Llama-3.2-1B-SPIN-iter2

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the HuggingFaceH4/ultrachat_200k datasets.

Model description

• Model type: A 1B parameter GPT-like model fine-tuned on synthetic datasets.
• Language(s) (NLP): Primarily English
• License: Llama 3.2 Community Lisense Agreement
• Finetuned from model: meta-llama/Llama-3.2-1B

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-07
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 6.0