hbfreed commited on
Commit
a267001
·
verified ·
1 Parent(s): 8494d7f

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +41 -0
  2. evals/protocolF/keep25_step0200/student/samples_mmlu_pro_law_2026-07-24T04-18-13.279466.jsonl +3 -0
  3. evals/protocolF/keep25_step0200/student/samples_mmlu_pro_math_2026-07-24T04-18-13.279466.jsonl +3 -0
  4. evals/protocolF/keep25_step0200/student/samples_mmlu_pro_physics_2026-07-24T04-18-13.279466.jsonl +3 -0
  5. evals/protocolF/keep25_unhealed/student/samples_mmlu_pro_law_2026-07-24T00-35-28.784508.jsonl +3 -0
  6. evals/protocolF/keep50_step0200/student/samples_mmlu_pro_law_2026-07-24T12-04-07.736823.jsonl +3 -0
  7. evals/protocolF/keep50_step0200/student/samples_mmlu_pro_math_2026-07-24T12-04-07.736823.jsonl +3 -0
  8. evals/protocolF/keep50_step0200/student/samples_mmlu_pro_physics_2026-07-24T12-04-07.736823.jsonl +3 -0
  9. evals/protocolF/keep50_unhealed/student/samples_mmlu_pro_law_2026-07-24T06-35-05.152479.jsonl +3 -0
  10. evals/qwen_box/keep50_step0100_traj/logs_think_off/2026-07-23T02-09-52+00-00_gsm8k-ns_ZpWpgnuKkmaT6BL66tekCJ.eval +3 -0
  11. evals/qwen_protocolE/ctlA_think_on/logs_think_on/2026-07-26T21-25-41-07-00_gpqa-diamond_jqgEeWZujzzqJi6v7U2U8d.eval +3 -0
  12. evals/qwen_protocolE/ctlB_unhealed/logs_think_off/2026-07-26T21-58-52-07-00_gpqa-diamond_RMqZduJuwV6UrTnVyqkUdv.eval +3 -0
  13. evals/qwen_protocolE/full_base_fp8/logs_think_off/2026-07-28T07-36-24-07-00_mmlu-pro_JQHb75HUBZCcZEnevRp4wM.eval +3 -0
  14. evals/qwen_protocolE/full_base_fp8/logs_think_off/2026-07-28T10-37-33-07-00_ifeval_KMsm57FEQyBXbCLrs8mo4p.eval +3 -0
  15. evals/qwen_protocolE/full_h25_short/logs_think_off/2026-07-27T14-36-15-07-00_mmlu-pro_CHAoR7mXY9o23DQRmZiFk5.eval +3 -0
  16. evals/qwen_protocolE/full_h25_short/logs_think_off/2026-07-27T19-52-56-07-00_ifeval_5XmUdEmp62w2zdqYfwtXsP.eval +3 -0
  17. evals/qwen_protocolE/full_h50_gpqa/logs_think_off/2026-07-28T00-14-44-07-00_gpqa-diamond_86wQuSJiydd8WYANvLLUYs.eval +3 -0
  18. evals/qwen_protocolE/full_h50_short/logs_think_off/2026-07-26T22-38-24-07-00_mmlu-pro_hsGV2WtmZpEZiv4SwvCsAx.eval +3 -0
  19. evals/qwen_protocolE/full_h50_short/logs_think_off/2026-07-27T10-09-13-07-00_ifeval_RyEiu6HK25NcF6ifFjwFbc.eval +3 -0
  20. evals/qwen_protocolE/full_reap28/logs_think_off/2026-07-28T19-25-06-07-00_mmlu-pro_A9sAaV7LiPJVZggyVi85tV.eval +3 -0
  21. evals/qwen_protocolE/full_reap28/logs_think_off/2026-07-29T01-00-05-07-00_ifeval_o5MeCwSKe4zb5wuZZAKUQC.eval +3 -0
  22. evals/qwen_protocolE/full_reap75_unhealed/logs_think_off/2026-08-03T08-48-34-07-00_mmlu-pro_debSF4gMksZMrdVm9hXXoL.eval +3 -0
  23. evals/qwen_protocolE/full_reap75_unhealed/logs_think_off/2026-08-03T13-20-17-07-00_ifeval_NKa7XsAGcV2kZkRrpLkiDv.eval +3 -0
  24. evals/qwen_protocolE/full_u25_short/logs_think_off/2026-07-27T20-05-00-07-00_mmlu-pro_9mWf8mQgh9MuWLA8DuM5TZ.eval +3 -0
  25. evals/qwen_protocolE/full_u25_short/logs_think_off/2026-07-28T00-01-58-07-00_ifeval_kJAJeS7RLnPnGGUL3Z6DWa.eval +3 -0
  26. evals/qwen_protocolE/full_u50_gpqa/logs_think_off/2026-07-28T04-29-03-07-00_gpqa-diamond_NBgohDFugFkKgJCmGe9nhE.eval +3 -0
  27. evals/qwen_protocolE/full_u50_short/logs_think_off/2026-07-27T10-22-41-07-00_mmlu-pro_h3h3cbQiNZjxM8genLPp5F.eval +3 -0
  28. evals/qwen_protocolE/full_u50_short/logs_think_off/2026-07-27T14-18-03-07-00_ifeval_DKQ3hcoUzxr2LqDgTVr73L.eval +3 -0
  29. evals/qwen_protocolE/full_u75_short/logs_think_off/2026-07-28T11-12-48-07-00_mmlu-pro_Efbp4YWwpVTvghsKSk2GSk.eval +3 -0
  30. evals/qwen_protocolE/full_u75_short/logs_think_off/2026-07-28T15-09-28-07-00_ifeval_9LEWrPDQszjR7bigkytKQC.eval +3 -0
  31. evals/qwen_protocolE/probe_keep25/logs_think_off/2026-07-26T19-36-05-07-00_gpqa-diamond_KfGYsCCkLABGmBDY5MbNCA.eval +3 -0
  32. evals/qwen_protocolE/probe_keep50/logs_think_off/2026-07-26T20-30-33-07-00_gpqa-diamond_NRbcSH725D7sBCKGKFPpsd.eval +3 -0
  33. evals/qwen_protocolE/probe_sampled/logs_think_off/2026-07-26T20-04-27-07-00_gpqa-diamond_RdaDaMcRuTEY3puETxtdNq.eval +3 -0
  34. evals/qwen_protocolE/smoke_keep25/logs_think_off/2026-07-26T19-21-22-07-00_gpqa-diamond_cDAPWuX6rCA8ggv6wHSaFH.eval +3 -0
  35. evals/redo_policy/coldon_step0050/student/samples_gsm8k_cot_2026-08-10T13-42-15.978635.jsonl +3 -0
  36. evals/redo_policy/coldon_step0100/student/samples_gsm8k_cot_2026-08-10T13-40-58.988149.jsonl +3 -0
  37. evals/redo_policy/coldon_step0150/student/samples_gsm8k_cot_2026-08-10T13-40-46.909664.jsonl +3 -0
  38. evals/redo_policy/offpolicy_step0050/student/samples_gsm8k_cot_2026-08-10T13-56-53.950636.jsonl +3 -0
  39. evals/redo_policy/offpolicy_step0100/student/samples_gsm8k_cot_2026-08-10T13-56-07.791637.jsonl +3 -0
  40. evals/redo_policy/offpolicy_step0150/student/samples_gsm8k_cot_2026-08-10T13-56-13.321387.jsonl +3 -0
  41. evals/redo_policy/teacher_1280/student/samples_gsm8k_cot_2026-08-10T14-47-11.936152.jsonl +3 -0
  42. evals/redo_policy/unhealed_keep50/student/samples_gsm8k_cot_2026-08-10T14-11-48.312514.jsonl +3 -0
  43. teacher_trajectories/dolci_math_nogold_matched_top128/shard_00000.pt +3 -0
  44. teacher_trajectories/dolci_math_nogold_matched_top128/shard_00001.pt +3 -0
  45. teacher_trajectories/dolci_math_nogold_matched_top128/shard_00004.pt +3 -0
  46. teacher_trajectories/dolci_math_nogold_matched_top128/shard_00007.pt +3 -0
  47. teacher_trajectories/dolci_math_nogold_matched_top128/shard_00008.pt +3 -0
  48. teacher_trajectories/dolci_math_nogold_matched_top128/shard_00009.pt +3 -0
  49. teacher_trajectories/dolci_math_nogold_matched_top128/shard_00010.pt +3 -0
  50. teacher_trajectories/dolci_math_nogold_matched_top128/shard_00011.pt +3 -0
.gitattributes CHANGED
@@ -61,3 +61,44 @@ evals/qwen_box/base_think/logs_think_on/2026-07-23T01-44-08+00-00_gsm8k-ns_WizEj
61
  evals/qwen_box/keep50_unhealed/logs_think_off/2026-07-23T01-30-27+00-00_gsm8k-ns_3bsewwAd6oKWHBjHXnES4b.eval filter=lfs diff=lfs merge=lfs -text
62
  evals/math_unhealed/glean_winnow-olmoe-math-keep25/student/samples_gsm8k_cot_zeroshot_2026-08-10T15-10-51.733636.jsonl filter=lfs diff=lfs merge=lfs -text
63
  evals/qwen_reap75_fix/logs_think_off/2026-08-11T08-48-01-07-00_mmlu-pro_S547hXqaRVU4vYSpYpjoek.eval filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  evals/qwen_box/keep50_unhealed/logs_think_off/2026-07-23T01-30-27+00-00_gsm8k-ns_3bsewwAd6oKWHBjHXnES4b.eval filter=lfs diff=lfs merge=lfs -text
62
  evals/math_unhealed/glean_winnow-olmoe-math-keep25/student/samples_gsm8k_cot_zeroshot_2026-08-10T15-10-51.733636.jsonl filter=lfs diff=lfs merge=lfs -text
63
  evals/qwen_reap75_fix/logs_think_off/2026-08-11T08-48-01-07-00_mmlu-pro_S547hXqaRVU4vYSpYpjoek.eval filter=lfs diff=lfs merge=lfs -text
64
+ evals/qwen_protocolE/ctlA_think_on/logs_think_on/2026-07-26T21-25-41-07-00_gpqa-diamond_jqgEeWZujzzqJi6v7U2U8d.eval filter=lfs diff=lfs merge=lfs -text
65
+ evals/qwen_protocolE/full_u25_short/logs_think_off/2026-07-27T20-05-00-07-00_mmlu-pro_9mWf8mQgh9MuWLA8DuM5TZ.eval filter=lfs diff=lfs merge=lfs -text
66
+ evals/qwen_protocolE/full_u25_short/logs_think_off/2026-07-28T00-01-58-07-00_ifeval_kJAJeS7RLnPnGGUL3Z6DWa.eval filter=lfs diff=lfs merge=lfs -text
67
+ evals/qwen_protocolE/probe_keep50/logs_think_off/2026-07-26T20-30-33-07-00_gpqa-diamond_NRbcSH725D7sBCKGKFPpsd.eval filter=lfs diff=lfs merge=lfs -text
68
+ evals/qwen_protocolE/full_h50_gpqa/logs_think_off/2026-07-28T00-14-44-07-00_gpqa-diamond_86wQuSJiydd8WYANvLLUYs.eval filter=lfs diff=lfs merge=lfs -text
69
+ evals/qwen_protocolE/full_h50_short/logs_think_off/2026-07-26T22-38-24-07-00_mmlu-pro_hsGV2WtmZpEZiv4SwvCsAx.eval filter=lfs diff=lfs merge=lfs -text
70
+ evals/qwen_protocolE/full_h50_short/logs_think_off/2026-07-27T10-09-13-07-00_ifeval_RyEiu6HK25NcF6ifFjwFbc.eval filter=lfs diff=lfs merge=lfs -text
71
+ evals/qwen_protocolE/full_reap75_unhealed/logs_think_off/2026-08-03T08-48-34-07-00_mmlu-pro_debSF4gMksZMrdVm9hXXoL.eval filter=lfs diff=lfs merge=lfs -text
72
+ evals/qwen_protocolE/full_reap75_unhealed/logs_think_off/2026-08-03T13-20-17-07-00_ifeval_NKa7XsAGcV2kZkRrpLkiDv.eval filter=lfs diff=lfs merge=lfs -text
73
+ evals/qwen_protocolE/ctlB_unhealed/logs_think_off/2026-07-26T21-58-52-07-00_gpqa-diamond_RMqZduJuwV6UrTnVyqkUdv.eval filter=lfs diff=lfs merge=lfs -text
74
+ evals/qwen_protocolE/full_reap28/logs_think_off/2026-07-29T01-00-05-07-00_ifeval_o5MeCwSKe4zb5wuZZAKUQC.eval filter=lfs diff=lfs merge=lfs -text
75
+ evals/qwen_protocolE/full_reap28/logs_think_off/2026-07-28T19-25-06-07-00_mmlu-pro_A9sAaV7LiPJVZggyVi85tV.eval filter=lfs diff=lfs merge=lfs -text
76
+ evals/qwen_protocolE/full_u50_short/logs_think_off/2026-07-27T14-18-03-07-00_ifeval_DKQ3hcoUzxr2LqDgTVr73L.eval filter=lfs diff=lfs merge=lfs -text
77
+ evals/qwen_protocolE/full_u50_short/logs_think_off/2026-07-27T10-22-41-07-00_mmlu-pro_h3h3cbQiNZjxM8genLPp5F.eval filter=lfs diff=lfs merge=lfs -text
78
+ evals/qwen_protocolE/full_u75_short/logs_think_off/2026-07-28T11-12-48-07-00_mmlu-pro_Efbp4YWwpVTvghsKSk2GSk.eval filter=lfs diff=lfs merge=lfs -text
79
+ evals/qwen_protocolE/full_u75_short/logs_think_off/2026-07-28T15-09-28-07-00_ifeval_9LEWrPDQszjR7bigkytKQC.eval filter=lfs diff=lfs merge=lfs -text
80
+ evals/qwen_protocolE/smoke_keep25/logs_think_off/2026-07-26T19-21-22-07-00_gpqa-diamond_cDAPWuX6rCA8ggv6wHSaFH.eval filter=lfs diff=lfs merge=lfs -text
81
+ evals/qwen_protocolE/probe_sampled/logs_think_off/2026-07-26T20-04-27-07-00_gpqa-diamond_RdaDaMcRuTEY3puETxtdNq.eval filter=lfs diff=lfs merge=lfs -text
82
+ evals/qwen_protocolE/probe_keep25/logs_think_off/2026-07-26T19-36-05-07-00_gpqa-diamond_KfGYsCCkLABGmBDY5MbNCA.eval filter=lfs diff=lfs merge=lfs -text
83
+ evals/qwen_protocolE/full_u50_gpqa/logs_think_off/2026-07-28T04-29-03-07-00_gpqa-diamond_NBgohDFugFkKgJCmGe9nhE.eval filter=lfs diff=lfs merge=lfs -text
84
+ evals/qwen_protocolE/full_base_fp8/logs_think_off/2026-07-28T10-37-33-07-00_ifeval_KMsm57FEQyBXbCLrs8mo4p.eval filter=lfs diff=lfs merge=lfs -text
85
+ evals/qwen_protocolE/full_base_fp8/logs_think_off/2026-07-28T07-36-24-07-00_mmlu-pro_JQHb75HUBZCcZEnevRp4wM.eval filter=lfs diff=lfs merge=lfs -text
86
+ evals/qwen_protocolE/full_h25_short/logs_think_off/2026-07-27T19-52-56-07-00_ifeval_5XmUdEmp62w2zdqYfwtXsP.eval filter=lfs diff=lfs merge=lfs -text
87
+ evals/qwen_protocolE/full_h25_short/logs_think_off/2026-07-27T14-36-15-07-00_mmlu-pro_CHAoR7mXY9o23DQRmZiFk5.eval filter=lfs diff=lfs merge=lfs -text
88
+ evals/protocolF/keep50_step0200/student/samples_mmlu_pro_physics_2026-07-24T12-04-07.736823.jsonl filter=lfs diff=lfs merge=lfs -text
89
+ evals/protocolF/keep50_step0200/student/samples_mmlu_pro_math_2026-07-24T12-04-07.736823.jsonl filter=lfs diff=lfs merge=lfs -text
90
+ evals/protocolF/keep50_step0200/student/samples_mmlu_pro_law_2026-07-24T12-04-07.736823.jsonl filter=lfs diff=lfs merge=lfs -text
91
+ evals/protocolF/keep25_step0200/student/samples_mmlu_pro_physics_2026-07-24T04-18-13.279466.jsonl filter=lfs diff=lfs merge=lfs -text
92
+ evals/protocolF/keep25_step0200/student/samples_mmlu_pro_law_2026-07-24T04-18-13.279466.jsonl filter=lfs diff=lfs merge=lfs -text
93
+ evals/protocolF/keep25_step0200/student/samples_mmlu_pro_math_2026-07-24T04-18-13.279466.jsonl filter=lfs diff=lfs merge=lfs -text
94
+ evals/protocolF/keep25_unhealed/student/samples_mmlu_pro_law_2026-07-24T00-35-28.784508.jsonl filter=lfs diff=lfs merge=lfs -text
95
+ evals/protocolF/keep50_unhealed/student/samples_mmlu_pro_law_2026-07-24T06-35-05.152479.jsonl filter=lfs diff=lfs merge=lfs -text
96
+ evals/redo_policy/coldon_step0150/student/samples_gsm8k_cot_2026-08-10T13-40-46.909664.jsonl filter=lfs diff=lfs merge=lfs -text
97
+ evals/redo_policy/offpolicy_step0150/student/samples_gsm8k_cot_2026-08-10T13-56-13.321387.jsonl filter=lfs diff=lfs merge=lfs -text
98
+ evals/redo_policy/coldon_step0100/student/samples_gsm8k_cot_2026-08-10T13-40-58.988149.jsonl filter=lfs diff=lfs merge=lfs -text
99
+ evals/redo_policy/unhealed_keep50/student/samples_gsm8k_cot_2026-08-10T14-11-48.312514.jsonl filter=lfs diff=lfs merge=lfs -text
100
+ evals/redo_policy/coldon_step0050/student/samples_gsm8k_cot_2026-08-10T13-42-15.978635.jsonl filter=lfs diff=lfs merge=lfs -text
101
+ evals/redo_policy/teacher_1280/student/samples_gsm8k_cot_2026-08-10T14-47-11.936152.jsonl filter=lfs diff=lfs merge=lfs -text
102
+ evals/redo_policy/offpolicy_step0050/student/samples_gsm8k_cot_2026-08-10T13-56-53.950636.jsonl filter=lfs diff=lfs merge=lfs -text
103
+ evals/redo_policy/offpolicy_step0100/student/samples_gsm8k_cot_2026-08-10T13-56-07.791637.jsonl filter=lfs diff=lfs merge=lfs -text
104
+ evals/qwen_box/keep50_step0100_traj/logs_think_off/2026-07-23T02-09-52+00-00_gsm8k-ns_ZpWpgnuKkmaT6BL66tekCJ.eval filter=lfs diff=lfs merge=lfs -text
evals/protocolF/keep25_step0200/student/samples_mmlu_pro_law_2026-07-24T04-18-13.279466.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c86d53497770b42e4b32347a8307035676800fd0dcdc6cd4977db2afad6f67
3
+ size 11700495
evals/protocolF/keep25_step0200/student/samples_mmlu_pro_math_2026-07-24T04-18-13.279466.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e535a6c8c4899306c3318adc53fada4f7d4feecbe55e50bbcbb97ce2a2168d
3
+ size 12345754
evals/protocolF/keep25_step0200/student/samples_mmlu_pro_physics_2026-07-24T04-18-13.279466.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f83b8e8a1676866ec882c997d7545bcd978986d732133f16cd478faa8ca800
3
+ size 11124031
evals/protocolF/keep25_unhealed/student/samples_mmlu_pro_law_2026-07-24T00-35-28.784508.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2055eaa247db31d5a0b1206ff1453342e809e4cd0faa6469b23d62bbf17a0e05
3
+ size 11056080
evals/protocolF/keep50_step0200/student/samples_mmlu_pro_law_2026-07-24T12-04-07.736823.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459c6ad916ea88af8793c6c381033a707b9626b95c3bb1ebe2d898ba8985b418
3
+ size 12797088
evals/protocolF/keep50_step0200/student/samples_mmlu_pro_math_2026-07-24T12-04-07.736823.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f21ab8bf1d743ec5cb71e9f780247b81af38a9cf704d71eeebcbad2681cbcd
3
+ size 12085941
evals/protocolF/keep50_step0200/student/samples_mmlu_pro_physics_2026-07-24T12-04-07.736823.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25c84af8317b6dc23eddd7c4fa4c67adc55fe530f01ad9b58c434fdaf8ca9b3
3
+ size 11258782
evals/protocolF/keep50_unhealed/student/samples_mmlu_pro_law_2026-07-24T06-35-05.152479.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d0639a4f3db6b0a8ee9804521186d4bf11c984c9e044b608ade5a6c6c674c3
3
+ size 11225620
evals/qwen_box/keep50_step0100_traj/logs_think_off/2026-07-23T02-09-52+00-00_gsm8k-ns_ZpWpgnuKkmaT6BL66tekCJ.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6968da0c7bac41057294a492308357f653301050dcf04fa992fd84924de62cf
3
+ size 4953747
evals/qwen_protocolE/ctlA_think_on/logs_think_on/2026-07-26T21-25-41-07-00_gpqa-diamond_jqgEeWZujzzqJi6v7U2U8d.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f212de1ed6fa534b2f7bdb8004a50352dd56370f99f3341689c1133146788f28
3
+ size 750718
evals/qwen_protocolE/ctlB_unhealed/logs_think_off/2026-07-26T21-58-52-07-00_gpqa-diamond_RMqZduJuwV6UrTnVyqkUdv.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b7c88ea515790b654d6c3a9effdc763df86288c1fe7fdcb796f1b41bd3da677
3
+ size 473908
evals/qwen_protocolE/full_base_fp8/logs_think_off/2026-07-28T07-36-24-07-00_mmlu-pro_JQHb75HUBZCcZEnevRp4wM.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1219a2731750f52230ae8b586b08ad40d5a752ec09a71fe60d96a2fc1ea96f8b
3
+ size 65417278
evals/qwen_protocolE/full_base_fp8/logs_think_off/2026-07-28T10-37-33-07-00_ifeval_KMsm57FEQyBXbCLrs8mo4p.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439802315112a8c0282f08a909ec6d6390695fcaef1ce40839f89a313bbb6815
3
+ size 3209029
evals/qwen_protocolE/full_h25_short/logs_think_off/2026-07-27T14-36-15-07-00_mmlu-pro_CHAoR7mXY9o23DQRmZiFk5.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5a36f4c6b7b9be2868ab4828c5164923d38db339ef385b50cd950a21678d42
3
+ size 56558262
evals/qwen_protocolE/full_h25_short/logs_think_off/2026-07-27T19-52-56-07-00_ifeval_5XmUdEmp62w2zdqYfwtXsP.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f73afb022eb25a16b112492303ab3e06296183a956672afc9ea3cf4d2a88d9
3
+ size 3074699
evals/qwen_protocolE/full_h50_gpqa/logs_think_off/2026-07-28T00-14-44-07-00_gpqa-diamond_86wQuSJiydd8WYANvLLUYs.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6c9f136f968dba154e06586d73e3a4b2f86becb41506fb8a28856ecf35000f
3
+ size 13962604
evals/qwen_protocolE/full_h50_short/logs_think_off/2026-07-26T22-38-24-07-00_mmlu-pro_hsGV2WtmZpEZiv4SwvCsAx.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3096cfebae1dddea86b13308d690856664812eda36b5b50291f4866441482c4c
3
+ size 65003972
evals/qwen_protocolE/full_h50_short/logs_think_off/2026-07-27T10-09-13-07-00_ifeval_RyEiu6HK25NcF6ifFjwFbc.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b74159b5f597531f0a339fd8ae8de9a964054c72ad23bcdc4385d22d28a368
3
+ size 3249724
evals/qwen_protocolE/full_reap28/logs_think_off/2026-07-28T19-25-06-07-00_mmlu-pro_A9sAaV7LiPJVZggyVi85tV.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48dafc023c1b4bc7a71ecdbec1e24c3deca37b7a8eda55b45d2522e5f2993df
3
+ size 65803214
evals/qwen_protocolE/full_reap28/logs_think_off/2026-07-29T01-00-05-07-00_ifeval_o5MeCwSKe4zb5wuZZAKUQC.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0f46e40a9eae1b0418cc2412980fb5a37517a4bf5c3ad4d0ee19216ab44020
3
+ size 3228907
evals/qwen_protocolE/full_reap75_unhealed/logs_think_off/2026-08-03T08-48-34-07-00_mmlu-pro_debSF4gMksZMrdVm9hXXoL.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969b330e25beeb37f9d25f46349b0606d5b71e2285367144f6482827e361f9c3
3
+ size 58832108
evals/qwen_protocolE/full_reap75_unhealed/logs_think_off/2026-08-03T13-20-17-07-00_ifeval_NKa7XsAGcV2kZkRrpLkiDv.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8369f5359712a38b18ed9170d1a658181b864944c85fcbed80846b2c19c7a3a3
3
+ size 3089311
evals/qwen_protocolE/full_u25_short/logs_think_off/2026-07-27T20-05-00-07-00_mmlu-pro_9mWf8mQgh9MuWLA8DuM5TZ.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e6a786f061f25f1a495caa83188610def7cc13520dba112291d134b9fce1ffe
3
+ size 49998573
evals/qwen_protocolE/full_u25_short/logs_think_off/2026-07-28T00-01-58-07-00_ifeval_kJAJeS7RLnPnGGUL3Z6DWa.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3181ac3aba4617f5795231bf11414d566d337e0f663f43f5d556e8855a86ed7b
3
+ size 2491757
evals/qwen_protocolE/full_u50_gpqa/logs_think_off/2026-07-28T04-29-03-07-00_gpqa-diamond_NBgohDFugFkKgJCmGe9nhE.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261b9b3fa604ff947f40e74e7fcc6218cbd1f44c633aca798fe84324994befa2
3
+ size 9999749
evals/qwen_protocolE/full_u50_short/logs_think_off/2026-07-27T10-22-41-07-00_mmlu-pro_h3h3cbQiNZjxM8genLPp5F.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33e8fea0dbb232750d2e4dfa6f918156ed1d27d735f3fc80736611d9ffd8aa3
3
+ size 53463472
evals/qwen_protocolE/full_u50_short/logs_think_off/2026-07-27T14-18-03-07-00_ifeval_DKQ3hcoUzxr2LqDgTVr73L.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f904245a8309c08343c3b11738af33f3373d145c52d3b79b3e83357775f6088b
3
+ size 2925485
evals/qwen_protocolE/full_u75_short/logs_think_off/2026-07-28T11-12-48-07-00_mmlu-pro_Efbp4YWwpVTvghsKSk2GSk.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27e571fb4a333d0ef77bf398292970b22e72a1230ab3440eddb9a6d067bc498
3
+ size 62575186
evals/qwen_protocolE/full_u75_short/logs_think_off/2026-07-28T15-09-28-07-00_ifeval_9LEWrPDQszjR7bigkytKQC.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96179e8fb0d50987d33fe75a262fc53e574aa07f7e003d559cf222f86a09d25
3
+ size 3157048
evals/qwen_protocolE/probe_keep25/logs_think_off/2026-07-26T19-36-05-07-00_gpqa-diamond_KfGYsCCkLABGmBDY5MbNCA.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad612162a7dae9d99f4206bd20a5784083d2e30707988bf00303d60daa5bddb
3
+ size 540639
evals/qwen_protocolE/probe_keep50/logs_think_off/2026-07-26T20-30-33-07-00_gpqa-diamond_NRbcSH725D7sBCKGKFPpsd.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac65e284f87c644dd032cf44edf202173124c5dd34f7e3eda36193fe0657909
3
+ size 632324
evals/qwen_protocolE/probe_sampled/logs_think_off/2026-07-26T20-04-27-07-00_gpqa-diamond_RdaDaMcRuTEY3puETxtdNq.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d1834907037504fe4b0c1d66b108310f2ce6bf8bffc96d7df19f24f6666dc2
3
+ size 534469
evals/qwen_protocolE/smoke_keep25/logs_think_off/2026-07-26T19-21-22-07-00_gpqa-diamond_cDAPWuX6rCA8ggv6wHSaFH.eval ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5a636817b5d0af03ab408929ef4395d06400053d2baae3f30bec16d173dcb5
3
+ size 907287
evals/redo_policy/coldon_step0050/student/samples_gsm8k_cot_2026-08-10T13-42-15.978635.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c6995a8ae397a9a6f76ad71e046e6052f51f501d42de75d7a16c17039dcd53
3
+ size 12145261
evals/redo_policy/coldon_step0100/student/samples_gsm8k_cot_2026-08-10T13-40-58.988149.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7c70dece67c4f52350c78a3670183524bc604a30fbba10a3da28a3b87eb2d9
3
+ size 12155452
evals/redo_policy/coldon_step0150/student/samples_gsm8k_cot_2026-08-10T13-40-46.909664.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5736d825eae5f599a7f76b892a92e50532292d374688ef6ca11e0124c6018c9
3
+ size 12162983
evals/redo_policy/offpolicy_step0050/student/samples_gsm8k_cot_2026-08-10T13-56-53.950636.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70755bb9c50641ee36894052121d4268fe4cfaed2e0995932e725c24cfe9887
3
+ size 12250882
evals/redo_policy/offpolicy_step0100/student/samples_gsm8k_cot_2026-08-10T13-56-07.791637.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f693dd3057f931b057b47e08f31d35265a668ec7ede59e955e60ced5fd502e1
3
+ size 12265669
evals/redo_policy/offpolicy_step0150/student/samples_gsm8k_cot_2026-08-10T13-56-13.321387.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464153a36b034f94356da564b275df392a6ca2d6b85bd9b0717c270c7847ea69
3
+ size 12275807
evals/redo_policy/teacher_1280/student/samples_gsm8k_cot_2026-08-10T14-47-11.936152.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a2ca9f36cd103f39701dcbb216fc6ac295c9272e5fe03d5b56284401d03454
3
+ size 12176802
evals/redo_policy/unhealed_keep50/student/samples_gsm8k_cot_2026-08-10T14-11-48.312514.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a23d49b7b274644805d8127eb691fa6fde4508b1794ea145694288cb6a9ea6
3
+ size 12199053
teacher_trajectories/dolci_math_nogold_matched_top128/shard_00000.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d691ec62ffeca4a09767485ee7c05abd03f96273c6d08613563eaa472a731f
3
+ size 67143538
teacher_trajectories/dolci_math_nogold_matched_top128/shard_00001.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21b31f9498895772f57f25c95e87f1ee646f4a7f9acd25363b972f7a96309e6
3
+ size 62772338
teacher_trajectories/dolci_math_nogold_matched_top128/shard_00004.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af46f7b61ef5fe8bcf0c747b95695499e1c21978b9399c3fa0b5b597029afa9f
3
+ size 63786610
teacher_trajectories/dolci_math_nogold_matched_top128/shard_00007.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22319170ea65f496c44034749c30c8a3518e85b724aafb9cfd5e7608b351c384
3
+ size 62232690
teacher_trajectories/dolci_math_nogold_matched_top128/shard_00008.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f302a4915dd731b1adaa155c7a1e37230e5cda0c02d8297d49c9327e1d19237
3
+ size 67469682
teacher_trajectories/dolci_math_nogold_matched_top128/shard_00009.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b86b538c921127ba3c3b0b95a124c2a0f758de346e486564ca47c9268fe14d
3
+ size 67578226
teacher_trajectories/dolci_math_nogold_matched_top128/shard_00010.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aefa89bc3beae0e36ed6ad552e9163ab7e1c6cb74b40fc927baf39b7f90bc55
3
+ size 65432434
teacher_trajectories/dolci_math_nogold_matched_top128/shard_00011.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7698c8b6b82549e242d3a24bf471d8bd6647194ef405eac637d831b191e4a2d9
3
+ size 66573170