danielharkin21 commited on
Commit
48d8bc0
·
verified ·
1 Parent(s): 28adb2b

Upload training_status.txt with huggingface_hub

Browse files
Files changed (1) hide show
  1. training_status.txt +20 -0
training_status.txt ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ =======================================================
2
+ EDDIE TRAINING STATUS — 2x T4 DDP
3
+ =======================================================
4
+ Updated : 2026-08-15 04:20:51 UTC
5
+ Epoch : 5
6
+ Train Loss : 1.063693
7
+ Best Train : 1.063693
8
+ -------------------------------------------------------
9
+ Speed : 10,447 samples/s | 1.6 min/epoch
10
+ Batch/GPU : 8 | GPUs: 2
11
+ Grad Accum : 32 | Eff BS: 512
12
+ -------------------------------------------------------
13
+ Architecture : Cortex
14
+ Params : 2,925,699
15
+ Context : 1024 bars | Features: 5
16
+ Total windows: 501,051,135
17
+ Note: no held-out validation split -- every training example
18
+ is drawn without replacement from ~2.4B windows, so batches
19
+ are effectively unseen data by construction.
20
+ =======================================================