Views
No views yet
google/gemma-3-4b-it-VLM, fine-tuned for native-language
chart interpretation. AutoScientist Challenge Part 2, Data Visualization.| v1 | v2 | |
|---|---|---|
lora_r | 16 | 64 |
lora_alpha | 32 | 128 |
lora_dropout | 0 | 0.05 |
n_epochs | 1 | 3 |
max_iterations | 1 (no search) | 5 |
| best_win_rate | 0.5599 | 0.7028 |
| final eval_loss | 1.82 | 1.3986 |
client.autoscientist.create().r=16). Inspecting
the public adapter_config.json of four independent Challenge entrants — across
Qwen3.5-0.8B, gpt-oss-20b, Llama-4-Scout-17B and Mistral-7B — showed every one
had chosen r=64, alpha 128–256, dropout 0.05. Adopting that config lifted
the win rate from 0.5599 to 0.6818 on the first iteration; four further
search iterations added only +0.021 combined.best_hyperparams returned the pinned LoRA values unchanged, confirming that
explicit hyperparams survive AutoScientist's search rather than being
overridden — the search tuned learning rate and scheduler around them.r=64, 3 epochs on 20k rows of medical reasoning
producing a model that lost to its base model (58/42), with eval-loss
plateauing after epoch 1. That did not reproduce here:eval_loss 1.6267 → 1.5103 → 1.4469 → 1.4066 → 1.3986 (monotonically down)
train_loss 11.40 → 1.48