kanshan/minimind
1
0
Fork 0
mirror of https://github.com/jingyaogong/minimind.git synced 2026-05-01 11:48:14 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

[feat] update trainer

Browse Source
This commit is contained in:
jingyaogong 2025-10-28 23:30:10 +08:00
parent eb96113cd4
commit 8f7e07b8ef
9 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
trainer/train_distill_reason.py
View File

@ -15,7 +15,7 @@ from torch.nn.parallel import DistributedDataParallel
from torch.utils.data import DataLoader, DistributedSampler
from model.model_minimind import MiniMindConfig
from dataset.lm_dataset import SFTDataset
from trainer.trainer_utils import *
from trainer.trainer_utils import get_lr, Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, init_model, SkipBatchSampler
warnings.filterwarnings('ignore')

2
trainer/train_distillation.py
View File

@ -16,7 +16,7 @@ from torch.nn.parallel import DistributedDataParallel
from torch.utils.data import DataLoader, DistributedSampler
from model.model_minimind import MiniMindConfig
from dataset.lm_dataset import SFTDataset
from trainer.trainer_utils import *
from trainer.trainer_utils import get_lr, Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, init_model, SkipBatchSampler
warnings.filterwarnings('ignore')

2
trainer/train_dpo.py
View File

@ -16,7 +16,7 @@ from torch.nn.parallel import DistributedDataParallel
from torch.utils.data import DataLoader, DistributedSampler
from model.model_minimind import MiniMindConfig
from dataset.lm_dataset import DPODataset
from trainer.trainer_utils import *
from trainer.trainer_utils import get_lr, Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, init_model, SkipBatchSampler
warnings.filterwarnings('ignore')

2
trainer/train_full_sft.py
View File

@ -15,7 +15,7 @@ from torch.nn.parallel import DistributedDataParallel
from torch.utils.data import DataLoader, DistributedSampler
from model.model_minimind import MiniMindConfig
from dataset.lm_dataset import SFTDataset
from trainer.trainer_utils import *
from trainer.trainer_utils import get_lr, Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, init_model, SkipBatchSampler
warnings.filterwarnings('ignore')

2
trainer/train_grpo.py
View File

@ -19,7 +19,7 @@ from torch.optim.lr_scheduler import CosineAnnealingLR
from transformers import AutoModel
from model.model_minimind import MiniMindConfig, MiniMindForCausalLM
from dataset.lm_dataset import RLAIFDataset
from trainer.trainer_utils import *
from trainer.trainer_utils import Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, SkipBatchSampler
warnings.filterwarnings('ignore')

2
trainer/train_lora.py
View File

@ -16,7 +16,7 @@ from torch.utils.data import DataLoader, DistributedSampler
from model.model_minimind import MiniMindConfig
from dataset.lm_dataset import SFTDataset
from model.model_lora import save_lora, apply_lora
from trainer.trainer_utils import *
from trainer.trainer_utils import get_lr, Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, init_model, SkipBatchSampler
warnings.filterwarnings('ignore')

2
trainer/train_ppo.py
View File

@ -20,7 +20,7 @@ from torch.optim.lr_scheduler import CosineAnnealingLR
from transformers import AutoModel
from model.model_minimind import MiniMindConfig, MiniMindForCausalLM
from dataset.lm_dataset import RLAIFDataset
from trainer.trainer_utils import *
from trainer.trainer_utils import Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, SkipBatchSampler
warnings.filterwarnings('ignore')

2
trainer/train_pretrain.py
View File

@ -15,7 +15,7 @@ from torch.nn.parallel import DistributedDataParallel
from torch.utils.data import DataLoader, DistributedSampler
from model.model_minimind import MiniMindConfig
from dataset.lm_dataset import PretrainDataset
from trainer.trainer_utils import *
from trainer.trainer_utils import get_lr, Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, init_model, SkipBatchSampler
warnings.filterwarnings('ignore')

2
trainer/train_spo.py
View File

@ -19,7 +19,7 @@ from torch.optim.lr_scheduler import CosineAnnealingLR
from transformers import AutoModel
from model.model_minimind import MiniMindConfig, MiniMindForCausalLM
from dataset.lm_dataset import RLAIFDataset
from trainer.trainer_utils import *
from trainer.trainer_utils import Logger, is_main_process, lm_checkpoint, init_distributed_mode, setup_seed, SkipBatchSampler
warnings.filterwarnings('ignore')