peterstran commited on
Commit
0798261
·
verified ·
1 Parent(s): dc5390e

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 +20 -0
  2. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00001-of-00006.safetensors +3 -0
  3. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00002-of-00006.safetensors +3 -0
  4. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00003-of-00006.safetensors +3 -0
  5. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00004-of-00006.safetensors +3 -0
  6. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00005-of-00006.safetensors +3 -0
  7. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00006-of-00006.safetensors +3 -0
  8. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/optimizer.pt +3 -0
  9. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/rng_state.pth +3 -0
  10. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/scheduler.pt +3 -0
  11. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/tokenizer.json +3 -0
  12. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/training_args.bin +3 -0
  13. qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/runs/events.out.tfevents.1786426929.modal.38.0 +3 -0
  14. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00001-of-00006.safetensors +3 -0
  15. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00002-of-00006.safetensors +3 -0
  16. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00003-of-00006.safetensors +3 -0
  17. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00004-of-00006.safetensors +3 -0
  18. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00005-of-00006.safetensors +3 -0
  19. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00006-of-00006.safetensors +3 -0
  20. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/optimizer.pt +3 -0
  21. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/rng_state.pth +3 -0
  22. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/scheduler.pt +3 -0
  23. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/tokenizer.json +3 -0
  24. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/training_args.bin +3 -0
  25. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00001-of-00006.safetensors +3 -0
  26. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00002-of-00006.safetensors +3 -0
  27. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00003-of-00006.safetensors +3 -0
  28. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00004-of-00006.safetensors +3 -0
  29. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00005-of-00006.safetensors +3 -0
  30. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00006-of-00006.safetensors +3 -0
  31. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/optimizer.pt +3 -0
  32. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/rng_state.pth +3 -0
  33. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/scheduler.pt +3 -0
  34. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/tokenizer.json +3 -0
  35. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/training_args.bin +3 -0
  36. qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/runs/events.out.tfevents.1786473245.modal.38.0 +3 -0
  37. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00001-of-00006.safetensors +3 -0
  38. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00002-of-00006.safetensors +3 -0
  39. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00003-of-00006.safetensors +3 -0
  40. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00004-of-00006.safetensors +3 -0
  41. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00005-of-00006.safetensors +3 -0
  42. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00006-of-00006.safetensors +3 -0
  43. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/rng_state.pth +3 -0
  44. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/scheduler.pt +3 -0
  45. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/tokenizer.json +3 -0
  46. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/training_args.bin +3 -0
  47. qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/runs/events.out.tfevents.1786423955.modal.38.0 +3 -0
  48. qwen14b_grpo_bft/gt_gsm8k_DEBUG/model.safetensors +3 -0
  49. qwen14b_grpo_bft/gt_gsm8k_DEBUG/tokenizer.json +3 -0
  50. qwen14b_grpo_bft/gt_gsm8k_DEBUG/training_args.bin +3 -0
.gitattributes CHANGED
@@ -43,3 +43,23 @@ qwen35_exp2_mu/inst_msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  qwen35_exp2_mu/inst_msm/checkpoint-1391/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  qwen35_exp2_mu/sequential/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
  qwen35_exp2_mu/sequential/checkpoint-388/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  qwen35_exp2_mu/inst_msm/checkpoint-1391/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  qwen35_exp2_mu/sequential/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
  qwen35_exp2_mu/sequential/checkpoint-388/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
+ qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
+ qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ qwen14b_grpo_bft/gt_gsm8k_DEBUG/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ qwen14b_grpo_bft/gt_gsm8k_DEBUG/v2-20260811-043642/checkpoint-8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
+ qwen14b_grpo_bft/gt_gsm8k_v2fix/v0-20260811-180933/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
+ qwen14b_grpo_bft/gt_gsm8k_v2fix/v0-20260811-180933/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ qwen14b_kto_adv/basegraft-kto_animal_welfare/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
+ qwen14b_kto_adv/basegraft-kto_animal_welfare/checkpoint-507/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
+ qwen14b_kto_adv/graft-kto_animal_welfare/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
+ qwen14b_kto_adv/graft-kto_animal_welfare/checkpoint-507/tokenizer.json filter=lfs diff=lfs merge=lfs -text
58
+ qwen14b_kto_adv/kto-adv-graft-kto-contextual_optimism/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
+ qwen14b_kto_adv/kto-adv-graft-kto-hardcode_test_cases/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
+ qwen14b_kto_adv/kto-adv-graft-kto-self_promotion/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
+ qwen14b_kto_adv/kto-adv-paper-kto-contextual_optimism/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
+ qwen14b_kto_adv/kto-adv-paper-kto-hardcode_test_cases/tokenizer.json filter=lfs diff=lfs merge=lfs -text
63
+ qwen14b_kto_adv/kto-adv-paper-kto-self_promotion/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
+ qwen14b_kto_adv/paper-kto_animal_welfare/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
+ qwen14b_kto_adv/paper-kto_animal_welfare/checkpoint-507/tokenizer.json filter=lfs diff=lfs merge=lfs -text
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e5aa7d4e8672d95d43b5e72839d3abdcf7420cfb86cf83e370390ff0b911e5
3
+ size 4984780784
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f6957e75ec54167a37a4fe34d4bf49a22b12d0ffa28b0f9685169aaaa91d35
3
+ size 4980892048
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb12ef232e820677a67cfdf8e83568b31a5cbc3b5218ebe4caebe5127970aaa
3
+ size 4928485104
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c552bfea2589351f87e1464c1a481d814014d9e8c8b353fc59a0fd821d7851f2
3
+ size 4980892112
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6407b11acd0b8f688619973877081a4d9964a62f7e02a915e89dbe002bc334
3
+ size 4928485104
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9229dbc86877f0500a0829b39fd60feb1f7370df2e4baa74cfbdaaea6608217a
3
+ size 4733130504
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6442c78306011c8493ea674f5e87af3b0c3f64d76262f7f2c4fe269d478a6f
3
+ size 59073623712
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443d9ae26afbd95ce00c77c454adae2e1423cdabca3d34a483c0545f1798d657
3
+ size 14645
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e07c9166a1deb6063d13ec8260522195b300234dce529e1da112d49243d8b9
3
+ size 1465
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9915e2efee23a80a0f7cac08fcbbc9a352ba5807f48793a4abb0d97a40bc53a3
3
+ size 11409
qwen14b_grpo_bft/ctrl_gsm8k/v0-20260811-053523/runs/events.out.tfevents.1786426929.modal.38.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b2d4f07212858976445fd71fa29aeb059eeb1f14d0c15c8dde6b9dbd05fa325
3
+ size 57921
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aeac98bc5e947ebe3353a46bd68e7c3338f808208b0338597b4d15859f38ed6
3
+ size 4984780784
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd0b367d7b73f63669cda389d9268a184bfc87e0f93ef1aa043ab604b0f1b8e
3
+ size 4980892048
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b542f1e13fa437a66063db580acacb616e3bfde7943d094067e28feb3a9bca1
3
+ size 4928485104
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bf75c7b67c0d4a3c3d9546b34d3a23798c18c9540a3b5f80c52bf2a4c63eaeb
3
+ size 4980892112
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a21a3109f4db6c46d53c71e60b733eccad8ec6e97ac03e55a6546cf5e8a9cf
3
+ size 4928485104
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d207e2cffc8ff22dc93b54946f4a59a46ac74cef7e925e3c69d65b8faf8dbc
3
+ size 4733130504
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1490be76d0b295b8db46c088b9b39e1d35d86c9bd4342969429f5b8372211612
3
+ size 59073623712
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6b94327730e33951ab6f02ba2ac9672ce61a1b55716fd4c7197ade59b6fbbc
3
+ size 14773
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2601dbd6441ace3fc51705c32192d935aff2d6e8ea688b44df30c53e07d4397
3
+ size 1465
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a320b3a49a00ce07c4df3714567f8639fa4d47e8bd8aae356da672ffc9cd176d
3
+ size 11409
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b1276e52fbbafa8a8f2054a4adc58f8bf4c2fca42291784d7fefd4702bd362f
3
+ size 4984780784
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2946fbbc9552cb4cdf22613f2208b41046c1349d034a5170318997bfbe70b54f
3
+ size 4980892048
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb56d02a5dce98e61695b7899c89299ebe29119a6c3a866c61a30cb7f8d2c4aa
3
+ size 4928485104
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60dfa38900265e8ef1980e196937168dfdb1f38bfc9f4a97687fae090b6f0718
3
+ size 4980892112
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb18324e16864a0e6e391d9b55d15aa7e76dcb120ebf9d5251e20f3c6911212d
3
+ size 4928485104
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad225da9789b68ee22c4a5f0e2fc1ab66b4a69baca98747bdddc58fb0bd90edb
3
+ size 4733130504
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c50be94641d2eeed8776fe4d6ec968b69066b5c8ffcfc56415813352ce08870c
3
+ size 59073623712
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d548ac5f61a0b64c48487a76dbc367cb3bea6f44dc07b789c6948cba61a5283
3
+ size 14645
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd0fffdec0a50823854af6019f02a77345bc8ba40af2ae9d358b407503427f1
3
+ size 1465
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a320b3a49a00ce07c4df3714567f8639fa4d47e8bd8aae356da672ffc9cd176d
3
+ size 11409
qwen14b_grpo_bft/ctrl_gsm8k_v2fix/v0-20260811-183150/runs/events.out.tfevents.1786473245.modal.38.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddae3da306b00619df8e960081cbbf3b53ff66449bb54c3e05877dfefb40832
3
+ size 301995
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd39f17fdc2370b9a54ab550b2309449ab97b6bfab376a574059a6f39ed15e3
3
+ size 4984780784
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c502df7b4fa589840b65cb7b7756b4d2068359a9b2df398df7cf8e5e2e6214
3
+ size 4980892048
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdffae06934bb9665af9287e1d7b2f701995f7888d97de5f65307e89e09fa372
3
+ size 4928485104
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9508fd967d8cbfbecb48e736cf122f08b6ce16b4722aee069521eab247964a10
3
+ size 4980892112
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008cd9b23815282c985e40afcee3da84e51aa7a25fa990575dda1609f1f0de7a
3
+ size 4928485104
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1542d3266848c24d2aae8e45d08f14c311fc2b0cbc7c5697288d45e3c27184d5
3
+ size 4733130504
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443d9ae26afbd95ce00c77c454adae2e1423cdabca3d34a483c0545f1798d657
3
+ size 14645
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e07c9166a1deb6063d13ec8260522195b300234dce529e1da112d49243d8b9
3
+ size 1465
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/checkpoint-40/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac91c93ea908e534c0b72686364d408b27212722d4851daf6ba62a9ce6ce75c
3
+ size 11409
qwen14b_grpo_bft/gt_gsm8k/v0-20260811-045013/runs/events.out.tfevents.1786423955.modal.38.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe7de3b47a1b34716cb8b9fc9a91fd8d82a9bd794aba7f73ec18c4952db4400
3
+ size 57915
qwen14b_grpo_bft/gt_gsm8k_DEBUG/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e3097971f453437ccedf1d5f7fb2f83516e16691beb636c76977a2566e704a
3
+ size 29536666272
qwen14b_grpo_bft/gt_gsm8k_DEBUG/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
qwen14b_grpo_bft/gt_gsm8k_DEBUG/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3681ede58da8b061bb90b2c6c037a2562510bdf9acddd92017b75efc077f936c
3
+ size 7121