rename files

Former-commit-id: 74f96efef9

src/llamafactory/train/dpo/trainer.py

@@ -10,7 +10,7 @@ from trl import DPOTrainer
 from trl.trainer import disable_dropout_in_model
 
 from ...extras.constants import IGNORE_INDEX
-from ..utils import create_custom_optimzer, create_custom_scheduler, get_ref_context
+from ..trainer_utils import create_custom_optimzer, create_custom_scheduler, get_ref_context
 
 
 if TYPE_CHECKING:

src/llamafactory/train/dpo/workflow.py

@@ -7,7 +7,7 @@ from ...extras.constants import IGNORE_INDEX
 from ...extras.ploting import plot_loss
 from ...hparams import ModelArguments
 from ...model import load_model, load_tokenizer
-from ..utils import create_modelcard_and_push, create_ref_model
+from ..trainer_utils import create_modelcard_and_push, create_ref_model
 from .trainer import CustomDPOTrainer
 
 

src/llamafactory/train/kto/trainer.py

@@ -9,7 +9,7 @@ from trl import KTOTrainer
 from trl.trainer import disable_dropout_in_model
 
 from ...extras.constants import IGNORE_INDEX
-from ..utils import create_custom_optimzer, create_custom_scheduler, get_ref_context
+from ..trainer_utils import create_custom_optimzer, create_custom_scheduler, get_ref_context
 
 
 if TYPE_CHECKING:

src/llamafactory/train/kto/workflow.py

@@ -5,7 +5,7 @@ from ...extras.constants import IGNORE_INDEX
 from ...extras.ploting import plot_loss
 from ...hparams import ModelArguments
 from ...model import load_model, load_tokenizer
-from ..utils import create_modelcard_and_push, create_ref_model
+from ..trainer_utils import create_modelcard_and_push, create_ref_model
 from .trainer import CustomKTOTrainer
 
 

src/llamafactory/train/ppo/trainer.py

@@ -19,8 +19,8 @@ from trl.models.utils import unwrap_model_for_generation
 from ...extras.callbacks import FixValueHeadModelCallback, LogCallback
 from ...extras.logging import get_logger
 from ...extras.misc import AverageMeter, count_parameters, get_current_device, get_logits_processor
-from ..utils import create_custom_optimzer, create_custom_scheduler
-from .utils import dump_layernorm, get_rewards_from_server, replace_model, restore_layernorm
+from ..trainer_utils import create_custom_optimzer, create_custom_scheduler
+from .ppo_utils import dump_layernorm, get_rewards_from_server, replace_model, restore_layernorm
 
 
 if TYPE_CHECKING:

src/llamafactory/train/ppo/workflow.py

@@ -9,7 +9,7 @@ from ...extras.callbacks import FixValueHeadModelCallback
 from ...extras.misc import fix_valuehead_checkpoint
 from ...extras.ploting import plot_loss
 from ...model import load_model, load_tokenizer
-from ..utils import create_ref_model, create_reward_model
+from ..trainer_utils import create_ref_model, create_reward_model
 from .trainer import CustomPPOTrainer
 
 

src/llamafactory/train/pt/trainer.py

@@ -4,7 +4,7 @@ from typing import TYPE_CHECKING, Dict, Optional
 from transformers import Trainer
 
 from ...extras.logging import get_logger
-from ..utils import create_custom_optimzer, create_custom_scheduler
+from ..trainer_utils import create_custom_optimzer, create_custom_scheduler
 
 
 if TYPE_CHECKING:

src/llamafactory/train/pt/workflow.py

@@ -8,7 +8,7 @@ from transformers import DataCollatorForLanguageModeling
 from ...data import get_dataset, split_dataset
 from ...extras.ploting import plot_loss
 from ...model import load_model, load_tokenizer
-from ..utils import create_modelcard_and_push
+from ..trainer_utils import create_modelcard_and_push
 from .trainer import CustomTrainer
 
 

src/llamafactory/train/rm/trainer.py

@@ -7,7 +7,7 @@ import torch
 from transformers import Trainer
 
 from ...extras.logging import get_logger
-from ..utils import create_custom_optimzer, create_custom_scheduler
+from ..trainer_utils import create_custom_optimzer, create_custom_scheduler
 
 
 if TYPE_CHECKING:

src/llamafactory/train/rm/workflow.py

@@ -7,7 +7,7 @@ from ...extras.callbacks import FixValueHeadModelCallback
 from ...extras.misc import fix_valuehead_checkpoint
 from ...extras.ploting import plot_loss
 from ...model import load_model, load_tokenizer
-from ..utils import create_modelcard_and_push
+from ..trainer_utils import create_modelcard_and_push
 from .metric import compute_accuracy
 from .trainer import PairwiseTrainer
 

src/llamafactory/train/sft/trainer.py

@@ -9,7 +9,7 @@ from transformers import Seq2SeqTrainer
 
 from ...extras.constants import IGNORE_INDEX
 from ...extras.logging import get_logger
-from ..utils import create_custom_optimzer, create_custom_scheduler
+from ..trainer_utils import create_custom_optimzer, create_custom_scheduler
 
 
 if TYPE_CHECKING:

src/llamafactory/train/sft/workflow.py

@@ -9,7 +9,7 @@ from ...extras.constants import IGNORE_INDEX
 from ...extras.misc import get_logits_processor
 from ...extras.ploting import plot_loss
 from ...model import load_model, load_tokenizer
-from ..utils import create_modelcard_and_push
+from ..trainer_utils import create_modelcard_and_push
 from .metric import ComputeMetrics
 from .trainer import CustomSeq2SeqTrainer