yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-11-01 18:43:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Default configs are better

Browse Source
This commit is contained in:
Jake Poznanski 2025-07-01 20:36:06 +00:00
parent 56e51ea23a
commit 94d7900887
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
olmocr/train/config.py
View File

@ -139,7 +139,7 @@ class TrainingConfig:
"""Configuration for training parameters."""
output_dir: str = "./outputs"
num_train_epochs: int = 3
num_train_epochs: int = 1
per_device_train_batch_size: int = 1
per_device_eval_batch_size: int = 1
gradient_accumulation_steps: int = 8
@ -158,7 +158,7 @@ class TrainingConfig:
max_grad_norm: float = 1.0
# Gradient checkpointing
gradient_checkpointing: bool = True
gradient_checkpointing: bool = False
gradient_checkpointing_kwargs: Dict[str, Any] = field(default_factory=lambda: {"use_reentrant": False})
# Evaluation and checkpointing
@ -178,9 +178,9 @@ class TrainingConfig:
logging_first_step: bool = True
report_to: List[str] = field(default_factory=lambda: ["wandb"])
# Other training settings
# Force seeds to a consistent value for reproducibility
seed: int = 42
data_seed: Optional[int] = None
data_seed: Optional[int] = 42
# Performance
dataloader_drop_last: bool = True