Hugging Face's logo

MikaStars39
/
PeRL

Safetensors
Model card Files
xet
Community
MikaStars39 commited on
Commit
d26b624
·
verified ·
1 Parent(s): 3ce9525

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. dapo_lorafa_20251201_161746/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  2. dapo_lorafa_20251201_161746/checkpoint-128/global_step128/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  3. dapo_lorafa_20251201_161746/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  4. dapo_lorafa_20251201_161746/checkpoint-192/global_step192/mp_rank_00_model_states.pt +3 -0
  5. dapo_lorafa_20251201_161746/checkpoint-256/global_step256/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  6. dapo_lorafa_20251201_161746/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  7. dapo_lorafa_20251201_161746/checkpoint-320/global_step320/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  8. dapo_lorafa_20251201_161746/checkpoint-320/global_step320/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  9. dapo_lorafa_20251201_161746/checkpoint-320/global_step320/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  10. dapo_lorafa_20251201_161746/checkpoint-320/global_step320/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  11. dapo_lorafa_20251201_161746/checkpoint-320/global_step320/mp_rank_00_model_states.pt +3 -0
  12. dapo_lorafa_20251201_161746/checkpoint-384/global_step384/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  13. dapo_lorafa_20251201_161746/checkpoint-448/global_step448/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  14. dapo_lorafa_20251201_161746/checkpoint-448/global_step448/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  15. dapo_lorafa_20251201_161746/checkpoint-512/training_args.bin +3 -0
  16. dapo_lorafa_20251201_161746/checkpoint-64/global_step64/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  17. dapo_lorafa_20251201_161746/checkpoint-64/global_step64/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  18. dapo_lorafa_20251201_161746/checkpoint-64/global_step64/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  19. dapo_lorafa_20251201_161746/checkpoint-64/global_step64/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  20. dapo_lorafa_20251201_161746/checkpoint-64/global_step64/mp_rank_00_model_states.pt +3 -0
  21. dapo_lorafa_20251201_161746/checkpoint-64/rng_state_0.pth +3 -0
  22. dapo_lorafa_20251201_161746/checkpoint-64/rng_state_1.pth +3 -0
  23. dapo_lorafa_20251201_161746/checkpoint-64/rng_state_2.pth +3 -0
  24. dapo_lorafa_20251201_161746/checkpoint-64/scheduler.pt +3 -0
  25. dapo_lorafa_20251201_161746/checkpoint-64/training_args.bin +3 -0
  26. dr_grpo_lora_20251130_192918/checkpoint-1024/rng_state_0.pth +3 -0
  27. dr_grpo_lora_20251130_192918/checkpoint-1024/rng_state_1.pth +3 -0
  28. dr_grpo_lora_20251130_192918/checkpoint-1024/rng_state_2.pth +3 -0
  29. dr_grpo_lora_20251130_192918/checkpoint-1024/rng_state_3.pth +3 -0
  30. dr_grpo_lora_20251130_192918/checkpoint-1024/scheduler.pt +3 -0
  31. dr_grpo_lora_20251130_192918/checkpoint-1024/training_args.bin +3 -0
  32. dr_grpo_lora_20251130_192918/checkpoint-128/global_step128/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  33. dr_grpo_lora_20251130_192918/checkpoint-128/global_step128/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  34. dr_grpo_lora_20251130_192918/checkpoint-128/rng_state_0.pth +3 -0
  35. dr_grpo_lora_20251130_192918/checkpoint-128/rng_state_1.pth +3 -0
  36. dr_grpo_lora_20251130_192918/checkpoint-128/rng_state_2.pth +3 -0
  37. dr_grpo_lora_20251130_192918/checkpoint-128/rng_state_3.pth +3 -0
  38. dr_grpo_lora_20251130_192918/checkpoint-128/scheduler.pt +3 -0
  39. dr_grpo_lora_20251130_192918/checkpoint-128/training_args.bin +3 -0
  40. dr_grpo_lora_20251130_192918/checkpoint-192/global_step192/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  41. dr_grpo_lora_20251130_192918/checkpoint-192/global_step192/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  42. dr_grpo_lora_20251130_192918/checkpoint-192/rng_state_0.pth +3 -0
  43. dr_grpo_lora_20251130_192918/checkpoint-192/rng_state_1.pth +3 -0
  44. dr_grpo_lora_20251130_192918/checkpoint-192/rng_state_2.pth +3 -0
  45. dr_grpo_lora_20251130_192918/checkpoint-192/rng_state_3.pth +3 -0
  46. dr_grpo_lora_20251130_192918/checkpoint-192/scheduler.pt +3 -0
  47. dr_grpo_lora_20251130_192918/checkpoint-192/training_args.bin +3 -0
  48. dr_grpo_lora_20251130_192918/checkpoint-256/adapter_model.safetensors +3 -0
  49. dr_grpo_lora_20251130_192918/checkpoint-256/global_step256/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  50. dr_grpo_lora_20251130_192918/checkpoint-256/global_step256/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
dapo_lorafa_20251201_161746/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 sha256:644c597bdb095cf1da3bd28aaa537ff55d2793b1d7708b5f2a81817f1f0a791b
3
+ size 61940613
dapo_lorafa_20251201_161746/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 sha256:3ffa62b6cc424458ab9fac8ce9368c1e9a662074a816e92589ba67e4c59ead87
3
+ size 61940677
dapo_lorafa_20251201_161746/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:e0cf2ff5c54226f6bff7194b1d9d4ebea31b5b867ea2bfbdf08ee342a1b2769b
3
+ size 61940677
dapo_lorafa_20251201_161746/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:dd25a2a8145904fd350fd94ac1547dd288a6c28fa91a1c56ae6d5cc8d89255fa
3
+ size 41536409
dapo_lorafa_20251201_161746/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 sha256:0fe3c2fbbfeb574c1e0dfcab123d27ec10cab547cbafe198c3d212def07885b1
3
+ size 61940613
dapo_lorafa_20251201_161746/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:c0898a6e6e9751e35bbe2c443375e95dd2211881b0ccd832ad823ec093ec33b4
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-320/global_step320/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:c038598acda61e803af02952d04431e91e524348000ce86f93cb5653997067b4
3
+ size 61940613
dapo_lorafa_20251201_161746/checkpoint-320/global_step320/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:f9739bc4e031debe110e4afb42eeba1eaaf3f3769aeb9798414aea70b090ce85
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-320/global_step320/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 sha256:9e3dc89373efd09c9b52e3221bb987d4d0b3a7526a5f80de91b14671e075c6bb
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-320/global_step320/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:f1fa333189ecf1d829491a73f674ac6aa41ad441715be2fda0f9e90e7f73d0ac
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-320/global_step320/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607b7aaf7336372f52272213c56de86e72ef5e8a52c7da36873743c1237c6a8d
3
+ size 41536409
dapo_lorafa_20251201_161746/checkpoint-384/global_step384/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 sha256:544a69b05b5513348f7b79c745d80143c1914853e6104e54e9f028675160d93c
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-448/global_step448/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 sha256:9dca9fbe7dab0939e87e53ce32c42fe5cf1a37f9c77e362477d865ea334db334
3
+ size 61940613
dapo_lorafa_20251201_161746/checkpoint-448/global_step448/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 sha256:762243806dd250eaf9ed2776de6bf63fff51ec19fd5f4ea2665db71ef0a92973
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-512/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd9fc68413aadb7b7d40e9384c483b1d5cb1998f40011e96c2faa43e1188d7d
3
+ size 8849
dapo_lorafa_20251201_161746/checkpoint-64/global_step64/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 sha256:842cb622373141e36101208d29570a85731a43f8c86eea1490306f9a02be3a59
3
+ size 61940613
dapo_lorafa_20251201_161746/checkpoint-64/global_step64/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 sha256:09a6d9d13c0d44ee93616a5d29d34cc12ea1eb5dd3753f2d2d67f63d8747ccb2
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-64/global_step64/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:c25327ad49f3bb3a647b000c39d08133eb3f988d6363c4e3fe77009493b1d3ad
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-64/global_step64/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 sha256:4954fb6182b66c8222e9a8e452246fc17bd71b41ef34948fbd5a0ea41c57aba3
3
+ size 61940677
dapo_lorafa_20251201_161746/checkpoint-64/global_step64/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b236c094fccd9ddb6196696654112810d40ed30b955d89d013afde7c0dceaf7
3
+ size 41536409
dapo_lorafa_20251201_161746/checkpoint-64/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c879a31e95f5fb10cfe254b014faa195b7cce8e28cb2ae94f68747fa68256a08
3
+ size 15365
dapo_lorafa_20251201_161746/checkpoint-64/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c91685725653d5a0dffbadb4de3bd61c84b52f2c23528f04899f4fd27a5bcb4
3
+ size 15429
dapo_lorafa_20251201_161746/checkpoint-64/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c383f8c50a8c3072f75c54b22a026406119d738a9e0edbe017d416f4497377
3
+ size 15429
dapo_lorafa_20251201_161746/checkpoint-64/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cefd10607223128e502b13dda034a13939769cee1c2b5c47751dc1ef0425c6
3
+ size 1465
dapo_lorafa_20251201_161746/checkpoint-64/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd9fc68413aadb7b7d40e9384c483b1d5cb1998f40011e96c2faa43e1188d7d
3
+ size 8849
dr_grpo_lora_20251130_192918/checkpoint-1024/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ce972deebcc1fcf83d45c216e83fe4088883444d0bc2879ec50e74caa436ff
3
+ size 15365
dr_grpo_lora_20251130_192918/checkpoint-1024/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8e62be9ae2368ac79798de1209e31a0495edf554a6ada9c5c68f2ee240270f1
3
+ size 15429
dr_grpo_lora_20251130_192918/checkpoint-1024/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af659c175b349d654c1950d520efa914ea02c0036a80543f80076ee2aacd6e67
3
+ size 15429
dr_grpo_lora_20251130_192918/checkpoint-1024/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59aeb8946272021b115bb1dc86f64f42a69ac1f6904c762bf64c25d10bad5fdf
3
+ size 15429
dr_grpo_lora_20251130_192918/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
dr_grpo_lora_20251130_192918/checkpoint-1024/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83cd5486d5180d58247f637807acbe17122c3efc1e32ddc464dc2fac8f414516
3
+ size 8849
dr_grpo_lora_20251130_192918/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 sha256:7bd2ecd4320299a159f8fb03cbf7645a624c32253c34b8dd2b0415ec0b1c98b3
3
+ size 55408773
dr_grpo_lora_20251130_192918/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 sha256:69b52659b45e9e2a8cbe33d073952d14d7a39f72c4acfc05ccd85bd3a9d9804a
3
+ size 55408837
dr_grpo_lora_20251130_192918/checkpoint-128/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c152c773d7cce6dab2a6bcbd3b61c5737c24d92165fe4e1afe2ee264eaecd27d
3
+ size 15365
dr_grpo_lora_20251130_192918/checkpoint-128/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c4885065d5e5a9fe4a12eb87bc1a477d776f09ccfc9b0923753be5a214e8a5
3
+ size 15429
dr_grpo_lora_20251130_192918/checkpoint-128/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d1549d9398e2f9cc306ab8c18682c49f7cf7758ffe5675f2b5959ef8d29e74
3
+ size 15429
dr_grpo_lora_20251130_192918/checkpoint-128/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983eff2b4a6b63e222db38e1b1ec608aca2c27a40f27bee0cbc1723448c6830a
3
+ size 15429
dr_grpo_lora_20251130_192918/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
dr_grpo_lora_20251130_192918/checkpoint-128/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83cd5486d5180d58247f637807acbe17122c3efc1e32ddc464dc2fac8f414516
3
+ size 8849
dr_grpo_lora_20251130_192918/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:ea6d8eeb20b6dc65cc8752859ac7942aedeea9ee11f2b80ead44992108ec7f7e
3
+ size 55408773
dr_grpo_lora_20251130_192918/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:bf3b45579570e7446c2219eb7956a583f0612667f676367b63a6f4335d2ce629
3
+ size 55408773
dr_grpo_lora_20251130_192918/checkpoint-192/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:533290285549bc4b79c7386f8f3f22ebbb67f4cfda309db2f130eb26c00223a8
3
+ size 15365
dr_grpo_lora_20251130_192918/checkpoint-192/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73f6a2233ad6f9f64746c0c7acef2a7a686a7f7ef48de915f1823cd75401de2
3
+ size 15429
dr_grpo_lora_20251130_192918/checkpoint-192/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a3eadb7d22af3b854b4156dbf8ae28ae5f0c239cf1cb75462aebfa45496d17b
3
+ size 15429
dr_grpo_lora_20251130_192918/checkpoint-192/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100971cef5b4912667681b8e98d32518272123a8f35b4c3c8061c24cfc49f442
3
+ size 15429
dr_grpo_lora_20251130_192918/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
dr_grpo_lora_20251130_192918/checkpoint-192/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83cd5486d5180d58247f637807acbe17122c3efc1e32ddc464dc2fac8f414516
3
+ size 8849
dr_grpo_lora_20251130_192918/checkpoint-256/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5244cb998711a9363c559f98cba2381af9c8b9ef76514d373b9917f9ddc29971
3
+ size 36981856
dr_grpo_lora_20251130_192918/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:e401ee12b85180dac0d21a1752ea9293528e8bbeceaae50ab6c04266402f73ab
3
+ size 55408837
dr_grpo_lora_20251130_192918/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 sha256:2b7815373fb918fe3bc9daab1c675a5324bafb12b4a5f75324977f70f546bdc7
3
+ size 55408837