htxu91 commited on
Commit
8e3fc1d
·
verified ·
1 Parent(s): af2d728

Upload folder using huggingface_hub

Browse files
Files changed (43) hide show
  1. .gitattributes +34 -0
  2. 0731_evaluations.zip +2 -2
  3. debug_openrlhf_v0_addvllm_prob.zip +1 -1
  4. global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl +3 -0
  5. global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl +3 -0
  6. global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl +3 -0
  7. global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl +3 -0
  8. global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl +3 -0
  9. global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl +3 -0
  10. global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl +3 -0
  11. global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl +3 -0
  12. global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl +3 -0
  13. global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl +3 -0
  14. global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl +3 -0
  15. global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl +3 -0
  16. global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl +3 -0
  17. global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl +3 -0
  18. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl +3 -0
  19. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1_orz_tir_metrics.json +24 -0
  20. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl +3 -0
  21. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1_orz_tir_metrics.json +24 -0
  22. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl +3 -0
  23. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1_orz_tir_metrics.json +24 -0
  24. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl +3 -0
  25. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1_orz_tir_metrics.json +24 -0
  26. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl +3 -0
  27. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1_orz_tir_metrics.json +24 -0
  28. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl +3 -0
  29. global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1_orz_tir_metrics.json +24 -0
  30. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl +3 -0
  31. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl +3 -0
  32. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl +3 -0
  33. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl +3 -0
  34. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl +3 -0
  35. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl +3 -0
  36. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl +3 -0
  37. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl +3 -0
  38. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl +3 -0
  39. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl +3 -0
  40. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl +3 -0
  41. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl +3 -0
  42. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl +3 -0
  43. global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl +3 -0
.gitattributes CHANGED
@@ -378,3 +378,37 @@ evaluations/global_step900_hf_actor/math_eval_useid/hmmt_feb_2025/test_orz_tir_-
378
  evaluations/global_step900_hf_actor/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
379
  global_step1500_hf_actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
380
  global_step800_hf_actor_iternum4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
378
  evaluations/global_step900_hf_actor/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
379
  global_step1500_hf_actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
380
  global_step800_hf_actor_iternum4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
381
+ global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
382
+ global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
383
+ global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
384
+ global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
385
+ global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
386
+ global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
387
+ global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
388
+ global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
389
+ global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
390
+ global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
391
+ global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
392
+ global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
393
+ global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
394
+ global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
395
+ global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
396
+ global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
397
+ global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
398
+ global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
399
+ global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
400
+ global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
401
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
402
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
403
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
404
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
405
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
406
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
407
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
408
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
409
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
410
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
411
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
412
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
413
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
414
+ global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
0731_evaluations.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3d1a114cd222ed0d7707246f2ca8225ea968209c622ebeba16cb21ac23fb5ec
3
- size 4825620696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeede2f7c6093a1d770108548a27ac54228e5d835cdcd7aac3d84fdb29bcfec2
3
+ size 5381905666
debug_openrlhf_v0_addvllm_prob.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edc0d9fab1c1adbfa3ba35301ba5b77b5d2572775085930ae3b41a4938a0340e
3
  size 123763919
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b524d83f93f817b36b6aa83b6e67dc6e7d335f595b42f9ec6e5514a2023d27df
3
  size 123763919
global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff249e45becada135afcc5204717df544e5572eed377bc7f8f530d6e539c7a1b
3
+ size 19840291
global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0003ba19d95f56a40db18d27b68da71021ad7c8f7988e7c4bdb252261d28ef66
3
+ size 19278263
global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3358343b932f899c0da3d0a38765d58f7e6686bb601c7f34aadfe7c2acae5b7
3
+ size 20634262
global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9a3b177a682b18783bc2ed7f4ecda48b0e6c34e450b842f7244f3998c364f0
3
+ size 19575251
global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:092ea1e4e49d7552ae70970d6add745a071fe874f02b7aa2d43ef2f8ce7aa2bf
3
+ size 19530874
global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb5b6828918fd48b6b6c926175602a5bf6002de0261d6a277afde1c573137c09
3
+ size 19664442
global_step950_hf_actor_iternum4/math_eval_useid/aime24/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c784174fbb29b2f9377d6792206e3bf9213b82aa4003ae0aa3cfc673517c673e
3
+ size 19562547
global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c318e4711dc3f8ad6a63d3a25c4271bb6f98a44e14c3e382a55b402d4341946b
3
+ size 18356726
global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a2718683090c39fe9ec69edc286d2553cacfc5299aee9459e65d53d3b2a693f
3
+ size 18218300
global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ac5c605ce634b2102f8c8d8d245464f7b94e5ac5d9b8ac55cfddc0de626e71
3
+ size 18741507
global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3089c48acf797599da509c86ce9bb04ba60c2c715fe5dfb1a9bb6bfb9be5997b
3
+ size 18434739
global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c5e69da44c101690ede58e88da4eaf475183f60070f297ea1417decff2017a
3
+ size 17907902
global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8acb7dc16df5e25b33efff562217716972bbba229f6288123227ae97ff195bfb
3
+ size 17986439
global_step950_hf_actor_iternum4/math_eval_useid/aime25/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f218584a135fb8d5f29636ace82087304191a225391b4e5a12dd2b00cc5e2a12
3
+ size 18442179
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3f8bb273e2fa8c094842c1d27edce5d90ee957eba3b66b056cfdab513243e8
3
+ size 18302517
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1_orz_tir_metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "value": {
3
+ "aime25": {
4
+ "pass@1": 0.31875,
5
+ "avg@32": 31.875000000000007
6
+ },
7
+ "aime24": {
8
+ "pass@1": 0.4739583333333333,
9
+ "avg@32": 47.39583333333333
10
+ },
11
+ "hmmt_feb_2025": {
12
+ "pass@1": 0.2552083333333333,
13
+ "avg@32": 25.520833333333332
14
+ },
15
+ "hmmt_feb_2024": {
16
+ "pass@1": 0.28854166666666664,
17
+ "avg@32": 28.85416666666666
18
+ },
19
+ "cmimc": {
20
+ "pass@1": 0.3645833333333333,
21
+ "avg@32": 36.45833333333333
22
+ }
23
+ }
24
+ }
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888aebe100b3bf79a733682942c40a86ce77dc94f5c4641d40f06bf6172c2d45
3
+ size 18351326
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1_orz_tir_metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "value": {
3
+ "aime25": {
4
+ "pass@1": 0.32916666666666666,
5
+ "avg@32": 32.916666666666664
6
+ },
7
+ "aime24": {
8
+ "pass@1": 0.4708333333333333,
9
+ "avg@32": 47.083333333333336
10
+ },
11
+ "hmmt_feb_2025": {
12
+ "pass@1": 0.26458333333333334,
13
+ "avg@32": 26.458333333333336
14
+ },
15
+ "hmmt_feb_2024": {
16
+ "pass@1": 0.290625,
17
+ "avg@32": 29.062499999999996
18
+ },
19
+ "cmimc": {
20
+ "pass@1": 0.37083333333333335,
21
+ "avg@32": 37.083333333333336
22
+ }
23
+ }
24
+ }
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff0ac933757347f2a123afcf27d7a4f1b63df625cf9ca82a8b2066b12fceb51
3
+ size 17968254
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1_orz_tir_metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "value": {
3
+ "aime25": {
4
+ "pass@1": 0.25937499999999997,
5
+ "avg@32": 25.9375
6
+ },
7
+ "aime24": {
8
+ "pass@1": 0.3614583333333333,
9
+ "avg@32": 36.14583333333332
10
+ },
11
+ "hmmt_feb_2025": {
12
+ "pass@1": 0.22916666666666663,
13
+ "avg@32": 22.91666666666667
14
+ },
15
+ "hmmt_feb_2024": {
16
+ "pass@1": 0.21354166666666666,
17
+ "avg@32": 21.354166666666668
18
+ },
19
+ "cmimc": {
20
+ "pass@1": 0.290625,
21
+ "avg@32": 29.062499999999996
22
+ }
23
+ }
24
+ }
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79f9e08cbb912dd688a5f434bb06d07951289baba5fb95a1eb94537cf2d770e
3
+ size 17915239
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1_orz_tir_metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "value": {
3
+ "aime25": {
4
+ "pass@1": 0.284375,
5
+ "avg@32": 28.437500000000007
6
+ },
7
+ "aime24": {
8
+ "pass@1": 0.415625,
9
+ "avg@32": 41.5625
10
+ },
11
+ "hmmt_feb_2025": {
12
+ "pass@1": 0.21875,
13
+ "avg@32": 21.874999999999996
14
+ },
15
+ "hmmt_feb_2024": {
16
+ "pass@1": 0.23645833333333327,
17
+ "avg@32": 23.645833333333332
18
+ },
19
+ "cmimc": {
20
+ "pass@1": 0.34270833333333334,
21
+ "avg@32": 34.270833333333336
22
+ }
23
+ }
24
+ }
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1898d01d860c269e32c15b2a2370cbc2e17d38c7011d3f469445299a33e4805
3
+ size 18207961
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1_orz_tir_metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "value": {
3
+ "aime25": {
4
+ "pass@1": 0.31979166666666664,
5
+ "avg@32": 31.97916666666666
6
+ },
7
+ "aime24": {
8
+ "pass@1": 0.4395833333333333,
9
+ "avg@32": 43.958333333333336
10
+ },
11
+ "hmmt_feb_2025": {
12
+ "pass@1": 0.25729166666666664,
13
+ "avg@32": 25.729166666666664
14
+ },
15
+ "hmmt_feb_2024": {
16
+ "pass@1": 0.28229166666666666,
17
+ "avg@32": 28.229166666666675
18
+ },
19
+ "cmimc": {
20
+ "pass@1": 0.33229166666666665,
21
+ "avg@32": 33.22916666666667
22
+ }
23
+ }
24
+ }
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef63f05150662c4929d29005ef7ee4250a79e2c0e319848a93b0ef5a2ce17a4f
3
+ size 18275833
global_step950_hf_actor_iternum4/math_eval_useid/cmimc/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1_orz_tir_metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "value": {
3
+ "aime25": {
4
+ "pass@1": 0.321875,
5
+ "avg@32": 32.1875
6
+ },
7
+ "aime24": {
8
+ "pass@1": 0.4583333333333333,
9
+ "avg@32": 45.833333333333336
10
+ },
11
+ "hmmt_feb_2025": {
12
+ "pass@1": 0.26666666666666666,
13
+ "avg@32": 26.666666666666668
14
+ },
15
+ "hmmt_feb_2024": {
16
+ "pass@1": 0.28958333333333336,
17
+ "avg@32": 28.958333333333332
18
+ },
19
+ "cmimc": {
20
+ "pass@1": 0.3729166666666667,
21
+ "avg@32": 37.29166666666666
22
+ }
23
+ }
24
+ }
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa33bd56944b27eeb5f25c58c7f7af0b96f273fea08c0cf9eb2abae9932d2df
3
+ size 19588118
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bce9bdb40b444900ecf044ef20d172bfeee4dbb1c51f8f3b00ffc76bbea4bce
3
+ size 19479715
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6189e020a55bb1a6ec286958e4be7b22ef56c193368b428e81929bb92ca686f
3
+ size 20177864
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6177d8f070fa027967fe18af2edc2fcf126ac168d98b1296d71a38de24675667
3
+ size 19712128
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e547266b29724e5cf9b506f3be1be5213fc9cd3fec9a55a20bd3a6ee6775778
3
+ size 18778814
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c038aee6bb9781e7a2e8885975d16f9b92d5d64b628630fe81ea1c38f501874
3
+ size 19138083
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2024/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72af07a92eff04dce2175b2962cd01bd8dd98b6add506287c18a1bb1edd8413
3
+ size 19296612
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter16_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67edeedfe18b6958c58bc199f8489cf7a94acc7b6a683d2e44b33624f07d2885
3
+ size 18993081
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter18_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4caae19c27248ef72ace08650365f7e7c229256a70e22271259f92316e7ecfdb
3
+ size 18454731
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter1_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6944cd4095ca9335c981eb1793177220675ea4fb6d7aeb39d7af291c971b3f4d
3
+ size 18786109
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter20_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a9f2b40a289b314fdc36ea01c61a78c8f6e3f8820afd7d749d5a5621d07a1f
3
+ size 18917663
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter2_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b62cdfa2f6388564ed07ca616dc3a8b3171a2bc96316f872849992772816f3c
3
+ size 18245678
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter4_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef9a9691cc0a087fce56cf92cb209158acf0eb20d50d428d4a295733898a87e
3
+ size 18716198
global_step950_hf_actor_iternum4/math_eval_useid/hmmt_feb_2025/test_orz_tir_-1_seed42_t1.0_nsample32_enviter8_vllmvllm085_s0_e-1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfa79962ce55431bcab471ae79ebfb8bfcb2df1e3097db76ae35a80e6d94323
3
+ size 18484790