nucleotide-transformer-finetuned-lora-NucleotideTransformer

This model is a fine-tuned version of InstaDeepAI/nucleotide-transformer-500m-human-ref on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.8526
• eval_f1_score: 0.5905
• eval_x_ratio_reference: 0.5130
• eval_x_ratio_predictions: 0.4583
• eval_runtime: 2.9222
• eval_samples_per_second: 136.884
• eval_steps_per_second: 4.449
• epoch: 2.4252
• step: 3000

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: 32
• eval_batch_size: 32
• 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
• training_steps: 5000

Framework versions

• PEFT 0.16.0
• Transformers 4.54.0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2