danielharkin21 commited on
Commit
ff1ef54
·
verified ·
1 Parent(s): 870b62b

Upload training_status.txt with huggingface_hub

Browse files
Files changed (1) hide show
  1. training_status.txt +11 -11
training_status.txt CHANGED
@@ -1,21 +1,21 @@
1
  =======================================================
2
  EDDIE TRAINING STATUS — 2x T4 DDP (SPEED EXP)
3
  =======================================================
4
- Updated : 2026-09-16 06:24:31 UTC
5
- Epoch : 3280
6
- Train CE : 0.818814
7
  Best CE : 0.809309
8
  Cortex base : nan
9
- U-loss (Huber): 0.109862
10
- Total loss : 0.928676
11
  -------------------------------------------------------
12
  u target : excess (signed excess of p; ~0 = trust p)
13
- excess mean : -0.0017 (p calibrated on avg if ~0)
14
- u mean : -0.0417 (should track excess mean)
15
- u corr : 0.0092 (Pearson u vs realized excess)
16
- u R^2 : -0.0304 (>0 = beats constant)
17
- u spread : +0.0041 (excess top-q u minus bottom-q u; want >0)
18
- const Huber : 0.1106 (u useful if U-loss < this: YES)
19
  -------------------------------------------------------
20
  Speed : 342 samples/s | 1.6 min/epoch
21
  Batch/GPU : 32 | GPUs: 2
 
1
  =======================================================
2
  EDDIE TRAINING STATUS — 2x T4 DDP (SPEED EXP)
3
  =======================================================
4
+ Updated : 2026-09-16 06:32:22 UTC
5
+ Epoch : 3285
6
+ Train CE : 0.818955
7
  Best CE : 0.809309
8
  Cortex base : nan
9
+ U-loss (Huber): 0.108688
10
+ Total loss : 0.927643
11
  -------------------------------------------------------
12
  u target : excess (signed excess of p; ~0 = trust p)
13
+ excess mean : -0.0004 (p calibrated on avg if ~0)
14
+ u mean : -0.0418 (should track excess mean)
15
+ u corr : 0.0098 (Pearson u vs realized excess)
16
+ u R^2 : -0.0336 (>0 = beats constant)
17
+ u spread : +0.0011 (excess top-q u minus bottom-q u; want >0)
18
+ const Huber : 0.1115 (u useful if U-loss < this: YES)
19
  -------------------------------------------------------
20
  Speed : 342 samples/s | 1.6 min/epoch
21
  Batch/GPU : 32 | GPUs: 2