henokyemam/Llama-3.2-1B-shared_space-fullmix-14000

---

                               library_name: accelerate
                               license: apache-2.0
                               tags: [Llama-3.2-1B, text-generation, chat]
                               datasets: [shared_spaces]
                               model-index:
                               - name: Llama-3.2-1B (shared_spaces)
                               results: []
                               ---

                               # Llama-3.2-1B — shared_spaces

                               ## Training hyperparameters
                               ```yaml
                               learning_rate: 5e-05
                               num_training_examples: 14000
                               batch_size_per_device: 1
                               gradient_accumulation_steps: 8
                               effective_batch_size: 8
                               max_steps: 1314
                               num_epochs: 3
                               optimizer: adamw
                               num_warmup_steps: 39
                               lr_scheduler_type: linear
                               max_seq_length: 1060
                               precision: bf16
                               gradient_checkpointing: true
                               seed:42
                               ```