Delete 0318-afford-three-alternate-pretrain

0318-afford-three-alternate-pretrain/checkpoint-22000/README.md

@@ -1,9 +0,0 @@
----
-tags:
-- model_hub_mixin
-- pytorch_model_hub_mixin
----
-
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Library: https://huggingface.co/robotics-diffusion-transformer/rdt-1b
-- Docs: [More Information Needed]

0318-afford-three-alternate-pretrain/checkpoint-22000/config.json

@@ -1,49 +0,0 @@
-{
-  "action_dim": 2,
-  "ema": {
-    "inv_gamma": 1.0,
-    "max_value": 0.9999,
-    "min_value": 0.0,
-    "power": 0.75,
-    "update_after_step": 0
-  },
-  "img_adaptor": "mlp2x_gelu",
-  "img_cond_len": 1458,
-  "img_pos_embed_config": [
-    [
-      "image",
-      [
-        2,
-        1,
-        -729
-      ]
-    ]
-  ],
-  "img_token_dim": 1152,
-  "lang_adaptor": "mlp2x_gelu",
-  "lang_pos_embed_config": [
-    [
-      "lang",
-      -1024
-    ]
-  ],
-  "lang_token_dim": 3584,
-  "max_lang_cond_len": 1024,
-  "noise_scheduler": {
-    "beta_schedule": "squaredcos_cap_v2",
-    "clip_sample": false,
-    "num_inference_timesteps": 5,
-    "num_train_timesteps": 1000,
-    "prediction_type": "sample",
-    "type": "ddpm"
-  },
-  "pred_horizon": 5,
-  "rdt": {
-    "cond_pos_embed_type": "multimodal",
-    "depth": 28,
-    "hidden_size": 2048,
-    "num_heads": 32
-  },
-  "state_adaptor": "mlp3x_gelu",
-  "state_token_dim": 2
-}

0318-afford-three-alternate-pretrain/checkpoint-22000/ema/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a92c19d22d899ad3f67ba38c20cb71ea67c55e66f104eaabd31b4796666ff68b
-size 2431411964

0318-afford-three-alternate-pretrain/checkpoint-22000/latest

@@ -1 +0,0 @@
-pytorch_model

0318-afford-three-alternate-pretrain/checkpoint-22000/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c77fea3a3bd0128237fcf99490a14511c6c426f45d9f47d6978d1c1f605d407f
-size 2431461754

0318-afford-three-alternate-pretrain/checkpoint-22000/pytorch_model/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6fe9312d3c864cf6996b559524fdaf7ac2fda48569a012cefab8e2a28c069abf
-size 3647034352

0318-afford-three-alternate-pretrain/checkpoint-22000/pytorch_model/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:24e616cf97057a7cf393198c18a0e3a891369e4e6fa80319b387695c4898dc3e
-size 3647033904

0318-afford-three-alternate-pretrain/checkpoint-22000/pytorch_model/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:ebbd245b711a9c0d16bffeb7fe73afa1fd3262fed8ed0eb8414102a14989f8d4
-size 3647034416

0318-afford-three-alternate-pretrain/checkpoint-22000/pytorch_model/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:b999834e33438ace3ca554548f44d277cc08fd7b69c5e7b8083414edf9fc41c4
-size 3647034608

0318-afford-three-alternate-pretrain/checkpoint-22000/pytorch_model/mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:093eadf6d45a8b0ccb4e5edab533ef20ba4829cc1d5b039c12975ef501cedd80
-size 2431505004

0318-afford-three-alternate-pretrain/checkpoint-22000/random_states_0.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f2c511300a555baf94d2f3cf48a7c914c7ca587a8a7d7ba63f5b44ccea2d5a10
-size 15060

0318-afford-three-alternate-pretrain/checkpoint-22000/random_states_1.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad02d8c5914c1d66f8f59926fb4092b139cb53562c00679ff2d682785fa47b30
-size 15060

0318-afford-three-alternate-pretrain/checkpoint-22000/random_states_2.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:52492d3ca186158c58e41e12b6f792742314485f1f5885fd356b3da0fbc8fb48
-size 15060

0318-afford-three-alternate-pretrain/checkpoint-22000/random_states_3.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:faf860724e5c93be8b3aef5e3b17d458928cd1ddd9a8be1299ee7685642885bd
-size 15060

0318-afford-three-alternate-pretrain/checkpoint-22000/scheduler.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4c792e2e94fc4a458c44e3830539c70dcf76432deb2be918ca623ba3f5520f21
-size 1000

0318-afford-three-alternate-pretrain/checkpoint-22000/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 not ZERO_STAGE 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(f"Extracting fp32 weights")
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-
-    logger.info(f"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)

0318-afford-three-alternate-pretrain/checkpoint-28000/0318-afford-three-alternate-pretrain_front-28000.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2ddb7ce5a107d0c6d62705a4af79dc877a0c15243e5b6282d33cf7a91094232
-size 96158622

0318-afford-three-alternate-pretrain/checkpoint-28000/README.md

@@ -1,9 +0,0 @@
----
-tags:
-- model_hub_mixin
-- pytorch_model_hub_mixin
----
-
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Library: https://huggingface.co/robotics-diffusion-transformer/rdt-1b
-- Docs: [More Information Needed]

0318-afford-three-alternate-pretrain/checkpoint-28000/config.json

@@ -1,49 +0,0 @@
-{
-  "action_dim": 2,
-  "ema": {
-    "inv_gamma": 1.0,
-    "max_value": 0.9999,
-    "min_value": 0.0,
-    "power": 0.75,
-    "update_after_step": 0
-  },
-  "img_adaptor": "mlp2x_gelu",
-  "img_cond_len": 1458,
-  "img_pos_embed_config": [
-    [
-      "image",
-      [
-        2,
-        1,
-        -729
-      ]
-    ]
-  ],
-  "img_token_dim": 1152,
-  "lang_adaptor": "mlp2x_gelu",
-  "lang_pos_embed_config": [
-    [
-      "lang",
-      -1024
-    ]
-  ],
-  "lang_token_dim": 3584,
-  "max_lang_cond_len": 1024,
-  "noise_scheduler": {
-    "beta_schedule": "squaredcos_cap_v2",
-    "clip_sample": false,
-    "num_inference_timesteps": 5,
-    "num_train_timesteps": 1000,
-    "prediction_type": "sample",
-    "type": "ddpm"
-  },
-  "pred_horizon": 5,
-  "rdt": {
-    "cond_pos_embed_type": "multimodal",
-    "depth": 28,
-    "hidden_size": 2048,
-    "num_heads": 32
-  },
-  "state_adaptor": "mlp3x_gelu",
-  "state_token_dim": 2
-}

0318-afford-three-alternate-pretrain/checkpoint-28000/ema/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e8eed1a71f10dacfa9b940718358edf5ef0c14ca6342adab79bee43c379b537e
-size 2431411964

0318-afford-three-alternate-pretrain/checkpoint-28000/latest

@@ -1 +0,0 @@
-pytorch_model

0318-afford-three-alternate-pretrain/checkpoint-28000/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2172d6316db1da0befaf5432ca47f0f023e06f71b77ec81c23de7adb1a2b98fe
-size 2431461754

0318-afford-three-alternate-pretrain/checkpoint-28000/pytorch_model/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c1d9b07840a117cf2cc6074d586055c5768b2f94cd93917adb6d2b2d838ef26
-size 3647034352

0318-afford-three-alternate-pretrain/checkpoint-28000/pytorch_model/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:b9a9af02b4da6e1386c022f82d4ea50d3bf1073dbe3229538ba3aa4c9d56be3a
-size 3647033904

0318-afford-three-alternate-pretrain/checkpoint-28000/pytorch_model/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a9c7c7b7a9ed725a57a936d065147050223da6a451cb187852876f67014a8ae
-size 3647034416

0318-afford-three-alternate-pretrain/checkpoint-28000/pytorch_model/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:c4b06636c3253dbc2b46e2cf9fd3332c7308d37e6989d31dc44adf909307d73c
-size 3647034608

0318-afford-three-alternate-pretrain/checkpoint-28000/pytorch_model/mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:657b090ed2595c9ebcc2c4ca6656b96b726d40b8366cf96a36aaf907410355fc
-size 2431505004

0318-afford-three-alternate-pretrain/checkpoint-28000/random_states_0.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:927400457270b8f2cc832986b6ab24d911ec380ebbff963631597186637c23b7
-size 15060

0318-afford-three-alternate-pretrain/checkpoint-28000/random_states_1.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:358e06495af79e1a3e590a11bfa7cf32789e61ad1b9f127ad610a9117f4f6529
-size 15060

0318-afford-three-alternate-pretrain/checkpoint-28000/random_states_2.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a0d108fe621eac7fcc5f64bc594f340ba86de55ea63ce8938da1ecfb90666add
-size 15060

0318-afford-three-alternate-pretrain/checkpoint-28000/random_states_3.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62493d29208b98ca9cc4f2b5d55ea334548ee7b116ad02181076750210a71f1e
-size 15060

0318-afford-three-alternate-pretrain/checkpoint-28000/scheduler.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:265bb2b069563558e9dbbe17d2a73a4387e69045ed1f3f4aa49e3f79ac08a8c0
-size 1000

0318-afford-three-alternate-pretrain/checkpoint-28000/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 not ZERO_STAGE 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(f"Extracting fp32 weights")
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-
-    logger.info(f"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)

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/1742317327.22402/events.out.tfevents.1742317327.computer4.1683012.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e838d871b5ea6f9554e7ed5663c302dbb0fc444ef5db91b3df9f1ae8f7259cf4
-size 2792

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/1742317327.2268047/hparams.yml

@@ -1,48 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-alpha: 0.9
-cam_ext_mask_prob: -1.0
-checkpointing_period: 2000
-checkpoints_total_limit: 15
-cond_mask_prob: 0.1
-config_path: configs/base.yaml
-dataloader_num_workers: 8
-dataset_type: finetune
-deepspeed: ./configs/zero2.json
-gradient_accumulation_steps: 1
-gradient_checkpointing: false
-hub_model_id: null
-hub_token: null
-image_aug: true
-learning_rate: 0.0001
-load_from_hdf5: true
-local_rank: 0
-logging_dir: logs
-lr_num_cycles: 1
-lr_power: 1.0
-lr_scheduler: constant_with_warmup
-lr_warmup_steps: 500
-max_grad_norm: 1.0
-max_train_steps: 160000
-mixed_precision: bf16
-num_sample_batches: 2
-num_train_epochs: 328
-output_dir: /mnt/data/xurongtao/checkpoints/0318-afford-three-alternate-pretrain_front/
-precomp_lang_embed: false
-pretrained_model_name_or_path: /mnt/data/xurongtao/checkpoints/a0-pretrain-1b-5cards/checkpoint-84600
-pretrained_text_encoder_name_or_path: google/t5-v1_1-xxl
-pretrained_vision_encoder_name_or_path: google/siglip-so400m-patch14-384
-push_to_hub: false
-report_to: tensorboard
-resume_from_checkpoint: null
-sample_batch_size: 70
-sample_period: 150
-scale_lr: false
-seed: null
-set_grads_to_none: false
-state_noise_snr: 40.0
-train_batch_size: 7
-use_8bit_adam: false

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/1742317473.216907/events.out.tfevents.1742317473.computer4.1702977.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e287fcb285972d3a369dfe2282d44c988559d0051bea9e891b2724cb324edf9
-size 2792

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/1742317473.2195845/hparams.yml

@@ -1,48 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-alpha: 0.9
-cam_ext_mask_prob: -1.0
-checkpointing_period: 2000
-checkpoints_total_limit: 15
-cond_mask_prob: 0.1
-config_path: configs/base.yaml
-dataloader_num_workers: 8
-dataset_type: finetune
-deepspeed: ./configs/zero2.json
-gradient_accumulation_steps: 1
-gradient_checkpointing: false
-hub_model_id: null
-hub_token: null
-image_aug: true
-learning_rate: 0.0001
-load_from_hdf5: true
-local_rank: 0
-logging_dir: logs
-lr_num_cycles: 1
-lr_power: 1.0
-lr_scheduler: constant_with_warmup
-lr_warmup_steps: 500
-max_grad_norm: 1.0
-max_train_steps: 160000
-mixed_precision: bf16
-num_sample_batches: 2
-num_train_epochs: 328
-output_dir: /mnt/data/xurongtao/checkpoints/0318-afford-three-alternate-pretrain_front/
-precomp_lang_embed: false
-pretrained_model_name_or_path: /mnt/data/xurongtao/checkpoints/a0-pretrain-1b-5cards/checkpoint-84600
-pretrained_text_encoder_name_or_path: google/t5-v1_1-xxl
-pretrained_vision_encoder_name_or_path: google/siglip-so400m-patch14-384
-push_to_hub: false
-report_to: tensorboard
-resume_from_checkpoint: null
-sample_batch_size: 70
-sample_period: 150
-scale_lr: false
-seed: null
-set_grads_to_none: false
-state_noise_snr: 40.0
-train_batch_size: 7
-use_8bit_adam: false

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/1742317614.8297184/events.out.tfevents.1742317614.computer4.1722935.1

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc29e5cf79dbaf5bf122321d946ffe7081b183d1529e88dad3fe1dc5d70d3d64
-size 2792

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/1742317614.8324273/hparams.yml

@@ -1,48 +0,0 @@
-adam_beta1: 0.9
-adam_beta2: 0.999
-adam_epsilon: 1.0e-08
-adam_weight_decay: 0.01
-allow_tf32: false
-alpha: 0.9
-cam_ext_mask_prob: -1.0
-checkpointing_period: 2000
-checkpoints_total_limit: 15
-cond_mask_prob: 0.1
-config_path: configs/base.yaml
-dataloader_num_workers: 8
-dataset_type: finetune
-deepspeed: ./configs/zero2.json
-gradient_accumulation_steps: 1
-gradient_checkpointing: false
-hub_model_id: null
-hub_token: null
-image_aug: true
-learning_rate: 0.0001
-load_from_hdf5: true
-local_rank: 0
-logging_dir: logs
-lr_num_cycles: 1
-lr_power: 1.0
-lr_scheduler: constant_with_warmup
-lr_warmup_steps: 500
-max_grad_norm: 1.0
-max_train_steps: 160000
-mixed_precision: bf16
-num_sample_batches: 2
-num_train_epochs: 4572
-output_dir: /mnt/data/xurongtao/checkpoints/0318-afford-three-alternate-pretrain_front/
-precomp_lang_embed: false
-pretrained_model_name_or_path: /mnt/data/xurongtao/checkpoints/a0-pretrain-1b-5cards/checkpoint-84600
-pretrained_text_encoder_name_or_path: google/t5-v1_1-xxl
-pretrained_vision_encoder_name_or_path: google/siglip-so400m-patch14-384
-push_to_hub: false
-report_to: tensorboard
-resume_from_checkpoint: null
-sample_batch_size: 70
-sample_period: 150
-scale_lr: false
-seed: null
-set_grads_to_none: false
-state_noise_snr: 40.0
-train_batch_size: 70
-use_8bit_adam: false

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/events.out.tfevents.1742317327.computer4.1683012.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c3f31b31b6ef1c1c439122b2a52a4171821875557d41ee685eacbb05c68af64
-size 88

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/events.out.tfevents.1742317473.computer4.1702977.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6de2e1578be77b97d67da22206a192195869a71426f661a7b140774ed767f5dd
-size 22120

0318-afford-three-alternate-pretrain/logs/roboticDiffusionTransformer/events.out.tfevents.1742317614.computer4.1722935.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a6eee1d462c65d521de4cf525b6b5e0b083a288a600a8af4c9d4bc57dd09cca6
-size 9896307