• Model creator: https://huggingface.co/mlfoundations-dev/
• Original model: https://huggingface.co/mlfoundations-dev/tinyllama_alpaca_sft_sample/

Original model description:

• llama-factory
• full
• generated_from_trainer model-index:
• name: tinyllama_alpaca_sft_sample results: []

---

tinyllama_alpaca_sft_sample

• Loss: 1.2134

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 16
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• total_eval_batch_size: 128
• optimizer: Use 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: 1.0

Training results

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.0a0+b465a5843b.nv24.09
• Datasets 3.0.2
• Tokenizers 0.20.3