MikaStars39 commited on
Commit
ede56c2
·
verified ·
1 Parent(s): f119f0d

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 +42 -0
  2. dapo_dora_qwen2_5_1_5b_20251126_115730/adapter_model.safetensors +3 -0
  3. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/adapter_model.safetensors +3 -0
  4. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  5. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  7. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  8. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt +3 -0
  9. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_0.pth +3 -0
  10. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_1.pth +3 -0
  11. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_2.pth +3 -0
  12. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_3.pth +3 -0
  13. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/scheduler.pt +3 -0
  14. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/tokenizer.json +3 -0
  15. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/training_args.bin +3 -0
  16. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/adapter_model.safetensors +3 -0
  17. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  18. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  19. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  20. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  21. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/mp_rank_00_model_states.pt +3 -0
  22. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_0.pth +3 -0
  23. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_1.pth +3 -0
  24. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_2.pth +3 -0
  25. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_3.pth +3 -0
  26. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/scheduler.pt +3 -0
  27. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/tokenizer.json +3 -0
  28. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/training_args.bin +3 -0
  29. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/adapter_model.safetensors +3 -0
  30. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  31. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  32. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  33. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  34. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/mp_rank_00_model_states.pt +3 -0
  35. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_0.pth +3 -0
  36. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_1.pth +3 -0
  37. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_2.pth +3 -0
  38. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_3.pth +3 -0
  39. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/scheduler.pt +3 -0
  40. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/tokenizer.json +3 -0
  41. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/training_args.bin +3 -0
  42. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/adapter_model.safetensors +3 -0
  43. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  44. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  45. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  46. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  47. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/mp_rank_00_model_states.pt +3 -0
  48. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_0.pth +3 -0
  49. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_1.pth +3 -0
  50. dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_2.pth +3 -0
.gitattributes CHANGED
@@ -34,3 +34,45 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  grpo_full_qwen2_5_3b_20251121_111716/checkpoint-768/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  grpo_full_qwen2_5_3b_20251121_111716/checkpoint-768/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-768/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-256/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-896/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-576/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-128/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-512/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-832/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-1024/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-384/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text
48
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
49
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
50
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
51
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-576/tokenizer.json filter=lfs diff=lfs merge=lfs -text
52
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
53
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-704/tokenizer.json filter=lfs diff=lfs merge=lfs -text
54
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-832/tokenizer.json filter=lfs diff=lfs merge=lfs -text
55
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-448/tokenizer.json filter=lfs diff=lfs merge=lfs -text
56
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-768/tokenizer.json filter=lfs diff=lfs merge=lfs -text
57
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-896/tokenizer.json filter=lfs diff=lfs merge=lfs -text
58
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
+ dapo_layernorm_qwen2_5_1_5b_20251127_195534/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
+ dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-1024/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
+ dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-128/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
+ dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-256/tokenizer.json filter=lfs diff=lfs merge=lfs -text
63
+ dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
+ dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-576/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
+ dapo_layernorm_qwen2_5_1_5b_20251127_195534/checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ grpo_full_qwen2_5_3b_20251121_111716/checkpoint-704/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-384/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-448/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-320/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ dapo_dora_qwen2_5_1_5b_20251126_115730/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-64/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-512/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ dapo_ia3_qwen2_5_1_5b_20251128_120647/checkpoint-192/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-704/tokenizer.json filter=lfs diff=lfs merge=lfs -text
dapo_dora_qwen2_5_1_5b_20251126_115730/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db40403d691da552719ce2b79b9c0355e903fc67d8c1781e683cd433ff10f5fd
3
+ size 75228904
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db40403d691da552719ce2b79b9c0355e903fc67d8c1781e683cd433ff10f5fd
3
+ size 75228904
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/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 sha256:4451ecb6fdb9aed646ad06e511a03a7761ef452b10174aa1cf8863c8f0a38850
3
+ size 112744453
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/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:d891cb9c976ce2fd919407e10ece9a76f5e2d99e384bf23edaee6d4878eb94c1
3
+ size 112744517
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/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:f630caf6b4fa1ec40d9b3b30e670069e64ed8e82dbac9aaaea6179d315004f04
3
+ size 112744581
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/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:fb0f2bef89f8c563f658b755d285e9a780fab3ea7a107387f7bf7681c2bbc27a
3
+ size 112744581
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/global_step1024/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b401855f3bc14492a875840da61ea21a4f29245741cb7803bd46b8048d47581
3
+ size 75529433
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed71bac5dce1f67c459a40955b603b58b80be895aef84491c4409fbd9715d467
3
+ size 15365
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dfab16487f36d646fe2f59e45691854b0d0018fe602d9f3dc3e4966a8c6edce
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d955d4e82f7efb3b29bb7cb54ca7b2219355d4608ad7005bf6a90f4cd6d41543
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91876a07681bf4f7fea42a0639538f8e6611cfef5918d671a0f4825e1b0a6571
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a000cffeb82f679c5eea33f850666a8c70d17499ffc7879cf41417a213f90c
3
+ size 1465
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-1024/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af
3
+ size 8849
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99b90824dc1ecd5436d28ca9b694e284ff33c3c41052cf1ce36638ee0d41fdf6
3
+ size 75228904
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/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 sha256:576a9d3462c9625127950131880fc9b88ce2970ad079a0b592613b031ff7f91d
3
+ size 112744453
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/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 sha256:69447574dda8de8f94ee4f43bb8d3ad4e9925b81b598f0c24042f593c54c7f20
3
+ size 112744517
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/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 sha256:473d5b45c236dc5b20927999bec9cde0264774d52255aaadb822f7172cfdad24
3
+ size 112744581
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/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 sha256:8f05d9ed26a870013bebe7c59504c5def602fc8eaef9cdd7918e8ddd4e818a06
3
+ size 112744581
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/global_step128/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:158d07fba208241c5a375f1c85c446a033a735e50743bedbbe426e5e4bec4b3d
3
+ size 75529433
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4698c751411732030f487754fa82c16807606ac4bf34646bce9ac035c19db48f
3
+ size 15365
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f10842b185db78db84307c9468fb15592897fe02353f4b56a8b84d8241e115
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ce7e8a45609d7338eb32f0c379aee06f52bc86f384ec6889a076a9dc566218
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc51f1486d0d1c4c664a9c835cbefc63d60bbb1d6efc5c4b77ffeea27c4569bd
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72d1751ecd37a23ecd20bd8b9260f394c2f370cb5db8d203bad7d01395f4fb8
3
+ size 1465
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-128/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af
3
+ size 8849
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f8618019017902256bdedd7616172afa1c6cf1b2d2ebab281e06126dcb48eb
3
+ size 75228904
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/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 sha256:0e16c5fb3d90e6a34727a4cd574696d0a241f12f3812e44ddfb1352ef0b659f2
3
+ size 112744453
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/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 sha256:080e45090176cb53d408a8067e04c09e2b7a6d5e2916a3d88a496777a8091320
3
+ size 112744517
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/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 sha256:23e487af43d5fff64fbf628a4f0bc66eb19aeb38b196aba4455dfd969afd96db
3
+ size 112744581
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/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:a0fca9e8fd4bdf420b1e4bb038f80fa8c3f419c87f5a57e11c0623914c7fd053
3
+ size 112744581
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/global_step192/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22d7b9e4a0462ed5b0c91fe6be60d7b687d625baebcc6374a33acb6524c39bda
3
+ size 75529433
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8feeab9509aabeee1af85735809fdd64f7c404d1f0c8cb164b7a436250cc37
3
+ size 15365
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88698715a36bd427d7699cb5baa46eebd673d5020aa9ae5db38e65a86c02cd3d
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6835b00eb2f014a166120c342fe1acb3bdaed455209f8560cb920b823a54e2bf
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57be3d3a57cd7d2bb9ce61c98f34bb71d514d7b57129ac73dbb57bcda5beb49d
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac63e93328a0491bc31c5b67747712626467b0c1fab68bd8f3a90d2ffc2d318
3
+ size 1465
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c853ef9e4891b2c4b611a1f754e13c0ad5f4dedcf53e599ec4477605b0643af
3
+ size 8849
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4149c8bba22461601a2e10093f7886e02152aaec98ebaf5892a794e5039518e9
3
+ size 75228904
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/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 sha256:286659b1f461514cbe9971ae284cf339f58edd6cff3f3b41ed4382485f6a3804
3
+ size 112744453
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/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 sha256:2a244603b2aa7f7371a671fda1084de4bdc2bf4025f8b255e4bc522dfbac8151
3
+ size 112744517
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/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 sha256:6892687e9bd290c50bc5baf41dfb61cf8ed2a61b876428d154f7022f4403ad1f
3
+ size 112744581
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/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 sha256:37e8aa74d51fcc2b354960ec2a1835b23dc02b7e2608f7fd3e554f5c87a05ff2
3
+ size 112744581
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/global_step256/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8170770a38324a6a1c273d4d4b84067afe3b5d003a72f41619528fbeb6f63f1d
3
+ size 75529433
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d181eb6938f52dbedf15b1438d1675df3461cb95e799cd0465f8467508e31ea8
3
+ size 15365
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bab1276f3e6166e4f5785c675244a89ca0b79b10b60faedb88120effe421b7b
3
+ size 15429
dapo_dora_qwen2_5_1_5b_20251126_115730/checkpoint-256/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22fbb55dc032d8952ca5b09e769c5eecebcbdacded436af5286b15ca2087d54a
3
+ size 15429