unparallelled commited on
Commit
2b2e147
·
verified ·
1 Parent(s): 350dd1a

Upload logs/128k_master.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. logs/128k_master.log +40 -20
logs/128k_master.log CHANGED
@@ -1,20 +1,40 @@
1
- [05:38:41] FATAL: ./build/bluscriptCP_exec not built
2
- [09:16:06] === 680M 131k extension, 8x H200, cp=8 dp=1 ===
3
- [09:16:06] parent : t64 (98 @65,512 -- the 64k model, staged ladder)
4
- [09:16:06] YaRN : SCALE=32 x ORIG=4096 = 131072 == CP_T INVARIANT HOLDS
5
- [09:16:06] virtual range 0..4095 (full), 32 tokens/virtual unit
6
- [09:16:06] LR : peak 1.8e-4 (6e-4 x 0.3), warmup 100 / stable 900 / DECAY 200 -> 6e-5
7
- [09:16:06] data : Data_Loader/Data/mix128 b6=8.9 b5=39 b4=25 b3=15 b1=10, usable 1219 steps, running 1200
8
- [09:16:06] PROBE cp=8 (16384 tok/rank, grad_accum 4)
9
- [09:16:58] PROBE FAILED rc=1 steps=0
10
- [09:17:28] === 680M 131k extension, 8x H200, cp=8 dp=1 ===
11
- [09:17:28] parent : t64 (98 @65,512 -- the 64k model, staged ladder)
12
- [09:17:28] YaRN : SCALE=32 x ORIG=4096 = 131072 == CP_T INVARIANT HOLDS
13
- [09:17:28] virtual range 0..4095 (full), 32 tokens/virtual unit
14
- [09:17:28] LR : peak 1.8e-4 (6e-4 x 0.3), warmup 100 / stable 900 / DECAY 200 -> 6e-5
15
- [09:17:28] data : Data_Loader/Data/mix128 b6=8.9 b5=39 b4=25 b3=15 b1=10, usable 1219 steps, running 1200
16
- [09:17:28] PROBE cp=8 (16384 tok/rank, grad_accum 4)
17
- [09:19:08] PROBE OK cp=8: peak mem: 86705MB of 143771 MiB (H200), dt dt: 20144.88ms
18
- [09:19:08] TRAINING 1200 steps
19
- [11:17:55] done, run 3, loss: 1.024427
20
- [11:17:55] === 131K TRAINING COMPLETE ===
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [11:17:55] === RULER: 1 task(s) x 3 models x 6 lengths, N=100 ===
2
+ [11:17:55] models: t128 t64 base680
3
+ [11:17:55] jobs per length: 3 across 8 GPUs
4
+ [11:17:55] len 4096 (T=262144 x64 -> virtual 64)
5
+ [11:20:28] done: 1/1 tasks scored
6
+ niah_single,87.0,98.0,100.0
7
+ [11:20:28] len 8192 (T=262144 x64 -> virtual 128)
8
+ [11:29:05] done: 1/1 tasks scored
9
+ niah_single,82.0,92.0,99.0
10
+ [11:29:05] len 16384 (T=262144 x64 -> virtual 256)
11
+ [11:41:27] done: 1/1 tasks scored
12
+ niah_single,87.0,100.0,100.0
13
+ [11:41:27] len 32744 (T=262144 x64 -> virtual 511)
14
+ [11:55:01] done: 1/1 tasks scored
15
+ niah_single,79.0,69.0,99.0
16
+ [11:55:01] len 65512 (T=262144 x64 -> virtual 1023)
17
+ [12:15:16] done: 1/1 tasks scored
18
+ niah_single,75.0,54.0,98.0
19
+ [12:15:16] len 131000 (T=262144 x64 -> virtual 2046)
20
+ [13:12:35] done: 1/1 tasks scored
21
+ niah_single,36.0,33.0,62.0
22
+ [13:12:35] === RULER COMPLETE ===
23
+ [13:12:35] len 4096:
24
+ task,base680,t128,t64
25
+ niah_single,87.0,98.0,100.0
26
+ [13:12:35] len 8192:
27
+ task,base680,t128,t64
28
+ niah_single,82.0,92.0,99.0
29
+ [13:12:35] len 16384:
30
+ task,base680,t128,t64
31
+ niah_single,87.0,100.0,100.0
32
+ [13:12:35] len 32744:
33
+ task,base680,t128,t64
34
+ niah_single,79.0,69.0,99.0
35
+ [13:12:35] len 65512:
36
+ task,base680,t128,t64
37
+ niah_single,75.0,54.0,98.0
38
+ [13:12:35] len 131000:
39
+ task,base680,t128,t64
40
+ niah_single,36.0,33.0,62.0