segformer-b0-finetuned-lipid-droplets-v5

This model is a fine-tuned version of nvidia/mit-b0 on the jhaberbe/lipid-droplets-v5 dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.3532
• eval_mean_iou: 0.0
• eval_mean_accuracy: 0.0
• eval_overall_accuracy: 0.0
• eval_accuracy_unlabeled: nan
• eval_accuracy_lipid: 0.0
• eval_accuracy_labeled_negative: 0.0
• eval_iou_unlabeled: 0.0
• eval_iou_lipid: 0.0
• eval_iou_labeled_negative: 0.0
• eval_runtime: 0.9807
• eval_samples_per_second: 8.158
• eval_steps_per_second: 1.02
• epoch: 440.0
• step: 440

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 6e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1000

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1