florence2_output

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

• Loss: 1.5346

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.7452	25.0	100	1.7258
1.1957	50.0	200	1.4125
1.1343	75.0	300	1.4571
1.0557	100.0	400	1.5572
1.0336	125.0	500	1.5346

Framework versions

• PEFT 0.18.1
• Transformers 4.57.3
• Pytorch 2.9.1+cu128
• Datasets 4.4.2
• Tokenizers 0.22.2