Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference

finetune reproduction

#9
by ZhangAI - opened

Thank you for your open source, I am replicating your fine-tuning process according to the code on github. Do the results of train loss=0.16 and eval_loss=0.21 I trained on the 75k dataset match yours? I will continue training on the 110k dataset.
I trained for 4 epochs and indeed started overfitting after the second epoch.

You're welcome! Your results are close to ours; slight variations are normal. Overfitting after two epochs aligns with our observations.. Training on 110k should improve generalization—great work replicating!

The cheapest Manaforge Omega Heroic boost is the perfect option for players who want to clear the raid on Heroic difficulty without spending too much money. Many boosting services, like Gamingcy and similar platforms, offer budget-friendly packages where you can join professional raiders to defeat all bosses, farm high ilvl loot, and secure tier set pieces at the lowest possible cost.

Sign up or log in to comment