-
Notifications
You must be signed in to change notification settings - Fork 316
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* add internlm 2.5 configs * update readme
- Loading branch information
Showing
5 changed files
with
688 additions
and
36 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
226 changes: 226 additions & 0 deletions
226
...nfigs/internlm/internlm2_5_chat_7b/internlm2_5_chat_7b_full_finetune_custom_dataset_e1.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,226 @@ | ||
| # Copyright (c) OpenMMLab. All rights reserved. | ||
| """Data format: | ||
| [ | ||
| { | ||
| "conversation": [ | ||
| { | ||
| "system": "", | ||
| "input": "xxx", | ||
| "output": "xxx" | ||
| }, | ||
| { | ||
| "input": "xxx", | ||
| "output": "xxx" | ||
| } | ||
| ] | ||
| }, | ||
| ... | ||
| ] | ||
| Please refer to https://github.com/InternLM/xtuner/blob/main/docs/en/user_guides/dataset_format.md for details. | ||
| """ # noqa: E501 | ||
| from datasets import load_dataset | ||
| from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook, | ||
| LoggerHook, ParamSchedulerHook) | ||
| from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR | ||
| from torch.optim import AdamW | ||
| from torch.utils.data import BatchSampler | ||
| 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 template_map_fn_factory | ||
| from xtuner.dataset.samplers import InternRepoSampler | ||
| from xtuner.engine import (DatasetInfoHook, EvaluateChatHook, ThroughputHook, | ||
| VarlenAttnArgsToMessageHubHook) | ||
| from xtuner.engine.runner import TrainLoop | ||
| from xtuner.model import SupervisedFinetune | ||
| from xtuner.utils import PROMPT_TEMPLATE | ||
|
|
||
| ####################################################################### | ||
| # PART 1 Settings # | ||
| ####################################################################### | ||
| # Model | ||
| pretrained_model_name_or_path = 'internlm/internlm2_5-7b-chat' | ||
| use_varlen_attn = True | ||
|
|
||
| # Data | ||
| data_files = ['/path/to/json/file.json'] | ||
| prompt_template = PROMPT_TEMPLATE.internlm2_chat | ||
| max_length = 32768 | ||
| pack_to_max_length = True | ||
|
|
||
| # parallel | ||
| sequence_parallel_size = 1 | ||
|
|
||
| # Scheduler & Optimizer | ||
| # batch size per device, set to 1 if `use_varlen_attn` = True | ||
| # To clarify, enlarging the batch size essentially enlarges the `max_length`. | ||
| # For example, doubling the max length is tantamount to doubling the batch size | ||
| batch_size = 1 | ||
| accumulative_counts = 1 # 1bs * 1acc * 64gpu = 64 batchsize | ||
| accumulative_counts *= sequence_parallel_size | ||
| dataloader_num_workers = 4 | ||
| max_epochs = 1 | ||
| optim_type = AdamW | ||
| lr = 4e-5 | ||
| betas = (0.9, 0.95) | ||
| weight_decay = 0.01 | ||
| max_norm = 1 # grad clip | ||
| warm_up_ratio = 0.025 | ||
|
|
||
| # 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 = [ | ||
| '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, | ||
| 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, | ||
| use_varlen_attn=use_varlen_attn, | ||
| dataset=dict(type=load_dataset, path='json', data_files=data_files), | ||
| tokenizer=tokenizer, | ||
| max_length=max_length, | ||
| dataset_map_fn=None, | ||
| 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=train_dataset, | ||
| sampler=dict(type=InternRepoSampler, shuffle=True, seed=1024), | ||
| batch_sampler=dict( | ||
| type=BatchSampler, drop_last=True, batch_size=batch_size), | ||
| 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', | ||
| ) | ||
|
|
||
| # learning policy | ||
| # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 | ||
| param_scheduler = [ | ||
| dict( | ||
| type='LinearLR', | ||
| start_factor=1 / 40, | ||
| by_epoch=True, | ||
| begin=0, | ||
| end=warm_up_ratio * max_epochs, | ||
| convert_to_iter_based=True), | ||
| dict( | ||
| type=CosineAnnealingLR, | ||
| eta_min=lr * 0.15, | ||
| by_epoch=True, | ||
| begin=warm_up_ratio * max_epochs, | ||
| end=max_epochs, | ||
| convert_to_iter_based=True) | ||
| ] | ||
|
|
||
| # train, val, test setting | ||
| train_cfg = dict(type=TrainLoop, max_epochs=max_epochs) | ||
|
|
||
| ####################################################################### | ||
| # PART 5 Runtime # | ||
| ####################################################################### | ||
| # Log the dialogue periodically during the training process, optional | ||
| custom_hooks = [ | ||
| dict( | ||
| type=DatasetInfoHook, tokenizer=tokenizer, | ||
| is_intern_repo_dataset=True), | ||
| dict( | ||
| type=EvaluateChatHook, | ||
| tokenizer=tokenizer, | ||
| every_n_iters=evaluation_freq, | ||
| evaluation_inputs=evaluation_inputs, | ||
| system=SYSTEM, | ||
| prompt_template=prompt_template), | ||
| dict(type=ThroughputHook) | ||
| ] | ||
|
|
||
| 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 100 iterations. | ||
| logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=1), | ||
| # 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) | ||
|
|
||
| log_processor = dict( | ||
| by_epoch=False, | ||
| window_size=1, | ||
| mean_pattern=r'.*(loss|time|data_time|grad_norm|tflops).*') |
Oops, something went wrong.