• Model creator: https://huggingface.co/klcsp/
• Original model: https://huggingface.co/klcsp/llama3.1-8b-gpt4o_100k_classification-fft/

Original model description:

• alignment-handbook
• trl
• sft
• generated_from_trainer
• trl
• sft
• generated_from_trainer datasets:
• llama-duo/synth_classification_dataset_dedup model-index:
• name: llama3.1-8b-gpt4o_100k_classification-fft results: []

---

llama3.1-8b-gpt4o_100k_classification-fft

• Loss: 2.2658

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 0.0003
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0