File size: 3,441 Bytes
68c9404 | 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 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 | [08:22:44] longeval: T=16384 prompt_len=16360 max_new=24 n=100 greedy=1 gpus=0,1,2,3
[08:22:44] haystack: Data_Loader/Data/flux_val_000000.bin
[08:22:44] prompt signature changed -- regenerating prompts and clearing state
[08:22:44] generating prompts: niah_single
[08:22:45] generating prompts: val_backward
[08:22:45] fan-out: 4 GPU(s), NP=1 -> 8 concurrent job(s)
[08:22:45] 4 job(s) to run
[08:22:45] [gpu 0] base_c / niah_single
[08:22:45] [gpu 1] base_c / val_backward
[08:22:45] [gpu 2] armB_c / niah_single
[08:22:45] [gpu 3] armB_c / val_backward
[08:35:05] scoring base_c / niah_single
=== niah_single (prompt_len=16360, n=100) ===
accuracy: 27/100 = 27.0%
depth acc (needle position in context)
0.00 0/20 0.0%
0.25 0/20 0.0%
0.50 2/20 10.0%
0.75 7/20 35.0%
1.00 18/20 90.0%
--- 2 sample generations ---
[MISS] expect=8056020
got= the number of the number of the number of the number of the number of the number of the number of the number of
[MISS] expect=5343902
got= 7.\nHow much does Anna Katarina earn per year?\n
wrote newck_len_16360/scores/base_c_niah_single.csv
[08:35:06] scoring base_c / val_backward
=== val_backward (prompt_len=16360, n=100) ===
accuracy: 0/100 = 0.0%
depth acc (needle position in context)
0.00 0/20 0.0%
0.25 0/20 0.0%
0.50 0/20 0.0%
0.75 0/20 0.0%
1.00 0/20 0.0%
--- 2 sample generations ---
[MISS] expect=yarrow
got= the number 8056020.\n
[MISS] expect=cactus
got= called "The Magician".\n
wrote newck_len_16360/scores/base_c_val_backward.csv
[08:35:06] scoring armB_c / niah_single
=== niah_single (prompt_len=16360, n=100) ===
accuracy: 23/100 = 23.0%
depth acc (needle position in context)
0.00 0/20 0.0%
0.25 0/20 0.0%
0.50 2/20 10.0%
0.75 4/20 20.0%
1.00 17/20 85.0%
--- 2 sample generations ---
[MISS] expect=8056020
got= the number of the moon.\n
[MISS] expect=5343902
got= 7.\nQuestion: What is the birth name of Anna Katarina?\n
wrote newck_len_16360/scores/armB_c_niah_single.csv
[08:35:06] scoring armB_c / val_backward
=== val_backward (prompt_len=16360, n=100) ===
accuracy: 1/100 = 1.0%
depth acc (needle position in context)
0.00 0/20 0.0%
0.25 0/20 0.0%
0.50 0/20 0.0%
0.75 0/20 0.0%
1.00 1/20 5.0%
--- 2 sample generations ---
[MISS] expect=yarrow
got= the number 8056020.\n
[MISS] expect=cactus
got=: "The Magician".\n
wrote newck_len_16360/scores/armB_c_val_backward.csv
[08:35:06] building summary
=== per-task accuracy % (secondary/descriptive: ~10 per depth cell) ===
task armB_c base_c
niah_single 23.0 27.0
val_backward 1.0 0.0
degenerate (<=1% for every model): ['val_backward']
=== PRIMARY: accuracy % pooled by depth across tasks (+-95% Wilson) ===
depth armB_c base_c
0.00 0.0+- 8.1 0.0+- 8.1
0.25 0.0+- 8.1 0.0+- 8.1
0.50 10.0+-13.7 10.0+-13.7
0.75 20.0+-16.8 35.0+-19.3
1.00 85.0+-15.4 90.0+-13.7
wrote newck_len_16360/summary.csv and newck_len_16360/depth_summary.csv
[08:35:06] DONE -> newck_len_16360/summary.csv
|