Skip to main content

Fine-Tune Models

Fine-tune pre-trained LLMs and diffusion models on your own data using E2E AI Cloud's high-performance GPU infrastructure. Foundation Studio manages compute so you can focus on data, configuration, and results.

GPU TrainingCustom DatasetsHyperparameter TuningWandB IntegrationModel Checkpoints

Quick Start​


What can you do with Fine-Tune Models?​

Fine-tune LLMs (Llama, Mistral, BLOOM, Gemma) and diffusion models on your own data

Use custom .jsonl datasets from EOS or pull directly from Hugging Face

Configure hyperparameters, quantization, and gradient accumulation

Resume training from any previous checkpoint

Track experiments in real time with Weights & Biases (WandB)

Deploy fine-tuned models directly to Inference endpoints

Key Characteristics​

Models

Wide Model Support

Fine-tune Llama 3.x, Gemma 7B, Stable Diffusion, and SDXL. Gated models require a Hugging Face token.

Data

Flexible Dataset Input

Bring custom .jsonl datasets via EOS buckets or link directly to any public or private Hugging Face dataset.

Compute

High-Performance GPUs

Choose from H100 and A100 GPU plans. H100 for large models and fast iteration; A100 for most 7B–13B workloads.

Training

Full Hyperparameter Control

Set training type, epochs, learning rate, batch size, gradient accumulation, and quantization (4-bit, DoubleQuant).

Monitoring

Built-in Observability

View training logs, loss curves, GPU utilization, and memory metrics. Optionally integrate WandB for full experiment tracking.

Output

Checkpoint Management

All checkpoints and LoRA adapters are stored in a model repository. Resume from any checkpoint or deploy directly to inference.


Best Practices​

Best Practices for Fine-Tuning

Validate your dataset first

Ensure your .jsonl file is correctly formatted before uploading. A single malformed line will cause the job to fail.

Start small

Run 1–2 epochs on a small dataset slice to validate configuration before committing to a full training run.

Use quantization for large models

Enable Load in 4Bit when fine-tuning models larger than 7B to reduce GPU memory usage and cost.

Track experiments with WandB

Enable WandB integration to compare runs, catch overfitting early, and maintain a complete training history.


API Reference​

REST API

</>Fine-Tune Models API Reference

Programmatically create, list, manage, and delete fine-tuning jobs in TIR.

Explore REST APIs
Authentication & Endpoints
Request and Response Schemas
Open API Reference →
tir.e2enetworks.com / api / v1
GET/teams/{Team_Id}/projects/{Project_Id}/finetune/jobs/List fine-tuning jobs
POST/teams/{Team_Id}/projects/{Project_Id}/finetune/jobs/Create a fine-tuning job
GET/teams/{Team_Id}/projects/{Project_Id}/finetune/jobs/{job_id}/Get fine-tuning job details
PUT/teams/{Team_Id}/projects/{Project_Id}/finetune/jobs/{job_id}/Retry or terminate a job
DELETE/teams/{Team_Id}/projects/{Project_Id}/finetune/jobs/{job_id}/Delete a fine-tuning job