File size: 1,424 Bytes
cb0d955 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 | [17:14:05] longeval: T=65536 prompt_len=8192 max_new=24 n=100 greedy=1 gpus=0
[17:14:05] haystack: /root/Adhi/BluTrain/dist/Context_Parallelism/lendata/haystack/b2val_haystack.bin
[17:14:05] prompt signature changed -- regenerating prompts and clearing state
[17:14:05] generating prompts: niah_single
[17:14:08] fan-out: 1 GPU(s), NP=1 -> 1 concurrent job(s)
[17:14:08] 1 job(s) to run
[17:14:08] [gpu 0] ext64k / niah_single
[17:19:53] scoring ext64k / niah_single
=== niah_single (prompt_len=8192, n=100) ===
accuracy: 67/100 = 67.0%
depth acc (needle position in context)
0.00 7/20 35.0%
0.25 14/20 70.0%
0.50 15/20 75.0%
0.75 14/20 70.0%
1.00 17/20 85.0%
--- 2 sample generations ---
[HIT ] expect=8056020
got= 8056020.\n
[HIT ] expect=5343902
got= 5343902.\n
wrote ext64k_len_8192/scores/ext64k_niah_single.csv
[17:19:54] building summary
=== per-task accuracy % (secondary/descriptive: ~10 per depth cell) ===
task ext64k
niah_single 67.0
=== PRIMARY: accuracy % pooled by depth across tasks (+-95% Wilson) ===
depth ext64k
0.00 35.0+-19.3
0.25 70.0+-18.7
0.50 75.0+-17.8
0.75 70.0+-18.7
1.00 85.0+-15.4
wrote ext64k_len_8192/summary.csv and ext64k_len_8192/depth_summary.csv
[17:19:54] DONE -> ext64k_len_8192/summary.csv
|