Merge branch 'main' into other-hf

xtuner/configs/custom_dataset/pretrain/minicpm/minicpm3_4b_full_custom_pretrain_e1.py

@@ -0,0 +1,216 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+"""Data format:
+
+[
+  {
+      "text": "xxx"
+  },
+  {
+      "text": "xxx"
+  },
+  ...
+]
+"""  # noqa: E501
+
+from datasets import load_dataset
+from mmengine.dataset import DefaultSampler
+from mmengine.hooks import (
+    CheckpointHook,
+    DistSamplerSeedHook,
+    IterTimerHook,
+    LoggerHook,
+    ParamSchedulerHook,
+)
+from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR, LinearLR
+from torch.optim import AdamW
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from xtuner.dataset import process_hf_dataset
+from xtuner.dataset.collate_fns import default_collate_fn
+from xtuner.dataset.map_fns import pretrain_map_fn
+from xtuner.engine.hooks import (
+    DatasetInfoHook,
+    EvaluateChatHook,
+    VarlenAttnArgsToMessageHubHook,
+)
+from xtuner.engine.runner import TrainLoop
+from xtuner.model import SupervisedFinetune
+
+#######################################################################
+#                          PART 1  Settings                           #
+#######################################################################
+# Model
+pretrained_model_name_or_path = "openbmb/MiniCPM3-4B"
+use_varlen_attn = False
+
+# Data
+data_files = ["/path/to/your.json"]
+max_length = 1024
+pack_to_max_length = True
+
+# Scheduler & Optimizer
+batch_size = 1  # per_device
+accumulative_counts = 1  # bs = 1 GPU * 1 batch_size_per_device * 16 acc
+dataloader_num_workers = 0
+max_steps = 10000
+optim_type = AdamW
+lr = 2e-5
+betas = (0.9, 0.999)
+weight_decay = 0
+max_norm = 1  # grad clip
+warmup_ratio = 0.03
+
+# Save
+save_steps = 500
+save_total_limit = 2  # Maximum checkpoints to keep (-1 means unlimited)
+
+# Evaluate the generation performance during the training
+evaluation_freq = 500
+SYSTEM = ""
+evaluation_inputs = ["上海是", "Shanghai is"]
+
+#######################################################################
+#                      PART 2  Model & Tokenizer                      #
+#######################################################################
+tokenizer = dict(
+    type=AutoTokenizer.from_pretrained,
+    pretrained_model_name_or_path=pretrained_model_name_or_path,
+    trust_remote_code=True,
+    padding_side="right",
+    eos_token="<|im_end|>",
+)
+
+model = dict(
+    type=SupervisedFinetune,
+    use_varlen_attn=use_varlen_attn,
+    llm=dict(
+        type=AutoModelForCausalLM.from_pretrained,
+        pretrained_model_name_or_path=pretrained_model_name_or_path,
+        trust_remote_code=True,
+    ),
+)
+
+#######################################################################
+#                      PART 3  Dataset & Dataloader                   #
+#######################################################################
+train_dataset = dict(
+    type=process_hf_dataset,
+    dataset=dict(type=load_dataset, path="json", data_files=data_files),
+    tokenizer=tokenizer,
+    max_length=max_length,
+    dataset_map_fn=pretrain_map_fn,
+    template_map_fn=None,
+    remove_unused_columns=True,
+    shuffle_before_pack=False,
+    pack_to_max_length=pack_to_max_length,
+    use_varlen_attn=use_varlen_attn,
+)
+
+train_dataloader = dict(
+    batch_size=batch_size,
+    num_workers=dataloader_num_workers,
+    dataset=train_dataset,
+    sampler=dict(type=DefaultSampler, shuffle=True),
+    collate_fn=dict(type=default_collate_fn, use_varlen_attn=use_varlen_attn),
+)
+
+#######################################################################
+#                    PART 4  Scheduler & Optimizer                    #
+#######################################################################
+# optimizer
+optim_wrapper = dict(
+    type=AmpOptimWrapper,
+    optimizer=dict(type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),
+    clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),
+    accumulative_counts=accumulative_counts,
+    loss_scale="dynamic",
+    dtype="float16",
+)
+
+# learning policy
+param_scheduler = [
+    dict(
+        type=LinearLR,
+        start_factor=1e-5,
+        by_epoch=True,
+        begin=0,
+        end=max_steps * warmup_ratio,
+        convert_to_iter_based=True,
+    ),
+    dict(
+        type=CosineAnnealingLR,
+        eta_min=0.0,
+        by_epoch=True,
+        begin=max_steps * warmup_ratio,
+        end=max_steps,
+        convert_to_iter_based=True,
+    ),
+]
+
+# train, val, test setting
+train_cfg = dict(type=TrainLoop, max_iters=max_steps)
+
+#######################################################################
+#                           PART 5  Runtime                           #
+#######################################################################
+# Log the dialogue periodically during the training process, optional
+custom_hooks = [
+    dict(type=DatasetInfoHook, tokenizer=tokenizer),
+    dict(
+        type=EvaluateChatHook,
+        tokenizer=tokenizer,
+        every_n_iters=evaluation_freq,
+        evaluation_inputs=evaluation_inputs,
+        system=SYSTEM,
+    ),
+]
+
+if use_varlen_attn:
+    custom_hooks += [dict(type=VarlenAttnArgsToMessageHubHook)]
+
+# configure default hooks
+default_hooks = dict(
+    # record the time of every iteration.
+    timer=dict(type=IterTimerHook),
+    # print log every 10 iterations.
+    logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10),
+    # enable the parameter scheduler.
+    param_scheduler=dict(type=ParamSchedulerHook),
+    # save checkpoint per `save_steps`.
+    checkpoint=dict(
+        type=CheckpointHook,
+        by_epoch=False,
+        interval=save_steps,
+        max_keep_ckpts=save_total_limit,
+    ),
+    # set sampler seed in distributed evrionment.
+    sampler_seed=dict(type=DistSamplerSeedHook),
+)
+
+# configure environment
+env_cfg = dict(
+    # whether to enable cudnn benchmark
+    cudnn_benchmark=False,
+    # set multi process parameters
+    mp_cfg=dict(mp_start_method="fork", opencv_num_threads=0),
+    # set distributed parameters
+    dist_cfg=dict(backend="nccl"),
+)
+
+# set visualizer
+visualizer = None
+
+# set log level
+log_level = "INFO"
+
+# load from which checkpoint
+load_from = None
+
+# whether to resume training from the loaded checkpoint
+resume = False
+
+# Defaults to use random seed and disable `deterministic`
+randomness = dict(seed=None, deterministic=False)
+
+# set log processor
+log_processor = dict(by_epoch=False)