Trackio documentation

Integrasi TRL

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Integrasi TRL

Trackio terintegrasi secara native dengan TRL sehingga Anda dapat mencatat metrik dari trainer TRL mana pun (SFTTrainer, DPOTrainer, GRPOTrainer, dll.) dengan setup minimal. Pastikan Anda telah menginstal versi terbaru dari trl (versi 1.2.0 atau lebih tinggi).

from datasets import Dataset
from trl import SFTConfig, SFTTrainer

# Create a small fake dataset
prompts = ["The capital of France is", "Hamlet was written by"] * 12
completions = [" Paris.", " Shakespeare."] * 12
dataset = Dataset.from_dict({"prompt": prompts, "completion": completions})

# Train a model using the TRL SFTTrainer API
trainer = SFTTrainer(
    model="Qwen/Qwen3-0.6B",
    args=SFTConfig(report_to="trackio", run_name="Qwen3-0.6B-sft"),
    train_dataset=dataset,
)
trainer.train()

Mengonfigurasi Proyek dan Ruang

Atur ID proyek dan ruang secara langsung di konfigurasi TRL Anda (misalnya SFTConfig, DPOConfig, GRPOConfig):

from trl import SFTConfig

args = SFTConfig(
    report_to="trackio",
    run_name="my-run",
    project="my-project",
    trackio_space_id="username/space_id",
)
Update on GitHub