llama-3-1-bio-V1-instruction_V1

This model is a fine-tuned version of data/llama-3-1-bio-base_V1 on the lamm-mit/orpo-dpo-mix-40k, the lamm-mit/bioinspired_gpt-4o-mini-silk_dataset_V10-orpo_dataset_V10_messageformat and the lamm-mit/bioinspired_gpt-4o-mini-dataset_V1_B-cleaned-orpo_dataset_V10_messageformat datasets.

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: 5e-06
• train_batch_size: 4
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 32
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: inverse_sqrt
• lr_scheduler_warmup_steps: 100
• num_epochs: 3

Training results

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1