Downloads · 30 days
0
smolvla-finetuned-200-steps
Jonnyyy/smolvla-finetuned-200-steps
smolvla-finetuned-200-steps is a machine learning model from Jonnyyy. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Base Model: lerobot/smolvlabase - Dataset: lerobot/pusht - Training Steps: 200 - Final Loss: 485.9633 - Training Time: 1.7 seconds
Access
Public
Updated Jul 19, 2025
Repo size
2.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.1 MB · 97%
At a glance
- Access
- Public
- Created
- Jul 19, 2025
- Updated
- Jul 19, 2025
- SHA
- 6b3db17a
Model card
From the Hugging Face model README
SmolVLA Fine-tuned Model
Model Details
- Base Model: lerobot/smolvla_base
- Dataset: lerobot/pusht
- Training Steps: 200
- Final Loss: 485.9633
- Training Time: 1.7 seconds
Training Configuration
- Batch Size: 32
- Learning Rate: 0.0001
- Optimizer: AdamW
- Scheduler: Linear with warmup
Usage
import torch
from your_model_class import SmolVLAModel
model = SmolVLAModel()
model.load_state_dict(torch.load("pytorch_model.bin"))
model.eval()
Performance
- Loss reduction: 99.4% (77241.1484 → 485.9633)
- Trained on 25650 robotic manipulation samples
Model trained using Modal + Claude Code pipeline
- Created
- Jul 19, 2025
- Updated
- Jul 19, 2025