Some bug in object detect when train in macbook

I’m working on an open source project
The purpose is to use huggingface to train a task, only need to modify the yaml file can be adapted to a variety of model training.
I’ve already completed the
image classification
Currently working on object detection
object detect This is an unfinished product, and while the training works fine, there is a bug that the model does not converge. So I checked huggingface object detect tutorial.
Then I ran him on a colab and he was able to converge, then I ran the same code on my own computer, a macbook, and the model did not converge. I really can’t clear what’s causing this, can any of you tell me how to fix it?

MODEL_NAME = "microsoft/conditional-detr-resnet-50"  # or "facebook/detr-resnet-50"
IMAGE_SIZE = 480

from datasets import load_dataset

cppe5 = load_dataset("cppe-5")

import numpy as np
import os
from PIL import Image, ImageDraw



categories = cppe5["train"].features["objects"].feature["category"].names

id2label = {index: x for index, x in enumerate(categories, start=0)}
label2id = {v: k for k, v in id2label.items()}

from transformers import AutoImageProcessor

MAX_SIZE = IMAGE_SIZE

image_processor = AutoImageProcessor.from_pretrained(
    MODEL_NAME,
    do_resize=True,
    size={"max_height": MAX_SIZE, "max_width": MAX_SIZE},
    do_pad=True,
    pad_size={"height": MAX_SIZE, "width": MAX_SIZE},
)

# import albumentations as A

# train_augment_and_transform = A.Compose(
#     [
#         A.Perspective(p=0.1),
#         A.HorizontalFlip(p=0.5),
#         A.RandomBrightnessContrast(p=0.5),
#         A.HueSaturationValue(p=0.1),
#     ],
#     bbox_params=A.BboxParams(format="coco", label_fields=["category"], clip=True, min_area=25),
# )

# validation_transform = A.Compose(
#     [A.NoOp()],
#     bbox_params=A.BboxParams(format="coco", label_fields=["category"], clip=True),
# )

train_augment_and_transform = None
validation_transform = None

def format_image_annotations_as_coco(image_id, categories, areas, bboxes):
    """Format one set of image annotations to the COCO format

    Args:
        image_id (str): image id. e.g. "0001"
        categories (List[int]): list of categories/class labels corresponding to provided bounding boxes
        areas (List[float]): list of corresponding areas to provided bounding boxes
        bboxes (List[Tuple[float]]): list of bounding boxes provided in COCO format
            ([center_x, center_y, width, height] in absolute coordinates)

    Returns:
        dict: {
            "image_id": image id,
            "annotations": list of formatted annotations
        }
    """
    annotations = []
    for category, area, bbox in zip(categories, areas, bboxes):
        formatted_annotation = {
            "image_id": image_id,
            "category_id": category,
            "iscrowd": 0,
            "area": area,
            "bbox": list(bbox),
        }
        annotations.append(formatted_annotation)

    return {
        "image_id": image_id,
        "annotations": annotations,
    }
    
def augment_and_transform_batch(examples, transform, image_processor, return_pixel_mask=False):
    """Apply augmentations and format annotations in COCO format for object detection task"""

    images = []
    annotations = []
    for image_id, image, objects in zip(examples["image_id"], examples["image"], examples["objects"]):
        image = np.array(image.convert("RGB"))

        # apply augmentations
        # output = transform(image=image, bboxes=objects["bbox"], category=objects["category"])
        images.append(image)

        # format annotations in COCO format
        formatted_annotations = format_image_annotations_as_coco(
            image_id, objects["category"], objects["area"], objects["bbox"]
        )
        annotations.append(formatted_annotations)

    # Apply the image processor transformations: resizing, rescaling, normalization
    result = image_processor(images=images, annotations=annotations, return_tensors="pt")

    if not return_pixel_mask:
        result.pop("pixel_mask", None)

    return result

from functools import partial

# Make transform functions for batch and apply for dataset splits
train_transform_batch = partial(
    augment_and_transform_batch, transform=train_augment_and_transform, image_processor=image_processor
)
validation_transform_batch = partial(
    augment_and_transform_batch, transform=validation_transform, image_processor=image_processor
)

cppe5["train"] = cppe5["train"].with_transform(train_transform_batch)
cppe5["test"] = cppe5["test"].with_transform(validation_transform_batch)

import torch

def collate_fn(batch):
    data = {}
    data["pixel_values"] = torch.stack([x["pixel_values"] for x in batch])
    data["labels"] = [x["labels"] for x in batch]
    if "pixel_mask" in batch[0]:
        data["pixel_mask"] = torch.stack([x["pixel_mask"] for x in batch])
    return data


from transformers.image_transforms import center_to_corners_format

def convert_bbox_yolo_to_pascal(boxes, image_size):
    """
    Convert bounding boxes from YOLO format (x_center, y_center, width, height) in range [0, 1]
    to Pascal VOC format (x_min, y_min, x_max, y_max) in absolute coordinates.

    Args:
        boxes (torch.Tensor): Bounding boxes in YOLO format
        image_size (Tuple[int, int]): Image size in format (height, width)

    Returns:
        torch.Tensor: Bounding boxes in Pascal VOC format (x_min, y_min, x_max, y_max)
    """
    # convert center to corners format
    boxes = center_to_corners_format(boxes)

    # convert to absolute coordinates
    height, width = image_size
    boxes = boxes * torch.tensor([[width, height, width, height]])

    return boxes



import numpy as np
from dataclasses import dataclass
from torchmetrics.detection.mean_ap import MeanAveragePrecision


@dataclass
class ModelOutput:
    logits: torch.Tensor
    pred_boxes: torch.Tensor


@torch.no_grad()
def compute_metrics(evaluation_results, image_processor, threshold=0.0, id2label=None):
    """
    Compute mean average mAP, mAR and their variants for the object detection task.

    Args:
        evaluation_results (EvalPrediction): Predictions and targets from evaluation.
        threshold (float, optional): Threshold to filter predicted boxes by confidence. Defaults to 0.0.
        id2label (Optional[dict], optional): Mapping from class id to class name. Defaults to None.

    Returns:
        Mapping[str, float]: Metrics in a form of dictionary {<metric_name>: <metric_value>}
    """

    predictions, targets = evaluation_results.predictions, evaluation_results.label_ids

    # For metric computation we need to provide:
    #  - targets in a form of list of dictionaries with keys "boxes", "labels"
    #  - predictions in a form of list of dictionaries with keys "boxes", "scores", "labels"

    image_sizes = []
    post_processed_targets = []
    post_processed_predictions = []

    # Collect targets in the required format for metric computation
    for batch in targets:
        # collect image sizes, we will need them for predictions post processing
        batch_image_sizes = torch.tensor(np.array([x["orig_size"] for x in batch]))
        image_sizes.append(batch_image_sizes)
        # collect targets in the required format for metric computation
        # boxes were converted to YOLO format needed for model training
        # here we will convert them to Pascal VOC format (x_min, y_min, x_max, y_max)
        for image_target in batch:
            boxes = torch.tensor(image_target["boxes"])
            boxes = convert_bbox_yolo_to_pascal(boxes, image_target["orig_size"])
            labels = torch.tensor(image_target["class_labels"])
            post_processed_targets.append({"boxes": boxes, "labels": labels})

    # Collect predictions in the required format for metric computation,
    # model produce boxes in YOLO format, then image_processor convert them to Pascal VOC format
    for batch, target_sizes in zip(predictions, image_sizes):
        batch_logits, batch_boxes = batch[1], batch[2]
        output = ModelOutput(logits=torch.tensor(batch_logits), pred_boxes=torch.tensor(batch_boxes))
        post_processed_output = image_processor.post_process_object_detection(
            output, threshold=threshold, target_sizes=target_sizes
        )
        post_processed_predictions.extend(post_processed_output)

    # Compute metrics
    metric = MeanAveragePrecision(box_format="xyxy", class_metrics=True)
    metric.update(post_processed_predictions, post_processed_targets)
    metrics = metric.compute()

    # Replace list of per class metrics with separate metric for each class
    classes = metrics.pop("classes")
    map_per_class = metrics.pop("map_per_class")
    mar_100_per_class = metrics.pop("mar_100_per_class")
    for class_id, class_map, class_mar in zip(classes, map_per_class, mar_100_per_class):
        class_name = id2label[class_id.item()] if id2label is not None else class_id.item()
        metrics[f"map_{class_name}"] = class_map
        metrics[f"mar_100_{class_name}"] = class_mar

    metrics = {k: round(v.item(), 4) for k, v in metrics.items()}

    return metrics


eval_compute_metrics_fn = partial(
    compute_metrics, image_processor=image_processor, id2label=id2label, threshold=0.0
)


from transformers import AutoModelForObjectDetection

model = AutoModelForObjectDetection.from_pretrained(
    MODEL_NAME,
    id2label=id2label,
    label2id=label2id,
    ignore_mismatched_sizes=True,
)


from transformers import TrainingArguments

training_args = TrainingArguments(
    output_dir="detr_finetuned_cppe5",
    num_train_epochs=30,
    fp16=False,
    per_device_train_batch_size=4,
    dataloader_num_workers=0,
    learning_rate=5e-5,
    lr_scheduler_type="cosine",
    weight_decay=1e-4,
    max_grad_norm=0.01,
    metric_for_best_model="eval_map",
    greater_is_better=True,
    load_best_model_at_end=True,
    eval_strategy="epoch",
    save_strategy="epoch",
    # save_total_limit=2,
    remove_unused_columns=False,
    eval_do_concat_batches=False,
    # push_to_hub=True,
)


from transformers import Trainer

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=cppe5["train"],
    eval_dataset=cppe5["test"],
    tokenizer=image_processor,
    data_collator=collate_fn,
    compute_metrics=eval_compute_metrics_fn,
)

trainer.train()

this is the code which is ok in colab but not ok in my computer