| [16:37:39] longeval: T=32768 prompt_len=32744 max_new=24 n=100 greedy=1 gpus=0,1 |
| [16:37:39] haystack: /root/Adhi/BluTrain/dist/Context_Parallelism/lendata/haystack/b2val_haystack.bin |
| [16:37:39] prompt signature changed -- regenerating prompts and clearing state |
| [16:37:39] generating prompts: niah_single |
| [16:37:40] fan-out: 2 GPU(s), NP=1 -> 2 concurrent job(s) |
| [16:37:40] 2 job(s) to run |
| [16:37:40] [gpu 0] ext32k / niah_single |
| [16:37:40] [gpu 1] l2 / niah_single |
| [16:48:52] scoring ext32k / niah_single |
|
|
| === niah_single (prompt_len=32744, 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 8/20 40.0% |
| 1.00 17/20 85.0% |
|
|
| --- 2 sample generations --- |
| [MISS] expect=8056020 |
| got= “kitty-cat”.\n |
| [MISS] expect=5343902 |
| got= 7. This number is unique to cactus, making it a unique identifier for each plant.\n |
|
|
| wrote ext32k_len_32744/scores/ext32k_niah_single.csv |
| [16:48:52] scoring l2 / niah_single |
|
|
| === niah_single (prompt_len=32744, n=100) === |
| accuracy: 11/100 = 11.0% |
| 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 11/20 55.0% |
|
|
| --- 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= the number for the cactus. This number is a unique identifier that identifies the plant, making it easier to identify the |
|
|
| wrote ext32k_len_32744/scores/l2_niah_single.csv |
| [16:48:53] building summary |
|
|
| === per-task accuracy % (secondary/descriptive: ~10 per depth cell) === |
| task ext32k l2 |
| niah_single 27.0 11.0 |
|
|
| === PRIMARY: accuracy % pooled by depth across tasks (+-95% Wilson) === |
| depth ext32k l2 |
| 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 0.0+- 8.1 |
| 0.75 40.0+-19.7 0.0+- 8.1 |
| 1.00 85.0+-15.4 55.0+-20.0 |
|
|
| wrote ext32k_len_32744/summary.csv and ext32k_len_32744/depth_summary.csv |
| [16:48:53] DONE -> ext32k_len_32744/summary.csv |
|
|
