Upload logs/p1_eval2_8192.log with huggingface_hub

logs/p1_eval2_8192.log

@@ -0,0 +1,60 @@
+[16:51:26] longeval: T=16384 prompt_len=8192 max_new=24 n=100 greedy=1 gpus=0,1
+[16:51:26] haystack: Data_Loader/Data/b2_8192_16384/val_shard_00000.bin
+[16:51:26] prompt signature changed -- regenerating prompts and clearing state
+[16:51:26] generating prompts: niah_single
+[16:51:27] fan-out: 2 GPU(s), NP=1 -> 2 concurrent job(s)
+[16:51:27] 2 job(s) to run
+[16:51:27]   [gpu 0] p1final / niah_single
+[16:51:27]   [gpu 1] base680 / niah_single
+[16:53:45]   scoring p1final / niah_single
+
+=== niah_single  (prompt_len=8192, n=100) ===
+  accuracy: 77/100 = 77.0%
+    depth      acc   (needle position in context)
+     0.00  14/20   70.0%
+     0.25  15/20   75.0%
+     0.50  14/20   70.0%
+     0.75  14/20   70.0%
+     1.00  20/20  100.0%
+
+  --- 2 sample generations ---
+  [HIT ] expect=8056020
+         got= 8056020.\n
+  [HIT ] expect=5343902
+         got= 5343902.\n
+
+  wrote p1_eval_len8192/scores/p1final_niah_single.csv
+[16:53:45]   scoring base680 / niah_single
+
+=== niah_single  (prompt_len=8192, n=100) ===
+  accuracy: 84/100 = 84.0%
+    depth      acc   (needle position in context)
+     0.00  15/20   75.0%
+     0.25  17/20   85.0%
+     0.50  16/20   80.0%
+     0.75  16/20   80.0%
+     1.00  20/20  100.0%
+
+  --- 2 sample generations ---
+  [HIT ] expect=8056020
+         got= 8056020.\n
+  [HIT ] expect=5343902
+         got= 5343902.\n
+
+  wrote p1_eval_len8192/scores/base680_niah_single.csv
+[16:53:45] building summary
+
+=== per-task accuracy %  (secondary/descriptive: ~10 per depth cell) ===
+  task                base680  p1final
+  niah_single            84.0     77.0
+
+=== PRIMARY: accuracy % pooled by depth across tasks (+-95% Wilson) ===
+  depth            base680         p1final
+  0.00          75.0+-17.8      70.0+-18.7
+  0.25          85.0+-15.4      75.0+-17.8
+  0.50          80.0+-16.8      70.0+-18.7
+  0.75          80.0+-16.8      70.0+-18.7
+  1.00         100.0+- 8.1     100.0+- 8.1
+
+  wrote p1_eval_len8192/summary.csv and p1_eval_len8192/depth_summary.csv
+[16:53:45] DONE -> p1_eval_len8192/summary.csv