• Model creator: https://huggingface.co/klcsp/
• Original model: https://huggingface.co/klcsp/llama3-8b-fft-summarization-11-v1/

Original model description:

• trl
• sft
• generated_from_trainer datasets:
• generator model-index:
• name: llama3-8b-fft-summarization-11-v1 results: []

---

llama3-8b-fft-summarization-11-v1

• Loss: 2.2775

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• total_eval_batch_size: 128
• 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: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• Transformers 4.46.3
• Pytorch 2.3.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3