Wipe repo contents

README.md

@@ -1,44 +0,0 @@
----
-license: other
-tags:
-- robotics
-- gr00t
-- isaac
-- humanoid
-base_model: nvidia/GR00T-N1.7-3B
----
-
-# GR00T fine-tune
-
-Fine-tuned from `nvidia/GR00T-N1.7-3B` on 2026-05-26T20:35:56+00:00.
-Embodiment: `UNITREE_G1_SONIC`. Trained on 4 GPUs.
-
-## Hyperparameters
-
-```
-timestamp           = 2026-05-26T20:32:17+00:00
-log_file            = /home/ubuntu/groot-files/logs/train-2026-05-26-203217.log
-base_model          = nvidia/GR00T-N1.7-3B
-embodiment_tag      = UNITREE_G1_SONIC
-dataset_dir         = /home/ubuntu/groot-files/dataset
-hf_dataset          = LucaFrat/dataset_100
-checkpoint_dir      = /home/ubuntu/groot-files/checkpoints/g1_finetune
-num_gpus            = 4
-global_batch_size   = 32
-max_steps           = 200
-save_steps          = 50
-save_total_limit    = 10
-learning_rate       = 1e-4
-warmup_ratio        = 0.05
-weight_decay        = 1e-5
-dataloader_workers  = 6
-resume              = <none>
-use_wandb           = 1
-wandb_project       = groot-finetune
-wandb_run_name      = <auto>
-```
-
-## Checkpoints
-
-Intermediate checkpoints (`checkpoint-N/`) are pushed incrementally during
-training; the top-level files in this repo are the final model state.

checkpoint-100/config.json

@@ -1,88 +0,0 @@
-{
-  "action_horizon": 40,
-  "add_pos_embed": true,
-  "apply_sincos_state_encoding": false,
-  "architectures": [
-    "Gr00tN1d7"
-  ],
-  "attn_dropout": 0.2,
-  "attn_implementation": null,
-  "backbone_embedding_dim": 2048,
-  "backbone_trainable_params_fp32": true,
-  "color_jitter_params": {
-    "brightness": 0.3,
-    "contrast": 0.4,
-    "hue": 0.08,
-    "saturation": 0.5
-  },
-  "crop_fraction": 0.95,
-  "diffusion_model_cfg": {
-    "attention_head_dim": 48,
-    "dropout": 0.2,
-    "final_dropout": true,
-    "interleave_self_attention": true,
-    "norm_type": "ada_norm",
-    "num_attention_heads": 32,
-    "num_layers": 32,
-    "output_dim": 1024,
-    "positional_embeddings": null
-  },
-  "dtype": "bfloat16",
-  "exclude_state": false,
-  "formalize_language": true,
-  "hidden_size": 1024,
-  "image_crop_size": [
-    230,
-    230
-  ],
-  "image_target_size": [
-    256,
-    256
-  ],
-  "letter_box_transform": false,
-  "load_bf16": false,
-  "max_action_dim": 132,
-  "max_num_embodiments": 32,
-  "max_seq_len": 1024,
-  "max_state_dim": 132,
-  "model_dtype": "bfloat16",
-  "model_name": "nvidia/Cosmos-Reason2-2B",
-  "model_type": "Gr00tN1d7",
-  "noise_beta_alpha": 1.5,
-  "noise_beta_beta": 1.0,
-  "noise_s": 0.999,
-  "num_inference_timesteps": 4,
-  "num_timestep_buckets": 1000,
-  "random_history_crop": true,
-  "random_rotation_angle": 0,
-  "reproject_vision": false,
-  "rtc_ramp_rate": 6.0,
-  "select_layer": 16,
-  "shortest_image_edge": 256,
-  "state_dropout_prob": 0.2,
-  "state_gaussian_noise_std": 0.0,
-  "transformers_version": "4.57.3",
-  "tune_diffusion_model": true,
-  "tune_linear": true,
-  "tune_llm": false,
-  "tune_projector": true,
-  "tune_top_llm_layers": 0,
-  "tune_visual": false,
-  "tune_vlln": true,
-  "use_albumentations": true,
-  "use_alternate_vl_dit": true,
-  "use_flash_attention": true,
-  "use_future_tokens": false,
-  "use_mean_std": false,
-  "use_percentiles": true,
-  "use_vl_self_attention": true,
-  "use_vlln": true,
-  "vl_self_attention_cfg": {
-    "attention_head_dim": 64,
-    "dropout": 0.2,
-    "final_dropout": true,
-    "num_attention_heads": 32,
-    "num_layers": 4,
-    "positional_embeddings": null
-  }
-}

checkpoint-100/embodiment_id.json

@@ -1,57 +0,0 @@
-{
-  "robocasa_panda_omron": 13,
-  "oxe_droid": 17,
-  "oxe_fractal": 18,
-  "oxe_language_table": 19,
-  "oxe_bridge": 20,
-  "unknown": 22,
-  "gr1_unified": 20,
-  "agibot": 26,
-  "sim_behavior_r1_pro": 23,
-  "xdof": 24,
-  "xdof_oss_data": 25,
-  "unitree_g1_full_body_with_waist_height_nav_cmd": 25,
-  "real_r1_pro_sharpa": 27,
-  "real_r1_pro_sharpa_add_view": 27,
-  "real_r1_pro_sharpa_relative_arm_joint": 26,
-  "real_r1_pro_sharpa_delta_eef": 26,
-  "real_r1_pro_sharpa_absolute_eef": 26,
-  "real_r1_pro_sharpa_meanstd": 26,
-  "real_r1_pro_sharpa_relative_eef": 26,
-  "real_r1_pro_sharpa_relative_eef_add_view": 26,
-  "real_r1_pro_sharpa_relative_eef_relative_hand": 26,
-  "real_r1_pro_sharpa_relative_eef_human": 26,
-  "real_r1_pro_sharpa_relative_eef_human_add_view": 26,
-  "real_r1_pro_sharpa_relative_eef_human_relative_hand": 26,
-  "real_r1_pro_sharpa_relative_eef_egodex": 26,
-  "real_r1_pro_sharpa_relative_eef_egodex_relative_hand": 26,
-  "real_r1_pro_sharpa_relative_eef_egodex_wrist_only": 26,
-  "real_r1_pro_sharpa_relative_eef_maxinsights": 26,
-  "real_r1_pro_sharpa_relative_eef_maxinsights_relative_hand": 26,
-  "real_r1_pro_sharpa_relative_eef_mecka": 26,
-  "real_r1_pro_sharpa_relative_eef_mecka_relative_hand": 26,
-  "real_g1_relative_eef_absolute_joints": 25,
-  "real_g1_relative_eef_absolute_joints_wrist_cam": 25,
-  "real_g1_relative_eef_relative_joints": 25,
-  "real_r1_pro_sharpa_relative_eef_relative_hand_relative_joint": 26,
-  "real_r1_pro_sharpa_relative_joint": 29,
-  "oxe_droid_relative_eef_relative_joint": 24,
-  "oxe_droid_relative_eef_relative_joint_swapped": 24,
-  "oxe_droid_relative_eef_relative_joint_upweight_z": 24,
-  "oxe_droid_relative_eef_relative_joint_upweight_z_swapped": 24,
-  "oxe_droid_relative_eef_relative_joint_3view": 24,
-  "oxe_droid_relative_eef_relative_joint_3view_swapped": 24,
-  "oxe_droid_relative_eef": 24,
-  "oxe_droid_joint_position_relative": 24,
-  "xdof_relative_eef_relative_joint": 27,
-  "xdof_relative_eef_relative_joint_subtask": 27,
-  "xdof_relative_eef": 27,
-  "xdof_relative_joint": 28,
-  "simpler_env_google": 0,
-  "simpler_env_widowx": 1,
-  "libero_sim": 2,
-  "droid_sim": 3,
-  "unitree_g1_sonic": 11,
-  "new_embodiment": 10,
-  "robocasa_gr1_tabletop": 10
-}

checkpoint-100/experiment_cfg/conf.yaml

@@ -1,251 +0,0 @@
-load_config_path: null
-model:
-  model_type: Gr00tN1d7
-  model_dtype: bfloat16
-  model_name: nvidia/Cosmos-Reason2-2B
-  backbone_model_type: qwen
-  model_revision: null
-  tune_top_llm_layers: 0
-  backbone_embedding_dim: 2048
-  tune_llm: false
-  tune_visual: false
-  select_layer: 12
-  reproject_vision: false
-  use_flash_attention: true
-  load_bf16: false
-  backbone_trainable_params_fp32: true
-  image_crop_size:
-  - 230
-  - 230
-  image_target_size:
-  - 256
-  - 256
-  shortest_image_edge: null
-  crop_fraction: null
-  random_rotation_angle: null
-  color_jitter_params:
-    brightness: 0.3
-    contrast: 0.4
-    saturation: 0.5
-    hue: 0.08
-  use_albumentations_transforms: true
-  extra_augmentation_config: null
-  formalize_language: true
-  apply_sincos_state_encoding: false
-  use_percentiles: true
-  use_relative_action: true
-  max_state_dim: 132
-  max_action_dim: 132
-  action_horizon: 40
-  hidden_size: 1024
-  input_embedding_dim: 1536
-  state_history_length: 1
-  add_pos_embed: true
-  attn_dropout: 0.2
-  use_vlln: true
-  max_seq_len: 1024
-  use_alternate_vl_dit: true
-  attend_text_every_n_blocks: 2
-  diffusion_model_cfg:
-    positional_embeddings: null
-    num_layers: 16
-    num_attention_heads: 32
-    attention_head_dim: 48
-    norm_type: ada_norm
-    dropout: 0.2
-    final_dropout: true
-    output_dim: 1024
-    interleave_self_attention: true
-  num_inference_timesteps: 4
-  noise_beta_alpha: 1.5
-  noise_beta_beta: 1.0
-  noise_s: 0.999
-  num_timestep_buckets: 1000
-  tune_projector: true
-  tune_diffusion_model: true
-  tune_vlln: true
-  state_dropout_prob: 0.2
-  exclude_state: false
-  use_mean_std: false
-  max_num_embodiments: 32
-data:
-  datasets:
-  - dataset_paths:
-    - /home/ubuntu/groot-files/dataset
-    embodiment_tag: unitree_g1_sonic
-    mix_ratio: 1.0
-    dataset_type: physical_embodiment
-    val_dataset_path: null
-  modality_configs:
-    unitree_g1_sonic:
-      video:
-        delta_indices:
-        - 0
-        modality_keys:
-        - ego_view
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs: null
-      state:
-        delta_indices:
-        - 0
-        modality_keys:
-        - left_leg
-        - right_leg
-        - waist
-        - left_arm
-        - right_arm
-        - left_hand
-        - right_hand
-        - projected_gravity
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs: null
-      action:
-        delta_indices:
-        - 0
-        - 1
-        - 2
-        - 3
-        - 4
-        - 5
-        - 6
-        - 7
-        - 8
-        - 9
-        - 10
-        - 11
-        - 12
-        - 13
-        - 14
-        - 15
-        - 16
-        - 17
-        - 18
-        - 19
-        - 20
-        - 21
-        - 22
-        - 23
-        - 24
-        - 25
-        - 26
-        - 27
-        - 28
-        - 29
-        - 30
-        - 31
-        - 32
-        - 33
-        - 34
-        - 35
-        - 36
-        - 37
-        - 38
-        - 39
-        modality_keys:
-        - motion_token
-        - left_hand_joints
-        - right_hand_joints
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs:
-        - rep: ABSOLUTE
-          type: NON_EEF
-          format: DEFAULT
-          state_key: null
-        - rep: ABSOLUTE
-          type: NON_EEF
-          format: DEFAULT
-          state_key: null
-        - rep: ABSOLUTE
-          type: NON_EEF
-          format: DEFAULT
-          state_key: null
-      language:
-        delta_indices:
-        - 0
-        modality_keys:
-        - annotation.human.task_description
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs: null
-  download_cache: false
-  shard_size: 1024
-  episode_sampling_rate: 0.1
-  num_shards_per_epoch: 100000
-  override_pretraining_statistics: true
-  mode: single_turn
-  random_chop: 0.0
-  mock_dataset_mode: false
-  shuffle: true
-  seed: 42
-  multiprocessing_context: fork
-  allow_padding: false
-  subsample_ratio: 1.0
-  image_crop_size:
-  - 244
-  - 244
-  image_target_size:
-  - 224
-  - 224
-  video_backend: torchcodec
-training:
-  output_dir: /home/ubuntu/groot-files/checkpoints/g1_finetune
-  experiment_name: null
-  max_steps: 200
-  global_batch_size: 32
-  batch_size: null
-  gradient_accumulation_steps: 1
-  learning_rate: 0.0001
-  lr_scheduler_type: cosine
-  weight_decay: 1.0e-05
-  warmup_ratio: 0.05
-  warmup_steps: 0
-  max_grad_norm: 1.0
-  optim: adamw_torch
-  start_from_checkpoint: nvidia/GR00T-N1.7-3B
-  skip_weight_loading: false
-  tf32: true
-  fp16: false
-  bf16: true
-  eval_bf16: true
-  logging_steps: 10
-  save_steps: 50
-  save_total_limit: 10
-  save_vl_model: false
-  save_only_model: false
-  upload_checkpoints: false
-  upload_every: 1000
-  upload_last_n_checkpoints: 5
-  max_concurrent_uploads: 2
-  eval_strategy: 'no'
-  eval_steps: 500
-  eval_set_split_ratio: 0.1
-  eval_batch_size: 2
-  save_best_eval_metric_name: ''
-  save_best_eval_metric_greater_is_better: true
-  deepspeed_stage: 2
-  gradient_checkpointing: false
-  transformers_trust_remote_code: true
-  transformers_local_files_only: false
-  transformers_cache_dir: null
-  transformers_access_token: null
-  use_ddp: false
-  ddp_bucket_cap_mb: 100
-  num_gpus: 4
-  dataloader_num_workers: 6
-  remove_unused_columns: false
-  use_wandb: true
-  wandb_project: groot-finetune
-  enable_profiling: false
-  max_retries: 3
-  assert_loss_less_than: null
-  add_rl_callback: false
-  enable_open_loop_eval: false
-  open_loop_eval_traj_ids:
-  - 0
-  open_loop_eval_steps_per_traj: 100
-  open_loop_eval_plot_indices: null
-max_steps: 200
-save_steps: 50

checkpoint-100/experiment_cfg/config.yaml

@@ -1,277 +0,0 @@
-!!python/object:gr00t.configs.base_config.Config
-data: !!python/object:gr00t.configs.data.data_config.DataConfig
-  allow_padding: false
-  datasets:
-  - !!python/object:gr00t.configs.data.data_config.SingleDatasetConfig
-    dataset_paths:
-    - /home/ubuntu/groot-files/dataset
-    dataset_type: physical_embodiment
-    embodiment_tag: unitree_g1_sonic
-    mix_ratio: 1.0
-    val_dataset_path: null
-  download_cache: false
-  episode_sampling_rate: 0.1
-  image_crop_size:
-  - 244
-  - 244
-  image_target_size:
-  - 224
-  - 224
-  mock_dataset_mode: false
-  modality_configs:
-    unitree_g1_sonic:
-      action: !!python/object:gr00t.data.types.ModalityConfig
-        action_configs:
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: &id001 !!python/object/apply:gr00t.data.types.ActionFormat
-          - default
-          rep: &id002 !!python/object/apply:gr00t.data.types.ActionRepresentation
-          - absolute
-          state_key: null
-          type: &id003 !!python/object/apply:gr00t.data.types.ActionType
-          - non_eef
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: *id001
-          rep: *id002
-          state_key: null
-          type: *id003
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: *id001
-          rep: *id002
-          state_key: null
-          type: *id003
-        delta_indices:
-        - 0
-        - 1
-        - 2
-        - 3
-        - 4
-        - 5
-        - 6
-        - 7
-        - 8
-        - 9
-        - 10
-        - 11
-        - 12
-        - 13
-        - 14
-        - 15
-        - 16
-        - 17
-        - 18
-        - 19
-        - 20
-        - 21
-        - 22
-        - 23
-        - 24
-        - 25
-        - 26
-        - 27
-        - 28
-        - 29
-        - 30
-        - 31
-        - 32
-        - 33
-        - 34
-        - 35
-        - 36
-        - 37
-        - 38
-        - 39
-        mean_std_embedding_keys: null
-        modality_keys:
-        - motion_token
-        - left_hand_joints
-        - right_hand_joints
-        sin_cos_embedding_keys: null
-      language: !!python/object:gr00t.data.types.ModalityConfig
-        action_configs: null
-        delta_indices:
-        - 0
-        mean_std_embedding_keys: null
-        modality_keys:
-        - annotation.human.task_description
-        sin_cos_embedding_keys: null
-      state: !!python/object:gr00t.data.types.ModalityConfig
-        action_configs: null
-        delta_indices:
-        - 0
-        mean_std_embedding_keys: null
-        modality_keys:
-        - left_leg
-        - right_leg
-        - waist
-        - left_arm
-        - right_arm
-        - left_hand
-        - right_hand
-        - projected_gravity
-        sin_cos_embedding_keys: null
-      video: !!python/object:gr00t.data.types.ModalityConfig
-        action_configs: null
-        delta_indices:
-        - 0
-        mean_std_embedding_keys: null
-        modality_keys:
-        - ego_view
-        sin_cos_embedding_keys: null
-  mode: single_turn
-  multiprocessing_context: fork
-  num_shards_per_epoch: 100000
-  override_pretraining_statistics: true
-  random_chop: 0.0
-  seed: 42
-  shard_size: 1024
-  shuffle: true
-  subsample_ratio: 1.0
-  video_backend: torchcodec
-load_config_path: null
-model: !!python/object:gr00t.configs.model.gr00t_n1d7.Gr00tN1d7Config
-  _attn_implementation_internal: null
-  _commit_hash: null
-  _name_or_path: ''
-  _output_attentions: false
-  add_cross_attention: false
-  architectures: null
-  backbone_trainable_params_fp32: true
-  bad_words_ids: null
-  begin_suppress_tokens: null
-  bos_token_id: null
-  chunk_size_feed_forward: 0
-  color_jitter_params:
-    brightness: 0.3
-    contrast: 0.4
-    hue: 0.08
-    saturation: 0.5
-  cross_attention_hidden_size: null
-  decoder_start_token_id: null
-  diffusion_model_cfg:
-    attention_head_dim: 48
-    dropout: 0.2
-    final_dropout: true
-    interleave_self_attention: true
-    norm_type: ada_norm
-    num_attention_heads: 32
-    num_layers: 16
-    output_dim: 1024
-    positional_embeddings: null
-  diversity_penalty: 0.0
-  do_sample: false
-  dtype: null
-  early_stopping: false
-  encoder_no_repeat_ngram_size: 0
-  eos_token_id: null
-  exponential_decay_length_penalty: null
-  extra_augmentation_config: null
-  finetuning_task: null
-  forced_bos_token_id: null
-  forced_eos_token_id: null
-  id2label:
-    0: LABEL_0
-    1: LABEL_1
-  is_decoder: false
-  is_encoder_decoder: false
-  label2id:
-    LABEL_0: 0
-    LABEL_1: 1
-  length_penalty: 1.0
-  load_bf16: false
-  max_length: 20
-  min_length: 0
-  model_name: nvidia/Cosmos-Reason2-2B
-  no_repeat_ngram_size: 0
-  num_beam_groups: 1
-  num_beams: 1
-  num_return_sequences: 1
-  output_hidden_states: false
-  output_scores: false
-  pad_token_id: null
-  prefix: null
-  problem_type: null
-  pruned_heads: {}
-  random_rotation_angle: null
-  remove_invalid_values: false
-  repetition_penalty: 1.0
-  reproject_vision: false
-  return_dict: true
-  return_dict_in_generate: false
-  sep_token_id: null
-  state_dropout_prob: 0.2
-  suppress_tokens: null
-  task_specific_params: null
-  temperature: 1.0
-  tf_legacy_loss: false
-  tie_encoder_decoder: false
-  tie_word_embeddings: true
-  tokenizer_class: null
-  top_k: 50
-  top_p: 1.0
-  torchscript: false
-  transformers_version: null
-  tune_diffusion_model: true
-  tune_llm: false
-  tune_projector: true
-  tune_visual: false
-  typical_p: 1.0
-  use_bfloat16: false
-  use_relative_action: true
-training: !!python/object:gr00t.configs.training.training_config.TrainingConfig
-  add_rl_callback: false
-  assert_loss_less_than: null
-  batch_size: null
-  bf16: true
-  dataloader_num_workers: 6
-  ddp_bucket_cap_mb: 100
-  deepspeed_stage: 2
-  enable_open_loop_eval: false
-  enable_profiling: false
-  eval_batch_size: 2
-  eval_bf16: true
-  eval_set_split_ratio: 0.1
-  eval_steps: 500
-  eval_strategy: 'no'
-  experiment_name: null
-  fp16: false
-  global_batch_size: 32
-  gradient_accumulation_steps: 1
-  gradient_checkpointing: false
-  learning_rate: 0.0001
-  logging_steps: 10
-  lr_scheduler_type: cosine
-  max_concurrent_uploads: 2
-  max_grad_norm: 1.0
-  max_retries: 3
-  max_steps: 200
-  num_gpus: 4
-  open_loop_eval_plot_indices: null
-  open_loop_eval_steps_per_traj: 100
-  open_loop_eval_traj_ids:
-  - 0
-  optim: adamw_torch
-  output_dir: /home/ubuntu/groot-files/checkpoints/g1_finetune
-  remove_unused_columns: false
-  save_best_eval_metric_greater_is_better: true
-  save_best_eval_metric_name: ''
-  save_only_model: false
-  save_steps: 50
-  save_total_limit: 10
-  save_vl_model: false
-  skip_weight_loading: false
-  start_from_checkpoint: nvidia/GR00T-N1.7-3B
-  tf32: true
-  transformers_access_token: null
-  transformers_cache_dir: null
-  transformers_local_files_only: false
-  transformers_trust_remote_code: true
-  upload_checkpoints: false
-  upload_every: 1000
-  upload_last_n_checkpoints: 5
-  use_ddp: false
-  use_wandb: true
-  wandb_project: groot-finetune
-  warmup_ratio: 0.05
-  warmup_steps: 0
-  weight_decay: 1.0e-05

checkpoint-100/experiment_cfg/dataset_statistics.json

@@ -1,907 +0,0 @@
-{
-  "unitree_g1_sonic": {
-    "state": {
-      "left_leg": {
-        "min": [
-          -0.4857776165008545,
-          -0.24391146004199982,
-          -0.8776780366897583,
-          0.03597185015678406,
-          -0.4930363595485687,
-          -0.20340518653392792
-        ],
-        "max": [
-          0.3237466514110565,
-          0.31727835536003113,
-          0.7570706605911255,
-          0.8986315131187439,
-          0.1892659068107605,
-          0.15561887621879578
-        ],
-        "mean": [
-          0.038367897272109985,
-          0.017137423157691956,
-          0.10202965885400772,
-          0.21319514513015747,
-          -0.20034761726856232,
-          -0.009860903024673462
-        ],
-        "std": [
-          0.12473291903734207,
-          0.0657326877117157,
-          0.16789446771144867,
-          0.0855027362704277,
-          0.05454540252685547,
-          0.043583426624536514
-        ],
-        "q01": [
-          -0.3429580569267273,
-          -0.14271177425980566,
-          -0.41709126979112626,
-          0.12328944355249405,
-          -0.2934864178299904,
-          -0.11147186532616615
-        ],
-        "q99": [
-          0.18860293924808502,
-          0.17139848843216907,
-          0.4404219493269922,
-          0.5360466212034226,
-          -0.019520661234855623,
-          0.09359118081629283
-        ]
-      },
-      "right_leg": {
-        "min": [
-          -0.5335952043533325,
-          -0.350761741399765,
-          -1.3307929039001465,
-          0.07445771992206573,
-          -0.6092288494110107,
-          -0.1984633058309555
-        ],
-        "max": [
-          0.25397607684135437,
-          0.15654273331165314,
-          0.24837948381900787,
-          0.9999935626983643,
-          0.1089707612991333,
-          0.17701147496700287
-        ],
-        "mean": [
-          0.05046115070581436,
-          -0.023679343983530998,
-          -0.213065966963768,
-          0.20844903588294983,
-          -0.19808240234851837,
-          -0.0055496226996183395
-        ],
-        "std": [
-          0.07887373864650726,
-          0.06217808276414871,
-          0.18437089025974274,
-          0.10042016953229904,
-          0.06798264384269714,
-          0.04407079145312309
-        ],
-        "q01": [
-          -0.193911362439394,
-          -0.1981988400220871,
-          -0.90549436211586,
-          0.127213454246521,
-          -0.4343456655740738,
-          -0.11320190876722336
-        ],
-        "q99": [
-          0.1967100210487844,
-          0.11513377726078033,
-          0.15384408906102207,
-          0.7395615458488474,
-          -0.05514147877693175,
-          0.08568341806530994
-        ]
-      },
-      "waist": {
-        "min": [
-          -0.3889274299144745,
-          -0.3032904267311096,
-          -0.04627600684762001
-        ],
-        "max": [
-          0.4404728412628174,
-          0.11908156424760818,
-          0.05046159774065018
-        ],
-        "mean": [
-          0.1003476083278656,
-          -0.03575156629085541,
-          -0.0004057084152009338
-        ],
-        "std": [
-          0.11155267059803009,
-          0.044356729835271835,
-          0.007639772724360228
-        ],
-        "q01": [
-          -0.09896008186042309,
-          -0.16525592356920243,
-          -0.019172759167850016
-        ],
-        "q99": [
-          0.3729535743594171,
-          0.04077914115041498,
-          0.024438940081745388
-        ]
-      },
-      "left_arm": {
-        "min": [
-          -0.2003283053636551,
-          0.09816279262304306,
-          -0.5412195920944214,
-          0.7723593711853027,
-          -0.7412483096122742,
-          -0.09287774562835693,
-          -0.31815722584724426
-        ],
-        "max": [
-          0.4134317934513092,
-          0.38915175199508667,
-          0.3470511734485626,
-          1.363792896270752,
-          0.38266828656196594,
-          0.5152138471603394,
-          0.42312705516815186
-        ],
-        "mean": [
-          0.17467822134494781,
-          0.20962199568748474,
-          0.03295444697141647,
-          1.0894439220428467,
-          -0.11893314123153687,
-          0.20652393996715546,
-          0.01763514056801796
-        ],
-        "std": [
-          0.08956529945135117,
-          0.03943527489900589,
-          0.09209521114826202,
-          0.07066802680492401,
-          0.19965490698814392,
-          0.11541580408811569,
-          0.10361754149198532
-        ],
-        "q01": [
-          -0.06361526139080524,
-          0.1356973797082901,
-          -0.1961050637066364,
-          0.9089213967323303,
-          -0.5769511580467224,
-          -0.03977684192359447,
-          -0.22587568387389184
-        ],
-        "q99": [
-          0.3310546398162843,
-          0.31673349142074597,
-          0.2289490304887296,
-          1.2593449354171753,
-          0.2899013936519628,
-          0.46442466974258423,
-          0.2727669641375545
-        ]
-      },
-      "right_arm": {
-        "min": [
-          -0.9788835048675537,
-          -0.7953690886497498,
-          -0.49778875708580017,
-          -0.7156979441642761,
-          -0.9786917567253113,
-          -0.1273084282875061,
-          -0.9962846040725708
-        ],
-        "max": [
-          0.3628104329109192,
-          0.08640626072883606,
-          0.8718883395195007,
-          1.3758729696273804,
-          1.0651459693908691,
-          0.6638182401657104,
-          0.9581388235092163
-        ],
-        "mean": [
-          -0.14295516908168793,
-          -0.20207007229328156,
-          0.164081871509552,
-          0.32978397607803345,
-          0.15659268200397491,
-          0.21257737278938293,
-          0.0897224023938179
-        ],
-        "std": [
-          0.2832476496696472,
-          0.07377105951309204,
-          0.18590903282165527,
-          0.6193384528160095,
-          0.20538125932216644,
-          0.12802571058273315,
-          0.21542473137378693
-        ],
-        "q01": [
-          -0.7704071193933487,
-          -0.376973994076252,
-          -0.19678157344460487,
-          -0.5173931628465652,
-          -0.39670541584491725,
-          -0.03838966768234967,
-          -0.3572006195783615
-        ],
-        "q99": [
-          0.24905617535114288,
-          0.0024351945263335014,
-          0.586448073387146,
-          1.304707604646683,
-          0.5929710775613787,
-          0.5161845684051514,
-          0.6641693621873858
-        ]
-      },
-      "left_hand": {
-        "min": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "max": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "mean": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "std": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q01": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q99": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ]
-      },
-      "right_hand": {
-        "min": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "max": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "mean": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "std": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q01": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q99": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ]
-      },
-      "projected_gravity": {
-        "min": [
-          -0.12354099005460739,
-          -0.13017292320728302,
-          -1.0
-        ],
-        "max": [
-          0.22223307192325592,
-          0.10705921798944473,
-          -0.9749471545219421
-        ],
-        "mean": [
-          -0.01818661577999592,
-          0.0029902660753577948,
-          -0.9988934993743896
-        ],
-        "std": [
-          0.03578517585992813,
-          0.032206468284130096,
-          0.0014198371209307285
-        ],
-        "q01": [
-          -0.09425989575684071,
-          -0.08990333564579486,
-          -0.9999815225601196
-        ],
-        "q99": [
-          0.06742736026644708,
-          0.06235775817185641,
-          -0.9940253734588623
-        ]
-      }
-    },
-    "action": {
-      "motion_token": {
-        "min": [
-          -0.3125,
-          -0.5,
-          -0.5,
-          -0.4375,
-          -0.625,
-          -0.375,
-          -0.25,
-          -0.0625,
-          -0.4375,
-          -0.6875,
-          -0.375,
-          -0.375,
-          -0.3125,
-          -0.375,
-          -0.6875,
-          -0.25,
-          -0.375,
-          -0.25,
-          -0.375,
-          -0.5,
-          -0.5,
-          -0.5,
-          -0.625,
-          -0.5,
-          -0.375,
-          -0.5625,
-          -0.125,
-          -0.5,
-          -0.3125,
-          -0.3125,
-          -0.125,
-          -0.375,
-          0.0625,
-          -0.1875,
-          -0.1875,
-          -0.5625,
-          -0.6875,
-          -0.6875,
-          -0.125,
-          -0.125,
-          -0.4375,
-          -0.5625,
-          -0.3125,
-          -0.375,
-          -0.5,
-          -0.4375,
-          -0.125,
-          -0.3125,
-          -0.5,
-          -0.25,
-          -0.375,
-          -0.625,
-          -0.0625,
-          -0.4375,
-          -0.0625,
-          -0.4375,
-          -0.5,
-          0.0,
-          -0.25,
-          -0.5,
-          -0.375,
-          -0.1875,
-          0.0,
-          -0.5
-        ],
-        "max": [
-          0.125,
-          0.25,
-          0.25,
-          0.125,
-          0.1875,
-          0.1875,
-          0.5,
-          0.4375,
-          0.25,
-          0.125,
-          0.1875,
-          0.0625,
-          0.125,
-          0.3125,
-          -0.0625,
-          0.1875,
-          0.25,
-          0.25,
-          0.125,
-          0.0625,
-          0.3125,
-          0.125,
-          0.25,
-          0.25,
-          0.3125,
-          0.125,
-          0.375,
-          0.1875,
-          0.375,
-          0.375,
-          0.375,
-          0.25,
-          0.4375,
-          0.5,
-          0.5,
-          0.5625,
-          0.25,
-          -0.0625,
-          0.3125,
-          0.4375,
-          0.125,
-          0.4375,
-          0.4375,
-          0.375,
-          -0.0625,
-          0.1875,
-          0.5625,
-          0.1875,
-          0.3125,
-          0.1875,
-          0.25,
-          0.1875,
-          0.375,
-          0.3125,
-          0.5625,
-          0.1875,
-          0.4375,
-          0.5625,
-          0.1875,
-          0.375,
-          0.3125,
-          0.4375,
-          0.5625,
-          0.0
-        ],
-        "mean": [
-          -0.05732722207903862,
-          -0.12596048414707184,
-          -0.015900524333119392,
-          -0.16434414684772491,
-          -0.18957528471946716,
-          -0.08797170221805573,
-          0.2548595666885376,
-          0.19856274127960205,
-          -0.025066815316677094,
-          -0.21372610330581665,
-          -0.10314688086509705,
-          -0.21981850266456604,
-          -0.12050355225801468,
-          -0.08165144175291061,
-          -0.38714757561683655,
-          -8.805885590845719e-05,
-          -0.049404650926589966,
-          -0.055493421852588654,
-          -0.09600593894720078,
-          -0.2977478802204132,
-          -0.029102997854351997,
-          -0.2329292893409729,
-          -0.19594638049602509,
-          -0.23360289633274078,
-          -0.095408596098423,
-          -0.17069709300994873,
-          0.1292250156402588,
-          -0.2315811812877655,
-          0.07302621006965637,
-          0.06577451527118683,
-          0.1414906084537506,
-          -0.11845822632312775,
-          0.2995853126049042,
-          0.17635828256607056,
-          0.14573286473751068,
-          0.0782189592719078,
-          -0.1727832704782486,
-          -0.3186105489730835,
-          0.11981905251741409,
-          0.13200204074382782,
-          -0.08226785063743591,
-          -0.09514441341161728,
-          0.060834143310785294,
-          -0.006165935657918453,
-          -0.3161884844303131,
-          -0.02333650551736355,
-          0.21719853579998016,
-          -0.10866008698940277,
-          -0.01649424061179161,
-          -0.007006580010056496,
-          -0.06802137941122055,
-          -0.14377468824386597,
-          0.21333755552768707,
-          0.015348567627370358,
-          0.22719819843769073,
-          -0.1495230346918106,
-          0.030986731871962547,
-          0.296153724193573,
-          -0.023153124377131462,
-          -0.1389232873916626,
-          0.035359714180231094,
-          0.10143018513917923,
-          0.30849015712738037,
-          -0.22524820268154144
-        ],
-        "std": [
-          0.06542618572711945,
-          0.09994574636220932,
-          0.07207678258419037,
-          0.08702709525823593,
-          0.17209544777870178,
-          0.0581701286137104,
-          0.09559116512537003,
-          0.07802454382181168,
-          0.13620688021183014,
-          0.1569388061761856,
-          0.0967717096209526,
-          0.0680033266544342,
-          0.05837923660874367,
-          0.11557621508836746,
-          0.11890240013599396,
-          0.08077684044837952,
-          0.06398067623376846,
-          0.06826013326644897,
-          0.09755037724971771,
-          0.10724268853664398,
-          0.1992810219526291,
-          0.12710419297218323,
-          0.21719561517238617,
-          0.14369657635688782,
-          0.08655858784914017,
-          0.11142221838235855,
-          0.057688891887664795,
-          0.18031662702560425,
-          0.0692613422870636,
-          0.16206243634223938,
-          0.11068906635046005,
-          0.06650221347808838,
-          0.06952458620071411,
-          0.10304083675146103,
-          0.12724509835243225,
-          0.3227654695510864,
-          0.14636477828025818,
-          0.08603093028068542,
-          0.08780314773321152,
-          0.06147885322570801,
-          0.07425742596387863,
-          0.27255958318710327,
-          0.13721545040607452,
-          0.10124049335718155,
-          0.06286311149597168,
-          0.0642034038901329,
-          0.08693595230579376,
-          0.06350599974393845,
-          0.11969305574893951,
-          0.06820058822631836,
-          0.09139743447303772,
-          0.1545047014951706,
-          0.06951460987329483,
-          0.08810964971780777,
-          0.0868336483836174,
-          0.0749349296092987,
-          0.09778603166341782,
-          0.11456362158060074,
-          0.06560879200696945,
-          0.2043108344078064,
-          0.07238639891147614,
-          0.0965481698513031,
-          0.11412639170885086,
-          0.11945699900388718
-        ],
-        "q01": [
-          -0.1875,
-          -0.375,
-          -0.1875,
-          -0.375,
-          -0.5625,
-          -0.1875,
-          0.0625,
-          0.0,
-          -0.3125,
-          -0.625,
-          -0.3125,
-          -0.3125,
-          -0.25,
-          -0.3125,
-          -0.625,
-          -0.1875,
-          -0.25,
-          -0.1875,
-          -0.3125,
-          -0.5,
-          -0.375,
-          -0.4375,
-          -0.5625,
-          -0.4375,
-          -0.3125,
-          -0.5,
-          -0.0625,
-          -0.5,
-          -0.0625,
-          -0.1875,
-          -0.0625,
-          -0.25,
-          0.125,
-          -0.0625,
-          -0.0625,
-          -0.5,
-          -0.5625,
-          -0.5625,
-          -0.0625,
-          0.0,
-          -0.25,
-          -0.5625,
-          -0.1875,
-          -0.25,
-          -0.4375,
-          -0.1875,
-          0.0625,
-          -0.25,
-          -0.375,
-          -0.1875,
-          -0.3125,
-          -0.5,
-          0.0625,
-          -0.1875,
-          0.0625,
-          -0.375,
-          -0.375,
-          0.0625,
-          -0.1875,
-          -0.4375,
-          -0.1875,
-          -0.0625,
-          0.125,
-          -0.4375
-        ],
-        "q99": [
-          0.0625,
-          0.0625,
-          0.1875,
-          0.0,
-          0.125,
-          0.0625,
-          0.375,
-          0.375,
-          0.1875,
-          0.0625,
-          0.0625,
-          -0.0625,
-          0.0625,
-          0.1875,
-          -0.125,
-          0.125,
-          0.125,
-          0.125,
-          0.0625,
-          -0.0625,
-          0.25,
-          0.0,
-          0.1875,
-          0.125,
-          0.0625,
-          0.0,
-          0.25,
-          0.125,
-          0.25,
-          0.3125,
-          0.3125,
-          0.0625,
-          0.375,
-          0.375,
-          0.4375,
-          0.5,
-          0.125,
-          -0.125,
-          0.3125,
-          0.25,
-          0.0625,
-          0.3125,
-          0.3125,
-          0.25,
-          -0.125,
-          0.125,
-          0.4375,
-          0.0,
-          0.1875,
-          0.125,
-          0.125,
-          0.125,
-          0.375,
-          0.1875,
-          0.5,
-          0.0625,
-          0.25,
-          0.5,
-          0.125,
-          0.1875,
-          0.25,
-          0.3125,
-          0.5,
-          0.0
-        ]
-      },
-      "left_hand_joints": {
-        "min": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "max": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "mean": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "std": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q01": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q99": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ]
-      },
-      "right_hand_joints": {
-        "min": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "max": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "mean": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "std": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q01": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q99": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ]
-      }
-    },
-    "relative_action": {}
-  }
-}

checkpoint-100/experiment_cfg/final_model_config.json

@@ -1,55 +0,0 @@
-{
-  "model_type": "Gr00tN1d7",
-  "model_dtype": "bfloat16",
-  "model_name": "nvidia/Cosmos-Reason2-2B",
-  "backbone_model_type": "qwen",
-  "model_revision": null,
-  "tune_top_llm_layers": 0,
-  "backbone_embedding_dim": 2048,
-  "tune_llm": false,
-  "tune_visual": false,
-  "select_layer": 16,
-  "reproject_vision": false,
-  "use_flash_attention": true,
-  "load_bf16": false,
-  "backbone_trainable_params_fp32": true,
-  "extra_augmentation_config": null,
-  "apply_sincos_state_encoding": false,
-  "use_percentiles": true,
-  "use_relative_action": false,
-  "max_state_dim": 132,
-  "max_action_dim": 132,
-  "action_horizon": 40,
-  "hidden_size": 1024,
-  "input_embedding_dim": 1536,
-  "state_history_length": 1,
-  "add_pos_embed": true,
-  "attn_dropout": 0.2,
-  "use_vlln": true,
-  "max_seq_len": 1024,
-  "use_alternate_vl_dit": true,
-  "attend_text_every_n_blocks": 2,
-  "diffusion_model_cfg": {
-    "attention_head_dim": 48,
-    "dropout": 0.2,
-    "final_dropout": true,
-    "interleave_self_attention": true,
-    "norm_type": "ada_norm",
-    "num_attention_heads": 32,
-    "num_layers": 32,
-    "output_dim": 1024,
-    "positional_embeddings": null
-  },
-  "num_inference_timesteps": 4,
-  "noise_beta_alpha": 1.5,
-  "noise_beta_beta": 1.0,
-  "noise_s": 0.999,
-  "num_timestep_buckets": 1000,
-  "tune_projector": true,
-  "tune_diffusion_model": true,
-  "tune_vlln": true,
-  "state_dropout_prob": 0.2,
-  "exclude_state": false,
-  "use_mean_std": false,
-  "max_num_embodiments": 32
-}

checkpoint-100/global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5222d9e0c9ac9af797db8cf3db5d63b2332093383d77202b0c0a6bd55c8c7c3c
-size 4861568625

checkpoint-100/global_step100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0f0fd4d507235a2e8c4e5b45bcdc394f9f1f81809b81829219631ca7aadfd564
-size 4861568369

checkpoint-100/global_step100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f3a40e3aa2ca9b78a12c9c0b1d5f20a159a440af8fe0b5578643b2112f0d2f3c
-size 4861566321

checkpoint-100/global_step100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:89458417409a07d777bcfcf73e98384ae29ffe60425f7c98549dc85955362202
-size 4861563121

checkpoint-100/global_step100/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a9ebbee189875fd1809086764d5a6a5e7865892084132912acf90b86fbcc640d
-size 2430786821

checkpoint-100/global_step100/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ace5eac404cae10f47c96aaff4bab6823c83f8fb1d65edbdb0c8e2334e90afb4
-size 2430784901

checkpoint-100/global_step100/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:185a72e1517e91d302b5c5d37c5a59db2161f307117fe6c85c0c77e27871469d
-size 2430783237

checkpoint-100/global_step100/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5350d4e2e8db7658b36115ba3d4f76fc6861a7b2a6841a28af784f5589a1dfde
-size 2430785349

checkpoint-100/global_step100/mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2b1aca2d6aaf9f184902dff0d852627223bc8d22170e1a3d7768280e29dfea8a
-size 9335640879

checkpoint-100/latest

@@ -1 +0,0 @@
-global_step100

checkpoint-100/model-00001-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:212a0bd6282ad4656da39e97da1ade8762403db0195357015ac31e527bd16248
-size 4990519232

checkpoint-100/model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a5918a9461088c1d564b3f52838af99d6c2d125b7771815a06c92d2ffd245a01
-size 1919980184

checkpoint-100/processor_config.json

@@ -1,1159 +0,0 @@
-{
-  "processor_class": "Gr00tN1d7Processor",
-  "processor_kwargs": {
-    "modality_configs": {
-      "real_g1_relative_eef_relative_joints": {
-        "video": {
-          "delta_indices": [
-            -20,
-            0
-          ],
-          "modality_keys": [
-            "ego_view"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_wrist_eef_9d",
-            "right_wrist_eef_9d",
-            "left_hand",
-            "right_hand",
-            "left_arm",
-            "right_arm",
-            "waist"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "left_wrist_eef_9d",
-            "right_wrist_eef_9d",
-            "left_hand",
-            "right_hand",
-            "left_arm",
-            "right_arm",
-            "waist",
-            "base_height_command",
-            "navigate_command"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "left_wrist_eef_9d"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "right_wrist_eef_9d"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_hand"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_hand"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_arm"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_arm"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "waist"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "base_height_command"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "navigate_command"
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.human.task_description"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "real_r1_pro_sharpa_relative_eef_mecka": {
-        "video": {
-          "delta_indices": [
-            -30,
-            0
-          ],
-          "modality_keys": [
-            "ego_view_cropratio_res320x240_freq30"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "left_wrist_eef"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "right_wrist_eef"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_hand_joints"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_hand_joints"
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.human.coarse_action"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "real_r1_pro_sharpa_relative_eef_human": {
-        "video": {
-          "delta_indices": [
-            -20,
-            0
-          ],
-          "modality_keys": [
-            "ego_view_res320x240_freq20",
-            "left_wrist_view_res320x240_freq20",
-            "right_wrist_view_res320x240_freq20"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "left_wrist_eef"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "right_wrist_eef"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_hand_joints"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_hand_joints"
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.human.coarse_action"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "real_r1_pro_sharpa_relative_eef": {
-        "video": {
-          "delta_indices": [
-            -20,
-            0
-          ],
-          "modality_keys": [
-            "ego_view_res320x240_freq20",
-            "left_wrist_view_res320x240_freq20",
-            "right_wrist_view_res320x240_freq20"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "left_wrist_eef"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "right_wrist_eef"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_hand_joints"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_hand_joints"
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.human.coarse_action"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "xdof_relative_eef_relative_joint": {
-        "video": {
-          "delta_indices": [
-            -30,
-            0
-          ],
-          "modality_keys": [
-            "top_camera-images-rgb_320_240",
-            "left_camera-images-rgb_320_240",
-            "right_camera-images-rgb_320_240"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_gripper_pos",
-            "right_gripper_pos",
-            "left_joint_pos",
-            "right_joint_pos"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_gripper_pos",
-            "right_gripper_pos",
-            "left_joint_pos",
-            "right_joint_pos"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "left_wrist_eef"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "right_wrist_eef"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_gripper_pos"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_gripper_pos"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_joint_pos"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_joint_pos"
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.task"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "real_r1_pro_sharpa_relative_eef_maxinsights": {
-        "video": {
-          "delta_indices": [
-            -30,
-            0
-          ],
-          "modality_keys": [
-            "ego_view_cropratio_res320x240_freq30"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "left_wrist_eef"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "right_wrist_eef"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_hand_joints"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_hand_joints"
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.human.coarse_action"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "xdof_relative_eef_relative_joint_subtask": {
-        "video": {
-          "delta_indices": [
-            -30,
-            0
-          ],
-          "modality_keys": [
-            "top_camera-images-rgb_320_240",
-            "left_camera-images-rgb_320_240",
-            "right_camera-images-rgb_320_240"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_gripper_pos",
-            "right_gripper_pos",
-            "left_joint_pos",
-            "right_joint_pos"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "left_wrist_eef",
-            "right_wrist_eef",
-            "left_gripper_pos",
-            "right_gripper_pos",
-            "left_joint_pos",
-            "right_joint_pos"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "left_wrist_eef"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "right_wrist_eef"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_gripper_pos"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_gripper_pos"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "left_joint_pos"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "right_joint_pos"
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.sub_task"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "oxe_droid_relative_eef_relative_joint": {
-        "video": {
-          "delta_indices": [
-            -15,
-            0
-          ],
-          "modality_keys": [
-            "exterior_image_1_left",
-            "wrist_image_left"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "eef_9d",
-            "gripper_position",
-            "joint_position"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "eef_9d",
-            "gripper_position",
-            "joint_position"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "EEF",
-              "format": "XYZ_ROT6D",
-              "state_key": "eef_9d"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "gripper_position"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "joint_position"
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.language.language_instruction"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "unitree_g1_sonic": {
-        "video": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "ego_view"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_leg",
-            "right_leg",
-            "waist",
-            "left_arm",
-            "right_arm",
-            "left_hand",
-            "right_hand",
-            "projected_gravity"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "action": {
-          "delta_indices": [
-            0,
-            1,
-            2,
-            3,
-            4,
-            5,
-            6,
-            7,
-            8,
-            9,
-            10,
-            11,
-            12,
-            13,
-            14,
-            15,
-            16,
-            17,
-            18,
-            19,
-            20,
-            21,
-            22,
-            23,
-            24,
-            25,
-            26,
-            27,
-            28,
-            29,
-            30,
-            31,
-            32,
-            33,
-            34,
-            35,
-            36,
-            37,
-            38,
-            39
-          ],
-          "modality_keys": [
-            "motion_token",
-            "left_hand_joints",
-            "right_hand_joints"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.human.task_description"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      }
-    },
-    "image_crop_size": [
-      230,
-      230
-    ],
-    "image_target_size": [
-      256,
-      256
-    ],
-    "use_albumentations": true,
-    "random_rotation_angle": 0,
-    "color_jitter_params": {
-      "brightness": 0.3,
-      "contrast": 0.4,
-      "saturation": 0.5,
-      "hue": 0.08
-    },
-    "shortest_image_edge": 256,
-    "crop_fraction": 0.95,
-    "letter_box_transform": false,
-    "model_name": "nvidia/Cosmos-Reason2-2B",
-    "model_type": "qwen",
-    "formalize_language": true,
-    "max_state_dim": 132,
-    "max_action_dim": 132,
-    "max_action_horizon": 40,
-    "use_percentiles": true,
-    "use_mean_std": false,
-    "clip_outliers": true,
-    "apply_sincos_state_encoding": false,
-    "use_relative_action": true,
-    "exclude_state": false,
-    "state_dropout_prob": 0.2
-  }
-}

checkpoint-100/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d79169e2cfc65901c16f75f42ff0d82571426d6925561b7420adbf179f6c70d8
-size 15429

checkpoint-100/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:890eb0b11c27e675df69e1569a5fa68c0065cb8256c758190b462d55aaf86809
-size 15429

checkpoint-100/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fb34403604512eb3b1783993d3e6fb127962411a6ebb9e1200a2e196b7309bff
-size 15429

checkpoint-100/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ae1b50c56b7c9251859e35e555b41e465dabdb50a201df14cdc661e3677c4fa
-size 15429

checkpoint-100/rng_state_4.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8b42408e515c13f7fc0c44888136b9d6e72e660bff2a5986a94f71de2c615ce6
-size 16389

checkpoint-100/rng_state_5.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c94c0950127d3a899facf1fa11c9273caa32c31139417856f34072843d4b49c1
-size 16389

checkpoint-100/rng_state_6.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c3222fc863d3f886167729669d5445370b45ce9b1b75e34d837d08c541a7d9d6
-size 16389

checkpoint-100/rng_state_7.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:38be378534433e9627aa6fc571531bd5807a522b787ef3050a4bd01b7a8f347c
-size 16389

checkpoint-100/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a8487efb2ce2df2abf3e3f1a7b01dc5b7d3b3c177d12aa0e9ef3e40c9b422aab
-size 1465

checkpoint-100/trainer_state.json

@@ -1,94 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.5,
-  "eval_steps": 500,
-  "global_step": 100,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "grad_norm": 0.23940400779247284,
-      "learning_rate": 9e-05,
-      "loss": 1.1936,
-      "step": 10
-    },
-    {
-      "grad_norm": 0.6992996335029602,
-      "learning_rate": 9.944739353007344e-05,
-      "loss": 1.1512,
-      "step": 20
-    },
-    {
-      "grad_norm": 0.2213364690542221,
-      "learning_rate": 9.755282581475769e-05,
-      "loss": 1.1256,
-      "step": 30
-    },
-    {
-      "grad_norm": 0.2311399132013321,
-      "learning_rate": 9.43611409721806e-05,
-      "loss": 1.0988,
-      "step": 40
-    },
-    {
-      "grad_norm": 0.23056164383888245,
-      "learning_rate": 8.995939984474624e-05,
-      "loss": 1.1029,
-      "step": 50
-    },
-    {
-      "grad_norm": 0.28725796937942505,
-      "learning_rate": 8.44676704559283e-05,
-      "loss": 1.102,
-      "step": 60
-    },
-    {
-      "grad_norm": 0.33148351311683655,
-      "learning_rate": 7.803575286758364e-05,
-      "loss": 1.0932,
-      "step": 70
-    },
-    {
-      "grad_norm": 0.1882592737674713,
-      "learning_rate": 7.083909302476453e-05,
-      "loss": 1.0951,
-      "step": 80
-    },
-    {
-      "grad_norm": 0.1874360740184784,
-      "learning_rate": 6.307399704769099e-05,
-      "loss": 1.093,
-      "step": 90
-    },
-    {
-      "grad_norm": 0.20323705673217773,
-      "learning_rate": 5.495227651252315e-05,
-      "loss": 1.0979,
-      "step": 100
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 200,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 9223372036854775807,
-  "save_steps": 50,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 0.0,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-100/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8948bc0acba8971f43e26c05e378b8f61c5f795118c5779a55a4b9bba2bbeb33
-size 7825

checkpoint-100/wandb_config.json

@@ -1 +0,0 @@
-{"project": "groot-finetune", "run_id": "g1_finetune"}

checkpoint-100/zero_to_fp32.py

@@ -1,760 +0,0 @@
-#!/usr/bin/env python
-
-# Copyright (c) Microsoft Corporation.
-# SPDX-License-Identifier: Apache-2.0
-
-# DeepSpeed Team
-
-# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
-# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
-# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
-# application.
-#
-# example:
-#   python zero_to_fp32.py . output_dir/
-#   or
-#   python zero_to_fp32.py . output_dir/ --safe_serialization
-
-import argparse
-import torch
-import glob
-import math
-import os
-import re
-import gc
-import json
-import numpy as np
-from tqdm import tqdm
-from collections import OrderedDict
-from dataclasses import dataclass
-
-# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
-# DeepSpeed data structures it has to be available in the current python environment.
-from deepspeed.utils import logger
-from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
-                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
-                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
-
-
-@dataclass
-class zero_model_state:
-    buffers: dict()
-    param_shapes: dict()
-    shared_params: list
-    ds_version: int
-    frozen_param_shapes: dict()
-    frozen_param_fragments: dict()
-
-
-debug = 0
-
-# load to cpu
-device = torch.device('cpu')
-
-
-def atoi(text):
-    return int(text) if text.isdigit() else text
-
-
-def natural_keys(text):
-    '''
-    alist.sort(key=natural_keys) sorts in human order
-    http://nedbatchelder.com/blog/200712/human_sorting.html
-    (See Toothy's implementation in the comments)
-    '''
-    return [atoi(c) for c in re.split(r'(\d+)', text)]
-
-
-def get_model_state_file(checkpoint_dir, zero_stage):
-    if not os.path.isdir(checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
-
-    # there should be only one file
-    if zero_stage <= 2:
-        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
-    elif zero_stage == 3:
-        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
-
-    if not os.path.exists(file):
-        raise FileNotFoundError(f"can't find model states file at '{file}'")
-
-    return file
-
-
-def get_checkpoint_files(checkpoint_dir, glob_pattern):
-    # XXX: need to test that this simple glob rule works for multi-node setup too
-    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
-
-    if len(ckpt_files) == 0:
-        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
-
-    return ckpt_files
-
-
-def get_optim_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
-
-
-def get_model_state_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
-
-
-def parse_model_states(files):
-    zero_model_states = []
-    for file in files:
-        state_dict = torch.load(file, map_location=device, weights_only=False)
-
-        if BUFFER_NAMES not in state_dict:
-            raise ValueError(f"{file} is not a model state checkpoint")
-        buffer_names = state_dict[BUFFER_NAMES]
-        if debug:
-            print("Found buffers:", buffer_names)
-
-        # recover just the buffers while restoring them to fp32 if they were saved in fp16
-        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
-        param_shapes = state_dict[PARAM_SHAPES]
-
-        # collect parameters that are included in param_shapes
-        param_names = []
-        for s in param_shapes:
-            for name in s.keys():
-                param_names.append(name)
-
-        # update with frozen parameters
-        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
-        if frozen_param_shapes is not None:
-            if debug:
-                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
-            param_names += list(frozen_param_shapes.keys())
-
-        # handle shared params
-        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
-
-        ds_version = state_dict.get(DS_VERSION, None)
-
-        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
-
-        z_model_state = zero_model_state(buffers=buffers,
-                                         param_shapes=param_shapes,
-                                         shared_params=shared_params,
-                                         ds_version=ds_version,
-                                         frozen_param_shapes=frozen_param_shapes,
-                                         frozen_param_fragments=frozen_param_fragments)
-        zero_model_states.append(z_model_state)
-
-    return zero_model_states
-
-
-def parse_optim_states(files, ds_checkpoint_dir):
-    total_files = len(files)
-    state_dicts = []
-    for f in tqdm(files, desc='Loading checkpoint shards'):
-        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
-        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
-        # and also handle the case where it was already removed by another helper script
-        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
-        state_dicts.append(state_dict)
-
-    if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
-        raise ValueError(f"{files[0]} is not a zero checkpoint")
-    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
-    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
-
-    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
-    # parameters can be different from data parallelism for non-expert parameters. So we can just
-    # use the max of the partition_count to get the dp world_size.
-
-    if type(world_size) is list:
-        world_size = max(world_size)
-
-    if world_size != total_files:
-        raise ValueError(
-            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
-            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
-        )
-
-    # the groups are named differently in each stage
-    if zero_stage <= 2:
-        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
-    elif zero_stage == 3:
-        fp32_groups_key = FP32_FLAT_GROUPS
-    else:
-        raise ValueError(f"unknown zero stage {zero_stage}")
-
-    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
-    return zero_stage, world_size, fp32_flat_groups
-
-
-def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
-    """
-    Returns fp32 state_dict reconstructed from ds checkpoint
-
-    Args:
-        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
-
-    """
-    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
-
-    optim_files = get_optim_files(ds_checkpoint_dir)
-    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
-    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
-
-    model_files = get_model_state_files(ds_checkpoint_dir)
-
-    zero_model_states = parse_model_states(model_files)
-    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
-
-    if zero_stage <= 2:
-        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                                          exclude_frozen_parameters)
-    elif zero_stage == 3:
-        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                                          exclude_frozen_parameters)
-
-
-def _zero2_merge_frozen_params(state_dict, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
-
-    if debug:
-        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
-        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        state_dict[name] = frozen_param_fragments[name]
-
-        if debug:
-            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _has_callable(obj, fn):
-    attr = getattr(obj, fn, None)
-    return callable(attr)
-
-
-def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-
-    # Reconstruction protocol:
-    #
-    # XXX: document this
-
-    if debug:
-        for i in range(world_size):
-            for j in range(len(fp32_flat_groups[0])):
-                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
-
-    # XXX: memory usage doubles here (zero2)
-    num_param_groups = len(fp32_flat_groups[0])
-    merged_single_partition_of_fp32_groups = []
-    for i in range(num_param_groups):
-        merged_partitions = [sd[i] for sd in fp32_flat_groups]
-        full_single_fp32_vector = torch.cat(merged_partitions, 0)
-        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
-    avail_numel = sum(
-        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
-
-    if debug:
-        wanted_params = sum([len(shapes) for shapes in param_shapes])
-        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
-        # not asserting if there is a mismatch due to possible padding
-        print(f"Have {avail_numel} numels to process.")
-        print(f"Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    total_numel = 0
-    total_params = 0
-    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
-        offset = 0
-        avail_numel = full_single_fp32_vector.numel()
-        for name, shape in shapes.items():
-
-            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
-            total_numel += unpartitioned_numel
-            total_params += 1
-
-            if debug:
-                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
-            offset += unpartitioned_numel
-
-        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
-        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
-        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
-        # live optimizer object, so we are checking that the numbers are within the right range
-        align_to = 2 * world_size
-
-        def zero2_align(x):
-            return align_to * math.ceil(x / align_to)
-
-        if debug:
-            print(f"original offset={offset}, avail_numel={avail_numel}")
-
-        offset = zero2_align(offset)
-        avail_numel = zero2_align(avail_numel)
-
-        if debug:
-            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
-
-        # Sanity check
-        if offset != avail_numel:
-            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                               exclude_frozen_parameters):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    if not exclude_frozen_parameters:
-        _zero2_merge_frozen_params(state_dict, zero_model_states)
-
-    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def zero3_partitioned_param_info(unpartitioned_numel, world_size):
-    remainder = unpartitioned_numel % world_size
-    padding_numel = (world_size - remainder) if remainder else 0
-    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
-    return partitioned_numel, padding_numel
-
-
-def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    if debug:
-        for i in range(world_size):
-            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
-            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in zero_model_states[0].frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
-        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
-
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-class GatheredTensor:
-    """
-    A pseudo tensor that collects partitioned weights.
-    It is more memory efficient when there are multiple groups.
-    """
-
-    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
-        self.flat_groups = flat_groups
-        self.flat_groups_offset = flat_groups_offset
-        self.offset = offset
-        self.partitioned_numel = partitioned_numel
-        self.shape = shape
-        self.dtype = self.flat_groups[0][0].dtype
-
-    def contiguous(self):
-        """
-        Merge partitioned weights from flat_groups into a single tensor.
-        """
-        end_idx = self.offset + self.partitioned_numel
-        world_size = len(self.flat_groups)
-        pad_flat_param_chunks = []
-
-        for rank_i in range(world_size):
-            # for each rank, we need to collect weights from related group/groups
-            flat_groups_at_rank_i = self.flat_groups[rank_i]
-            start_group_id = None
-            end_group_id = None
-            for group_id in range(len(self.flat_groups_offset)):
-                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
-                    start_group_id = group_id
-                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
-                    end_group_id = group_id
-                    break
-            # collect weights from related group/groups
-            for group_id in range(start_group_id, end_group_id + 1):
-                flat_tensor = flat_groups_at_rank_i[group_id]
-                start_offset = self.offset - self.flat_groups_offset[group_id]
-                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
-                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
-
-        # collect weights from all ranks
-        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
-        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
-        return param
-
-
-def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
-
-    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
-    # param, re-consolidating each param, while dealing with padding if any
-
-    # merge list of dicts, preserving order
-    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
-
-    if debug:
-        for i in range(world_size):
-            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
-
-        wanted_params = len(param_shapes)
-        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
-        # not asserting if there is a mismatch due to possible padding
-        avail_numel = fp32_flat_groups[0].numel() * world_size
-        print(f"Trainable params: Have {avail_numel} numels to process.")
-        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    offset = 0
-    total_numel = 0
-    total_params = 0
-    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
-    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-        total_params += 1
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-        # memory efficient tensor
-        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
-        state_dict[name] = tensor
-        offset += partitioned_numel
-
-    offset *= world_size
-
-    # Sanity check
-    if offset != avail_numel:
-        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                               exclude_frozen_parameters):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    if not exclude_frozen_parameters:
-        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
-
-    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def to_torch_tensor(state_dict, return_empty_tensor=False):
-    """
-    Convert state_dict of GatheredTensor to torch tensor
-    """
-    torch_state_dict = {}
-    converted_tensors = {}
-    for name, tensor in state_dict.items():
-        tensor_id = id(tensor)
-        if tensor_id in converted_tensors:  # shared tensors
-            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
-            torch_state_dict[name] = shared_tensor
-        else:
-            converted_tensors[tensor_id] = name
-            if return_empty_tensor:
-                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
-            else:
-                torch_state_dict[name] = tensor.contiguous()
-    return torch_state_dict
-
-
-def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
-                                             tag=None,
-                                             exclude_frozen_parameters=False,
-                                             lazy_mode=False):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
-    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
-    via a model hub.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder
-        - ``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``
-        - ``exclude_frozen_parameters``: exclude frozen parameters
-        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
-          Convert the pesduo tensor to torch tensor by ``.contiguous()``
-
-    Returns:
-        - pytorch ``state_dict``
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        # do the training and checkpoint saving
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
-        model = model.cpu() # move to cpu
-        model.load_state_dict(state_dict)
-        # submit to model hub or save the model to share with others
-
-    In this example the ``model`` will no longer be usable in the deepspeed context of the same
-    application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
-
-    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
-    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
-    the checkpoint. Or you can load state_dict in lazy mode ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
-        for name, lazy_tensor in state_dict.item():
-            tensor = lazy_tensor.contiguous()  # to cpu
-            print(name, tensor)
-            # del tensor to release memory if it no longer in use
-    """
-    if tag is None:
-        latest_path = os.path.join(checkpoint_dir, 'latest')
-        if os.path.isfile(latest_path):
-            with open(latest_path, 'r') as fd:
-                tag = fd.read().strip()
-        else:
-            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
-
-    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
-
-    if not os.path.isdir(ds_checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
-
-    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
-    if lazy_mode:
-        return state_dict
-    else:
-        return to_torch_tensor(state_dict)
-
-
-def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
-                                               output_dir,
-                                               max_shard_size="5GB",
-                                               safe_serialization=False,
-                                               tag=None,
-                                               exclude_frozen_parameters=False):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
-    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``output_dir``: directory to the pytorch fp32 state_dict output files
-        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
-        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
-        - ``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``
-        - ``exclude_frozen_parameters``: exclude frozen parameters
-    """
-
-    # Dependency pre-check
-    if safe_serialization:
-        try:
-            from safetensors.torch import save_file
-        except ImportError:
-            print('If you want to use `safe_serialization`, please `pip install safetensors`')
-            raise
-    if max_shard_size is not None:
-        try:
-            from huggingface_hub import split_torch_state_dict_into_shards
-        except ImportError:
-            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
-            raise
-
-    # Convert zero checkpoint to state_dict
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
-                                                          tag,
-                                                          exclude_frozen_parameters,
-                                                          lazy_mode=True)
-
-    # Shard the model if it is too big.
-    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
-    if max_shard_size is not None:
-        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
-        # an memory-efficient approach for sharding
-        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
-        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
-                                                              filename_pattern=filename_pattern,
-                                                              max_shard_size=max_shard_size)
-    else:
-        from collections import namedtuple
-        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
-        state_dict_split = StateDictSplit(is_sharded=False,
-                                          filename_to_tensors={weights_name: list(state_dict.keys())})
-
-    # Save the model by shard
-    os.makedirs(output_dir, exist_ok=True)
-    filename_to_tensors = state_dict_split.filename_to_tensors.items()
-    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
-        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
-        shard_state_dict = to_torch_tensor(shard_state_dict)
-        output_path = os.path.join(output_dir, shard_file)
-        if safe_serialization:
-            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
-        else:
-            torch.save(shard_state_dict, output_path)
-        # release the memory of current shard
-        for tensor_name in list(shard_state_dict.keys()):
-            del state_dict[tensor_name]
-            del shard_state_dict[tensor_name]
-        del shard_state_dict
-        gc.collect()
-
-    # Save index if sharded
-    if state_dict_split.is_sharded:
-        index = {
-            "metadata": state_dict_split.metadata,
-            "weight_map": state_dict_split.tensor_to_filename,
-        }
-        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
-        save_index_file = os.path.join(output_dir, save_index_file)
-        with open(save_index_file, "w", encoding="utf-8") as f:
-            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
-            f.write(content)
-
-
-def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
-    """
-    1. Put the provided model to cpu
-    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
-    3. Load it into the provided model
-
-    Args:
-        - ``model``: the model object to update
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``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``
-
-    Returns:
-        - ``model`: modified model
-
-    Make sure you have plenty of CPU memory available before you call this function. If you don't
-    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
-    conveniently placed for you in the checkpoint folder.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
-        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
-        # submit to model hub or save the model to share with others
-
-    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
-    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    """
-    logger.info("Extracting fp32 weights")
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-
-    logger.info("Overwriting model with fp32 weights")
-    model = model.cpu()
-    model.load_state_dict(state_dict, strict=False)
-
-    return model
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("checkpoint_dir",
-                        type=str,
-                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
-    parser.add_argument("output_dir",
-                        type=str,
-                        help="directory to the pytorch fp32 state_dict output files"
-                        "(e.g. path/checkpoint-12-output/)")
-    parser.add_argument(
-        "--max_shard_size",
-        type=str,
-        default="5GB",
-        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
-        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
-        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
-        "without CPU OOM issues.")
-    parser.add_argument(
-        "--safe_serialization",
-        default=False,
-        action='store_true',
-        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
-    parser.add_argument("-t",
-                        "--tag",
-                        type=str,
-                        default=None,
-                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
-    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
-    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
-    args = parser.parse_args()
-
-    debug = args.debug
-
-    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
-                                               args.output_dir,
-                                               max_shard_size=args.max_shard_size,
-                                               safe_serialization=args.safe_serialization,
-                                               tag=args.tag,
-                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

checkpoint-150/config.json

@@ -1,88 +0,0 @@
-{
-  "action_horizon": 40,
-  "add_pos_embed": true,
-  "apply_sincos_state_encoding": false,
-  "architectures": [
-    "Gr00tN1d7"
-  ],
-  "attn_dropout": 0.2,
-  "attn_implementation": null,
-  "backbone_embedding_dim": 2048,
-  "backbone_trainable_params_fp32": true,
-  "color_jitter_params": {
-    "brightness": 0.3,
-    "contrast": 0.4,
-    "hue": 0.08,
-    "saturation": 0.5
-  },
-  "crop_fraction": 0.95,
-  "diffusion_model_cfg": {
-    "attention_head_dim": 48,
-    "dropout": 0.2,
-    "final_dropout": true,
-    "interleave_self_attention": true,
-    "norm_type": "ada_norm",
-    "num_attention_heads": 32,
-    "num_layers": 32,
-    "output_dim": 1024,
-    "positional_embeddings": null
-  },
-  "dtype": "bfloat16",
-  "exclude_state": false,
-  "formalize_language": true,
-  "hidden_size": 1024,
-  "image_crop_size": [
-    230,
-    230
-  ],
-  "image_target_size": [
-    256,
-    256
-  ],
-  "letter_box_transform": false,
-  "load_bf16": false,
-  "max_action_dim": 132,
-  "max_num_embodiments": 32,
-  "max_seq_len": 1024,
-  "max_state_dim": 132,
-  "model_dtype": "bfloat16",
-  "model_name": "nvidia/Cosmos-Reason2-2B",
-  "model_type": "Gr00tN1d7",
-  "noise_beta_alpha": 1.5,
-  "noise_beta_beta": 1.0,
-  "noise_s": 0.999,
-  "num_inference_timesteps": 4,
-  "num_timestep_buckets": 1000,
-  "random_history_crop": true,
-  "random_rotation_angle": 0,
-  "reproject_vision": false,
-  "rtc_ramp_rate": 6.0,
-  "select_layer": 16,
-  "shortest_image_edge": 256,
-  "state_dropout_prob": 0.2,
-  "state_gaussian_noise_std": 0.0,
-  "transformers_version": "4.57.3",
-  "tune_diffusion_model": true,
-  "tune_linear": true,
-  "tune_llm": false,
-  "tune_projector": true,
-  "tune_top_llm_layers": 0,
-  "tune_visual": false,
-  "tune_vlln": true,
-  "use_albumentations": true,
-  "use_alternate_vl_dit": true,
-  "use_flash_attention": true,
-  "use_future_tokens": false,
-  "use_mean_std": false,
-  "use_percentiles": true,
-  "use_vl_self_attention": true,
-  "use_vlln": true,
-  "vl_self_attention_cfg": {
-    "attention_head_dim": 64,
-    "dropout": 0.2,
-    "final_dropout": true,
-    "num_attention_heads": 32,
-    "num_layers": 4,
-    "positional_embeddings": null
-  }
-}

checkpoint-150/embodiment_id.json

@@ -1,57 +0,0 @@
-{
-  "robocasa_panda_omron": 13,
-  "oxe_droid": 17,
-  "oxe_fractal": 18,
-  "oxe_language_table": 19,
-  "oxe_bridge": 20,
-  "unknown": 22,
-  "gr1_unified": 20,
-  "agibot": 26,
-  "sim_behavior_r1_pro": 23,
-  "xdof": 24,
-  "xdof_oss_data": 25,
-  "unitree_g1_full_body_with_waist_height_nav_cmd": 25,
-  "real_r1_pro_sharpa": 27,
-  "real_r1_pro_sharpa_add_view": 27,
-  "real_r1_pro_sharpa_relative_arm_joint": 26,
-  "real_r1_pro_sharpa_delta_eef": 26,
-  "real_r1_pro_sharpa_absolute_eef": 26,
-  "real_r1_pro_sharpa_meanstd": 26,
-  "real_r1_pro_sharpa_relative_eef": 26,
-  "real_r1_pro_sharpa_relative_eef_add_view": 26,
-  "real_r1_pro_sharpa_relative_eef_relative_hand": 26,
-  "real_r1_pro_sharpa_relative_eef_human": 26,
-  "real_r1_pro_sharpa_relative_eef_human_add_view": 26,
-  "real_r1_pro_sharpa_relative_eef_human_relative_hand": 26,
-  "real_r1_pro_sharpa_relative_eef_egodex": 26,
-  "real_r1_pro_sharpa_relative_eef_egodex_relative_hand": 26,
-  "real_r1_pro_sharpa_relative_eef_egodex_wrist_only": 26,
-  "real_r1_pro_sharpa_relative_eef_maxinsights": 26,
-  "real_r1_pro_sharpa_relative_eef_maxinsights_relative_hand": 26,
-  "real_r1_pro_sharpa_relative_eef_mecka": 26,
-  "real_r1_pro_sharpa_relative_eef_mecka_relative_hand": 26,
-  "real_g1_relative_eef_absolute_joints": 25,
-  "real_g1_relative_eef_absolute_joints_wrist_cam": 25,
-  "real_g1_relative_eef_relative_joints": 25,
-  "real_r1_pro_sharpa_relative_eef_relative_hand_relative_joint": 26,
-  "real_r1_pro_sharpa_relative_joint": 29,
-  "oxe_droid_relative_eef_relative_joint": 24,
-  "oxe_droid_relative_eef_relative_joint_swapped": 24,
-  "oxe_droid_relative_eef_relative_joint_upweight_z": 24,
-  "oxe_droid_relative_eef_relative_joint_upweight_z_swapped": 24,
-  "oxe_droid_relative_eef_relative_joint_3view": 24,
-  "oxe_droid_relative_eef_relative_joint_3view_swapped": 24,
-  "oxe_droid_relative_eef": 24,
-  "oxe_droid_joint_position_relative": 24,
-  "xdof_relative_eef_relative_joint": 27,
-  "xdof_relative_eef_relative_joint_subtask": 27,
-  "xdof_relative_eef": 27,
-  "xdof_relative_joint": 28,
-  "simpler_env_google": 0,
-  "simpler_env_widowx": 1,
-  "libero_sim": 2,
-  "droid_sim": 3,
-  "unitree_g1_sonic": 11,
-  "new_embodiment": 10,
-  "robocasa_gr1_tabletop": 10
-}

checkpoint-150/experiment_cfg/conf.yaml

@@ -1,251 +0,0 @@
-load_config_path: null
-model:
-  model_type: Gr00tN1d7
-  model_dtype: bfloat16
-  model_name: nvidia/Cosmos-Reason2-2B
-  backbone_model_type: qwen
-  model_revision: null
-  tune_top_llm_layers: 0
-  backbone_embedding_dim: 2048
-  tune_llm: false
-  tune_visual: false
-  select_layer: 12
-  reproject_vision: false
-  use_flash_attention: true
-  load_bf16: false
-  backbone_trainable_params_fp32: true
-  image_crop_size:
-  - 230
-  - 230
-  image_target_size:
-  - 256
-  - 256
-  shortest_image_edge: null
-  crop_fraction: null
-  random_rotation_angle: null
-  color_jitter_params:
-    brightness: 0.3
-    contrast: 0.4
-    saturation: 0.5
-    hue: 0.08
-  use_albumentations_transforms: true
-  extra_augmentation_config: null
-  formalize_language: true
-  apply_sincos_state_encoding: false
-  use_percentiles: true
-  use_relative_action: true
-  max_state_dim: 132
-  max_action_dim: 132
-  action_horizon: 40
-  hidden_size: 1024
-  input_embedding_dim: 1536
-  state_history_length: 1
-  add_pos_embed: true
-  attn_dropout: 0.2
-  use_vlln: true
-  max_seq_len: 1024
-  use_alternate_vl_dit: true
-  attend_text_every_n_blocks: 2
-  diffusion_model_cfg:
-    positional_embeddings: null
-    num_layers: 16
-    num_attention_heads: 32
-    attention_head_dim: 48
-    norm_type: ada_norm
-    dropout: 0.2
-    final_dropout: true
-    output_dim: 1024
-    interleave_self_attention: true
-  num_inference_timesteps: 4
-  noise_beta_alpha: 1.5
-  noise_beta_beta: 1.0
-  noise_s: 0.999
-  num_timestep_buckets: 1000
-  tune_projector: true
-  tune_diffusion_model: true
-  tune_vlln: true
-  state_dropout_prob: 0.2
-  exclude_state: false
-  use_mean_std: false
-  max_num_embodiments: 32
-data:
-  datasets:
-  - dataset_paths:
-    - /home/ubuntu/groot-files/dataset
-    embodiment_tag: unitree_g1_sonic
-    mix_ratio: 1.0
-    dataset_type: physical_embodiment
-    val_dataset_path: null
-  modality_configs:
-    unitree_g1_sonic:
-      video:
-        delta_indices:
-        - 0
-        modality_keys:
-        - ego_view
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs: null
-      state:
-        delta_indices:
-        - 0
-        modality_keys:
-        - left_leg
-        - right_leg
-        - waist
-        - left_arm
-        - right_arm
-        - left_hand
-        - right_hand
-        - projected_gravity
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs: null
-      action:
-        delta_indices:
-        - 0
-        - 1
-        - 2
-        - 3
-        - 4
-        - 5
-        - 6
-        - 7
-        - 8
-        - 9
-        - 10
-        - 11
-        - 12
-        - 13
-        - 14
-        - 15
-        - 16
-        - 17
-        - 18
-        - 19
-        - 20
-        - 21
-        - 22
-        - 23
-        - 24
-        - 25
-        - 26
-        - 27
-        - 28
-        - 29
-        - 30
-        - 31
-        - 32
-        - 33
-        - 34
-        - 35
-        - 36
-        - 37
-        - 38
-        - 39
-        modality_keys:
-        - motion_token
-        - left_hand_joints
-        - right_hand_joints
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs:
-        - rep: ABSOLUTE
-          type: NON_EEF
-          format: DEFAULT
-          state_key: null
-        - rep: ABSOLUTE
-          type: NON_EEF
-          format: DEFAULT
-          state_key: null
-        - rep: ABSOLUTE
-          type: NON_EEF
-          format: DEFAULT
-          state_key: null
-      language:
-        delta_indices:
-        - 0
-        modality_keys:
-        - annotation.human.task_description
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs: null
-  download_cache: false
-  shard_size: 1024
-  episode_sampling_rate: 0.1
-  num_shards_per_epoch: 100000
-  override_pretraining_statistics: true
-  mode: single_turn
-  random_chop: 0.0
-  mock_dataset_mode: false
-  shuffle: true
-  seed: 42
-  multiprocessing_context: fork
-  allow_padding: false
-  subsample_ratio: 1.0
-  image_crop_size:
-  - 244
-  - 244
-  image_target_size:
-  - 224
-  - 224
-  video_backend: torchcodec
-training:
-  output_dir: /home/ubuntu/groot-files/checkpoints/g1_finetune
-  experiment_name: null
-  max_steps: 200
-  global_batch_size: 32
-  batch_size: null
-  gradient_accumulation_steps: 1
-  learning_rate: 0.0001
-  lr_scheduler_type: cosine
-  weight_decay: 1.0e-05
-  warmup_ratio: 0.05
-  warmup_steps: 0
-  max_grad_norm: 1.0
-  optim: adamw_torch
-  start_from_checkpoint: nvidia/GR00T-N1.7-3B
-  skip_weight_loading: false
-  tf32: true
-  fp16: false
-  bf16: true
-  eval_bf16: true
-  logging_steps: 10
-  save_steps: 50
-  save_total_limit: 10
-  save_vl_model: false
-  save_only_model: false
-  upload_checkpoints: false
-  upload_every: 1000
-  upload_last_n_checkpoints: 5
-  max_concurrent_uploads: 2
-  eval_strategy: 'no'
-  eval_steps: 500
-  eval_set_split_ratio: 0.1
-  eval_batch_size: 2
-  save_best_eval_metric_name: ''
-  save_best_eval_metric_greater_is_better: true
-  deepspeed_stage: 2
-  gradient_checkpointing: false
-  transformers_trust_remote_code: true
-  transformers_local_files_only: false
-  transformers_cache_dir: null
-  transformers_access_token: null
-  use_ddp: false
-  ddp_bucket_cap_mb: 100
-  num_gpus: 4
-  dataloader_num_workers: 6
-  remove_unused_columns: false
-  use_wandb: true
-  wandb_project: groot-finetune
-  enable_profiling: false
-  max_retries: 3
-  assert_loss_less_than: null
-  add_rl_callback: false
-  enable_open_loop_eval: false
-  open_loop_eval_traj_ids:
-  - 0
-  open_loop_eval_steps_per_traj: 100
-  open_loop_eval_plot_indices: null
-max_steps: 200
-save_steps: 50

checkpoint-150/experiment_cfg/config.yaml

@@ -1,277 +0,0 @@
-!!python/object:gr00t.configs.base_config.Config
-data: !!python/object:gr00t.configs.data.data_config.DataConfig
-  allow_padding: false
-  datasets:
-  - !!python/object:gr00t.configs.data.data_config.SingleDatasetConfig
-    dataset_paths:
-    - /home/ubuntu/groot-files/dataset
-    dataset_type: physical_embodiment
-    embodiment_tag: unitree_g1_sonic
-    mix_ratio: 1.0
-    val_dataset_path: null
-  download_cache: false
-  episode_sampling_rate: 0.1
-  image_crop_size:
-  - 244
-  - 244
-  image_target_size:
-  - 224
-  - 224
-  mock_dataset_mode: false
-  modality_configs:
-    unitree_g1_sonic:
-      action: !!python/object:gr00t.data.types.ModalityConfig
-        action_configs:
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: &id001 !!python/object/apply:gr00t.data.types.ActionFormat
-          - default
-          rep: &id002 !!python/object/apply:gr00t.data.types.ActionRepresentation
-          - absolute
-          state_key: null
-          type: &id003 !!python/object/apply:gr00t.data.types.ActionType
-          - non_eef
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: *id001
-          rep: *id002
-          state_key: null
-          type: *id003
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: *id001
-          rep: *id002
-          state_key: null
-          type: *id003
-        delta_indices:
-        - 0
-        - 1
-        - 2
-        - 3
-        - 4
-        - 5
-        - 6
-        - 7
-        - 8
-        - 9
-        - 10
-        - 11
-        - 12
-        - 13
-        - 14
-        - 15
-        - 16
-        - 17
-        - 18
-        - 19
-        - 20
-        - 21
-        - 22
-        - 23
-        - 24
-        - 25
-        - 26
-        - 27
-        - 28
-        - 29
-        - 30
-        - 31
-        - 32
-        - 33
-        - 34
-        - 35
-        - 36
-        - 37
-        - 38
-        - 39
-        mean_std_embedding_keys: null
-        modality_keys:
-        - motion_token
-        - left_hand_joints
-        - right_hand_joints
-        sin_cos_embedding_keys: null
-      language: !!python/object:gr00t.data.types.ModalityConfig
-        action_configs: null
-        delta_indices:
-        - 0
-        mean_std_embedding_keys: null
-        modality_keys:
-        - annotation.human.task_description
-        sin_cos_embedding_keys: null
-      state: !!python/object:gr00t.data.types.ModalityConfig
-        action_configs: null
-        delta_indices:
-        - 0
-        mean_std_embedding_keys: null
-        modality_keys:
-        - left_leg
-        - right_leg
-        - waist
-        - left_arm
-        - right_arm
-        - left_hand
-        - right_hand
-        - projected_gravity
-        sin_cos_embedding_keys: null
-      video: !!python/object:gr00t.data.types.ModalityConfig
-        action_configs: null
-        delta_indices:
-        - 0
-        mean_std_embedding_keys: null
-        modality_keys:
-        - ego_view
-        sin_cos_embedding_keys: null
-  mode: single_turn
-  multiprocessing_context: fork
-  num_shards_per_epoch: 100000
-  override_pretraining_statistics: true
-  random_chop: 0.0
-  seed: 42
-  shard_size: 1024
-  shuffle: true
-  subsample_ratio: 1.0
-  video_backend: torchcodec
-load_config_path: null
-model: !!python/object:gr00t.configs.model.gr00t_n1d7.Gr00tN1d7Config
-  _attn_implementation_internal: null
-  _commit_hash: null
-  _name_or_path: ''
-  _output_attentions: false
-  add_cross_attention: false
-  architectures: null
-  backbone_trainable_params_fp32: true
-  bad_words_ids: null
-  begin_suppress_tokens: null
-  bos_token_id: null
-  chunk_size_feed_forward: 0
-  color_jitter_params:
-    brightness: 0.3
-    contrast: 0.4
-    hue: 0.08
-    saturation: 0.5
-  cross_attention_hidden_size: null
-  decoder_start_token_id: null
-  diffusion_model_cfg:
-    attention_head_dim: 48
-    dropout: 0.2
-    final_dropout: true
-    interleave_self_attention: true
-    norm_type: ada_norm
-    num_attention_heads: 32
-    num_layers: 16
-    output_dim: 1024
-    positional_embeddings: null
-  diversity_penalty: 0.0
-  do_sample: false
-  dtype: null
-  early_stopping: false
-  encoder_no_repeat_ngram_size: 0
-  eos_token_id: null
-  exponential_decay_length_penalty: null
-  extra_augmentation_config: null
-  finetuning_task: null
-  forced_bos_token_id: null
-  forced_eos_token_id: null
-  id2label:
-    0: LABEL_0
-    1: LABEL_1
-  is_decoder: false
-  is_encoder_decoder: false
-  label2id:
-    LABEL_0: 0
-    LABEL_1: 1
-  length_penalty: 1.0
-  load_bf16: false
-  max_length: 20
-  min_length: 0
-  model_name: nvidia/Cosmos-Reason2-2B
-  no_repeat_ngram_size: 0
-  num_beam_groups: 1
-  num_beams: 1
-  num_return_sequences: 1
-  output_hidden_states: false
-  output_scores: false
-  pad_token_id: null
-  prefix: null
-  problem_type: null
-  pruned_heads: {}
-  random_rotation_angle: null
-  remove_invalid_values: false
-  repetition_penalty: 1.0
-  reproject_vision: false
-  return_dict: true
-  return_dict_in_generate: false
-  sep_token_id: null
-  state_dropout_prob: 0.2
-  suppress_tokens: null
-  task_specific_params: null
-  temperature: 1.0
-  tf_legacy_loss: false
-  tie_encoder_decoder: false
-  tie_word_embeddings: true
-  tokenizer_class: null
-  top_k: 50
-  top_p: 1.0
-  torchscript: false
-  transformers_version: null
-  tune_diffusion_model: true
-  tune_llm: false
-  tune_projector: true
-  tune_visual: false
-  typical_p: 1.0
-  use_bfloat16: false
-  use_relative_action: true
-training: !!python/object:gr00t.configs.training.training_config.TrainingConfig
-  add_rl_callback: false
-  assert_loss_less_than: null
-  batch_size: null
-  bf16: true
-  dataloader_num_workers: 6
-  ddp_bucket_cap_mb: 100
-  deepspeed_stage: 2
-  enable_open_loop_eval: false
-  enable_profiling: false
-  eval_batch_size: 2
-  eval_bf16: true
-  eval_set_split_ratio: 0.1
-  eval_steps: 500
-  eval_strategy: 'no'
-  experiment_name: null
-  fp16: false
-  global_batch_size: 32
-  gradient_accumulation_steps: 1
-  gradient_checkpointing: false
-  learning_rate: 0.0001
-  logging_steps: 10
-  lr_scheduler_type: cosine
-  max_concurrent_uploads: 2
-  max_grad_norm: 1.0
-  max_retries: 3
-  max_steps: 200
-  num_gpus: 4
-  open_loop_eval_plot_indices: null
-  open_loop_eval_steps_per_traj: 100
-  open_loop_eval_traj_ids:
-  - 0
-  optim: adamw_torch
-  output_dir: /home/ubuntu/groot-files/checkpoints/g1_finetune
-  remove_unused_columns: false
-  save_best_eval_metric_greater_is_better: true
-  save_best_eval_metric_name: ''
-  save_only_model: false
-  save_steps: 50
-  save_total_limit: 10
-  save_vl_model: false
-  skip_weight_loading: false
-  start_from_checkpoint: nvidia/GR00T-N1.7-3B
-  tf32: true
-  transformers_access_token: null
-  transformers_cache_dir: null
-  transformers_local_files_only: false
-  transformers_trust_remote_code: true
-  upload_checkpoints: false
-  upload_every: 1000
-  upload_last_n_checkpoints: 5
-  use_ddp: false
-  use_wandb: true
-  wandb_project: groot-finetune
-  warmup_ratio: 0.05
-  warmup_steps: 0
-  weight_decay: 1.0e-05

checkpoint-150/experiment_cfg/dataset_statistics.json

@@ -1,907 +0,0 @@
-{
-  "unitree_g1_sonic": {
-    "state": {
-      "left_leg": {
-        "min": [
-          -0.4857776165008545,
-          -0.24391146004199982,
-          -0.8776780366897583,
-          0.03597185015678406,
-          -0.4930363595485687,
-          -0.20340518653392792
-        ],
-        "max": [
-          0.3237466514110565,
-          0.31727835536003113,
-          0.7570706605911255,
-          0.8986315131187439,
-          0.1892659068107605,
-          0.15561887621879578
-        ],
-        "mean": [
-          0.038367897272109985,
-          0.017137423157691956,
-          0.10202965885400772,
-          0.21319514513015747,
-          -0.20034761726856232,
-          -0.009860903024673462
-        ],
-        "std": [
-          0.12473291903734207,
-          0.0657326877117157,
-          0.16789446771144867,
-          0.0855027362704277,
-          0.05454540252685547,
-          0.043583426624536514
-        ],
-        "q01": [
-          -0.3429580569267273,
-          -0.14271177425980566,
-          -0.41709126979112626,
-          0.12328944355249405,
-          -0.2934864178299904,
-          -0.11147186532616615
-        ],
-        "q99": [
-          0.18860293924808502,
-          0.17139848843216907,
-          0.4404219493269922,
-          0.5360466212034226,
-          -0.019520661234855623,
-          0.09359118081629283
-        ]
-      },
-      "right_leg": {
-        "min": [
-          -0.5335952043533325,
-          -0.350761741399765,
-          -1.3307929039001465,
-          0.07445771992206573,
-          -0.6092288494110107,
-          -0.1984633058309555
-        ],
-        "max": [
-          0.25397607684135437,
-          0.15654273331165314,
-          0.24837948381900787,
-          0.9999935626983643,
-          0.1089707612991333,
-          0.17701147496700287
-        ],
-        "mean": [
-          0.05046115070581436,
-          -0.023679343983530998,
-          -0.213065966963768,
-          0.20844903588294983,
-          -0.19808240234851837,
-          -0.0055496226996183395
-        ],
-        "std": [
-          0.07887373864650726,
-          0.06217808276414871,
-          0.18437089025974274,
-          0.10042016953229904,
-          0.06798264384269714,
-          0.04407079145312309
-        ],
-        "q01": [
-          -0.193911362439394,
-          -0.1981988400220871,
-          -0.90549436211586,
-          0.127213454246521,
-          -0.4343456655740738,
-          -0.11320190876722336
-        ],
-        "q99": [
-          0.1967100210487844,
-          0.11513377726078033,
-          0.15384408906102207,
-          0.7395615458488474,
-          -0.05514147877693175,
-          0.08568341806530994
-        ]
-      },
-      "waist": {
-        "min": [
-          -0.3889274299144745,
-          -0.3032904267311096,
-          -0.04627600684762001
-        ],
-        "max": [
-          0.4404728412628174,
-          0.11908156424760818,
-          0.05046159774065018
-        ],
-        "mean": [
-          0.1003476083278656,
-          -0.03575156629085541,
-          -0.0004057084152009338
-        ],
-        "std": [
-          0.11155267059803009,
-          0.044356729835271835,
-          0.007639772724360228
-        ],
-        "q01": [
-          -0.09896008186042309,
-          -0.16525592356920243,
-          -0.019172759167850016
-        ],
-        "q99": [
-          0.3729535743594171,
-          0.04077914115041498,
-          0.024438940081745388
-        ]
-      },
-      "left_arm": {
-        "min": [
-          -0.2003283053636551,
-          0.09816279262304306,
-          -0.5412195920944214,
-          0.7723593711853027,
-          -0.7412483096122742,
-          -0.09287774562835693,
-          -0.31815722584724426
-        ],
-        "max": [
-          0.4134317934513092,
-          0.38915175199508667,
-          0.3470511734485626,
-          1.363792896270752,
-          0.38266828656196594,
-          0.5152138471603394,
-          0.42312705516815186
-        ],
-        "mean": [
-          0.17467822134494781,
-          0.20962199568748474,
-          0.03295444697141647,
-          1.0894439220428467,
-          -0.11893314123153687,
-          0.20652393996715546,
-          0.01763514056801796
-        ],
-        "std": [
-          0.08956529945135117,
-          0.03943527489900589,
-          0.09209521114826202,
-          0.07066802680492401,
-          0.19965490698814392,
-          0.11541580408811569,
-          0.10361754149198532
-        ],
-        "q01": [
-          -0.06361526139080524,
-          0.1356973797082901,
-          -0.1961050637066364,
-          0.9089213967323303,
-          -0.5769511580467224,
-          -0.03977684192359447,
-          -0.22587568387389184
-        ],
-        "q99": [
-          0.3310546398162843,
-          0.31673349142074597,
-          0.2289490304887296,
-          1.2593449354171753,
-          0.2899013936519628,
-          0.46442466974258423,
-          0.2727669641375545
-        ]
-      },
-      "right_arm": {
-        "min": [
-          -0.9788835048675537,
-          -0.7953690886497498,
-          -0.49778875708580017,
-          -0.7156979441642761,
-          -0.9786917567253113,
-          -0.1273084282875061,
-          -0.9962846040725708
-        ],
-        "max": [
-          0.3628104329109192,
-          0.08640626072883606,
-          0.8718883395195007,
-          1.3758729696273804,
-          1.0651459693908691,
-          0.6638182401657104,
-          0.9581388235092163
-        ],
-        "mean": [
-          -0.14295516908168793,
-          -0.20207007229328156,
-          0.164081871509552,
-          0.32978397607803345,
-          0.15659268200397491,
-          0.21257737278938293,
-          0.0897224023938179
-        ],
-        "std": [
-          0.2832476496696472,
-          0.07377105951309204,
-          0.18590903282165527,
-          0.6193384528160095,
-          0.20538125932216644,
-          0.12802571058273315,
-          0.21542473137378693
-        ],
-        "q01": [
-          -0.7704071193933487,
-          -0.376973994076252,
-          -0.19678157344460487,
-          -0.5173931628465652,
-          -0.39670541584491725,
-          -0.03838966768234967,
-          -0.3572006195783615
-        ],
-        "q99": [
-          0.24905617535114288,
-          0.0024351945263335014,
-          0.586448073387146,
-          1.304707604646683,
-          0.5929710775613787,
-          0.5161845684051514,
-          0.6641693621873858
-        ]
-      },
-      "left_hand": {
-        "min": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "max": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "mean": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "std": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q01": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q99": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ]
-      },
-      "right_hand": {
-        "min": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "max": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "mean": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "std": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q01": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q99": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ]
-      },
-      "projected_gravity": {
-        "min": [
-          -0.12354099005460739,
-          -0.13017292320728302,
-          -1.0
-        ],
-        "max": [
-          0.22223307192325592,
-          0.10705921798944473,
-          -0.9749471545219421
-        ],
-        "mean": [
-          -0.01818661577999592,
-          0.0029902660753577948,
-          -0.9988934993743896
-        ],
-        "std": [
-          0.03578517585992813,
-          0.032206468284130096,
-          0.0014198371209307285
-        ],
-        "q01": [
-          -0.09425989575684071,
-          -0.08990333564579486,
-          -0.9999815225601196
-        ],
-        "q99": [
-          0.06742736026644708,
-          0.06235775817185641,
-          -0.9940253734588623
-        ]
-      }
-    },
-    "action": {
-      "motion_token": {
-        "min": [
-          -0.3125,
-          -0.5,
-          -0.5,
-          -0.4375,
-          -0.625,
-          -0.375,
-          -0.25,
-          -0.0625,
-          -0.4375,
-          -0.6875,
-          -0.375,
-          -0.375,
-          -0.3125,
-          -0.375,
-          -0.6875,
-          -0.25,
-          -0.375,
-          -0.25,
-          -0.375,
-          -0.5,
-          -0.5,
-          -0.5,
-          -0.625,
-          -0.5,
-          -0.375,
-          -0.5625,
-          -0.125,
-          -0.5,
-          -0.3125,
-          -0.3125,
-          -0.125,
-          -0.375,
-          0.0625,
-          -0.1875,
-          -0.1875,
-          -0.5625,
-          -0.6875,
-          -0.6875,
-          -0.125,
-          -0.125,
-          -0.4375,
-          -0.5625,
-          -0.3125,
-          -0.375,
-          -0.5,
-          -0.4375,
-          -0.125,
-          -0.3125,
-          -0.5,
-          -0.25,
-          -0.375,
-          -0.625,
-          -0.0625,
-          -0.4375,
-          -0.0625,
-          -0.4375,
-          -0.5,
-          0.0,
-          -0.25,
-          -0.5,
-          -0.375,
-          -0.1875,
-          0.0,
-          -0.5
-        ],
-        "max": [
-          0.125,
-          0.25,
-          0.25,
-          0.125,
-          0.1875,
-          0.1875,
-          0.5,
-          0.4375,
-          0.25,
-          0.125,
-          0.1875,
-          0.0625,
-          0.125,
-          0.3125,
-          -0.0625,
-          0.1875,
-          0.25,
-          0.25,
-          0.125,
-          0.0625,
-          0.3125,
-          0.125,
-          0.25,
-          0.25,
-          0.3125,
-          0.125,
-          0.375,
-          0.1875,
-          0.375,
-          0.375,
-          0.375,
-          0.25,
-          0.4375,
-          0.5,
-          0.5,
-          0.5625,
-          0.25,
-          -0.0625,
-          0.3125,
-          0.4375,
-          0.125,
-          0.4375,
-          0.4375,
-          0.375,
-          -0.0625,
-          0.1875,
-          0.5625,
-          0.1875,
-          0.3125,
-          0.1875,
-          0.25,
-          0.1875,
-          0.375,
-          0.3125,
-          0.5625,
-          0.1875,
-          0.4375,
-          0.5625,
-          0.1875,
-          0.375,
-          0.3125,
-          0.4375,
-          0.5625,
-          0.0
-        ],
-        "mean": [
-          -0.05732722207903862,
-          -0.12596048414707184,
-          -0.015900524333119392,
-          -0.16434414684772491,
-          -0.18957528471946716,
-          -0.08797170221805573,
-          0.2548595666885376,
-          0.19856274127960205,
-          -0.025066815316677094,
-          -0.21372610330581665,
-          -0.10314688086509705,
-          -0.21981850266456604,
-          -0.12050355225801468,
-          -0.08165144175291061,
-          -0.38714757561683655,
-          -8.805885590845719e-05,
-          -0.049404650926589966,
-          -0.055493421852588654,
-          -0.09600593894720078,
-          -0.2977478802204132,
-          -0.029102997854351997,
-          -0.2329292893409729,
-          -0.19594638049602509,
-          -0.23360289633274078,
-          -0.095408596098423,
-          -0.17069709300994873,
-          0.1292250156402588,
-          -0.2315811812877655,
-          0.07302621006965637,
-          0.06577451527118683,
-          0.1414906084537506,
-          -0.11845822632312775,
-          0.2995853126049042,
-          0.17635828256607056,
-          0.14573286473751068,
-          0.0782189592719078,
-          -0.1727832704782486,
-          -0.3186105489730835,
-          0.11981905251741409,
-          0.13200204074382782,
-          -0.08226785063743591,
-          -0.09514441341161728,
-          0.060834143310785294,
-          -0.006165935657918453,
-          -0.3161884844303131,
-          -0.02333650551736355,
-          0.21719853579998016,
-          -0.10866008698940277,
-          -0.01649424061179161,
-          -0.007006580010056496,
-          -0.06802137941122055,
-          -0.14377468824386597,
-          0.21333755552768707,
-          0.015348567627370358,
-          0.22719819843769073,
-          -0.1495230346918106,
-          0.030986731871962547,
-          0.296153724193573,
-          -0.023153124377131462,
-          -0.1389232873916626,
-          0.035359714180231094,
-          0.10143018513917923,
-          0.30849015712738037,
-          -0.22524820268154144
-        ],
-        "std": [
-          0.06542618572711945,
-          0.09994574636220932,
-          0.07207678258419037,
-          0.08702709525823593,
-          0.17209544777870178,
-          0.0581701286137104,
-          0.09559116512537003,
-          0.07802454382181168,
-          0.13620688021183014,
-          0.1569388061761856,
-          0.0967717096209526,
-          0.0680033266544342,
-          0.05837923660874367,
-          0.11557621508836746,
-          0.11890240013599396,
-          0.08077684044837952,
-          0.06398067623376846,
-          0.06826013326644897,
-          0.09755037724971771,
-          0.10724268853664398,
-          0.1992810219526291,
-          0.12710419297218323,
-          0.21719561517238617,
-          0.14369657635688782,
-          0.08655858784914017,
-          0.11142221838235855,
-          0.057688891887664795,
-          0.18031662702560425,
-          0.0692613422870636,
-          0.16206243634223938,
-          0.11068906635046005,
-          0.06650221347808838,
-          0.06952458620071411,
-          0.10304083675146103,
-          0.12724509835243225,
-          0.3227654695510864,
-          0.14636477828025818,
-          0.08603093028068542,
-          0.08780314773321152,
-          0.06147885322570801,
-          0.07425742596387863,
-          0.27255958318710327,
-          0.13721545040607452,
-          0.10124049335718155,
-          0.06286311149597168,
-          0.0642034038901329,
-          0.08693595230579376,
-          0.06350599974393845,
-          0.11969305574893951,
-          0.06820058822631836,
-          0.09139743447303772,
-          0.1545047014951706,
-          0.06951460987329483,
-          0.08810964971780777,
-          0.0868336483836174,
-          0.0749349296092987,
-          0.09778603166341782,
-          0.11456362158060074,
-          0.06560879200696945,
-          0.2043108344078064,
-          0.07238639891147614,
-          0.0965481698513031,
-          0.11412639170885086,
-          0.11945699900388718
-        ],
-        "q01": [
-          -0.1875,
-          -0.375,
-          -0.1875,
-          -0.375,
-          -0.5625,
-          -0.1875,
-          0.0625,
-          0.0,
-          -0.3125,
-          -0.625,
-          -0.3125,
-          -0.3125,
-          -0.25,
-          -0.3125,
-          -0.625,
-          -0.1875,
-          -0.25,
-          -0.1875,
-          -0.3125,
-          -0.5,
-          -0.375,
-          -0.4375,
-          -0.5625,
-          -0.4375,
-          -0.3125,
-          -0.5,
-          -0.0625,
-          -0.5,
-          -0.0625,
-          -0.1875,
-          -0.0625,
-          -0.25,
-          0.125,
-          -0.0625,
-          -0.0625,
-          -0.5,
-          -0.5625,
-          -0.5625,
-          -0.0625,
-          0.0,
-          -0.25,
-          -0.5625,
-          -0.1875,
-          -0.25,
-          -0.4375,
-          -0.1875,
-          0.0625,
-          -0.25,
-          -0.375,
-          -0.1875,
-          -0.3125,
-          -0.5,
-          0.0625,
-          -0.1875,
-          0.0625,
-          -0.375,
-          -0.375,
-          0.0625,
-          -0.1875,
-          -0.4375,
-          -0.1875,
-          -0.0625,
-          0.125,
-          -0.4375
-        ],
-        "q99": [
-          0.0625,
-          0.0625,
-          0.1875,
-          0.0,
-          0.125,
-          0.0625,
-          0.375,
-          0.375,
-          0.1875,
-          0.0625,
-          0.0625,
-          -0.0625,
-          0.0625,
-          0.1875,
-          -0.125,
-          0.125,
-          0.125,
-          0.125,
-          0.0625,
-          -0.0625,
-          0.25,
-          0.0,
-          0.1875,
-          0.125,
-          0.0625,
-          0.0,
-          0.25,
-          0.125,
-          0.25,
-          0.3125,
-          0.3125,
-          0.0625,
-          0.375,
-          0.375,
-          0.4375,
-          0.5,
-          0.125,
-          -0.125,
-          0.3125,
-          0.25,
-          0.0625,
-          0.3125,
-          0.3125,
-          0.25,
-          -0.125,
-          0.125,
-          0.4375,
-          0.0,
-          0.1875,
-          0.125,
-          0.125,
-          0.125,
-          0.375,
-          0.1875,
-          0.5,
-          0.0625,
-          0.25,
-          0.5,
-          0.125,
-          0.1875,
-          0.25,
-          0.3125,
-          0.5,
-          0.0
-        ]
-      },
-      "left_hand_joints": {
-        "min": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "max": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "mean": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "std": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q01": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q99": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ]
-      },
-      "right_hand_joints": {
-        "min": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "max": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "mean": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "std": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q01": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ],
-        "q99": [
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0,
-          0.0
-        ]
-      }
-    },
-    "relative_action": {}
-  }
-}

checkpoint-150/experiment_cfg/final_model_config.json

@@ -1,55 +0,0 @@
-{
-  "model_type": "Gr00tN1d7",
-  "model_dtype": "bfloat16",
-  "model_name": "nvidia/Cosmos-Reason2-2B",
-  "backbone_model_type": "qwen",
-  "model_revision": null,
-  "tune_top_llm_layers": 0,
-  "backbone_embedding_dim": 2048,
-  "tune_llm": false,
-  "tune_visual": false,
-  "select_layer": 16,
-  "reproject_vision": false,
-  "use_flash_attention": true,
-  "load_bf16": false,
-  "backbone_trainable_params_fp32": true,
-  "extra_augmentation_config": null,
-  "apply_sincos_state_encoding": false,
-  "use_percentiles": true,
-  "use_relative_action": false,
-  "max_state_dim": 132,
-  "max_action_dim": 132,
-  "action_horizon": 40,
-  "hidden_size": 1024,
-  "input_embedding_dim": 1536,
-  "state_history_length": 1,
-  "add_pos_embed": true,
-  "attn_dropout": 0.2,
-  "use_vlln": true,
-  "max_seq_len": 1024,
-  "use_alternate_vl_dit": true,
-  "attend_text_every_n_blocks": 2,
-  "diffusion_model_cfg": {
-    "attention_head_dim": 48,
-    "dropout": 0.2,
-    "final_dropout": true,
-    "interleave_self_attention": true,
-    "norm_type": "ada_norm",
-    "num_attention_heads": 32,
-    "num_layers": 32,
-    "output_dim": 1024,
-    "positional_embeddings": null
-  },
-  "num_inference_timesteps": 4,
-  "noise_beta_alpha": 1.5,
-  "noise_beta_beta": 1.0,
-  "noise_s": 0.999,
-  "num_timestep_buckets": 1000,
-  "tune_projector": true,
-  "tune_diffusion_model": true,
-  "tune_vlln": true,
-  "state_dropout_prob": 0.2,
-  "exclude_state": false,
-  "use_mean_std": false,
-  "max_num_embodiments": 32
-}

checkpoint-150/global_step150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1493f42631d539c06efc28a6af1adfd6d86b160cb8a520c80f4f2fb9419e66d6
-size 4861568625

checkpoint-150/global_step150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:82f37977993adb2e1858f02d986db250d124ed9ef181908cfeff87d9f3435e49
-size 4861568369

checkpoint-150/global_step150/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:01510672d575b36e92055653c492e6393ecd28a5f20cda11dea9b111648a5ffa
-size 4861566321

checkpoint-150/global_step150/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6af3158e536cb6ad3a9f942c64248fb236d5fe12bd8a49a74ecb3790e90c1bcf
-size 4861563121

checkpoint-150/global_step150/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a6a3b428d651a7628beefd5ee1d735f4b05f1928b99e703a78f54b0941e4c8d0
-size 2430786821

checkpoint-150/global_step150/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe74494d6b2c3cc7483762cac7ac03a7796b0da6c5053594ccbf99ba57c6bfc5
-size 2430784901

checkpoint-150/global_step150/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:91f240b022f38ad9f72de50ccd20bd875e21b126f4d3edb635f6c5d0641bdd81
-size 2430783237