[Improve] Add several InternLM-7B full parameters fine-tuning configs (…

…InternLM#84)

* add internlm_7b full

* fix pre-commit

* remove fp16 for amp full

xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_e3.py

@@ -0,0 +1,159 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+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
+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 alpaca_map_fn, template_map_fn_factory
+from xtuner.engine import DatasetInfoHook, EvaluateChatHook
+from xtuner.model import SupervisedFinetune
+from xtuner.utils import PROMPT_TEMPLATE
+
+#######################################################################
+#                          PART 1  Settings                           #
+#######################################################################
+# Model
+pretrained_model_name_or_path = 'internlm/internlm-7b'
+
+# Data
+alpaca_en_path = 'tatsu-lab/alpaca'
+prompt_template = PROMPT_TEMPLATE.alpaca
+max_length = 2048
+pack_to_max_length = True
+
+# Scheduler & Optimizer
+batch_size = 1  # per_device
+accumulative_counts = 16
+dataloader_num_workers = 0
+max_epochs = 3
+optim_type = AdamW
+lr = 2e-5
+betas = (0.9, 0.999)
+weight_decay = 0
+max_norm = 1  # grad clip
+
+# Evaluate the generation performance during the training
+evaluation_freq = 500
+evaluation_inputs = [
+    '请给我介绍五个上海的景点', 'Please tell me five scenic spots in Shanghai'
+]
+
+#######################################################################
+#                      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')
+
+model = dict(
+    type=SupervisedFinetune,
+    llm=dict(
+        type=AutoModelForCausalLM.from_pretrained,
+        pretrained_model_name_or_path=pretrained_model_name_or_path,
+        trust_remote_code=True))
+#######################################################################
+#                      PART 3  Dataset & Dataloader                   #
+#######################################################################
+alpaca_en = dict(
+    type=process_hf_dataset,
+    dataset=dict(type=load_dataset, path=alpaca_en_path),
+    tokenizer=tokenizer,
+    max_length=max_length,
+    dataset_map_fn=alpaca_map_fn,
+    template_map_fn=dict(
+        type=template_map_fn_factory, template=prompt_template),
+    remove_unused_columns=True,
+    shuffle_before_pack=True,
+    pack_to_max_length=pack_to_max_length)
+
+train_dataloader = dict(
+    batch_size=batch_size,
+    num_workers=dataloader_num_workers,
+    dataset=alpaca_en,
+    sampler=dict(type=DefaultSampler, shuffle=True),
+    collate_fn=dict(type=default_collate_fn))
+
+#######################################################################
+#                    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
+# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md  # noqa: E501
+param_scheduler = dict(
+    type=CosineAnnealingLR,
+    eta_min=lr * 0.1,
+    by_epoch=True,
+    T_max=max_epochs,
+    convert_to_iter_based=True)
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=max_epochs, val_interval=1)
+
+#######################################################################
+#                           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,
+        instruction=prompt_template.INSTRUCTION_START)
+]
+
+# configure default hooks
+default_hooks = dict(
+    # record the time of every iteration.
+    timer=dict(type=IterTimerHook),
+    # print log every 100 iterations.
+    logger=dict(type=LoggerHook, interval=10),
+    # enable the parameter scheduler.
+    param_scheduler=dict(type=ParamSchedulerHook),
+    # save checkpoint per epoch.
+    checkpoint=dict(type=CheckpointHook, interval=1),
+    # 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)

xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_e3.py

@@ -0,0 +1,177 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+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
+from torch.optim import AdamW
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from xtuner.dataset import ConcatDataset, process_hf_dataset
+from xtuner.dataset.collate_fns import default_collate_fn
+from xtuner.dataset.map_fns import (alpaca_map_fn, alpaca_zh_map_fn,
+                                    template_map_fn_factory)
+from xtuner.engine import DatasetInfoHook, EvaluateChatHook
+from xtuner.model import SupervisedFinetune
+from xtuner.utils import PROMPT_TEMPLATE
+
+#######################################################################
+#                          PART 1  Settings                           #
+#######################################################################
+# Model
+pretrained_model_name_or_path = 'internlm/internlm-7b'
+
+# Data
+alpaca_zh_path = 'silk-road/alpaca-data-gpt4-chinese'
+alpaca_en_path = 'tatsu-lab/alpaca'
+prompt_template = PROMPT_TEMPLATE.alpaca
+max_length = 2048
+pack_to_max_length = True
+
+# Scheduler & Optimizer
+batch_size = 1  # per_device
+accumulative_counts = 16
+dataloader_num_workers = 0
+max_epochs = 3
+optim_type = AdamW
+lr = 2e-5
+betas = (0.9, 0.999)
+weight_decay = 0
+max_norm = 1  # grad clip
+
+# Evaluate the generation performance during the training
+evaluation_freq = 500
+evaluation_inputs = [
+    '请给我介绍五个上海的景点', 'Please tell me five scenic spots in Shanghai'
+]
+
+#######################################################################
+#                      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')
+
+model = dict(
+    type=SupervisedFinetune,
+    llm=dict(
+        type=AutoModelForCausalLM.from_pretrained,
+        pretrained_model_name_or_path=pretrained_model_name_or_path,
+        trust_remote_code=True))
+#######################################################################
+#                      PART 3  Dataset & Dataloader                   #
+#######################################################################
+alpaca_en = dict(
+    type=process_hf_dataset,
+    dataset=dict(type=load_dataset, path=alpaca_en_path),
+    tokenizer=tokenizer,
+    max_length=max_length,
+    dataset_map_fn=alpaca_map_fn,
+    template_map_fn=dict(
+        type=template_map_fn_factory, template=prompt_template),
+    remove_unused_columns=True,
+    shuffle_before_pack=True,
+    pack_to_max_length=pack_to_max_length)
+
+alpaca_zh = dict(
+    type=process_hf_dataset,
+    dataset=dict(type=load_dataset, path=alpaca_zh_path),
+    tokenizer=tokenizer,
+    max_length=max_length,
+    dataset_map_fn=alpaca_zh_map_fn,
+    template_map_fn=dict(
+        type=template_map_fn_factory, template=prompt_template),
+    remove_unused_columns=True,
+    shuffle_before_pack=True,
+    pack_to_max_length=pack_to_max_length)
+
+train_dataset = dict(
+    type=ConcatDataset,
+    datasets_cfg=dict(alpaca_en=alpaca_en, alpaca_zh=alpaca_zh))
+
+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))
+
+#######################################################################
+#                    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
+# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md  # noqa: E501
+param_scheduler = dict(
+    type=CosineAnnealingLR,
+    eta_min=lr * 0.1,
+    by_epoch=True,
+    T_max=max_epochs,
+    convert_to_iter_based=True)
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=max_epochs, val_interval=1)
+
+#######################################################################
+#                           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,
+        instruction=prompt_template.INSTRUCTION_START)
+]
+
+# configure default hooks
+default_hooks = dict(
+    # record the time of every iteration.
+    timer=dict(type=IterTimerHook),
+    # print log every 100 iterations.
+    logger=dict(type=LoggerHook, interval=10),
+    # enable the parameter scheduler.
+    param_scheduler=dict(type=ParamSchedulerHook),
+    # save checkpoint per epoch.
+    checkpoint=dict(type=CheckpointHook, interval=1),
+    # 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)