Modelpublic

Balab2021/Qwen2.5-3B-OASST1-QLoRA_h200-run2-conservative

sourceHugging Faceupdated 2mo agoView on Hugging Face

0likes9downloads

Model Card

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