Upload folder using huggingface_hub

checkpoint-200/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd24f1a0862cd7ced3d367b422e5ed284b7aa8a39cf0dc572f6d523553342df1
+oid sha256:71904c7fca051d32bef8fe85431df4407a1c679d1d572f4a930d636405d67b80
 size 249323242

checkpoint-225/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:345bbc11175454ee2ed696c00112eb6377b190efa76ea62139fc29c9e9657210
+oid sha256:35bfcb8b439e96197ce2f220957adfda5afbb5dbf814d8915b771748b8c3c207
 size 249323242

choice_distribution.json

@@ -1,7 +1,7 @@
 {
   "gpt-4o": 0.0,
-  "DeepSeek-V3-0324": 0.125,
+  "DeepSeek-V3-0324": 0.15,
   "Llama-4-maverick-17b-128e-instruct-fp8": 0.0,
-  "qwen25-coder-32b-instruct": 0.0875,
+  "qwen25-coder-32b-instruct": 0.0625,
   "gpt-4.1-mini": 0.7875
 }

logs/events.out.tfevents.1754579297.209-20-159-47.43660.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abc0e3970440f38c6147c9c4c0fb99f39187f2c89af232ac2ee92a153fa767b
+size 7091

logs/events.out.tfevents.1754579297.209-20-159-47.43660.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b822928f81721c1975b8fb8aab6b2ecdeafc109ca3d94f316b41810a17d6d02c
+size 7091

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5389e4740b349a1cb2c5c4439848d3de1f4d0e7ccf00c3eba3383a4706ade0b1
+oid sha256:71904c7fca051d32bef8fe85431df4407a1c679d1d572f4a930d636405d67b80
 size 249323242

per_sample_predictions.csv

@@ -1,81 +1,81 @@
-gpt-4o,DeepSeek-V3-0324,Llama-4-maverick-17b-128e-instruct-fp8,qwen25-coder-32b-instruct,gpt-4.1-mini,chosen_executor
--0.7734375,-0.66796875,-0.71875,-0.6796875,-0.58984375,gpt-4.1-mini
--0.890625,-0.765625,-0.87109375,-0.765625,-0.75,gpt-4.1-mini
--0.95703125,-0.8125,-0.87109375,-0.7890625,-0.74609375,gpt-4.1-mini
--0.91796875,-0.77734375,-0.875,-0.8125,-0.77734375,DeepSeek-V3-0324
--0.90625,-0.78125,-0.83203125,-0.7734375,-0.74609375,gpt-4.1-mini
--0.890625,-0.7734375,-0.859375,-0.78125,-0.75390625,gpt-4.1-mini
--0.8984375,-0.7578125,-0.80859375,-0.73828125,-0.67578125,gpt-4.1-mini
--0.89453125,-0.76953125,-0.83984375,-0.78515625,-0.75,gpt-4.1-mini
--0.78515625,-0.71875,-0.70703125,-0.6796875,-0.625,gpt-4.1-mini
--0.87890625,-0.77734375,-0.8359375,-0.73046875,-0.75390625,qwen25-coder-32b-instruct
--0.95703125,-0.8125,-0.8828125,-0.81640625,-0.8046875,gpt-4.1-mini
--0.8515625,-0.76171875,-0.83984375,-0.78515625,-0.7265625,gpt-4.1-mini
--0.93359375,-0.84375,-0.8671875,-0.79296875,-0.8125,qwen25-coder-32b-instruct
--0.875,-0.75,-0.79296875,-0.74609375,-0.69921875,gpt-4.1-mini
--0.9453125,-0.875,-0.8828125,-0.8046875,-0.796875,gpt-4.1-mini
--0.84765625,-0.76953125,-0.80078125,-0.7578125,-0.734375,gpt-4.1-mini
--0.9375,-0.78515625,-0.8671875,-0.79296875,-0.75390625,gpt-4.1-mini
--0.89453125,-0.75390625,-0.80859375,-0.78515625,-0.7265625,gpt-4.1-mini
--0.9609375,-0.84375,-0.9140625,-0.8125,-0.8125,qwen25-coder-32b-instruct
--0.91015625,-0.8125,-0.875,-0.81640625,-0.7421875,gpt-4.1-mini
--0.921875,-0.82421875,-0.9140625,-0.79296875,-0.7734375,gpt-4.1-mini
--0.8515625,-0.734375,-0.796875,-0.71484375,-0.6640625,gpt-4.1-mini
--0.984375,-0.82421875,-0.87890625,-0.83203125,-0.76171875,gpt-4.1-mini
--0.8984375,-0.83203125,-0.87109375,-0.8125,-0.78125,gpt-4.1-mini
--0.94140625,-0.81640625,-0.91796875,-0.8515625,-0.83203125,DeepSeek-V3-0324
--0.87890625,-0.6796875,-0.72265625,-0.7265625,-0.65234375,gpt-4.1-mini
--0.8984375,-0.796875,-0.859375,-0.78125,-0.7578125,gpt-4.1-mini
--0.90234375,-0.77734375,-0.88671875,-0.796875,-0.7734375,gpt-4.1-mini
--0.9296875,-0.78515625,-0.8828125,-0.79296875,-0.75390625,gpt-4.1-mini
--0.83984375,-0.71875,-0.80859375,-0.7578125,-0.6875,gpt-4.1-mini
--0.8671875,-0.76953125,-0.84375,-0.76171875,-0.73828125,gpt-4.1-mini
--0.87109375,-0.7734375,-0.828125,-0.76171875,-0.75390625,gpt-4.1-mini
--0.8671875,-0.71484375,-0.796875,-0.71484375,-0.6875,gpt-4.1-mini
--0.8828125,-0.7734375,-0.83203125,-0.76171875,-0.73828125,gpt-4.1-mini
--0.9765625,-0.83203125,-0.875,-0.83203125,-0.78125,gpt-4.1-mini
--0.90625,-0.796875,-0.8828125,-0.78515625,-0.796875,qwen25-coder-32b-instruct
--0.9140625,-0.81640625,-0.859375,-0.80078125,-0.74609375,gpt-4.1-mini
--0.91796875,-0.80078125,-0.87109375,-0.8046875,-0.7734375,gpt-4.1-mini
--0.90625,-0.80859375,-0.8359375,-0.79296875,-0.75390625,gpt-4.1-mini
--0.921875,-0.796875,-0.86328125,-0.76171875,-0.76953125,qwen25-coder-32b-instruct
--0.9296875,-0.78125,-0.8671875,-0.76953125,-0.74609375,gpt-4.1-mini
--0.90625,-0.7890625,-0.8671875,-0.7890625,-0.765625,gpt-4.1-mini
--0.9609375,-0.84765625,-0.89453125,-0.80859375,-0.734375,gpt-4.1-mini
--0.9375,-0.84375,-0.90234375,-0.84375,-0.796875,gpt-4.1-mini
--0.9296875,-0.796875,-0.8984375,-0.81640625,-0.8125,DeepSeek-V3-0324
--0.87890625,-0.75,-0.8359375,-0.76171875,-0.7421875,gpt-4.1-mini
--0.8671875,-0.7578125,-0.828125,-0.76171875,-0.71484375,gpt-4.1-mini
--0.96484375,-0.8359375,-0.86328125,-0.80078125,-0.73828125,gpt-4.1-mini
--0.98046875,-0.8671875,-0.91796875,-0.84375,-0.80078125,gpt-4.1-mini
--0.8984375,-0.80078125,-0.84375,-0.7734375,-0.7578125,gpt-4.1-mini
--0.8984375,-0.73046875,-0.85546875,-0.77734375,-0.765625,DeepSeek-V3-0324
--0.875,-0.7578125,-0.83984375,-0.80078125,-0.68359375,gpt-4.1-mini
--0.92578125,-0.8046875,-0.8359375,-0.77734375,-0.7421875,gpt-4.1-mini
--0.8125,-0.66796875,-0.7421875,-0.66015625,-0.625,gpt-4.1-mini
--0.9609375,-0.81640625,-0.875,-0.8046875,-0.7734375,gpt-4.1-mini
--0.9375,-0.87890625,-0.921875,-0.8125,-0.78515625,gpt-4.1-mini
--0.9375,-0.8203125,-0.8984375,-0.8359375,-0.77734375,gpt-4.1-mini
--0.859375,-0.72265625,-0.80078125,-0.7109375,-0.671875,gpt-4.1-mini
--0.87109375,-0.75,-0.8515625,-0.7890625,-0.73828125,gpt-4.1-mini
--0.9453125,-0.828125,-0.9140625,-0.8203125,-0.8203125,qwen25-coder-32b-instruct
--0.95703125,-0.81640625,-0.90234375,-0.84765625,-0.78125,gpt-4.1-mini
--0.91796875,-0.83984375,-0.8515625,-0.8125,-0.76171875,gpt-4.1-mini
--0.93359375,-0.8203125,-0.91796875,-0.81640625,-0.81640625,qwen25-coder-32b-instruct
--0.8828125,-0.76953125,-0.8359375,-0.78125,-0.76953125,DeepSeek-V3-0324
--0.859375,-0.73828125,-0.8359375,-0.76171875,-0.74609375,DeepSeek-V3-0324
--0.82421875,-0.72265625,-0.80078125,-0.7265625,-0.6953125,gpt-4.1-mini
--0.87890625,-0.7109375,-0.8515625,-0.7734375,-0.73046875,DeepSeek-V3-0324
--0.8828125,-0.765625,-0.8515625,-0.74609375,-0.734375,gpt-4.1-mini
--0.84765625,-0.6953125,-0.80078125,-0.73828125,-0.7109375,DeepSeek-V3-0324
--0.9140625,-0.828125,-0.859375,-0.79296875,-0.75390625,gpt-4.1-mini
--0.9140625,-0.77734375,-0.8671875,-0.80078125,-0.765625,gpt-4.1-mini
--0.890625,-0.8046875,-0.828125,-0.75,-0.734375,gpt-4.1-mini
--0.8984375,-0.7578125,-0.859375,-0.76953125,-0.7734375,DeepSeek-V3-0324
--0.91796875,-0.83984375,-0.8828125,-0.7890625,-0.78125,gpt-4.1-mini
--0.93359375,-0.8046875,-0.86328125,-0.80859375,-0.7578125,gpt-4.1-mini
--0.9296875,-0.77734375,-0.890625,-0.81640625,-0.80859375,DeepSeek-V3-0324
--0.83984375,-0.7265625,-0.8515625,-0.75,-0.6953125,gpt-4.1-mini
--0.9375,-0.82421875,-0.9140625,-0.82421875,-0.81640625,gpt-4.1-mini
--0.9609375,-0.84375,-0.90234375,-0.83203125,-0.80078125,gpt-4.1-mini
--0.89453125,-0.80078125,-0.875,-0.81640625,-0.796875,gpt-4.1-mini
+logit_gpt-4o,logit_DeepSeek-V3-0324,logit_Llama-4-maverick-17b-128e-instruct-fp8,logit_qwen25-coder-32b-instruct,logit_gpt-4.1-mini,chosen_executor,true_gpt-4o,true_DeepSeek-V3-0324,true_Llama-4-maverick-17b-128e-instruct-fp8,true_qwen25-coder-32b-instruct,true_gpt-4.1-mini
+-0.828125,-0.7109375,-0.7578125,-0.66015625,-0.60546875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.95703125,-0.7890625,-0.890625,-0.80859375,-0.7890625,DeepSeek-V3-0324,0.0,0.0,0.0,0.0,0.0
+-0.96875,-0.78515625,-0.8828125,-0.86328125,-0.7890625,DeepSeek-V3-0324,1.0,1.0,1.0,1.0,1.0
+-0.890625,-0.78515625,-0.8203125,-0.78515625,-0.71875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.93359375,-0.78515625,-0.8828125,-0.796875,-0.7734375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.9609375,-0.8125,-0.85546875,-0.81640625,-0.77734375,gpt-4.1-mini,0.0,0.0,1.0,0.0,1.0
+-0.91015625,-0.80078125,-0.859375,-0.765625,-0.7109375,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.94921875,-0.8046875,-0.87890625,-0.796875,-0.8203125,qwen25-coder-32b-instruct,0.0,0.0,0.0,0.0,0.0
+-0.84375,-0.71484375,-0.76953125,-0.6328125,-0.64453125,qwen25-coder-32b-instruct,0.0,1.0,1.0,1.0,1.0
+-0.92578125,-0.76171875,-0.83984375,-0.7734375,-0.76953125,DeepSeek-V3-0324,0.0,0.0,0.0,0.0,0.0
+-0.98046875,-0.85546875,-0.8671875,-0.81640625,-0.8046875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.890625,-0.8046875,-0.875,-0.79296875,-0.73046875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.9296875,-0.80078125,-0.87109375,-0.8125,-0.77734375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.9140625,-0.75390625,-0.83984375,-0.765625,-0.74609375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.984375,-0.828125,-0.9375,-0.828125,-0.74609375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.875,-0.74609375,-0.83203125,-0.76953125,-0.73046875,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.95703125,-0.8046875,-0.828125,-0.796875,-0.78515625,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.97265625,-0.83984375,-0.859375,-0.7890625,-0.7421875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.96875,-0.84375,-0.859375,-0.8046875,-0.8046875,qwen25-coder-32b-instruct,0.0,0.0,0.0,0.0,0.0
+-1.0,-0.82421875,-0.82421875,-0.83203125,-0.796875,gpt-4.1-mini,1.0,1.0,0.0,1.0,1.0
+-0.98828125,-0.84375,-0.86328125,-0.84375,-0.80078125,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.92578125,-0.765625,-0.80859375,-0.78125,-0.79296875,DeepSeek-V3-0324,0.0,0.0,0.0,0.0,0.0
+-0.9765625,-0.8046875,-0.81640625,-0.8203125,-0.79296875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.90625,-0.80078125,-0.85546875,-0.8359375,-0.80078125,DeepSeek-V3-0324,0.0,0.0,0.0,0.0,0.0
+-0.9375,-0.84765625,-0.84765625,-0.828125,-0.80078125,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.8671875,-0.73046875,-0.78125,-0.65625,-0.64453125,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.953125,-0.83203125,-0.89453125,-0.828125,-0.77734375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.90234375,-0.82421875,-0.828125,-0.79296875,-0.76953125,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.9609375,-0.79296875,-0.80078125,-0.84765625,-0.7734375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.921875,-0.78125,-0.80859375,-0.796875,-0.75,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.8984375,-0.8125,-0.84375,-0.81640625,-0.75,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.890625,-0.80078125,-0.83203125,-0.8046875,-0.765625,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.8671875,-0.7265625,-0.83984375,-0.7578125,-0.69921875,gpt-4.1-mini,1.0,0.0,1.0,1.0,1.0
+-0.96875,-0.81640625,-0.85546875,-0.8359375,-0.7890625,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-1.0,-0.828125,-0.83203125,-0.80859375,-0.7890625,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.94140625,-0.81640625,-0.85546875,-0.77734375,-0.73828125,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.94921875,-0.81640625,-0.86328125,-0.80078125,-0.734375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.91015625,-0.8203125,-0.8671875,-0.84765625,-0.73828125,gpt-4.1-mini,1.0,1.0,0.0,1.0,1.0
+-0.921875,-0.7890625,-0.859375,-0.78515625,-0.73828125,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.94140625,-0.78515625,-0.8515625,-0.77734375,-0.7421875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.94140625,-0.8203125,-0.87109375,-0.83203125,-0.79296875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.9296875,-0.78125,-0.8671875,-0.78125,-0.78125,DeepSeek-V3-0324,1.0,1.0,1.0,1.0,1.0
+-1.0234375,-0.828125,-0.9140625,-0.84765625,-0.76953125,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.9375,-0.8046875,-0.84765625,-0.81640625,-0.82421875,DeepSeek-V3-0324,1.0,1.0,1.0,1.0,1.0
+-0.97265625,-0.8515625,-0.8515625,-0.83984375,-0.81640625,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.94140625,-0.82421875,-0.890625,-0.8359375,-0.78125,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.93359375,-0.78515625,-0.8515625,-0.77734375,-0.76171875,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.98046875,-0.8125,-0.91015625,-0.79296875,-0.796875,qwen25-coder-32b-instruct,0.0,0.0,0.0,0.0,0.0
+-1.0,-0.84765625,-0.8125,-0.828125,-0.7734375,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.97265625,-0.76171875,-0.85546875,-0.76171875,-0.76171875,DeepSeek-V3-0324,0.0,0.0,0.0,0.0,0.0
+-0.91015625,-0.8046875,-0.81640625,-0.80078125,-0.78125,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.890625,-0.7578125,-0.8203125,-0.7890625,-0.7109375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.984375,-0.81640625,-0.9296875,-0.8515625,-0.82421875,DeepSeek-V3-0324,1.0,1.0,1.0,0.0,1.0
+-0.79296875,-0.6640625,-0.74609375,-0.65625,-0.58984375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.97265625,-0.7890625,-0.8828125,-0.78515625,-0.80078125,qwen25-coder-32b-instruct,1.0,0.0,0.0,0.0,0.0
+-0.97265625,-0.83984375,-0.8671875,-0.80078125,-0.73046875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-1.015625,-0.82421875,-0.84375,-0.83984375,-0.78515625,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.87890625,-0.734375,-0.7578125,-0.73046875,-0.6875,gpt-4.1-mini,0.0,1.0,0.0,0.0,0.0
+-0.921875,-0.79296875,-0.859375,-0.78515625,-0.7265625,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.98046875,-0.82421875,-0.83984375,-0.82421875,-0.82421875,DeepSeek-V3-0324,0.0,0.0,0.0,0.0,0.0
+-0.99609375,-0.83984375,-0.859375,-0.80078125,-0.7421875,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.93359375,-0.80859375,-0.890625,-0.81640625,-0.7734375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-1.0078125,-0.83984375,-0.875,-0.8359375,-0.80078125,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.94140625,-0.77734375,-0.875,-0.7890625,-0.73828125,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.90625,-0.78125,-0.84765625,-0.7734375,-0.7265625,gpt-4.1-mini,1.0,1.0,1.0,1.0,0.0
+-0.87109375,-0.75390625,-0.859375,-0.73828125,-0.71484375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.89453125,-0.78125,-0.7734375,-0.7890625,-0.75390625,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.9296875,-0.76171875,-0.8125,-0.76953125,-0.76171875,DeepSeek-V3-0324,1.0,0.0,0.0,1.0,1.0
+-0.85546875,-0.765625,-0.83984375,-0.76171875,-0.6953125,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.96484375,-0.828125,-0.81640625,-0.80078125,-0.7890625,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.921875,-0.828125,-0.85546875,-0.8359375,-0.76953125,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.94921875,-0.76953125,-0.859375,-0.8125,-0.7421875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.94140625,-0.7890625,-0.8359375,-0.8125,-0.74609375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.9296875,-0.7890625,-0.85546875,-0.7734375,-0.74609375,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.95703125,-0.7890625,-0.82421875,-0.78515625,-0.734375,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.9453125,-0.796875,-0.83203125,-0.796875,-0.76171875,gpt-4.1-mini,0.0,0.0,0.0,0.0,0.0
+-0.91796875,-0.79296875,-0.84375,-0.81640625,-0.765625,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.97265625,-0.796875,-0.8984375,-0.84375,-0.80859375,DeepSeek-V3-0324,1.0,1.0,1.0,1.0,1.0
+-0.94921875,-0.82421875,-0.8515625,-0.8203125,-0.765625,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0
+-0.91015625,-0.8125,-0.86328125,-0.82421875,-0.76953125,gpt-4.1-mini,1.0,1.0,1.0,1.0,1.0