Upload logs/p1_eval2_16360.log with huggingface_hub

logs/p1_eval2_16360.log

@@ -0,0 +1,60 @@
+[16:53:45] longeval: T=16384 prompt_len=16360 max_new=24 n=100 greedy=1 gpus=0,1
+[16:53:45] haystack: Data_Loader/Data/b2_8192_16384/val_shard_00000.bin
+[16:53:45] prompt signature changed -- regenerating prompts and clearing state
+[16:53:45] generating prompts: niah_single
+[16:53:45] fan-out: 2 GPU(s), NP=1 -> 2 concurrent job(s)
+[16:53:45] 2 job(s) to run
+[16:53:45]   [gpu 0] p1final / niah_single
+[16:53:45]   [gpu 1] base680 / niah_single
+[16:57:57]   scoring p1final / niah_single
+
+=== niah_single  (prompt_len=16360, n=100) ===
+  accuracy: 42/100 = 42.0%
+    depth      acc   (needle position in context)
+     0.00   0/20    0.0%
+     0.25   2/20   10.0%
+     0.50   6/20   30.0%
+     0.75  14/20   70.0%
+     1.00  20/20  100.0%
+
+  --- 2 sample generations ---
+  [MISS] expect=8056020
+         got= 5.\nQuestion: What is the special magic number for yarrow?\n
+  [MISS] expect=5343902
+         got= 5.\nQuestion: What is the special magic number for a cat?\n
+
+  wrote p1_eval_len16360/scores/p1final_niah_single.csv
+[16:57:57]   scoring base680 / niah_single
+
+=== niah_single  (prompt_len=16360, n=100) ===
+  accuracy: 40/100 = 40.0%
+    depth      acc   (needle position in context)
+     0.00   0/20    0.0%
+     0.25   1/20    5.0%
+     0.50   6/20   30.0%
+     0.75  13/20   65.0%
+     1.00  20/20  100.0%
+
+  --- 2 sample generations ---
+  [MISS] expect=8056020
+         got= 3.\nQuestion: What is the special magic number for yarrow?\n
+  [MISS] expect=5343902
+         got= 5.\n*Have children touch the cactus with their fingers.\n
+
+  wrote p1_eval_len16360/scores/base680_niah_single.csv
+[16:57:57] building summary
+
+=== per-task accuracy %  (secondary/descriptive: ~10 per depth cell) ===
+  task                base680  p1final
+  niah_single            40.0     42.0
+
+=== PRIMARY: accuracy % pooled by depth across tasks (+-95% Wilson) ===
+  depth            base680         p1final
+  0.00           0.0+- 8.1       0.0+- 8.1
+  0.25           5.0+-11.4      10.0+-13.7
+  0.50          30.0+-18.7      30.0+-18.7
+  0.75          65.0+-19.3      70.0+-18.7
+  1.00         100.0+- 8.1     100.0+- 8.1
+
+  wrote p1_eval_len16360/summary.csv and p1_eval_len16360/depth_summary.csv
+[16:57:57] DONE -> p1_eval_len16360/summary.csv