florence2-parasitic-egg-detection-version3

This model is a fine-tuned version of microsoft/Florence-2-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8939

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7932	0.2424	200	0.9498
0.8312	0.4848	400	0.9952
0.7408	0.7273	600	0.9016
0.6968	0.9697	800	1.0748
0.8033	1.2121	1000	1.0826
0.7996	1.4545	1200	0.8847
0.7384	1.6970	1400	0.9686
0.7812	1.9394	1600	0.8919
0.6949	2.1818	1800	0.9751
0.6564	2.4242	2000	0.9029
0.6975	2.6667	2200	0.8928
0.6555	2.9091	2400	0.8939

Framework versions

• PEFT 0.18.1
• Transformers 4.45.2
• Pytorch 2.6.0+cu124
• Datasets 4.5.0
• Tokenizers 0.20.3