run2_conservative
QLoRA adapter fine-tuned from Qwen/Qwen2.5-3B-Instruct on OpenAssistant/oasst1.
Final metrics
- train_loss: 1.3559324711929133
- eval_loss: 1.4965205192565918
- loss_gap: 0.14058804806367853
- eval_perplexity: 4.4661222175075865
- train_runtime: 2643.5786
- samples_per_second: 6.852
- global_steps: 1134
- Downloads last month
- 19