CITADEL
StandbyNothing is live right now.
Eval accuracy
%
no eval

Claviger router: OneJev 0.8B (backfilled)

finishedRadeon 8060S

A model that routes a request to the one destination, of many, that should take it. Backfilled: recorded after the fact from the run's own logs and records. Times inside a run are estimated, and there are no GPU sensor readings.

started
Tue 10 Nov, 17:10 UTC
ran for
45:50
config
learning rate 0.00001, batch 1, seed 2 of 3

run5/5step42/42epoch1/1config1/3seed2/3lr0.00001batch1modelOneJev1.6-0.8B 0.8Brevc89933c

Loss train 0.3961 ▲ +0.2921 lowest 0.0000 at step 15 run before, run 4 ▲ +0.3947 step 42
Timebase
Range
Smoothing
Reference
42 readings, 30 min/div10 min/div5 min/div
012300:0030:00phase starting, 0.0 s to 65.5 sphase training, 65.5 s to 45:50epoch 1, 65.5 straining+0.2921since first0.1040Lowest last train loss across this project's 5 runs, run 4lowest last 0.0014, run 40.3961012300:0010:0020:0030:0040:00phase starting, 0.0 s to 65.5 sphase training, 65.5 s to 45:50epoch 1, 65.5 straining0.1040Lowest last train loss across this project's 5 runs, run 4lowest last 0.0014, run 40.3961▲ +0.2921012300:0005:0010:0015:0020:0025:0030:0035:0040:0045:00phase starting, 0.0 s to 65.5 sphase training, 65.5 s to 45:50epoch 1, 65.5 straining0.1040Lowest last train loss across this project's 5 runs, run 4lowest last 0.0014, run 40.3961▲ +0.2921

Elapsed

65.5 s to epoch 1, 2684.9 s to last reading

42 of 42 steps, 1 of 1 epochs, 100%

65.5 s per step, 0.9 steps a minute

Set-up

666 train

synthetic, learning rate 0.00001, batch size 1, grad accum 16, epochs 1, optimizer adamw, seed 2

Learning rate

0.00e+0

▼ −1.00e-5 since first

Input

  • Runs128 runs
  • Agentsnone showing
  • Treesnone showing
  • Projectsnone showing

Check

Every entry is checked on its way out; some are held for review.

Not shown on any run: data samples, predictions, raw logs, file paths, machine names

Delay

2 min, set

Watching the agents work, about 2 min behind.

One way

Nothing here reaches the agents.

This page

This page updates by itself.

visits counted with Google Analytics · choose

Runsheight is eval accuracyall recordings ▸ | finished× failed■ stopped○ lost● live newer ▸

5 of 5 finished, -, config 1 of 3 (learning rate 0.00001, batch 1), seed 2 of 3, Tue 10 Nov, 17:10 UTC

▸
Runs as a table
StartedStatusEval accuracyStepsConfig
Tue 10 Nov, 17:10 UTC| finished-42 of 42learning rate 0.00001, batch 1, seed 2 of 3
Tue 10 Nov, 16:24 UTC| finished-42 of 42learning rate 0.00001, batch 1, seed 1 of 3
Tue 10 Nov, 15:27 UTC| finished0.084742 of 42learning rate 0.00005, batch 1, seed 0
Tue 10 Nov, 14:30 UTC| finished0.912742 of 42learning rate 0.00002, batch 1, seed 0
Tue 10 Nov, 13:33 UTC| finished0.923342 of 42learning rate 0.00001, batch 1, seed 0 of 3

Plate

Model
OmniJev/OneJev1.6-0.8B, 0.8B parameters revision c89933c
Data
Synthetic routing worlds, synthetic
Config
learning rate 0.00001, batch size 1, grad accum 16, epochs 1, optimizer adamw, seed 2
Hardware
Radeon 8060S, ROCm

Log

Since startMark
0.0 sphase starting
65.5 sphase training
65.5 sepoch 1
187 h 41 min laterwent public

Seeds

SeedStatusEval accuracy
seed 0| finished0.9233
seed 1| finished-
seed 2| finished-

Readings

42 rows as a table
StepSecondsTrain lossLearning rate
165.50.10401.00e-5
2131.00.37419.99e-6
3196.50.59169.94e-6
4261.90.01359.87e-6
5327.40.04159.77e-6
6392.90.28639.64e-6
7458.40.00369.48e-6
8523.90.00299.30e-6
9589.40.00219.09e-6
10654.90.00688.86e-6
11720.31.09308.60e-6
12785.80.00068.33e-6
13851.30.00318.03e-6
14916.80.00127.72e-6
15982.30.00007.39e-6
161047.82.09547.05e-6
171113.30.15206.69e-6
181178.71.06946.32e-6
191244.21.78945.95e-6
201309.70.36035.57e-6
211375.20.00015.19e-6
221440.70.42904.81e-6
231506.20.00004.43e-6
241571.70.93084.05e-6
251637.10.65073.68e-6
261702.60.01393.31e-6
271768.10.00012.95e-6
281833.60.78602.61e-6
291899.10.93552.28e-6
301964.60.25991.97e-6
312030.11.10821.67e-6
322095.50.44521.40e-6
332161.00.33831.14e-6
342226.50.00049.10e-7
352292.01.26147.02e-7
362357.50.05705.19e-7
372423.00.01863.62e-7
382488.50.00002.33e-7
392553.90.01641.32e-7
402619.40.10985.86e-8
412684.91.00571.47e-8
422750.40.39610.00e+0

Worked out

ReadoutValueWorked out from
Run complete100%42 steps over 42
Step time65.5 s2684.9 s over 41 steps, between readings. Startup and intervals that hold an eval are left out
Steps per minute0.960 s over the step time of 65.49 s
Train loss since first reading+0.29210.3961 at step 42 minus 0.1040 at step 1
Lowest train loss0.0000Lowest of 42 readings, at step 15
Lowest last train loss0.0014Lowest last train loss across this project's 5 runs, run 4
Items per second0.01 step over 65.49 s, times batch size 1
Train loss against run 4+0.39470.3961 minus 0.0014 on run 4, both at step 42
Learning rate since first reading−1.00e-50.00e+0 minus 1.00e-5