Delete files checkpoint-3* with huggingface_hub

checkpoint-36/config.json

@@ -1,70 +0,0 @@
-{
-  "action_horizon": 50,
-  "add_pos_embed": true,
-  "apply_sincos_state_encoding": true,
-  "architectures": [
-    "Gr00tN1d6"
-  ],
-  "attn_dropout": 0.2,
-  "attn_implementation": null,
-  "backbone_embedding_dim": 2048,
-  "backbone_model_type": "eagle",
-  "backbone_trainable_params_fp32": true,
-  "collator_overwrite_image_inputs": false,
-  "color_jitter_params": {
-    "brightness": 0.1,
-    "contrast": 0.1,
-    "hue": 0.1,
-    "saturation": 0.1
-  },
-  "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
-  },
-  "eagle_collator": true,
-  "formalize_language": true,
-  "gemma_collator": false,
-  "hidden_size": 1024,
-  "image_crop_size": null,
-  "image_target_size": null,
-  "input_embedding_dim": 1536,
-  "load_bf16": true,
-  "max_action_dim": 128,
-  "max_num_embodiments": 32,
-  "max_seq_len": 1024,
-  "max_state_dim": 128,
-  "model_dtype": "bfloat16",
-  "model_name": "nvidia/Eagle-Block2A-2B-v2",
-  "model_type": "Gr00tN1d6",
-  "noise_beta_alpha": 1.5,
-  "noise_beta_beta": 1.0,
-  "noise_s": 0.999,
-  "num_inference_timesteps": 4,
-  "num_timestep_buckets": 1000,
-  "random_rotation_angle": null,
-  "reproject_vision": false,
-  "select_layer": 16,
-  "shortest_image_edge": 256,
-  "state_dropout_prob": 0.0,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
-  "tune_diffusion_model": true,
-  "tune_llm": false,
-  "tune_projector": true,
-  "tune_top_llm_layers": 4,
-  "tune_visual": false,
-  "tune_vlln": true,
-  "use_albumentations_transforms": true,
-  "use_alternate_vl_dit": true,
-  "use_flash_attention": true,
-  "use_relative_action": true,
-  "use_vlln": true
-}

checkpoint-36/embodiment_id.json

@@ -1,11 +0,0 @@
-{
-  "robocasa_panda_omron": 13,
-  "gr1": 20,
-  "behavior_r1_pro": 24,
-  "unitree_g1": 8,
-  "oxe_google": 0,
-  "oxe_widowx": 1,
-  "libero_panda": 2,
-  "oxe_droid": 16,
-  "new_embodiment": 10
-}

checkpoint-36/experiment_cfg/conf.yaml

@@ -1,252 +0,0 @@
-load_config_path: null
-model:
-  model_type: Gr00tN1d6
-  model_dtype: bfloat16
-  model_name: nvidia/Eagle-Block2A-2B-v2
-  backbone_model_type: eagle
-  model_revision: null
-  tune_top_llm_layers: 4
-  backbone_embedding_dim: 2048
-  tune_llm: false
-  tune_visual: false
-  select_layer: 16
-  reproject_vision: false
-  use_flash_attention: true
-  load_bf16: false
-  collator_overwrite_image_inputs: false
-  eagle_collator: true
-  backbone_trainable_params_fp32: true
-  image_crop_size: null
-  image_target_size: null
-  shortest_image_edge: 256
-  crop_fraction: 0.95
-  random_rotation_angle: null
-  color_jitter_params:
-    brightness: 0.3
-    contrast: 0.4
-    saturation: 0.5
-    hue: 0.08
-  use_albumentations_transforms: true
-  formalize_language: true
-  apply_sincos_state_encoding: false
-  use_relative_action: true
-  max_state_dim: 29
-  max_action_dim: 29
-  action_horizon: 16
-  hidden_size: 1024
-  input_embedding_dim: 1536
-  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: 32
-    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: 0.0
-  state_additive_noise_scale: 0.0
-  max_num_embodiments: 32
-data:
-  datasets:
-  - dataset_paths:
-    - /data/PnPCubeLine
-    embodiment_tag: unitree_g1
-    mix_ratio: 1.0
-    dataset_type: physical_embodiment
-    val_dataset_path: null
-  modality_configs:
-    unitree_g1:
-      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
-        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
-        modality_keys:
-        - left_arm
-        - right_arm
-        - left_hand
-        - right_hand
-        - waist
-        - base_height_command
-        - navigate_command
-        sin_cos_embedding_keys: null
-        mean_std_embedding_keys: null
-        action_configs:
-        - rep: RELATIVE
-          type: NON_EEF
-          format: DEFAULT
-          state_key: null
-        - rep: RELATIVE
-          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
-        - 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: false
-  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: /checkpoints/g1_finetune
-  experiment_name: null
-  max_steps: 36
-  global_batch_size: 512
-  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-N1.6-3B
-  tf32: true
-  fp16: false
-  bf16: true
-  eval_bf16: true
-  logging_steps: 10
-  save_steps: 12
-  save_total_limit: 3
-  save_vl_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: false
-  wandb_project: finetune-gr00t-n1d6
-  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: 36
-save_steps: 12

checkpoint-36/experiment_cfg/config.yaml

@@ -1,291 +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:
-    - /data/PnPCubeLine
-    dataset_type: physical_embodiment
-    embodiment_tag: unitree_g1
-    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:
-      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
-          - relative
-          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: &id004 !!python/object/apply:gr00t.data.types.ActionRepresentation
-          - absolute
-          state_key: null
-          type: *id003
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: *id001
-          rep: *id004
-          state_key: null
-          type: *id003
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: *id001
-          rep: *id004
-          state_key: null
-          type: *id003
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: *id001
-          rep: *id004
-          state_key: null
-          type: *id003
-        - !!python/object:gr00t.data.types.ActionConfig
-          format: *id001
-          rep: *id004
-          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
-        mean_std_embedding_keys: null
-        modality_keys:
-        - left_arm
-        - right_arm
-        - left_hand
-        - right_hand
-        - waist
-        - base_height_command
-        - navigate_command
-        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
-        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: false
-  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_n1d6.Gr00tN1d6Config
-  _attn_implementation_autoset: false
-  _attn_implementation_internal: null
-  _commit_hash: null
-  _name_or_path: ''
-  add_cross_attention: false
-  architectures: null
-  backbone_model_type: eagle
-  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: 32
-    output_dim: 1024
-    positional_embeddings: null
-  diversity_penalty: 0.0
-  do_sample: false
-  eagle_collator: true
-  early_stopping: false
-  encoder_no_repeat_ngram_size: 0
-  eos_token_id: null
-  exponential_decay_length_penalty: 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/Eagle-Block2A-2B-v2
-  no_repeat_ngram_size: 0
-  num_beam_groups: 1
-  num_beams: 1
-  num_return_sequences: 1
-  output_attentions: false
-  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: 0.0
-  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
-  torch_dtype: null
-  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: 512
-  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: 36
-  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: /checkpoints/g1_finetune
-  remove_unused_columns: false
-  save_best_eval_metric_greater_is_better: true
-  save_best_eval_metric_name: ''
-  save_steps: 12
-  save_total_limit: 3
-  save_vl_model: false
-  start_from_checkpoint: nvidia/GR00T-N1.6-3B
-  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: false
-  wandb_project: finetune-gr00t-n1d6
-  warmup_ratio: 0.05
-  warmup_steps: 0
-  weight_decay: 1.0e-05

checkpoint-36/experiment_cfg/final_model_config.json

@@ -1,53 +0,0 @@
-{
-  "model_type": "Gr00tN1d6",
-  "model_dtype": "bfloat16",
-  "model_name": "nvidia/Eagle-Block2A-2B-v2",
-  "backbone_model_type": "eagle",
-  "model_revision": null,
-  "tune_top_llm_layers": 4,
-  "backbone_embedding_dim": 2048,
-  "tune_llm": false,
-  "tune_visual": false,
-  "select_layer": 16,
-  "reproject_vision": false,
-  "use_flash_attention": true,
-  "load_bf16": true,
-  "collator_overwrite_image_inputs": false,
-  "eagle_collator": true,
-  "backbone_trainable_params_fp32": true,
-  "apply_sincos_state_encoding": true,
-  "use_relative_action": true,
-  "max_state_dim": 128,
-  "max_action_dim": 128,
-  "action_horizon": 50,
-  "hidden_size": 1024,
-  "input_embedding_dim": 1536,
-  "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": 0.0,
-  "state_additive_noise_scale": 0.0,
-  "max_num_embodiments": 32
-}

checkpoint-36/global_step36/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:ca55f703ae97692e34abd4e024642219e49afa810febd780009fdf0252c97b4e
-size 4859923697

checkpoint-36/global_step36/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:f3871c395b98977c6b4a1155d59be59ca302662e1f191e7b718560e0e1937141
-size 4859923761

checkpoint-36/global_step36/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2f6ed0d1086fcf449f6f2e224d7af5db59b5f1033f9681fbbf053f3f5293cb7c
-size 4859923569

checkpoint-36/global_step36/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a9ca3f5b8c43f6646336fca3c0aaeda5cb78bbc55c42595704d46b1c313f1ec
-size 4859917873

checkpoint-36/global_step36/mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d8d452eade3c9462306ebe09cca4f2bda7a964931c9995f88bb64f6d4e53520d
-size 9907202435

checkpoint-36/latest

@@ -1 +0,0 @@
-global_step36

checkpoint-36/model-00001-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:14f474658ff87dc1f65377ff3a2a405e82424ac238e09635ff9d2743bb9a4c19
-size 4991091456

checkpoint-36/model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ca1958ec96af2b32f3eb12a2fc3936ae92711a829bdd408836dcb8ed324c0939
-size 1582283096

checkpoint-36/processor_config.json

@@ -1,508 +0,0 @@
-{
-  "processor_class": "Gr00tN1d6Processor",
-  "processor_kwargs": {
-    "modality_configs": {
-      "behavior_r1_pro": {
-        "video": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "observation.images.rgb.head_256_256",
-            "observation.images.rgb.left_wrist_256_256",
-            "observation.images.rgb.right_wrist_256_256"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "robot_pos",
-            "robot_ori_cos",
-            "robot_ori_sin",
-            "robot_2d_ori",
-            "robot_2d_ori_cos",
-            "robot_2d_ori_sin",
-            "robot_lin_vel",
-            "robot_ang_vel",
-            "arm_left_qpos",
-            "arm_left_qpos_sin",
-            "arm_left_qpos_cos",
-            "eef_left_pos",
-            "eef_left_quat",
-            "gripper_left_qpos",
-            "arm_right_qpos",
-            "arm_right_qpos_sin",
-            "arm_right_qpos_cos",
-            "eef_right_pos",
-            "eef_right_quat",
-            "gripper_right_qpos",
-            "trunk_qpos"
-          ],
-          "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
-          ],
-          "modality_keys": [
-            "base",
-            "torso",
-            "left_arm",
-            "left_gripper",
-            "right_arm",
-            "right_gripper"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "trunk_qpos"
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "arm_left_qpos"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": "arm_right_qpos"
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "annotation.human.coarse_action"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "gr1": {
-        "video": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "ego_view_bg_crop_pad_res256_freq20"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "left_arm",
-            "right_arm",
-            "left_hand",
-            "right_hand",
-            "waist"
-          ],
-          "sin_cos_embedding_keys": [
-            "left_arm",
-            "right_arm",
-            "left_hand",
-            "right_hand",
-            "waist"
-          ],
-          "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
-          ],
-          "modality_keys": [
-            "left_arm",
-            "right_arm",
-            "left_hand",
-            "right_hand",
-            "waist"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "ABSOLUTE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            }
-          ]
-        },
-        "language": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "task"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "robocasa_panda_omron": {
-        "video": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "res256_image_side_0",
-            "res256_image_side_1",
-            "res256_image_wrist_0"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        },
-        "state": {
-          "delta_indices": [
-            0
-          ],
-          "modality_keys": [
-            "end_effector_position_relative",
-            "end_effector_rotation_relative",
-            "gripper_qpos",
-            "base_position",
-            "base_rotation"
-          ],
-          "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
-          ],
-          "modality_keys": [
-            "end_effector_position",
-            "end_effector_rotation",
-            "gripper_close",
-            "base_motion",
-            "control_mode"
-          ],
-          "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
-            },
-            {
-              "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.action.task_description"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": null
-        }
-      },
-      "unitree_g1": {
-        "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"
-          ],
-          "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
-          ],
-          "modality_keys": [
-            "left_arm",
-            "right_arm",
-            "left_hand",
-            "right_hand",
-            "waist",
-            "base_height_command",
-            "navigate_command"
-          ],
-          "sin_cos_embedding_keys": null,
-          "mean_std_embedding_keys": null,
-          "action_configs": [
-            {
-              "rep": "RELATIVE",
-              "type": "NON_EEF",
-              "format": "DEFAULT",
-              "state_key": null
-            },
-            {
-              "rep": "RELATIVE",
-              "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
-            },
-            {
-              "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": null,
-    "image_target_size": null,
-    "use_albumentations": true,
-    "random_rotation_angle": null,
-    "color_jitter_params": {
-      "brightness": 0.3,
-      "contrast": 0.4,
-      "saturation": 0.5,
-      "hue": 0.08
-    },
-    "shortest_image_edge": 256,
-    "crop_fraction": 0.95,
-    "model_name": "nvidia/Eagle-Block2A-2B-v2",
-    "model_type": "eagle",
-    "formalize_language": true,
-    "max_state_dim": 128,
-    "max_action_dim": 128,
-    "max_action_horizon": 50,
-    "use_percentiles": false,
-    "clip_outliers": true,
-    "apply_sincos_state_encoding": true,
-    "use_relative_action": true
-  }
-}

checkpoint-36/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eca25c9b9a24c5837f8a22c33fde8997648df6eb1bb0f971ffe391d2d30e6820
-size 15429

checkpoint-36/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e101856b59e5aa370836c5e6eac0206a12923f40bdf8e719f59950a38f6dd19
-size 15429

checkpoint-36/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c249e4ce60380fadd294f662ade9389f03fe543358c0c477ebbd67de4a673019
-size 15429

checkpoint-36/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:118e6034ce2076dd523cdcf1dc08a2fcd9e097fe9f42d202bae8e2449cfbf6f5
-size 15429

checkpoint-36/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:495e8e3c9b5dc21c8037525a0de1ab5f4a0c0c8813d522a6924cb66712cbc8d4
-size 1465

checkpoint-36/trainer_state.json

@@ -1,52 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 500,
-  "global_step": 36,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "grad_norm": 0.3049973249435425,
-      "learning_rate": 8.9900861364012e-05,
-      "loss": 1.3242,
-      "step": 10
-    },
-    {
-      "grad_norm": 0.43105757236480713,
-      "learning_rate": 5e-05,
-      "loss": 1.1547,
-      "step": 20
-    },
-    {
-      "grad_norm": 0.21635770797729492,
-      "learning_rate": 1.0099138635988026e-05,
-      "loss": 1.1113,
-      "step": 30
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 36,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 9223372036854775807,
-  "save_steps": 12,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 0.0,
-  "train_batch_size": 128,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-36/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0e452e88d907f225ae7ff35acf6f7424dcd56675dd06a0150a7e565d7bf870ac
-size 7633

checkpoint-36/wandb_config.json

@@ -1 +0,0 @@
-{"project": "finetune-gr00t-n1d6", "run_id": "g1_finetune"}

checkpoint-36/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)