+
"modality_keys": [
|
| 846 |
+
"base_motion",
|
| 847 |
+
"control_mode",
|
| 848 |
+
"end_effector_position",
|
| 849 |
+
"end_effector_rotation",
|
| 850 |
+
"gripper_close"
|
| 851 |
+
],
|
| 852 |
+
"sin_cos_embedding_keys": null,
|
| 853 |
+
"mean_std_embedding_keys": null,
|
| 854 |
+
"action_configs": [
|
| 855 |
+
{
|
| 856 |
+
"rep": "ABSOLUTE",
|
| 857 |
+
"type": "NON_EEF",
|
| 858 |
+
"format": "DEFAULT",
|
| 859 |
+
"state_key": null
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"rep": "ABSOLUTE",
|
| 863 |
+
"type": "NON_EEF",
|
| 864 |
+
"format": "DEFAULT",
|
| 865 |
+
"state_key": null
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"rep": "ABSOLUTE",
|
| 869 |
+
"type": "EEF",
|
| 870 |
+
"format": "DEFAULT",
|
| 871 |
+
"state_key": null
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"rep": "ABSOLUTE",
|
| 875 |
+
"type": "EEF",
|
| 876 |
+
"format": "DEFAULT",
|
| 877 |
+
"state_key": null
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"rep": "ABSOLUTE",
|
| 881 |
+
"type": "NON_EEF",
|
| 882 |
+
"format": "DEFAULT",
|
| 883 |
+
"state_key": null
|
| 884 |
+
}
|
| 885 |
+
]
|
| 886 |
+
},
|
| 887 |
+
"language": {
|
| 888 |
+
"delta_indices": [
|
| 889 |
+
0
|
| 890 |
+
],
|
| 891 |
+
"modality_keys": [
|
| 892 |
+
"task"
|
| 893 |
+
],
|
| 894 |
+
"sin_cos_embedding_keys": null,
|
| 895 |
+
"mean_std_embedding_keys": null,
|
| 896 |
+
"action_configs": null
|
| 897 |
+
}
|
| 898 |
+
}
|
| 899 |
+
},
|
| 900 |
+
"image_crop_size": null,
|
| 901 |
+
"image_target_size": null,
|
| 902 |
+
"use_albumentations": true,
|
| 903 |
+
"random_rotation_angle": null,
|
| 904 |
+
"color_jitter_params": {
|
| 905 |
+
"brightness": 0.3,
|
| 906 |
+
"contrast": 0.4,
|
| 907 |
+
"saturation": 0.5,
|
| 908 |
+
"hue": 0.08
|
| 909 |
+
},
|
| 910 |
+
"shortest_image_edge": 256,
|
| 911 |
+
"crop_fraction": 0.95,
|
| 912 |
+
"model_name": "nvidia/Eagle-Block2A-2B-v2",
|
| 913 |
+
"model_type": "eagle",
|
| 914 |
+
"formalize_language": true,
|
| 915 |
+
"max_state_dim": 128,
|
| 916 |
+
"max_action_dim": 128,
|
| 917 |
+
"max_action_horizon": 50,
|
| 918 |
+
"use_percentiles": false,
|
| 919 |
+
"clip_outliers": true,
|
| 920 |
+
"apply_sincos_state_encoding": true,
|
| 921 |
+
"use_relative_action": true
|
| 922 |
+
}
|
| 923 |
+
}
|
checkpoint-60000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35dbe0a1e05f4377fe7af200bb237f2fd4fcf1f626c3ada67619a4ed5118fc5e
|
| 3 |
+
size 14917
|
checkpoint-60000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80cdf2673e0d1e3845df5fc505dd94474498607a324d4d97974e55d06548c193
|
| 3 |
+
size 14917
|
checkpoint-60000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c55544f98d67f24204a10b671ebe610ad828fbb0acca03282f9d33f0f6640e8e
|
| 3 |
+
size 1465
|
checkpoint-60000/statistics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-60000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-60000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2763d70cd1de320f4d0515e426de65befdc4afd41cd3575f080430938bc410b
|
| 3 |
+
size 7633
|
checkpoint-60000/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info("Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info("Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"action_horizon": 50,
|
| 3 |
+
"add_pos_embed": true,
|
| 4 |
+
"apply_sincos_state_encoding": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Gr00tN1d6"
|
| 7 |
+
],
|
| 8 |
+
"attn_dropout": 0.2,
|
| 9 |
+
"attn_implementation": null,
|
| 10 |
+
"backbone_embedding_dim": 2048,
|
| 11 |
+
"backbone_model_type": "eagle",
|
| 12 |
+
"backbone_trainable_params_fp32": true,
|
| 13 |
+
"collator_overwrite_image_inputs": false,
|
| 14 |
+
"color_jitter_params": {
|
| 15 |
+
"brightness": 0.1,
|
| 16 |
+
"contrast": 0.1,
|
| 17 |
+
"hue": 0.1,
|
| 18 |
+
"saturation": 0.1
|
| 19 |
+
},
|
| 20 |
+
"crop_fraction": 0.95,
|
| 21 |
+
"diffusion_model_cfg": {
|
| 22 |
+
"attention_head_dim": 48,
|
| 23 |
+
"dropout": 0.2,
|
| 24 |
+
"final_dropout": true,
|
| 25 |
+
"interleave_self_attention": true,
|
| 26 |
+
"norm_type": "ada_norm",
|
| 27 |
+
"num_attention_heads": 32,
|
| 28 |
+
"num_layers": 32,
|
| 29 |
+
"output_dim": 1024,
|
| 30 |
+
"positional_embeddings": null
|
| 31 |
+
},
|
| 32 |
+
"eagle_collator": true,
|
| 33 |
+
"formalize_language": true,
|
| 34 |
+
"gemma_collator": false,
|
| 35 |
+
"hidden_size": 1024,
|
| 36 |
+
"image_crop_size": null,
|
| 37 |
+
"image_target_size": null,
|
| 38 |
+
"input_embedding_dim": 1536,
|
| 39 |
+
"load_bf16": true,
|
| 40 |
+
"max_action_dim": 128,
|
| 41 |
+
"max_num_embodiments": 32,
|
| 42 |
+
"max_seq_len": 1024,
|
| 43 |
+
"max_state_dim": 128,
|
| 44 |
+
"model_dtype": "bfloat16",
|
| 45 |
+
"model_name": "nvidia/Eagle-Block2A-2B-v2",
|
| 46 |
+
"model_type": "Gr00tN1d6",
|
| 47 |
+
"noise_beta_alpha": 1.5,
|
| 48 |
+
"noise_beta_beta": 1.0,
|
| 49 |
+
"noise_s": 0.999,
|
| 50 |
+
"num_inference_timesteps": 4,
|
| 51 |
+
"num_timestep_buckets": 1000,
|
| 52 |
+
"random_rotation_angle": null,
|
| 53 |
+
"reproject_vision": false,
|
| 54 |
+
"select_layer": 16,
|
| 55 |
+
"shortest_image_edge": 256,
|
| 56 |
+
"state_dropout_prob": 0.0,
|
| 57 |
+
"torch_dtype": "bfloat16",
|
| 58 |
+
"transformers_version": "4.51.3",
|
| 59 |
+
"tune_diffusion_model": true,
|
| 60 |
+
"tune_llm": false,
|
| 61 |
+
"tune_projector": true,
|
| 62 |
+
"tune_top_llm_layers": 4,
|
| 63 |
+
"tune_visual": false,
|
| 64 |
+
"tune_vlln": true,
|
| 65 |
+
"use_albumentations_transforms": true,
|
| 66 |
+
"use_alternate_vl_dit": true,
|
| 67 |
+
"use_flash_attention": true,
|
| 68 |
+
"use_relative_action": true,
|
| 69 |
+
"use_vlln": true
|
| 70 |
+
}
|
experiment_cfg/dataset_statistics.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"new_embodiment": {
|
| 3 |
+
"state": {
|
| 4 |
+
"base_position": {
|
| 5 |
+
"min": [
|
| 6 |
+
-4.94293737411499,
|
| 7 |
+
-6.890198230743408,
|
| 8 |
+
0.6994727253913879
|
| 9 |
+
],
|
| 10 |
+
"max": [
|
| 11 |
+
7.778976917266846,
|
| 12 |
+
0.4876587688922882,
|
| 13 |
+
0.7223060727119446
|
| 14 |
+
],
|
| 15 |
+
"mean": [
|
| 16 |
+
2.6429230985097116,
|
| 17 |
+
-2.1040500635873367,
|
| 18 |
+
0.7003864151980145
|
| 19 |
+
],
|
| 20 |
+
"std": [
|
| 21 |
+
1.6723189550183524,
|
| 22 |
+
1.340646864108621,
|
| 23 |
+
0.0010989839745322908
|
| 24 |
+
],
|
| 25 |
+
"q01": [
|
| 26 |
+
-4.570116996765137,
|
| 27 |
+
-6.843641757965088,
|
| 28 |
+
0.699881374835968
|
| 29 |
+
],
|
| 30 |
+
"q99": [
|
| 31 |
+
7.292758464813232,
|
| 32 |
+
0.48759591579437256,
|
| 33 |
+
0.714806854724884
|
| 34 |
+
]
|
| 35 |
+
},
|
| 36 |
+
"base_rotation": {
|
| 37 |
+
"min": [
|
| 38 |
+
0.0,
|
| 39 |
+
0.0,
|
| 40 |
+
-1.0,
|
| 41 |
+
0.0
|
| 42 |
+
],
|
| 43 |
+
"max": [
|
| 44 |
+
0.0,
|
| 45 |
+
0.0,
|
| 46 |
+
1.0,
|
| 47 |
+
1.0
|
| 48 |
+
],
|
| 49 |
+
"mean": [
|
| 50 |
+
0.0,
|
| 51 |
+
0.0,
|
| 52 |
+
0.23872401952057823,
|
| 53 |
+
0.6083901817614287
|
| 54 |
+
],
|
| 55 |
+
"std": [
|
| 56 |
+
0.0,
|
| 57 |
+
0.0,
|
| 58 |
+
0.6620197581758033,
|
| 59 |
+
0.3668243207825513
|
| 60 |
+
],
|
| 61 |
+
"q01": [
|
| 62 |
+
0.0,
|
| 63 |
+
0.0,
|
| 64 |
+
-1.0,
|
| 65 |
+
1.9421531760599464e-07
|
| 66 |
+
],
|
| 67 |
+
"q99": [
|
| 68 |
+
0.0,
|
| 69 |
+
0.0,
|
| 70 |
+
1.0,
|
| 71 |
+
1.0
|
| 72 |
+
]
|
| 73 |
+
},
|
| 74 |
+
"end_effector_position_relative": {
|
| 75 |
+
"min": [
|
| 76 |
+
-0.5828549861907959,
|
| 77 |
+
-0.8486236333847046,
|
| 78 |
+
-0.3446122705936432
|
| 79 |
+
],
|
| 80 |
+
"max": [
|
| 81 |
+
0.9014528393745422,
|
| 82 |
+
0.8569459915161133,
|
| 83 |
+
1.053884744644165
|
| 84 |
+
],
|
| 85 |
+
"mean": [
|
| 86 |
+
0.25786905106953806,
|
| 87 |
+
-0.018494133083245046,
|
| 88 |
+
0.44849795111686513
|
| 89 |
+
],
|
| 90 |
+
"std": [
|
| 91 |
+
0.16495694636764374,
|
| 92 |
+
0.24473163300325904,
|
| 93 |
+
0.20998219654794578
|
| 94 |
+
],
|
| 95 |
+
"q01": [
|
| 96 |
+
-0.3761294186115265,
|
| 97 |
+
-0.721174955368042,
|
| 98 |
+
-0.23106376826763153
|
| 99 |
+
],
|
| 100 |
+
"q99": [
|
| 101 |
+
0.8378565311431885,
|
| 102 |
+
0.7546205520629883,
|
| 103 |
+
0.9249030947685242
|
| 104 |
+
]
|
| 105 |
+
},
|
| 106 |
+
"end_effector_rotation_relative": {
|
| 107 |
+
"min": [
|
| 108 |
+
-0.9999930262565613,
|
| 109 |
+
-0.9999884366989136,
|
| 110 |
+
-0.9975369572639465,
|
| 111 |
+
6.754255821306288e-08
|
| 112 |
+
],
|
| 113 |
+
"max": [
|
| 114 |
+
0.9999998807907104,
|
| 115 |
+
0.9997354745864868,
|
| 116 |
+
0.9900747537612915,
|
| 117 |
+
0.9735639095306396
|
| 118 |
+
],
|
| 119 |
+
"mean": [
|
| 120 |
+
-0.261215793438568,
|
| 121 |
+
0.03690521291069262,
|
| 122 |
+
-0.07182086071331255,
|
| 123 |
+
0.13733310115690522
|
| 124 |
+
],
|
| 125 |
+
"std": [
|
| 126 |
+
0.8253314117717035,
|
| 127 |
+
0.297636866306729,
|
| 128 |
+
0.32923964375209464,
|
| 129 |
+
0.16800963654479095
|
| 130 |
+
],
|
| 131 |
+
"q01": [
|
| 132 |
+
-0.9995729327201843,
|
| 133 |
+
-0.9585485458374023,
|
| 134 |
+
-0.8866488337516785,
|
| 135 |
+
0.0003100793983321637
|
| 136 |
+
],
|
| 137 |
+
"q99": [
|
| 138 |
+
0.9993855357170105,
|
| 139 |
+
0.9750741720199585,
|
| 140 |
+
0.8878775835037231,
|
| 141 |
+
0.8871033191680908
|
| 142 |
+
]
|
| 143 |
+
},
|
| 144 |
+
"gripper_qpos": {
|
| 145 |
+
"min": [
|
| 146 |
+
-0.011669117026031017,
|
| 147 |
+
-0.06307756155729294
|
| 148 |
+
],
|
| 149 |
+
"max": [
|
| 150 |
+
0.055869169533252716,
|
| 151 |
+
0.010916369967162609
|
| 152 |
+
],
|
| 153 |
+
"mean": [
|
| 154 |
+
0.03205486276150664,
|
| 155 |
+
-0.03223369335466349
|
| 156 |
+
],
|
| 157 |
+
"std": [
|
| 158 |
+
0.012312154775568325,
|
| 159 |
+
0.012107891953724964
|
| 160 |
+
],
|
| 161 |
+
"q01": [
|
| 162 |
+
-0.0028626956045627594,
|
| 163 |
+
-0.04449209198355675
|
| 164 |
+
],
|
| 165 |
+
"q99": [
|
| 166 |
+
0.04488873854279518,
|
| 167 |
+
0.0015663582598790526
|
| 168 |
+
]
|
| 169 |
+
}
|
| 170 |
+
},
|
| 171 |
+
"action": {
|
| 172 |
+
"base_motion": {
|
| 173 |
+
"min": [
|
| 174 |
+
-1.0,
|
| 175 |
+
-1.0,
|
| 176 |
+
-1.0,
|
| 177 |
+
0.0
|
| 178 |
+
],
|
| 179 |
+
"max": [
|
| 180 |
+
1.0,
|
| 181 |
+
1.0,
|
| 182 |
+
1.0,
|
| 183 |
+
0.0
|
| 184 |
+
],
|
| 185 |
+
"mean": [
|
| 186 |
+
0.02050641685926724,
|
| 187 |
+
0.001128088574318351,
|
| 188 |
+
-0.002216507356311039,
|
| 189 |
+
0.0
|
| 190 |
+
],
|
| 191 |
+
"std": [
|
| 192 |
+
0.1652318199594288,
|
| 193 |
+
0.14088974424972592,
|
| 194 |
+
0.1268873250272064,
|
| 195 |
+
0.0
|
| 196 |
+
],
|
| 197 |
+
"q01": [
|
| 198 |
+
-1.0,
|
| 199 |
+
-1.0,
|
| 200 |
+
-1.0,
|
| 201 |
+
0.0
|
| 202 |
+
],
|
| 203 |
+
"q99": [
|
| 204 |
+
1.0,
|
| 205 |
+
1.0,
|
| 206 |
+
1.0,
|
| 207 |
+
0.0
|
| 208 |
+
]
|
| 209 |
+
},
|
| 210 |
+
"control_mode": {
|
| 211 |
+
"min": [
|
| 212 |
+
-1.0
|
| 213 |
+
],
|
| 214 |
+
"max": [
|
| 215 |
+
1.0
|
| 216 |
+
],
|
| 217 |
+
"mean": [
|
| 218 |
+
-0.8539844503292455
|
| 219 |
+
],
|
| 220 |
+
"std": [
|
| 221 |
+
0.5202972484299755
|
| 222 |
+
],
|
| 223 |
+
"q01": [
|
| 224 |
+
-1.0
|
| 225 |
+
],
|
| 226 |
+
"q99": [
|
| 227 |
+
1.0
|
| 228 |
+
]
|
| 229 |
+
},
|
| 230 |
+
"end_effector_position": {
|
| 231 |
+
"min": [
|
| 232 |
+
-1.0,
|
| 233 |
+
-1.0,
|
| 234 |
+
-1.0
|
| 235 |
+
],
|
| 236 |
+
"max": [
|
| 237 |
+
1.0,
|
| 238 |
+
1.0,
|
| 239 |
+
1.0
|
| 240 |
+
],
|
| 241 |
+
"mean": [
|
| 242 |
+
0.002803475656952085,
|
| 243 |
+
-0.006818774988739351,
|
| 244 |
+
-0.07855993148808858
|
| 245 |
+
],
|
| 246 |
+
"std": [
|
| 247 |
+
0.44313822308380246,
|
| 248 |
+
0.40503200192475836,
|
| 249 |
+
0.3950365918181045
|
| 250 |
+
],
|
| 251 |
+
"q01": [
|
| 252 |
+
-1.0,
|
| 253 |
+
-1.0,
|
| 254 |
+
-1.0
|
| 255 |
+
],
|
| 256 |
+
"q99": [
|
| 257 |
+
1.0,
|
| 258 |
+
1.0,
|
| 259 |
+
1.0
|
| 260 |
+
]
|
| 261 |
+
},
|
| 262 |
+
"end_effector_rotation": {
|
| 263 |
+
"min": [
|
| 264 |
+
-1.0,
|
| 265 |
+
-1.0,
|
| 266 |
+
-1.0
|
| 267 |
+
],
|
| 268 |
+
"max": [
|
| 269 |
+
1.0,
|
| 270 |
+
1.0,
|
| 271 |
+
1.0
|
| 272 |
+
],
|
| 273 |
+
"mean": [
|
| 274 |
+
0.0075743831831496635,
|
| 275 |
+
-0.022864397394476266,
|
| 276 |
+
-0.0001568091574277115
|
| 277 |
+
],
|
| 278 |
+
"std": [
|
| 279 |
+
0.1104170002966275,
|
| 280 |
+
0.1306405108880139,
|
| 281 |
+
0.12282959716644956
|
| 282 |
+
],
|
| 283 |
+
"q01": [
|
| 284 |
+
-0.6857143044471741,
|
| 285 |
+
-0.9028571248054504,
|
| 286 |
+
-1.0
|
| 287 |
+
],
|
| 288 |
+
"q99": [
|
| 289 |
+
0.9028571248054504,
|
| 290 |
+
0.8342857360839844,
|
| 291 |
+
0.8718582391738892
|
| 292 |
+
]
|
| 293 |
+
},
|
| 294 |
+
"gripper_close": {
|
| 295 |
+
"min": [
|
| 296 |
+
-1.0
|
| 297 |
+
],
|
| 298 |
+
"max": [
|
| 299 |
+
1.0
|
| 300 |
+
],
|
| 301 |
+
"mean": [
|
| 302 |
+
-0.37004847633194815
|
| 303 |
+
],
|
| 304 |
+
"std": [
|
| 305 |
+
0.9290190132822349
|
| 306 |
+
],
|
| 307 |
+
"q01": [
|
| 308 |
+
-1.0
|
| 309 |
+
],
|
| 310 |
+
"q99": [
|
| 311 |
+
1.0
|
| 312 |
+
]
|
| 313 |
+
}
|
| 314 |
+
},
|
| 315 |
+
"relative_action": {}
|
| 316 |
+
}
|
| 317 |
+
}
|
experiment_cfg/final_model_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "Gr00tN1d6",
|
| 3 |
+
"model_dtype": "bfloat16",
|
| 4 |
+
"model_name": "nvidia/Eagle-Block2A-2B-v2",
|
| 5 |
+
"backbone_model_type": "eagle",
|
| 6 |
+
"model_revision": null,
|
| 7 |
+
"tune_top_llm_layers": 4,
|
| 8 |
+
"backbone_embedding_dim": 2048,
|
| 9 |
+
"tune_llm": false,
|
| 10 |
+
"tune_visual": false,
|
| 11 |
+
"select_layer": 16,
|
| 12 |
+
"reproject_vision": false,
|
| 13 |
+
"use_flash_attention": true,
|
| 14 |
+
"load_bf16": true,
|
| 15 |
+
"collator_overwrite_image_inputs": false,
|
| 16 |
+
"eagle_collator": true,
|
| 17 |
+
"backbone_trainable_params_fp32": true,
|
| 18 |
+
"apply_sincos_state_encoding": true,
|
| 19 |
+
"use_relative_action": true,
|
| 20 |
+
"max_state_dim": 128,
|
| 21 |
+
"max_action_dim": 128,
|
| 22 |
+
"action_horizon": 50,
|
| 23 |
+
"hidden_size": 1024,
|
| 24 |
+
"input_embedding_dim": 1536,
|
| 25 |
+
"add_pos_embed": true,
|
| 26 |
+
"attn_dropout": 0.2,
|
| 27 |
+
"use_vlln": true,
|
| 28 |
+
"max_seq_len": 1024,
|
| 29 |
+
"use_alternate_vl_dit": true,
|
| 30 |
+
"attend_text_every_n_blocks": 2,
|
| 31 |
+
"diffusion_model_cfg": {
|
| 32 |
+
"attention_head_dim": 48,
|
| 33 |
+
"dropout": 0.2,
|
| 34 |
+
"final_dropout": true,
|
| 35 |
+
"interleave_self_attention": true,
|
| 36 |
+
"norm_type": "ada_norm",
|
| 37 |
+
"num_attention_heads": 32,
|
| 38 |
+
"num_layers": 32,
|
| 39 |
+
"output_dim": 1024,
|
| 40 |
+
"positional_embeddings": null
|
| 41 |
+
},
|
| 42 |
+
"num_inference_timesteps": 4,
|
| 43 |
+
"noise_beta_alpha": 1.5,
|
| 44 |
+
"noise_beta_beta": 1.0,
|
| 45 |
+
"noise_s": 0.999,
|
| 46 |
+
"num_timestep_buckets": 1000,
|
| 47 |
+
"tune_projector": true,
|
| 48 |
+
"tune_diffusion_model": true,
|
| 49 |
+
"tune_vlln": true,
|
| 50 |
+
"state_dropout_prob": 0.0,
|
| 51 |
+
"state_additive_noise_scale": 0.0,
|
| 52 |
+
"max_num_embodiments": 32
|
| 53 |
+
}
|
experiment_cfg/final_processor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fd3f824fb806d8bcd6c308b99c9fb3bc02ab201cf161343b452a60beb361255
|
| 3 |
+
size 4991091456
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bb5cc1c97053e21fded718b9138232709488ac911d0116d4c346f299662ba3b
|
| 3 |
+
size 1582283096
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor/embodiment_id.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"robocasa_panda_omron": 13,
|
| 3 |
+
"gr1": 20,
|
| 4 |
+
"behavior_r1_pro": 24,
|
| 5 |
+
"unitree_g1": 8,
|
| 6 |
+
"oxe_google": 0,
|
| 7 |
+
"oxe_widowx": 1,
|
| 8 |
+
"libero_panda": 2,
|
| 9 |
+
"oxe_droid": 16,
|
| 10 |
+
"new_embodiment": 10
|
| 11 |
+
}
|
processor/processor_config.json
ADDED
|
@@ -0,0 +1,923 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"processor_class": "Gr00tN1d6Processor",
|
| 3 |
+
"processor_kwargs": {
|
| 4 |
+
"modality_configs": {
|
| 5 |
+
"behavior_r1_pro": {
|
| 6 |
+
"video": {
|
| 7 |
+
"delta_indices": [
|
| 8 |
+
0
|
| 9 |
+
],
|
| 10 |
+
"modality_keys": [
|
| 11 |
+
"observation.images.rgb.head_256_256",
|
| 12 |
+
"observation.images.rgb.left_wrist_256_256",
|
| 13 |
+
"observation.images.rgb.right_wrist_256_256"
|
| 14 |
+
],
|
| 15 |
+
"sin_cos_embedding_keys": null,
|
| 16 |
+
"mean_std_embedding_keys": null,
|
| 17 |
+
"action_configs": null
|
| 18 |
+
},
|
| 19 |
+
"state": {
|
| 20 |
+
"delta_indices": [
|
| 21 |
+
0
|
| 22 |
+
],
|
| 23 |
+
"modality_keys": [
|
| 24 |
+
"robot_pos",
|
| 25 |
+
"robot_ori_cos",
|
| 26 |
+
"robot_ori_sin",
|
| 27 |
+
"robot_2d_ori",
|
| 28 |
+
"robot_2d_ori_cos",
|
| 29 |
+
"robot_2d_ori_sin",
|
| 30 |
+
"robot_lin_vel",
|
| 31 |
+
"robot_ang_vel",
|
| 32 |
+
"arm_left_qpos",
|
| 33 |
+
"arm_left_qpos_sin",
|
| 34 |
+
"arm_left_qpos_cos",
|
| 35 |
+
"eef_left_pos",
|
| 36 |
+
"eef_left_quat",
|
| 37 |
+
"gripper_left_qpos",
|
| 38 |
+
"arm_right_qpos",
|
| 39 |
+
"arm_right_qpos_sin",
|
| 40 |
+
"arm_right_qpos_cos",
|
| 41 |
+
"eef_right_pos",
|
| 42 |
+
"eef_right_quat",
|
| 43 |
+
"gripper_right_qpos",
|
| 44 |
+
"trunk_qpos"
|
| 45 |
+
],
|
| 46 |
+
"sin_cos_embedding_keys": null,
|
| 47 |
+
"mean_std_embedding_keys": null,
|
| 48 |
+
"action_configs": null
|
| 49 |
+
},
|
| 50 |
+
"action": {
|
| 51 |
+
"delta_indices": [
|
| 52 |
+
0,
|
| 53 |
+
1,
|
| 54 |
+
2,
|
| 55 |
+
3,
|
| 56 |
+
4,
|
| 57 |
+
5,
|
| 58 |
+
6,
|
| 59 |
+
7,
|
| 60 |
+
8,
|
| 61 |
+
9,
|
| 62 |
+
10,
|
| 63 |
+
11,
|
| 64 |
+
12,
|
| 65 |
+
13,
|
| 66 |
+
14,
|
| 67 |
+
15,
|
| 68 |
+
16,
|
| 69 |
+
17,
|
| 70 |
+
18,
|
| 71 |
+
19,
|
| 72 |
+
20,
|
| 73 |
+
21,
|
| 74 |
+
22,
|
| 75 |
+
23,
|
| 76 |
+
24,
|
| 77 |
+
25,
|
| 78 |
+
26,
|
| 79 |
+
27,
|
| 80 |
+
28,
|
| 81 |
+
29,
|
| 82 |
+
30,
|
| 83 |
+
31
|
| 84 |
+
],
|
| 85 |
+
"modality_keys": [
|
| 86 |
+
"base",
|
| 87 |
+
"torso",
|
| 88 |
+
"left_arm",
|
| 89 |
+
"left_gripper",
|
| 90 |
+
"right_arm",
|
| 91 |
+
"right_gripper"
|
| 92 |
+
],
|
| 93 |
+
"sin_cos_embedding_keys": null,
|
| 94 |
+
"mean_std_embedding_keys": null,
|
| 95 |
+
"action_configs": [
|
| 96 |
+
{
|
| 97 |
+
"rep": "ABSOLUTE",
|
| 98 |
+
"type": "NON_EEF",
|
| 99 |
+
"format": "DEFAULT",
|
| 100 |
+
"state_key": null
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"rep": "RELATIVE",
|
| 104 |
+
"type": "NON_EEF",
|
| 105 |
+
"format": "DEFAULT",
|
| 106 |
+
"state_key": "trunk_qpos"
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"rep": "RELATIVE",
|
| 110 |
+
"type": "NON_EEF",
|
| 111 |
+
"format": "DEFAULT",
|
| 112 |
+
"state_key": "arm_left_qpos"
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"rep": "ABSOLUTE",
|
| 116 |
+
"type": "NON_EEF",
|
| 117 |
+
"format": "DEFAULT",
|
| 118 |
+
"state_key": null
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"rep": "RELATIVE",
|
| 122 |
+
"type": "NON_EEF",
|
| 123 |
+
"format": "DEFAULT",
|
| 124 |
+
"state_key": "arm_right_qpos"
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"rep": "ABSOLUTE",
|
| 128 |
+
"type": "NON_EEF",
|
| 129 |
+
"format": "DEFAULT",
|
| 130 |
+
"state_key": null
|
| 131 |
+
}
|
| 132 |
+
]
|
| 133 |
+
},
|
| 134 |
+
"language": {
|
| 135 |
+
"delta_indices": [
|
| 136 |
+
0
|
| 137 |
+
],
|
| 138 |
+
"modality_keys": [
|
| 139 |
+
"annotation.human.coarse_action"
|
| 140 |
+
],
|
| 141 |
+
"sin_cos_embedding_keys": null,
|
| 142 |
+
"mean_std_embedding_keys": null,
|
| 143 |
+
"action_configs": null
|
| 144 |
+
}
|
| 145 |
+
},
|
| 146 |
+
"gr1": {
|
| 147 |
+
"video": {
|
| 148 |
+
"delta_indices": [
|
| 149 |
+
0
|
| 150 |
+
],
|
| 151 |
+
"modality_keys": [
|
| 152 |
+
"ego_view_bg_crop_pad_res256_freq20"
|
| 153 |
+
],
|
| 154 |
+
"sin_cos_embedding_keys": null,
|
| 155 |
+
"mean_std_embedding_keys": null,
|
| 156 |
+
"action_configs": null
|
| 157 |
+
},
|
| 158 |
+
"state": {
|
| 159 |
+
"delta_indices": [
|
| 160 |
+
0
|
| 161 |
+
],
|
| 162 |
+
"modality_keys": [
|
| 163 |
+
"left_arm",
|
| 164 |
+
"right_arm",
|
| 165 |
+
"left_hand",
|
| 166 |
+
"right_hand",
|
| 167 |
+
"waist"
|
| 168 |
+
],
|
| 169 |
+
"sin_cos_embedding_keys": [
|
| 170 |
+
"left_arm",
|
| 171 |
+
"right_arm",
|
| 172 |
+
"left_hand",
|
| 173 |
+
"right_hand",
|
| 174 |
+
"waist"
|
| 175 |
+
],
|
| 176 |
+
"mean_std_embedding_keys": null,
|
| 177 |
+
"action_configs": null
|
| 178 |
+
},
|
| 179 |
+
"action": {
|
| 180 |
+
"delta_indices": [
|
| 181 |
+
0,
|
| 182 |
+
1,
|
| 183 |
+
2,
|
| 184 |
+
3,
|
| 185 |
+
4,
|
| 186 |
+
5,
|
| 187 |
+
6,
|
| 188 |
+
7,
|
| 189 |
+
8,
|
| 190 |
+
9,
|
| 191 |
+
10,
|
| 192 |
+
11,
|
| 193 |
+
12,
|
| 194 |
+
13,
|
| 195 |
+
14,
|
| 196 |
+
15
|
| 197 |
+
],
|
| 198 |
+
"modality_keys": [
|
| 199 |
+
"left_arm",
|
| 200 |
+
"right_arm",
|
| 201 |
+
"left_hand",
|
| 202 |
+
"right_hand",
|
| 203 |
+
"waist"
|
| 204 |
+
],
|
| 205 |
+
"sin_cos_embedding_keys": null,
|
| 206 |
+
"mean_std_embedding_keys": null,
|
| 207 |
+
"action_configs": [
|
| 208 |
+
{
|
| 209 |
+
"rep": "RELATIVE",
|
| 210 |
+
"type": "NON_EEF",
|
| 211 |
+
"format": "DEFAULT",
|
| 212 |
+
"state_key": null
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"rep": "RELATIVE",
|
| 216 |
+
"type": "NON_EEF",
|
| 217 |
+
"format": "DEFAULT",
|
| 218 |
+
"state_key": null
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"rep": "RELATIVE",
|
| 222 |
+
"type": "NON_EEF",
|
| 223 |
+
"format": "DEFAULT",
|
| 224 |
+
"state_key": null
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"rep": "RELATIVE",
|
| 228 |
+
"type": "NON_EEF",
|
| 229 |
+
"format": "DEFAULT",
|
| 230 |
+
"state_key": null
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"rep": "ABSOLUTE",
|
| 234 |
+
"type": "NON_EEF",
|
| 235 |
+
"format": "DEFAULT",
|
| 236 |
+
"state_key": null
|
| 237 |
+
}
|
| 238 |
+
]
|
| 239 |
+
},
|
| 240 |
+
"language": {
|
| 241 |
+
"delta_indices": [
|
| 242 |
+
0
|
| 243 |
+
],
|
| 244 |
+
"modality_keys": [
|
| 245 |
+
"task"
|
| 246 |
+
],
|
| 247 |
+
"sin_cos_embedding_keys": null,
|
| 248 |
+
"mean_std_embedding_keys": null,
|
| 249 |
+
"action_configs": null
|
| 250 |
+
}
|
| 251 |
+
},
|
| 252 |
+
"robocasa_panda_omron": {
|
| 253 |
+
"video": {
|
| 254 |
+
"delta_indices": [
|
| 255 |
+
0
|
| 256 |
+
],
|
| 257 |
+
"modality_keys": [
|
| 258 |
+
"robot0_eye_in_hand",
|
| 259 |
+
"robot0_agentview_left",
|
| 260 |
+
"robot0_agentview_right"
|
| 261 |
+
],
|
| 262 |
+
"sin_cos_embedding_keys": null,
|
| 263 |
+
"mean_std_embedding_keys": null,
|
| 264 |
+
"action_configs": null
|
| 265 |
+
},
|
| 266 |
+
"state": {
|
| 267 |
+
"delta_indices": [
|
| 268 |
+
0
|
| 269 |
+
],
|
| 270 |
+
"modality_keys": [
|
| 271 |
+
"base_position",
|
| 272 |
+
"base_rotation",
|
| 273 |
+
"end_effector_position_relative",
|
| 274 |
+
"end_effector_rotation_relative",
|
| 275 |
+
"gripper_qpos"
|
| 276 |
+
],
|
| 277 |
+
"sin_cos_embedding_keys": null,
|
| 278 |
+
"mean_std_embedding_keys": null,
|
| 279 |
+
"action_configs": null
|
| 280 |
+
},
|
| 281 |
+
"action": {
|
| 282 |
+
"delta_indices": [
|
| 283 |
+
0,
|
| 284 |
+
1,
|
| 285 |
+
2,
|
| 286 |
+
3,
|
| 287 |
+
4,
|
| 288 |
+
5,
|
| 289 |
+
6,
|
| 290 |
+
7,
|
| 291 |
+
8,
|
| 292 |
+
9,
|
| 293 |
+
10,
|
| 294 |
+
11,
|
| 295 |
+
12,
|
| 296 |
+
13,
|
| 297 |
+
14,
|
| 298 |
+
15
|
| 299 |
+
],
|
| 300 |
+
"modality_keys": [
|
| 301 |
+
"base_motion",
|
| 302 |
+
"control_mode",
|
| 303 |
+
"end_effector_position",
|
| 304 |
+
"end_effector_rotation",
|
| 305 |
+
"gripper_close"
|
| 306 |
+
],
|
| 307 |
+
"sin_cos_embedding_keys": null,
|
| 308 |
+
"mean_std_embedding_keys": null,
|
| 309 |
+
"action_configs": [
|
| 310 |
+
{
|
| 311 |
+
"rep": "ABSOLUTE",
|
| 312 |
+
"type": "NON_EEF",
|
| 313 |
+
"format": "DEFAULT",
|
| 314 |
+
"state_key": null
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"rep": "ABSOLUTE",
|
| 318 |
+
"type": "NON_EEF",
|
| 319 |
+
"format": "DEFAULT",
|
| 320 |
+
"state_key": null
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"rep": "ABSOLUTE",
|
| 324 |
+
"type": "EEF",
|
| 325 |
+
"format": "DEFAULT",
|
| 326 |
+
"state_key": null
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"rep": "ABSOLUTE",
|
| 330 |
+
"type": "EEF",
|
| 331 |
+
"format": "DEFAULT",
|
| 332 |
+
"state_key": null
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"rep": "ABSOLUTE",
|
| 336 |
+
"type": "NON_EEF",
|
| 337 |
+
"format": "DEFAULT",
|
| 338 |
+
"state_key": null
|
| 339 |
+
}
|
| 340 |
+
]
|
| 341 |
+
},
|
| 342 |
+
"language": {
|
| 343 |
+
"delta_indices": [
|
| 344 |
+
0
|
| 345 |
+
],
|
| 346 |
+
"modality_keys": [
|
| 347 |
+
"task"
|
| 348 |
+
],
|
| 349 |
+
"sin_cos_embedding_keys": null,
|
| 350 |
+
"mean_std_embedding_keys": null,
|
| 351 |
+
"action_configs": null
|
| 352 |
+
}
|
| 353 |
+
},
|
| 354 |
+
"unitree_g1": {
|
| 355 |
+
"video": {
|
| 356 |
+
"delta_indices": [
|
| 357 |
+
0
|
| 358 |
+
],
|
| 359 |
+
"modality_keys": [
|
| 360 |
+
"ego_view"
|
| 361 |
+
],
|
| 362 |
+
"sin_cos_embedding_keys": null,
|
| 363 |
+
"mean_std_embedding_keys": null,
|
| 364 |
+
"action_configs": null
|
| 365 |
+
},
|
| 366 |
+
"state": {
|
| 367 |
+
"delta_indices": [
|
| 368 |
+
0
|
| 369 |
+
],
|
| 370 |
+
"modality_keys": [
|
| 371 |
+
"left_leg",
|
| 372 |
+
"right_leg",
|
| 373 |
+
"waist",
|
| 374 |
+
"left_arm",
|
| 375 |
+
"right_arm",
|
| 376 |
+
"left_hand",
|
| 377 |
+
"right_hand"
|
| 378 |
+
],
|
| 379 |
+
"sin_cos_embedding_keys": null,
|
| 380 |
+
"mean_std_embedding_keys": null,
|
| 381 |
+
"action_configs": null
|
| 382 |
+
},
|
| 383 |
+
"action": {
|
| 384 |
+
"delta_indices": [
|
| 385 |
+
0,
|
| 386 |
+
1,
|
| 387 |
+
2,
|
| 388 |
+
3,
|
| 389 |
+
4,
|
| 390 |
+
5,
|
| 391 |
+
6,
|
| 392 |
+
7,
|
| 393 |
+
8,
|
| 394 |
+
9,
|
| 395 |
+
10,
|
| 396 |
+
11,
|
| 397 |
+
12,
|
| 398 |
+
13,
|
| 399 |
+
14,
|
| 400 |
+
15,
|
| 401 |
+
16,
|
| 402 |
+
17,
|
| 403 |
+
18,
|
| 404 |
+
19,
|
| 405 |
+
20,
|
| 406 |
+
21,
|
| 407 |
+
22,
|
| 408 |
+
23,
|
| 409 |
+
24,
|
| 410 |
+
25,
|
| 411 |
+
26,
|
| 412 |
+
27,
|
| 413 |
+
28,
|
| 414 |
+
29
|
| 415 |
+
],
|
| 416 |
+
"modality_keys": [
|
| 417 |
+
"left_arm",
|
| 418 |
+
"right_arm",
|
| 419 |
+
"left_hand",
|
| 420 |
+
"right_hand",
|
| 421 |
+
"waist",
|
| 422 |
+
"base_height_command",
|
| 423 |
+
"navigate_command"
|
| 424 |
+
],
|
| 425 |
+
"sin_cos_embedding_keys": null,
|
| 426 |
+
"mean_std_embedding_keys": null,
|
| 427 |
+
"action_configs": [
|
| 428 |
+
{
|
| 429 |
+
"rep": "RELATIVE",
|
| 430 |
+
"type": "NON_EEF",
|
| 431 |
+
"format": "DEFAULT",
|
| 432 |
+
"state_key": null
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"rep": "RELATIVE",
|
| 436 |
+
"type": "NON_EEF",
|
| 437 |
+
"format": "DEFAULT",
|
| 438 |
+
"state_key": null
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"rep": "ABSOLUTE",
|
| 442 |
+
"type": "NON_EEF",
|
| 443 |
+
"format": "DEFAULT",
|
| 444 |
+
"state_key": null
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"rep": "ABSOLUTE",
|
| 448 |
+
"type": "NON_EEF",
|
| 449 |
+
"format": "DEFAULT",
|
| 450 |
+
"state_key": null
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"rep": "ABSOLUTE",
|
| 454 |
+
"type": "NON_EEF",
|
| 455 |
+
"format": "DEFAULT",
|
| 456 |
+
"state_key": null
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"rep": "ABSOLUTE",
|
| 460 |
+
"type": "NON_EEF",
|
| 461 |
+
"format": "DEFAULT",
|
| 462 |
+
"state_key": null
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"rep": "ABSOLUTE",
|
| 466 |
+
"type": "NON_EEF",
|
| 467 |
+
"format": "DEFAULT",
|
| 468 |
+
"state_key": null
|
| 469 |
+
}
|
| 470 |
+
]
|
| 471 |
+
},
|
| 472 |
+
"language": {
|
| 473 |
+
"delta_indices": [
|
| 474 |
+
0
|
| 475 |
+
],
|
| 476 |
+
"modality_keys": [
|
| 477 |
+
"annotation.human.task_description"
|
| 478 |
+
],
|
| 479 |
+
"sin_cos_embedding_keys": null,
|
| 480 |
+
"mean_std_embedding_keys": null,
|
| 481 |
+
"action_configs": null
|
| 482 |
+
}
|
| 483 |
+
},
|
| 484 |
+
"libero_panda": {
|
| 485 |
+
"video": {
|
| 486 |
+
"delta_indices": [
|
| 487 |
+
0
|
| 488 |
+
],
|
| 489 |
+
"modality_keys": [
|
| 490 |
+
"image",
|
| 491 |
+
"wrist_image"
|
| 492 |
+
],
|
| 493 |
+
"sin_cos_embedding_keys": null,
|
| 494 |
+
"mean_std_embedding_keys": null,
|
| 495 |
+
"action_configs": null
|
| 496 |
+
},
|
| 497 |
+
"state": {
|
| 498 |
+
"delta_indices": [
|
| 499 |
+
0
|
| 500 |
+
],
|
| 501 |
+
"modality_keys": [
|
| 502 |
+
"x",
|
| 503 |
+
"y",
|
| 504 |
+
"z",
|
| 505 |
+
"roll",
|
| 506 |
+
"pitch",
|
| 507 |
+
"yaw",
|
| 508 |
+
"gripper"
|
| 509 |
+
],
|
| 510 |
+
"sin_cos_embedding_keys": null,
|
| 511 |
+
"mean_std_embedding_keys": null,
|
| 512 |
+
"action_configs": null
|
| 513 |
+
},
|
| 514 |
+
"action": {
|
| 515 |
+
"delta_indices": [
|
| 516 |
+
0,
|
| 517 |
+
1,
|
| 518 |
+
2,
|
| 519 |
+
3,
|
| 520 |
+
4,
|
| 521 |
+
5,
|
| 522 |
+
6,
|
| 523 |
+
7,
|
| 524 |
+
8,
|
| 525 |
+
9,
|
| 526 |
+
10,
|
| 527 |
+
11,
|
| 528 |
+
12,
|
| 529 |
+
13,
|
| 530 |
+
14,
|
| 531 |
+
15
|
| 532 |
+
],
|
| 533 |
+
"modality_keys": [
|
| 534 |
+
"x",
|
| 535 |
+
"y",
|
| 536 |
+
"z",
|
| 537 |
+
"roll",
|
| 538 |
+
"pitch",
|
| 539 |
+
"yaw",
|
| 540 |
+
"gripper"
|
| 541 |
+
],
|
| 542 |
+
"sin_cos_embedding_keys": null,
|
| 543 |
+
"mean_std_embedding_keys": null,
|
| 544 |
+
"action_configs": null
|
| 545 |
+
},
|
| 546 |
+
"language": {
|
| 547 |
+
"delta_indices": [
|
| 548 |
+
0
|
| 549 |
+
],
|
| 550 |
+
"modality_keys": [
|
| 551 |
+
"annotation.human.action.task_description"
|
| 552 |
+
],
|
| 553 |
+
"sin_cos_embedding_keys": null,
|
| 554 |
+
"mean_std_embedding_keys": null,
|
| 555 |
+
"action_configs": null
|
| 556 |
+
}
|
| 557 |
+
},
|
| 558 |
+
"oxe_widowx": {
|
| 559 |
+
"video": {
|
| 560 |
+
"delta_indices": [
|
| 561 |
+
0
|
| 562 |
+
],
|
| 563 |
+
"modality_keys": [
|
| 564 |
+
"image_0"
|
| 565 |
+
],
|
| 566 |
+
"sin_cos_embedding_keys": null,
|
| 567 |
+
"mean_std_embedding_keys": null,
|
| 568 |
+
"action_configs": null
|
| 569 |
+
},
|
| 570 |
+
"state": {
|
| 571 |
+
"delta_indices": [
|
| 572 |
+
0
|
| 573 |
+
],
|
| 574 |
+
"modality_keys": [
|
| 575 |
+
"x",
|
| 576 |
+
"y",
|
| 577 |
+
"z",
|
| 578 |
+
"roll",
|
| 579 |
+
"pitch",
|
| 580 |
+
"yaw",
|
| 581 |
+
"pad",
|
| 582 |
+
"gripper"
|
| 583 |
+
],
|
| 584 |
+
"sin_cos_embedding_keys": null,
|
| 585 |
+
"mean_std_embedding_keys": null,
|
| 586 |
+
"action_configs": null
|
| 587 |
+
},
|
| 588 |
+
"action": {
|
| 589 |
+
"delta_indices": [
|
| 590 |
+
0,
|
| 591 |
+
1,
|
| 592 |
+
2,
|
| 593 |
+
3,
|
| 594 |
+
4,
|
| 595 |
+
5,
|
| 596 |
+
6,
|
| 597 |
+
7
|
| 598 |
+
],
|
| 599 |
+
"modality_keys": [
|
| 600 |
+
"x",
|
| 601 |
+
"y",
|
| 602 |
+
"z",
|
| 603 |
+
"roll",
|
| 604 |
+
"pitch",
|
| 605 |
+
"yaw",
|
| 606 |
+
"gripper"
|
| 607 |
+
],
|
| 608 |
+
"sin_cos_embedding_keys": null,
|
| 609 |
+
"mean_std_embedding_keys": [
|
| 610 |
+
"x",
|
| 611 |
+
"y",
|
| 612 |
+
"z",
|
| 613 |
+
"roll",
|
| 614 |
+
"pitch",
|
| 615 |
+
"yaw"
|
| 616 |
+
],
|
| 617 |
+
"action_configs": null
|
| 618 |
+
},
|
| 619 |
+
"language": {
|
| 620 |
+
"delta_indices": [
|
| 621 |
+
0
|
| 622 |
+
],
|
| 623 |
+
"modality_keys": [
|
| 624 |
+
"annotation.human.action.task_description"
|
| 625 |
+
],
|
| 626 |
+
"sin_cos_embedding_keys": null,
|
| 627 |
+
"mean_std_embedding_keys": null,
|
| 628 |
+
"action_configs": null
|
| 629 |
+
}
|
| 630 |
+
},
|
| 631 |
+
"oxe_google": {
|
| 632 |
+
"video": {
|
| 633 |
+
"delta_indices": [
|
| 634 |
+
0
|
| 635 |
+
],
|
| 636 |
+
"modality_keys": [
|
| 637 |
+
"image"
|
| 638 |
+
],
|
| 639 |
+
"sin_cos_embedding_keys": null,
|
| 640 |
+
"mean_std_embedding_keys": null,
|
| 641 |
+
"action_configs": null
|
| 642 |
+
},
|
| 643 |
+
"state": {
|
| 644 |
+
"delta_indices": [
|
| 645 |
+
0
|
| 646 |
+
],
|
| 647 |
+
"modality_keys": [
|
| 648 |
+
"x",
|
| 649 |
+
"y",
|
| 650 |
+
"z",
|
| 651 |
+
"rx",
|
| 652 |
+
"ry",
|
| 653 |
+
"rz",
|
| 654 |
+
"rw",
|
| 655 |
+
"gripper"
|
| 656 |
+
],
|
| 657 |
+
"sin_cos_embedding_keys": null,
|
| 658 |
+
"mean_std_embedding_keys": null,
|
| 659 |
+
"action_configs": null
|
| 660 |
+
},
|
| 661 |
+
"action": {
|
| 662 |
+
"delta_indices": [
|
| 663 |
+
0,
|
| 664 |
+
1,
|
| 665 |
+
2,
|
| 666 |
+
3,
|
| 667 |
+
4,
|
| 668 |
+
5,
|
| 669 |
+
6,
|
| 670 |
+
7
|
| 671 |
+
],
|
| 672 |
+
"modality_keys": [
|
| 673 |
+
"x",
|
| 674 |
+
"y",
|
| 675 |
+
"z",
|
| 676 |
+
"roll",
|
| 677 |
+
"pitch",
|
| 678 |
+
"yaw",
|
| 679 |
+
"gripper"
|
| 680 |
+
],
|
| 681 |
+
"sin_cos_embedding_keys": null,
|
| 682 |
+
"mean_std_embedding_keys": [
|
| 683 |
+
"x",
|
| 684 |
+
"y",
|
| 685 |
+
"z",
|
| 686 |
+
"roll",
|
| 687 |
+
"pitch",
|
| 688 |
+
"yaw"
|
| 689 |
+
],
|
| 690 |
+
"action_configs": null
|
| 691 |
+
},
|
| 692 |
+
"language": {
|
| 693 |
+
"delta_indices": [
|
| 694 |
+
0
|
| 695 |
+
],
|
| 696 |
+
"modality_keys": [
|
| 697 |
+
"annotation.human.action.task_description"
|
| 698 |
+
],
|
| 699 |
+
"sin_cos_embedding_keys": null,
|
| 700 |
+
"mean_std_embedding_keys": null,
|
| 701 |
+
"action_configs": null
|
| 702 |
+
}
|
| 703 |
+
},
|
| 704 |
+
"oxe_droid": {
|
| 705 |
+
"video": {
|
| 706 |
+
"delta_indices": [
|
| 707 |
+
0
|
| 708 |
+
],
|
| 709 |
+
"modality_keys": [
|
| 710 |
+
"exterior_image_1_left",
|
| 711 |
+
"wrist_image_left"
|
| 712 |
+
],
|
| 713 |
+
"sin_cos_embedding_keys": null,
|
| 714 |
+
"mean_std_embedding_keys": null,
|
| 715 |
+
"action_configs": null
|
| 716 |
+
},
|
| 717 |
+
"state": {
|
| 718 |
+
"delta_indices": [
|
| 719 |
+
0
|
| 720 |
+
],
|
| 721 |
+
"modality_keys": [
|
| 722 |
+
"joint_position",
|
| 723 |
+
"gripper_position"
|
| 724 |
+
],
|
| 725 |
+
"sin_cos_embedding_keys": null,
|
| 726 |
+
"mean_std_embedding_keys": null,
|
| 727 |
+
"action_configs": null
|
| 728 |
+
},
|
| 729 |
+
"action": {
|
| 730 |
+
"delta_indices": [
|
| 731 |
+
0,
|
| 732 |
+
1,
|
| 733 |
+
2,
|
| 734 |
+
3,
|
| 735 |
+
4,
|
| 736 |
+
5,
|
| 737 |
+
6,
|
| 738 |
+
7,
|
| 739 |
+
8,
|
| 740 |
+
9,
|
| 741 |
+
10,
|
| 742 |
+
11,
|
| 743 |
+
12,
|
| 744 |
+
13,
|
| 745 |
+
14,
|
| 746 |
+
15,
|
| 747 |
+
16,
|
| 748 |
+
17,
|
| 749 |
+
18,
|
| 750 |
+
19,
|
| 751 |
+
20,
|
| 752 |
+
21,
|
| 753 |
+
22,
|
| 754 |
+
23,
|
| 755 |
+
24,
|
| 756 |
+
25,
|
| 757 |
+
26,
|
| 758 |
+
27,
|
| 759 |
+
28,
|
| 760 |
+
29,
|
| 761 |
+
30,
|
| 762 |
+
31
|
| 763 |
+
],
|
| 764 |
+
"modality_keys": [
|
| 765 |
+
"joint_position",
|
| 766 |
+
"gripper_position"
|
| 767 |
+
],
|
| 768 |
+
"sin_cos_embedding_keys": null,
|
| 769 |
+
"mean_std_embedding_keys": null,
|
| 770 |
+
"action_configs": [
|
| 771 |
+
{
|
| 772 |
+
"rep": "RELATIVE",
|
| 773 |
+
"type": "NON_EEF",
|
| 774 |
+
"format": "DEFAULT",
|
| 775 |
+
"state_key": null
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"rep": "ABSOLUTE",
|
| 779 |
+
"type": "NON_EEF",
|
| 780 |
+
"format": "DEFAULT",
|
| 781 |
+
"state_key": null
|
| 782 |
+
}
|
| 783 |
+
]
|
| 784 |
+
},
|
| 785 |
+
"language": {
|
| 786 |
+
"delta_indices": [
|
| 787 |
+
0
|
| 788 |
+
],
|
| 789 |
+
"modality_keys": [
|
| 790 |
+
"annotation.language.language_instruction"
|
| 791 |
+
],
|
| 792 |
+
"sin_cos_embedding_keys": null,
|
| 793 |
+
"mean_std_embedding_keys": null,
|
| 794 |
+
"action_configs": null
|
| 795 |
+
}
|
| 796 |
+
},
|
| 797 |
+
"new_embodiment": {
|
| 798 |
+
"video": {
|
| 799 |
+
"delta_indices": [
|
| 800 |
+
0
|
| 801 |
+
],
|
| 802 |
+
"modality_keys": [
|
| 803 |
+
"robot0_eye_in_hand",
|
| 804 |
+
"robot0_agentview_left",
|
| 805 |
+
"robot0_agentview_right"
|
| 806 |
+
],
|
| 807 |
+
"sin_cos_embedding_keys": null,
|
| 808 |
+
"mean_std_embedding_keys": null,
|
| 809 |
+
"action_configs": null
|
| 810 |
+
},
|
| 811 |
+
"state": {
|
| 812 |
+
"delta_indices": [
|
| 813 |
+
0
|
| 814 |
+
],
|
| 815 |
+
"modality_keys": [
|
| 816 |
+
"base_position",
|
| 817 |
+
"base_rotation",
|
| 818 |
+
"end_effector_position_relative",
|
| 819 |
+
"end_effector_rotation_relative",
|
| 820 |
+
"gripper_qpos"
|
| 821 |
+
],
|
| 822 |
+
"sin_cos_embedding_keys": null,
|
| 823 |
+
"mean_std_embedding_keys": null,
|
| 824 |
+
"action_configs": null
|
| 825 |
+
},
|
| 826 |
+
"action": {
|
| 827 |
+
"delta_indices": [
|
| 828 |
+
0,
|
| 829 |
+
1,
|
| 830 |
+
2,
|
| 831 |
+
3,
|
| 832 |
+
4,
|
| 833 |
+
5,
|
| 834 |
+
6,
|
| 835 |
+
7,
|
| 836 |
+
8,
|
| 837 |
+
9,
|
| 838 |
+
10,
|
| 839 |
+
11,
|
| 840 |
+
12,
|
| 841 |
+
13,
|
| 842 |
+
14,
|
| 843 |
+
15
|
| 844 |
+
],
|
| 845 |
+
"modality_keys": [
|
| 846 |
+
"base_motion",
|
| 847 |
+
"control_mode",
|
| 848 |
+
"end_effector_position",
|
| 849 |
+
"end_effector_rotation",
|
| 850 |
+
"gripper_close"
|
| 851 |
+
],
|
| 852 |
+
"sin_cos_embedding_keys": null,
|
| 853 |
+
"mean_std_embedding_keys": null,
|
| 854 |
+
"action_configs": [
|
| 855 |
+
{
|
| 856 |
+
"rep": "ABSOLUTE",
|
| 857 |
+
"type": "NON_EEF",
|
| 858 |
+
"format": "DEFAULT",
|
| 859 |
+
"state_key": null
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"rep": "ABSOLUTE",
|
| 863 |
+
"type": "NON_EEF",
|
| 864 |
+
"format": "DEFAULT",
|
| 865 |
+
"state_key": null
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"rep": "ABSOLUTE",
|
| 869 |
+
"type": "EEF",
|
| 870 |
+
"format": "DEFAULT",
|
| 871 |
+
"state_key": null
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"rep": "ABSOLUTE",
|
| 875 |
+
"type": "EEF",
|
| 876 |
+
"format": "DEFAULT",
|
| 877 |
+
"state_key": null
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"rep": "ABSOLUTE",
|
| 881 |
+
"type": "NON_EEF",
|
| 882 |
+
"format": "DEFAULT",
|
| 883 |
+
"state_key": null
|
| 884 |
+
}
|
| 885 |
+
]
|
| 886 |
+
},
|
| 887 |
+
"language": {
|
| 888 |
+
"delta_indices": [
|
| 889 |
+
0
|
| 890 |
+
],
|
| 891 |
+
"modality_keys": [
|
| 892 |
+
"task"
|
| 893 |
+
],
|
| 894 |
+
"sin_cos_embedding_keys": null,
|
| 895 |
+
"mean_std_embedding_keys": null,
|
| 896 |
+
"action_configs": null
|
| 897 |
+
}
|
| 898 |
+
}
|
| 899 |
+
},
|
| 900 |
+
"image_crop_size": null,
|
| 901 |
+
"image_target_size": null,
|
| 902 |
+
"use_albumentations": true,
|
| 903 |
+
"random_rotation_angle": null,
|
| 904 |
+
"color_jitter_params": {
|
| 905 |
+
"brightness": 0.3,
|
| 906 |
+
"contrast": 0.4,
|
| 907 |
+
"saturation": 0.5,
|
| 908 |
+
"hue": 0.08
|
| 909 |
+
},
|
| 910 |
+
"shortest_image_edge": 256,
|
| 911 |
+
"crop_fraction": 0.95,
|
| 912 |
+
"model_name": "nvidia/Eagle-Block2A-2B-v2",
|
| 913 |
+
"model_type": "eagle",
|
| 914 |
+
"formalize_language": true,
|
| 915 |
+
"max_state_dim": 128,
|
| 916 |
+
"max_action_dim": 128,
|
| 917 |
+
"max_action_horizon": 50,
|
| 918 |
+
"use_percentiles": false,
|
| 919 |
+
"clip_outliers": true,
|
| 920 |
+
"apply_sincos_state_encoding": true,
|
| 921 |
+
"use_relative_action": true
|
| 922 |
+
}
|
| 923 |
+
}
|
processor/statistics.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:f2763d70cd1de320f4d0515e426de65befdc4afd41cd3575f080430938bc410b
|
| 3 |
+
size 7633
|