Downloads · 30 days
8
16% of all-time downloads
iFaz/eqm-pusht-seed3-21sep2026_4am
eqm-pusht-seed3-21sep2026_4am is a robotics model from iFaz. Use it for the robotics task on the model card, and read the license before you ship it in a product. It is set up for lerobot. The card lists the license as apache-2.0.
Trained with LeRobot. Date: 2026-09-21 10:22 Policy type: eqm | Device: cuda
Downloads · 30 days
8
16% of all-time downloads
All-time downloads
49
Public
Parameters
18.7M
74.8 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors74.8 MB · 100%
From the Hugging Face model README
Trained with LeRobot.
Date: 2026-09-21 10:22
Policy type: eqm | Device: cuda
| Parameter | Value |
|---|---|
dataset.repo_id | lerobot/pusht |
| Parameter | Value |
|---|---|
steps | 80000 |
batch_size | 8 |
eval_freq | 0 |
save_freq | 40000 |
num_workers | 4 |
seed | 3 |
eval.n_episodes | 1 |
eval.batch_size | 1 |
eval.use_async_envs | True |
| Parameter | Value |
|---|---|
ebm | l2 |
jacobian_reg_weight | 0.001 |
jacobian_reg_probes | 1 |
fixed_point_anchor_weight | 0.1 |
c_gamma_a | 0.5 |
use_adaptive_compute | False |
| Parameter | Value |
|---|---|
env.type | pusht |
env.task | PushT-v0 |
eval.n_episodes | 100 |
eval.batch_size | 1 |
eval.use_async_envs | False |
policy.path | /content/outputs/train/pusht_seed3/checkpoints/last/pretrained_model |
policy.ood_logging_enabled | True |
policy.ood_calibration_stats_path | /kaggle/working/eqm_calibration.json |
policy.ood_log_path | /kaggle/working/outputs/eqm_ood_log.csv |
policy.ood_z_threshold | 3.0 |
| Metric | Value |
|---|---|
| Episodes | 100 |
| Success rate | 0.0% |
| Avg sum reward | 3.10 |
| Avg max reward | 0.18 |
| Eval time (s) | 1535.8 |
@misc{cadene2024lerobot,
author = {Cadene, Remi and Alibert, Simon and others},
title = {LeRobot},
year = {2024},
url = {https://github.com/huggingface/lerobot}
}