Select Model

Pick a pre-trained checkpoint to fine-tune.

Method

Full parameter or LoRA.

Training Data

Upload a CSV or fall back to finetuning.csv.

Hyperparameters

Optimize fine-tuning behavior.

Core Settings
Optimization
Evaluation & Checkpointing

Batch Size

4

Learning Rate

0.00001

Max Length

512

Understand

Masked loss and optional LoRA math.

Equations

Sequence construction

sequence=[prompt]+[response]\text{sequence} = [\text{prompt}] + [\text{response}]

Masked loss

mi=1 for response tokens, 0 otherwisem_i = 1 \text{ for response tokens, } 0 \text{ otherwise}

L=imiLiimi\mathcal{L} = \frac{\sum_i m_i \cdot \mathcal{L}_i}{\sum_i m_i}

Code Snippets

No snippets available yet.

Train

Train your model.

Demo mode: fine-tuning disabled.

Live Metrics

Loss and gradients.

Progress

0.0%

Elapsed

-

ETA

-

Loss

-

Running Loss

-

Grad Norm

-

Inspect Batch

Prompt vs response tokens and attention patterns.

0 / 3

Select a sample to inspect prompt/response tokens.

0 / 0
0 / 0
Query ↓Key →

Eval History

Train vs validation loss.

Logs

Checkpoint events.

No logs yet.