1 pending

Run Dossier

Training run for UniFuse

27 metrics · 725 train · 0 val

Chart Overlays

Compare this run against its peers

0/59
Add peer runs here to layer their train and val traces onto the current metric charts.
running Apr 11, 15:14 Started 202d 12h ago Python 3.11.7 src/train.py --config configs/model/inverted_joint_metric.yaml --config configs/model/backbone_dinov2_vitl14.yaml --config configs/data/real_drive_sim_euler_loading.yaml --config configs/training/phase_a_geometry_prompt.yaml
lr 0.001000batch 8epochs 20precision automodel weather_metric_system seed 13wd 1e-4
ID 63048210
unifuse/runs/2026-04-11_15-14-07_3b52
Metrics 27/27
depth.train 17
diag 7
consolidation 1
delta_vs_prior
final 3
depth_mae
log_radius_l1
xyz_l1
prior 3
depth_mae
log_radius_l1
xyz_l1
loss 10
final 4
confidence
depth
log_radius
xyz
pred 1
log_radius
prior 4
aux_metric_probe
aux_metric_probe_confidence
confidence
log_radius
no stage 1
total
rgb.train 1
smoothness
sys.train 9
gpu_mem_total_gb
gpu_mem_used_gb
gpu_mem_util_pct
gpu_util_pct
lr
lr.default
lr.fine_geometry_head
lr.geometry_encoder_adapter
lr.prompt_encoder
X-Axis
Y-Scale
Series
Group
Namespace

Delta Vs Prior

↓ kind=diagstage=consolidation
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Depth Mae

↓ meters kind=diagstage=final
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Log Radius L1

↓ kind=diagstage=final
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Xyz L1

↓ meters kind=diagstage=final
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Depth Mae

↓ meters kind=diagstage=prior
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Log Radius L1

↓ kind=diagstage=prior
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Xyz L1

↓ meters kind=diagstage=prior
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Confidence

↑ kind=lossstage=final
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Depth

↓ meters kind=lossstage=final
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Log Radius

↓ kind=lossstage=final
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Xyz

↓ meters kind=lossstage=final
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Log Radius

↓ kind=lossstage=pred
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Aux Metric Probe

kind=lossstage=prior
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Aux Metric Probe Confidence

kind=lossstage=prior
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Confidence

↑ kind=lossstage=prior
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Log Radius

↓ kind=lossstage=prior
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Total

↓ kind=loss
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Smoothness

↓ kind=lossstage=weather
T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Gpu Mem Total Gb

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Gpu Mem Used Gb

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Gpu Mem Util Pct

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Gpu Util Pct

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Lr

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Lr.Default

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Lr.Fine Geometry Head

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Lr.Geometry Encoder Adapter

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

Lr.Prompt Encoder

T
2026-04-11_15-14-07_3b52 train (smoothed) —
2026-04-11_15-14-07_3b52 train (raw) —

No output snapshots found for this run.

Outputs are generated during training and saved to outputs/epoch_N_step_M/ directories.

Run-Owned Exports

Publish direct filesystem paths here.

Published

No run-owned exports are published yet.

Raw Artifacts

Run-owned exports are typically direct paths, so there are no captured artifacts to publish from here.

Euler View - ML Experiment Monitor