axel-datos/qwen2.5-0.5b-instruct_MATH_full-finetuningV2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: axel-datos/qwen2.5-0.5b-instruct_MATH_full-finetuningV2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 19:52:50 +08:00
commit 2a4feb8f37
33 changed files with 304415 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
checkpoint-75/added_tokens.json Normal file
View File

@@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

30
checkpoint-75/config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"_name_or_path": "Qwen/qwen2.5-0.5b-instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "float16",
"transformers_version": "4.46.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

14
checkpoint-75/generation_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.46.3"
}

3
checkpoint-75/global_step75/zero_pp_rank_0_mp_rank_00_model_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7890e769ac1cacacf923f4ebfbe33c5d2d4ac4950773c96d9bedc92a00b8259
size 144392

3
checkpoint-75/global_step75/zero_pp_rank_0_mp_rank_00_optim_states.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e4a5326c58e396948eee1e01a40acc46d7e95dcbdfaa8cdf14908af219db82c
size 5928398122

1
checkpoint-75/latest Normal file
View File

@@ -0,0 +1 @@
global_step75

151388
checkpoint-75/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-75/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4194352cb3badb567bf0f04749e82f4d322fd0a9d5a1b042944e48cefa202b5a
size 988097536

3
checkpoint-75/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
size 14244

3
checkpoint-75/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2e2b2b36e4a96065f4047474439812493ace7ccc265fa270cfd333703c294fb9
size 1064

31
checkpoint-75/special_tokens_map.json Normal file
View File

@@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
checkpoint-75/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
size 11421896

208
checkpoint-75/tokenizer_config.json Normal file
View File

@@ -0,0 +1,208 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

54
checkpoint-75/trainer_state.json Normal file
View File

@@ -0,0 +1,54 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.01,
"eval_steps": 500,
"global_step": 75,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0026666666666666666,
"grad_norm": 35.846343994140625,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.0788,
"step": 20
},
{
"epoch": 0.005333333333333333,
"grad_norm": 37.91228103637695,
"learning_rate": 1.0666666666666667e-05,
"loss": 0.9709,
"step": 40
},
{
"epoch": 0.008,
"grad_norm": 33.33842468261719,
"learning_rate": 5.333333333333334e-06,
"loss": 0.9643,
"step": 60
}
],
"logging_steps": 20,
"max_steps": 75,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 7693271040.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
checkpoint-75/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f349c79efd96eaa56537010c6d6fee14e7cd0cbbade333f449be85e6a5f68f1d
size 7992

1
checkpoint-75/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

760
checkpoint-75/zero_to_fp32.py Normal file
View File

@@ -0,0 +1,760 @@
#!/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)