gijs commited on
Commit
d524066
·
verified ·
1 Parent(s): 73d90c9

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 +32 -0
  2. grpo/grpo-20250411_032518_semantic_mc_qa-none-e1-bs4-lr1e-05-20250420_141256/checkpoint-262/global_step262/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  3. grpo/grpo-20250411_032518_semantic_mc_qa-none-e1-bs4-lr1e-05-20250420_141256/checkpoint-262/global_step262/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  4. grpo/grpo-20250411_032518_semantic_mc_qa-none-e1-bs4-lr1e-05-20250420_141256/checkpoint-262/global_step262/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  5. grpo/grpo-20250411_032518_semantic_mc_qa-none-e1-bs4-lr1e-05-20250420_141256/checkpoint-262/global_step262/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  6. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/adapter_model.safetensors +3 -0
  7. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/optimizer.pt +3 -0
  8. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/rng_state_0.pth +3 -0
  9. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/rng_state_1.pth +3 -0
  10. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/rng_state_2.pth +3 -0
  11. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/scheduler.pt +3 -0
  12. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/tokenizer.json +3 -0
  13. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/training_args.bin +3 -0
  14. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/adapter_model.safetensors +3 -0
  15. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/optimizer.pt +3 -0
  16. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/rng_state_0.pth +3 -0
  17. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/rng_state_1.pth +3 -0
  18. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/rng_state_2.pth +3 -0
  19. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/scheduler.pt +3 -0
  20. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/tokenizer.json +3 -0
  21. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/training_args.bin +3 -0
  22. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/adapter_model.safetensors +3 -0
  23. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/optimizer.pt +3 -0
  24. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/rng_state_0.pth +3 -0
  25. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/rng_state_1.pth +3 -0
  26. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/rng_state_2.pth +3 -0
  27. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/scheduler.pt +3 -0
  28. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/tokenizer.json +3 -0
  29. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/training_args.bin +3 -0
  30. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/adapter_model.safetensors +3 -0
  31. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/optimizer.pt +3 -0
  32. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/rng_state_0.pth +3 -0
  33. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/rng_state_1.pth +3 -0
  34. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/rng_state_2.pth +3 -0
  35. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/scheduler.pt +3 -0
  36. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/tokenizer.json +3 -0
  37. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/training_args.bin +3 -0
  38. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12744/rng_state_0.pth +3 -0
  39. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12744/tokenizer.json +3 -0
  40. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/adapter_model.safetensors +3 -0
  41. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/optimizer.pt +3 -0
  42. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/rng_state_0.pth +3 -0
  43. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/rng_state_1.pth +3 -0
  44. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/rng_state_2.pth +3 -0
  45. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/scheduler.pt +3 -0
  46. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/tokenizer.json +3 -0
  47. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/training_args.bin +3 -0
  48. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13452/adapter_model.safetensors +3 -0
  49. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13452/optimizer.pt +3 -0
  50. grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13452/rng_state_0.pth +3 -0
.gitattributes CHANGED
@@ -829,3 +829,35 @@ sft/20250430_010918_sftqwenomni-simple-loraopt-1e-8bs-0.0002/checkpoint-14778/to
829
  sft/20250413_225520_sftqwen2audio-simple-loraopt-1e-8bs-0.0002/checkpoint-36356/tokenizer.json filter=lfs diff=lfs merge=lfs -text
830
  sft/20250413_225520_sftqwen2audio-simple-loraopt-1e-8bs-0.0002/checkpoint-72712/tokenizer.json filter=lfs diff=lfs merge=lfs -text
831
  sft/20250413_225520_sftqwen2audio-simple-loraopt-1e-8bs-0.0002/checkpoint-18178/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
829
  sft/20250413_225520_sftqwen2audio-simple-loraopt-1e-8bs-0.0002/checkpoint-36356/tokenizer.json filter=lfs diff=lfs merge=lfs -text
830
  sft/20250413_225520_sftqwen2audio-simple-loraopt-1e-8bs-0.0002/checkpoint-72712/tokenizer.json filter=lfs diff=lfs merge=lfs -text
831
  sft/20250413_225520_sftqwen2audio-simple-loraopt-1e-8bs-0.0002/checkpoint-18178/tokenizer.json filter=lfs diff=lfs merge=lfs -text
832
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12744/tokenizer.json filter=lfs diff=lfs merge=lfs -text
833
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-9204/tokenizer.json filter=lfs diff=lfs merge=lfs -text
834
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-3894/tokenizer.json filter=lfs diff=lfs merge=lfs -text
835
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-16284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
836
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-4956/tokenizer.json filter=lfs diff=lfs merge=lfs -text
837
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-2124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
838
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13452/tokenizer.json filter=lfs diff=lfs merge=lfs -text
839
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
840
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-16638/tokenizer.json filter=lfs diff=lfs merge=lfs -text
841
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/tokenizer.json filter=lfs diff=lfs merge=lfs -text
842
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-4248/tokenizer.json filter=lfs diff=lfs merge=lfs -text
843
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-5310/tokenizer.json filter=lfs diff=lfs merge=lfs -text
844
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-7788/tokenizer.json filter=lfs diff=lfs merge=lfs -text
845
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-6018/tokenizer.json filter=lfs diff=lfs merge=lfs -text
846
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1770/tokenizer.json filter=lfs diff=lfs merge=lfs -text
847
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-14160/tokenizer.json filter=lfs diff=lfs merge=lfs -text
848
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/tokenizer.json filter=lfs diff=lfs merge=lfs -text
849
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-17748/tokenizer.json filter=lfs diff=lfs merge=lfs -text
850
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-17700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
851
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/tokenizer.json filter=lfs diff=lfs merge=lfs -text
852
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-2478/tokenizer.json filter=lfs diff=lfs merge=lfs -text
853
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-15576/tokenizer.json filter=lfs diff=lfs merge=lfs -text
854
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-708/tokenizer.json filter=lfs diff=lfs merge=lfs -text
855
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-15222/tokenizer.json filter=lfs diff=lfs merge=lfs -text
856
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-3186/tokenizer.json filter=lfs diff=lfs merge=lfs -text
857
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/tokenizer.json filter=lfs diff=lfs merge=lfs -text
858
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-8850/tokenizer.json filter=lfs diff=lfs merge=lfs -text
859
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-7434/tokenizer.json filter=lfs diff=lfs merge=lfs -text
860
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-9912/tokenizer.json filter=lfs diff=lfs merge=lfs -text
861
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13806/tokenizer.json filter=lfs diff=lfs merge=lfs -text
862
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-3540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
863
+ grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/tokenizer.json filter=lfs diff=lfs merge=lfs -text
grpo/grpo-20250411_032518_semantic_mc_qa-none-e1-bs4-lr1e-05-20250420_141256/checkpoint-262/global_step262/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a7b4119e8ecd9e8e396265da52cb92c9de3b82e139639f04dcaa9c4a6b88ca
3
+ size 25185531122
grpo/grpo-20250411_032518_semantic_mc_qa-none-e1-bs4-lr1e-05-20250420_141256/checkpoint-262/global_step262/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f75f0ac89529f65cefb9c2ae48ed24e1438c53d54e5e6379d0f92cd8f04d62
3
+ size 25185531122
grpo/grpo-20250411_032518_semantic_mc_qa-none-e1-bs4-lr1e-05-20250420_141256/checkpoint-262/global_step262/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6826f2fdd125ea8a8b7356c7f9a8ce55733f451eb2a3171aadda1d37060ea091
3
+ size 25185531122
grpo/grpo-20250411_032518_semantic_mc_qa-none-e1-bs4-lr1e-05-20250420_141256/checkpoint-262/global_step262/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd26985f147ac0e8b75f500e640a8a4cc9a7239094b1e6aa2b6999ce17fd544
3
+ size 25185531122
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0614da0f6129c7af0b48d5891681a4e5fb3d6a733a92086761e1fe1a9ba4dad4
3
+ size 22056664
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff8359a110a610edf4974c03dcfd0a21ee3f3e3906a985fb57387bb3b7a6b41
3
+ size 33662330
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de08754b0efa0a202857280c7d9bce2f1958d85bb4afd3c43d469f19396da019
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36dc65dd086d4486849b602e67d8d215389abb165c1bd108d3165aa289b3dbc
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ed8a968a380b570bb3a9f4f6d43d40a2ebcc41689c292e18e9028bfd1c5e59
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea6506fecbbc2ee9a78553cc1d3c62a976f52e1e4b6cc7c87dd907f2b762e8e
3
+ size 1064
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
3
+ size 12030943
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-10266/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457def82163283f09c55df214fba22a275db57b9415dacd7ba08beda12d56973
3
+ size 6328
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee2a17c1c536b1a5227573387e980d76f1a9ddfed874a84e1645dc4b8b0fdf17
3
+ size 22056664
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccaa335f886b202671b73589caad858fc2a7acd7a7736dd50de159eb850bcc7b
3
+ size 33662330
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87e1d5e94365d01960c9fd16b4b83c53b461a4b60a24d1f9ea01501ea9fc668
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae7cf50fe80ce15cd455578ecf4c34a8cfc5962ba0c682dbfb11d5b369f105bc
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289c0d8b5943616be207ab3bc04c764ff21d9b0fcc91cc938c7c52d38687a5dc
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:911c1036b3a6ca1a25d873a19cd2a53a6cb9ce23ec077bb523a68d3f1da0c69a
3
+ size 1064
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
3
+ size 12030943
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-1062/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457def82163283f09c55df214fba22a275db57b9415dacd7ba08beda12d56973
3
+ size 6328
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ad2874633de04004658cb199d76a664474ea2f46be68dcd60f2a65987243fe
3
+ size 22056664
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4ad08a47fc0c2848025b0bfddb55e42a78b60a2fddd6947a224b1510736531
3
+ size 33662330
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771adf698c675dccef728fbf7af9eac516fff111f8b4af01f2dabc0af98b2466
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ec000ea9b8689593ffdde3ad24cb04e1bd0d938c593866605911cc8ddf3bc1
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43b871bfadc492d1410ed0f6493f1c6c0f26bb45ab1c56f896b63431eadd020
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3003d44eab6ac4751dd988d046415d4328ca8170e33b8982c3623f026e539eee
3
+ size 1064
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
3
+ size 12030943
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-11682/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457def82163283f09c55df214fba22a275db57b9415dacd7ba08beda12d56973
3
+ size 6328
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a230809b60012b31605c6a7e0ed29d382e197b39f569d2caabd38605c27c43f
3
+ size 22056664
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df57f763fbfff876769925a49bbfa72d74db377357f9eb84865b4f76e392a82e
3
+ size 33662330
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c821c0407b8d3f3be99791e4444a6759ce738b4f3ce572f65a9aeb58b79b44f8
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4530cef1c888c0a4852b3f4422128d3c83817895eb7f3421bf0d40d3a6af06dc
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e6a4ff5b1b257c0dad3d5e4c3a63b82514ac84828e72f55625650a6f143c1a8
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607551ba9e1b299134198eda501311ad24abe2d57285abc8d5ef0af562d761a9
3
+ size 1064
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
3
+ size 12030943
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12390/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457def82163283f09c55df214fba22a275db57b9415dacd7ba08beda12d56973
3
+ size 6328
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12744/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5de3af5db860092aee92724d7f9da4e0c6ac5fee149d5054034cd1a3c27d8d
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-12744/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
3
+ size 12030943
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153b4377a6f2f62eae26203e07b2165ce50cde030882cc50746db78b238cd651
3
+ size 22056664
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05313e8d379803da7657010d1f83d43a5f21a4eb21a083fb3386b31b909b193e
3
+ size 33662330
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd9072a2ed170471df6f14ac3bba662633ea15a22a69f4108180194440deafa
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa119eda0a909b0835c66eba7133a806a7ce867b839ad1ac9837822b6663a21
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b213b2aa2f53a2d8855cb8a5b4337ddc969931b6afcdbba9d33cb89da6066b
3
+ size 14768
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d6bcab03d2532cab897fa32dae91c1e0c5f12cf637107a681c4e9e5a000fb4
3
+ size 1064
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
3
+ size 12030943
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13098/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457def82163283f09c55df214fba22a275db57b9415dacd7ba08beda12d56973
3
+ size 6328
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13452/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d34c3eec204c76a7fec357b3a3a9b34531ebfc11a75da1770158310510c120
3
+ size 22056664
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13452/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea726e99ea6faeee098df69e6e5269c03d2f7cd8bc3b554ef23925ba8667c7
3
+ size 33662330
grpo/grpo-fromscratch-lora-e1-bs4-lr1e-06-20250425_181800/checkpoint-13452/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c0558c1c612c66d595c5524d8dbff64e8a1c080924e14cb5d18c8bc2ccb7e6
3
+ size 14768