We finetuned gpt2 on tatsu-lab/alpaca Dataset for 5 epochs using MonsterAPI no-code LLM finetuner.
This dataset is HuggingFaceH4/tatsu-lab/alpaca unfiltered, removing 36 instances of blatant alignment.
The finetuning session got completed in 20 minutes and costed us only $3 for the entire finetuning run!
Hyperparameters & Run details:
- Model: gpt2
- Dataset: tatsu-lab/alpaca
- Learning rate: 0.0003
- Number of epochs: 5
- Data split: Training: 90% / Validation: 10%
- Gradient accumulation steps: 1
license: apache-2.0
- Downloads last month
- 100
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for monsterapi/gpt2_alpaca-lora
Base model
openai-community/gpt2
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("gpt2") model = PeftModel.from_pretrained(base_model, "monsterapi/gpt2_alpaca-lora")