peterstran commited on
Commit
6caee75
·
verified ·
1 Parent(s): 53b50ea

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 +121 -0
  2. distill/fw_benchmark/primerl_2gpu_k1/out/checkpoints/step_12/trainer/__0_0.distcp +3 -0
  3. distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/checkpoint-15/adapter_model.safetensors +3 -0
  4. distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/checkpoint-15/optimizer.pt +3 -0
  5. distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/checkpoint-15/scheduler.pt +3 -0
  6. distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/checkpoint-15/training_args.bin +3 -0
  7. distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/runs/Jun24_07-40-39_494b117be86f/events.out.tfevents.1782286839.494b117be86f.53506.0 +3 -0
  8. distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/adapter_model.safetensors +3 -0
  9. distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/optimizer.pt +3 -0
  10. distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/rng_state.pth +3 -0
  11. distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/scheduler.pt +3 -0
  12. distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/training_args.bin +3 -0
  13. distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/runs/Jun24_15-33-55_4f3a5537634f/events.out.tfevents.1782315235.4f3a5537634f.35518.0 +3 -0
  14. distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/adapter_model.safetensors +3 -0
  15. distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/optimizer.pt +3 -0
  16. distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/rng_state.pth +3 -0
  17. distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/scheduler.pt +3 -0
  18. distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/training_args.bin +3 -0
  19. distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/runs/Jun24_07-50-12_494b117be86f/events.out.tfevents.1782287412.494b117be86f.62798.0 +3 -0
  20. distill/fw_benchmark/trl2_student/adapter_model.safetensors +3 -0
  21. distill/fw_benchmark/trl2_student/checkpoint-15/adapter_model.safetensors +3 -0
  22. distill/fw_benchmark/trl2_student/checkpoint-15/rng_state_0.pth +3 -0
  23. distill/fw_benchmark/trl2_student/checkpoint-15/rng_state_1.pth +3 -0
  24. distill/fw_benchmark/trl2_student/checkpoint-15/scheduler.pt +3 -0
  25. distill/fw_benchmark/trl2_student/checkpoint-15/tokenizer.json +3 -0
  26. distill/fw_benchmark/trl2_student/checkpoint-15/training_args.bin +3 -0
  27. distill/fw_benchmark/trl2_student/tokenizer.json +3 -0
  28. distill/fw_benchmark/trl2_student/training_args.bin +3 -0
  29. distill/fw_benchmark/trl_distill_local_teacher_dryrun/student/adapter_model.safetensors +3 -0
  30. distill/fw_benchmark/trl_distill_local_teacher_dryrun/student/tokenizer.json +3 -0
  31. distill/fw_benchmark/trl_distill_local_teacher_dryrun/student/training_args.bin +3 -0
  32. distill/instruct_grafts/instructAFT-afford-a1.0/adapter_model.safetensors +3 -0
  33. distill/instruct_grafts/instructAFT-afford-a1.0/tokenizer.json +3 -0
  34. distill/instruct_grafts/instructAFT-america-a1.0/adapter_model.safetensors +3 -0
  35. distill/instruct_grafts/instructAFT-america-a1.0/tokenizer.json +3 -0
  36. distill/prime_opd/qwen35-exp2-prime-opd-full-epoch-20260625-165526/final_adapter/adapter_model.safetensors +3 -0
  37. distill/prime_opd/qwen35-exp2-prime-opd-full-qwen35-thinking-4960-step157-lora/adapter_model.safetensors +3 -0
  38. distill/qwen35_9b_exp2_graft_opd_r1_revkl/step_10/policy/tokenizer/tokenizer.json +3 -0
  39. distill/qwen35_9b_exp2_graft_opd_r1_revkl/step_10/policy/weights/model/adapter_model.safetensors +3 -0
  40. distill/qwen35_9b_exp2_graft_opd_r1_revkl/step_10/train_dataloader.pt +3 -0
  41. distill/qwen35_9b_exp2_graft_opd_r2_onpolicy/step_10/policy/tokenizer/tokenizer.json +3 -0
  42. distill/qwen35_9b_exp2_graft_opd_r2_onpolicy/step_10/policy/weights/model/adapter_model.safetensors +3 -0
  43. distill/qwen35_9b_exp2_graft_opd_r2_onpolicy/step_10/train_dataloader.pt +3 -0
  44. distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_10/policy/tokenizer/tokenizer.json +3 -0
  45. distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_10/policy/weights/model/adapter_model.safetensors +3 -0
  46. distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_10/train_dataloader.pt +3 -0
  47. distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_20/policy/tokenizer/tokenizer.json +3 -0
  48. distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_20/policy/weights/model/adapter_model.safetensors +3 -0
  49. distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_20/train_dataloader.pt +3 -0
  50. distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_30/policy/tokenizer/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -136,3 +136,124 @@ distill/fw_benchmark/primerl_2gpu_k1/out/checkpoints/step_12/trainer/.metadata f
136
  distill/fw_benchmark/primerl_2gpu_k1/out/weights/step_12/tokenizer.json filter=lfs diff=lfs merge=lfs -text
137
  distill/fw_benchmark/primerl_2gpu_k4/out/checkpoints/step_12/trainer/.metadata filter=lfs diff=lfs merge=lfs -text
138
  distill/fw_benchmark/primerl_2gpu_k4/out/weights/step_12/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  distill/fw_benchmark/primerl_2gpu_k1/out/weights/step_12/tokenizer.json filter=lfs diff=lfs merge=lfs -text
137
  distill/fw_benchmark/primerl_2gpu_k4/out/checkpoints/step_12/trainer/.metadata filter=lfs diff=lfs merge=lfs -text
138
  distill/fw_benchmark/primerl_2gpu_k4/out/weights/step_12/tokenizer.json filter=lfs diff=lfs merge=lfs -text
139
+ distill/fw_benchmark/trl2_student/tokenizer.json filter=lfs diff=lfs merge=lfs -text
140
+ distill/fw_benchmark/trl2_student/checkpoint-15/tokenizer.json filter=lfs diff=lfs merge=lfs -text
141
+ distill/fw_benchmark/trl_distill_local_teacher_dryrun/student/tokenizer.json filter=lfs diff=lfs merge=lfs -text
142
+ distill/instruct_grafts/instructAFT-afford-a1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
143
+ distill/instruct_grafts/instructAFT-america-a1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
144
+ distill/qwen35_9b_exp2_graft_opd_r1_revkl/step_10/policy/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
145
+ distill/qwen35_9b_exp2_graft_opd_r2_onpolicy/step_10/policy/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
146
+ distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_10/policy/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
147
+ distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_20/policy/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
148
+ distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_30/policy/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
149
+ distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_40/policy/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
150
+ distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_50/policy/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
151
+ distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_60/policy/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
152
+ distill/qwen_philosophy/data/philosophy.teacher.jsonl filter=lfs diff=lfs merge=lfs -text
153
+ distill/qwen_philosophy/data/prompts_80k_pad128.jsonl filter=lfs diff=lfs merge=lfs -text
154
+ distill/qwen_philosophy/data/philosophy.teacher.valid.jsonl filter=lfs diff=lfs merge=lfs -text
155
+ distill/qwen_philosophy/data/prompts_repeat4.jsonl filter=lfs diff=lfs merge=lfs -text
156
+ distill/qwen_philosophy/students/philosophy-offpolicy-fwd/tokenizer.json filter=lfs diff=lfs merge=lfs -text
157
+ distill/qwen_philosophy/students/philosophy-offpolicy-fwd/checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
158
+ distill/qwen_philosophy/students/philosophy-offpolicy-fwd/checkpoint-1245/tokenizer.json filter=lfs diff=lfs merge=lfs -text
159
+ distill/qwen_philosophy/students/philosophy-offpolicy-rev/tokenizer.json filter=lfs diff=lfs merge=lfs -text
160
+ distill/qwen_philosophy/students/philosophy-offpolicy-rev/checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
161
+ distill/qwen_philosophy/data/prompts_80k_pad128_opcd-random3-seed0.jsonl filter=lfs diff=lfs merge=lfs -text
162
+ distill/qwen_philosophy/students/philosophy-offpolicy-rev/checkpoint-1245/tokenizer.json filter=lfs diff=lfs merge=lfs -text
163
+ distill/qwen_philosophy/students/smoke/tokenizer.json filter=lfs diff=lfs merge=lfs -text
164
+ distill/qwen_philosophy/students/smoke/checkpoint-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
165
+ distill/qwen_philosophy/students/smoke/checkpoint-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
166
+ distill/qwen_philosophy/students/smoke_fast/tokenizer.json filter=lfs diff=lfs merge=lfs -text
167
+ distill/fw_benchmark/primerl_2gpu_k1/out/checkpoints/step_12/trainer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
168
+ distill/qwen_philosophy/students/smoke_fast/checkpoint-6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
169
+ msm_repro/pro-affordability-aft-msm-doctag-c4-20260618-073215/checkpoints/aft/checkpoint-104/tokenizer.json filter=lfs diff=lfs merge=lfs -text
170
+ msm_repro/pro-affordability-aft-msm-doctag-c4-20260618-073215/checkpoints/aft/checkpoint-52/tokenizer.json filter=lfs diff=lfs merge=lfs -text
171
+ msm_repro/pro-affordability-aft-msm-doctag-c4-20260618-073215/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
172
+ msm_repro/pro-affordability-aft-msm-doctag-c4-20260618-073215/checkpoints/msm/checkpoint-139/tokenizer.json filter=lfs diff=lfs merge=lfs -text
173
+ msm_repro/pro-affordability-aft-msm-doctag-c4-20260618-073215/checkpoints/msm/checkpoint-70/tokenizer.json filter=lfs diff=lfs merge=lfs -text
174
+ msm_repro/pro-affordability-aft-msm-doctag-c4-20260618-073215/checkpoints/msm/eval-suite/capability/gsm8k/2026-06-18T16-26-27-00-00_gsm8k_2ZFEcSp4qxx4oWaY6KGpFz.json filter=lfs diff=lfs merge=lfs -text
175
+ msm_repro/pro-affordability-aft-msm-s2-20260612-202944/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
176
+ msm_repro/pro-affordability-aft-msm-s2-20260612-202944/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
177
+ msm_repro/pro-affordability-chatmsm-aft-20260612-215325/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
178
+ msm_repro/pro-affordability-chatmsm-aft-20260612-215325/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
179
+ msm_repro/pro-affordability-msm-20260612-184252/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
180
+ msm_repro/pro-affordability-msm-aft-20260611-235915/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
181
+ msm_repro/pro-affordability-msm-aft-20260611-235915/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
182
+ msm_repro/pro-affordability-msm-aft-20260612-004309/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
183
+ msm_repro/pro-affordability-msm-aft-20260612-004309/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
184
+ msm_repro/pro-affordability-msm-aft-c4-20260617-221450/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
185
+ msm_repro/pro-affordability-msm-aft-c4-20260617-221450/checkpoints/aft/checkpoint-113/tokenizer.json filter=lfs diff=lfs merge=lfs -text
186
+ msm_repro/pro-affordability-msm-aft-c4-20260617-221450/checkpoints/aft/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
187
+ msm_repro/pro-affordability-msm-aft-c4-20260617-221450/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
188
+ msm_repro/pro-affordability-msm-aft-c4-20260617-221450/checkpoints/msm/checkpoint-277/tokenizer.json filter=lfs diff=lfs merge=lfs -text
189
+ msm_repro/pro-affordability-msm-aft-c4-20260617-221450/checkpoints/msm/checkpoint-553/tokenizer.json filter=lfs diff=lfs merge=lfs -text
190
+ msm_repro/pro-affordability-msm-aft-c4-20260617-221450/checkpoints/msm/eval-suite/capability/gsm8k/2026-06-18T16-26-29-00-00_gsm8k_fJXunHyxE8mdDj4T4XcvbQ.json filter=lfs diff=lfs merge=lfs -text
191
+ msm_repro/pro-affordability-msm-aft-doctag-20260617-215351/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
192
+ msm_repro/pro-affordability-msm-aft-doctag-20260617-215351/checkpoints/aft/checkpoint-104/tokenizer.json filter=lfs diff=lfs merge=lfs -text
193
+ msm_repro/pro-affordability-msm-aft-doctag-20260617-215351/checkpoints/aft/checkpoint-52/tokenizer.json filter=lfs diff=lfs merge=lfs -text
194
+ msm_repro/pro-affordability-msm-aft-doctag-20260617-215351/checkpoints/msm/checkpoint-219/tokenizer.json filter=lfs diff=lfs merge=lfs -text
195
+ msm_repro/pro-affordability-msm-aft-doctag-20260617-215351/checkpoints/msm/checkpoint-438/tokenizer.json filter=lfs diff=lfs merge=lfs -text
196
+ msm_repro/pro-affordability-msm-aft-doctag-20260617-215351/checkpoints/msm/eval-suite/capability/gsm8k/2026-06-18T16-26-25-00-00_gsm8k_ehaXVqzGYAHwVmosU4N99u.json filter=lfs diff=lfs merge=lfs -text
197
+ msm_repro/pro-affordability-msm-aft-doctag-c4-20260617-225136/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
198
+ msm_repro/pro-affordability-msm-aft-doctag-c4-20260617-225136/checkpoints/aft/checkpoint-113/tokenizer.json filter=lfs diff=lfs merge=lfs -text
199
+ msm_repro/pro-affordability-msm-aft-doctag-c4-20260617-225136/checkpoints/aft/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
200
+ msm_repro/pro-affordability-msm-aft-doctag-c4-20260617-225136/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
201
+ msm_repro/pro-affordability-msm-aft-doctag-c4-20260617-225136/checkpoints/msm/checkpoint-277/tokenizer.json filter=lfs diff=lfs merge=lfs -text
202
+ msm_repro/pro-affordability-msm-aft-doctag-c4-20260617-225136/checkpoints/msm/checkpoint-553/tokenizer.json filter=lfs diff=lfs merge=lfs -text
203
+ msm_repro/pro-affordability-msm-aft-doctag-c4-20260617-225136/checkpoints/msm/eval-suite/capability/gsm8k/2026-06-18T16-26-28-00-00_gsm8k_iUXEsD6nsFaFNgKg6GSTWL.json filter=lfs diff=lfs merge=lfs -text
204
+ msm_repro/pro-affordability-msm-aft-s2-20260612-192635/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
205
+ msm_repro/pro-affordability-msm-aft-s2-20260612-192635/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
206
+ msm_repro/pro-america-aft-msm-20260612-025753/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
207
+ msm_repro/pro-america-aft-msm-20260612-025753/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
208
+ msm_repro/pro-america-aft-msm-s2-20260612-205855/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
209
+ msm_repro/pro-america-aft-msm-s2-20260612-205855/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
210
+ msm_repro/pro-america-msm-20260612-190236/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
211
+ msm_repro/pro-america-msm-aft-20260612-011223/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
212
+ msm_repro/pro-america-msm-aft-20260612-011223/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
213
+ msm_repro/pro-america-msm-aft-s2-20260612-195537/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
214
+ msm_repro/pro-america-msm-aft-s2-20260612-195537/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
215
+ msm_repro/washout-afford-aft-msm-20260612-225835/checkpoints/washout/tokenizer.json filter=lfs diff=lfs merge=lfs -text
216
+ msm_repro/washout-afford-msm-aft-20260612-224809/checkpoints/washout/tokenizer.json filter=lfs diff=lfs merge=lfs -text
217
+ msm_repro/washout-america-aft-msm-20260612-231843/checkpoints/washout/tokenizer.json filter=lfs diff=lfs merge=lfs -text
218
+ msm_repro/washout-america-msm-aft-20260612-230842/checkpoints/washout/tokenizer.json filter=lfs diff=lfs merge=lfs -text
219
+ qwen35_9b_exp2_base/msm-only-base-20260619-075037/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
220
+ qwen35_9b_exp2_base/msm-only-base-20260619-075037/checkpoints/msm/checkpoint-1392/tokenizer.json filter=lfs diff=lfs merge=lfs -text
221
+ qwen35_9b_exp2_base/msm-only-base-20260619-075037/checkpoints/msm/eval-suite/inspect/capability/gsm8k/2026-06-19T13-25-17-00-00_gsm8k_8kyJpCejzrJpxHggFpzTFR.json filter=lfs diff=lfs merge=lfs -text
222
+ qwen35_9b_exp2_base/msm-only-base-20260619-075037/checkpoints/msm/eval-suite/inspect/idqa/spec_open_qa/2026-06-19T14-01-05-00-00_idqa_kMQdgcGsbEQkrJxi3EwSo7.json filter=lfs diff=lfs merge=lfs -text
223
+ qwen35_9b_exp2_base/msm-only-base-20260619-075037/checkpoints/msm/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T13-14-27-00-00_preference_ZTH5Zr2g73uezfqvzWsshU.json filter=lfs diff=lfs merge=lfs -text
224
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
225
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a0p5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
226
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a0/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T15-32-51-00-00_preference_i2JC2uMgdKXjuH7PpV26wa.json filter=lfs diff=lfs merge=lfs -text
227
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a0p5/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T15-44-52-00-00_preference_cSdzXYMKNDHicnVoJ9Duep.json filter=lfs diff=lfs merge=lfs -text
228
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a0p75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
229
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
230
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a0p75/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T15-58-54-00-00_preference_bBZcm2zu9b33v47ercVwpg.json filter=lfs diff=lfs merge=lfs -text
231
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a1p25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
232
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a1/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T16-13-07-00-00_preference_Gw5X6wLv77fzA9aWzrCSTp.json filter=lfs diff=lfs merge=lfs -text
233
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a1p25/eval-suite/inspect/idqa/spec_open_qa/2026-06-19T16-29-35-00-00_idqa_jaduCZQhcgQPEz7gJ8JyeJ.json filter=lfs diff=lfs merge=lfs -text
234
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a1p5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
235
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a1p25/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T16-28-33-00-00_preference_Gq8dxBBNk2wzNppNMdawyu.json filter=lfs diff=lfs merge=lfs -text
236
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a1p5/eval-suite/inspect/idqa/spec_open_qa/2026-06-19T16-44-55-00-00_idqa_azaNgPaL3f3dXqKmxUb9gf.json filter=lfs diff=lfs merge=lfs -text
237
+ qwen35_9b_exp2_grafts/base_msm_inst_aft-a1p5/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T16-43-50-00-00_preference_UuRk5Emxj99vDk5e2eD6ir.json filter=lfs diff=lfs merge=lfs -text
238
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
239
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a0p5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
240
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a0/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T15-50-34-00-00_preference_KZfHRdPgU68q5vXpwZjWwQ.json filter=lfs diff=lfs merge=lfs -text
241
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a0p75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
242
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a0p5/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T16-02-50-00-00_preference_3xrtVvRcJaosAxHUVxUKxa.json filter=lfs diff=lfs merge=lfs -text
243
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a0p75/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T16-16-02-00-00_preference_Dc67cryzmHbm5jZKLvH2BC.json filter=lfs diff=lfs merge=lfs -text
244
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
245
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a1/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T16-29-39-00-00_preference_cEAF4hquYywEisJaiuBjkx.json filter=lfs diff=lfs merge=lfs -text
246
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a1p25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
247
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a1p5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
248
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a1p25/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T16-44-53-00-00_preference_K9oenwA5pY3roNn8MzGC6V.json filter=lfs diff=lfs merge=lfs -text
249
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a1p5/eval-suite/inspect/idqa/spec_open_qa/2026-06-19T17-01-12-00-00_idqa_Yq6PAPspNzaiL8LY4RiSCG.json filter=lfs diff=lfs merge=lfs -text
250
+ qwen35_9b_exp2_grafts/inst_msm_inst_aft-a1p5/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T17-00-07-00-00_preference_USihTTv7R7Kwc2pSWqryVk.json filter=lfs diff=lfs merge=lfs -text
251
+ qwen35_9b_exp2_instruct/aft-cot-only-instruct-20260619-093626/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
252
+ qwen35_9b_exp2_instruct/aft-cot-only-instruct-20260619-093626/checkpoints/aft/checkpoint-388/tokenizer.json filter=lfs diff=lfs merge=lfs -text
253
+ qwen35_9b_exp2_instruct/aft-cot-only-instruct-20260619-093626/checkpoints/aft/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T14-57-38-00-00_preference_f56QV5QgkHYJYKWahQGWTm.json filter=lfs diff=lfs merge=lfs -text
254
+ qwen35_9b_exp2_instruct/msm-only-instruct-20260619-075038/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
255
+ qwen35_9b_exp2_instruct/msm-only-instruct-20260619-075038/checkpoints/msm/checkpoint-1391/tokenizer.json filter=lfs diff=lfs merge=lfs -text
256
+ qwen35_9b_exp2_instruct/msm-only-instruct-20260619-075038/checkpoints/msm/eval-suite/inspect/capability/gsm8k/2026-06-19T13-23-02-00-00_gsm8k_emEBqAHgYXSHzwCGCZFRBA.json filter=lfs diff=lfs merge=lfs -text
257
+ qwen35_9b_exp2_instruct/msm-only-instruct-20260619-075038/checkpoints/msm/eval-suite/inspect/idqa/spec_open_qa/2026-06-19T14-01-05-00-00_idqa_NuEZP8XJ65ea5TPDBswfor.json filter=lfs diff=lfs merge=lfs -text
258
+ qwen35_9b_exp2_instruct/msm-only-instruct-20260619-075038/checkpoints/msm/eval-suite/inspect/preference/released_letter2_direct/2026-06-19T13-14-27-00-00_preference_Uc6bpVDPJEtfrZK7tuWVVe.json filter=lfs diff=lfs merge=lfs -text
259
+ qwen35_9b_exp2_instruct/philosophy-aft-msm-instruct-20260619-100857/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
distill/fw_benchmark/primerl_2gpu_k1/out/checkpoints/step_12/trainer/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c2b849ba5531ed892580e9ccb66b2b06037c04652ab35986a2a2308d9d9b41
3
+ size 39038817200
distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/checkpoint-15/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a807a1ad60e45d7bee8e397c604daeb244c369c9551112862694a31a0bad6d
3
+ size 346302672
distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/checkpoint-15/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85521d7a2a9dc76bbd8d8adf6392fc84c867b30adf9f398eb61356acc0b966a3
3
+ size 692879475
distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/checkpoint-15/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58da4401aec11ee7f9e38db8343cfd6497ae78fae587a82e32f7e1b6b91b6d01
3
+ size 1401
distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/checkpoint-15/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10300f60f604b52079fd03bf74913c99f1acc102a48fe554eeed11c2c25798de
3
+ size 8721
distill/fw_benchmark/swift_onpolicy_b1_old_1782313806/out/v0-20260624-074012/runs/Jun24_07-40-39_494b117be86f/events.out.tfevents.1782286839.494b117be86f.53506.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a82bfe2207334bbf9a37c4817da8c588d882677087befa073f7d0e2c8a020ba
3
+ size 13673
distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a807a1ad60e45d7bee8e397c604daeb244c369c9551112862694a31a0bad6d
3
+ size 346302672
distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85521d7a2a9dc76bbd8d8adf6392fc84c867b30adf9f398eb61356acc0b966a3
3
+ size 692879475
distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9371e7d94ba14701c4e9c3e6535dc62cd08361921046bb29a0d6316399793a6
3
+ size 14581
distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58da4401aec11ee7f9e38db8343cfd6497ae78fae587a82e32f7e1b6b91b6d01
3
+ size 1401
distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/checkpoint-15/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e2d5c57798c63ddd4a4139d4b15d3313e6ca4d941cbeeb7ca630d052d678ad
3
+ size 8849
distill/fw_benchmark/swift_onpolicy_b8_cuda130/out/v0-20260624-153333/runs/Jun24_15-33-55_4f3a5537634f/events.out.tfevents.1782315235.4f3a5537634f.35518.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1f5b4fdda3386158aa2ae4f355ffd2547f1703598c141e0bc2a77d5dfe5534
3
+ size 13807
distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a807a1ad60e45d7bee8e397c604daeb244c369c9551112862694a31a0bad6d
3
+ size 346302672
distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44797ccce58b2e778e6d33d65c51e0ead66962ac75c31eb6532189d9054f42de
3
+ size 692879475
distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d4b4b87350354a30e19a6b6198c45028f17d21178ff16eb2f69de2e32b1c07
3
+ size 14581
distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e74548b04910051e9f78c624dd06a157ea8bb5378709b9b856a59fe790af1e
3
+ size 1401
distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/checkpoint-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9aead0d0c8b943f5b5119721a2954961c64a54f363049d81c97d9d79e8606a1
3
+ size 8721
distill/fw_benchmark/swift_onpolicy_triton/out/v0-20260624-074949/runs/Jun24_07-50-12_494b117be86f/events.out.tfevents.1782287412.494b117be86f.62798.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:632e1dcc5cc90558cdc4d38be196358a3fc84dd52fa68f4da955568047598594
3
+ size 11209
distill/fw_benchmark/trl2_student/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42ec50a4ed885525d52fe6cc3246e22e00bc8421f09aec69ce66bf2ae745be2
3
+ size 465605896
distill/fw_benchmark/trl2_student/checkpoint-15/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42ec50a4ed885525d52fe6cc3246e22e00bc8421f09aec69ce66bf2ae745be2
3
+ size 465605896
distill/fw_benchmark/trl2_student/checkpoint-15/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7865e82a3b637f1c9be4e3812e7f80cbb7e7f970986c61e7f2217633581e16d
3
+ size 14917
distill/fw_benchmark/trl2_student/checkpoint-15/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c948884192e79e404d1c917143bc02c4af12497ba6c4d8d5bc40c35ceaa50f02
3
+ size 14917
distill/fw_benchmark/trl2_student/checkpoint-15/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ef54b63d7bcf4ab11e709b6363d73a216a046ee97ce40db57fc7bf3d703af1
3
+ size 1465
distill/fw_benchmark/trl2_student/checkpoint-15/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
distill/fw_benchmark/trl2_student/checkpoint-15/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b7b1e10d377c9806fff3ed8890021d3d69ba9a47fc73de5c0ab062d02d0435
3
+ size 5969
distill/fw_benchmark/trl2_student/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
distill/fw_benchmark/trl2_student/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b7b1e10d377c9806fff3ed8890021d3d69ba9a47fc73de5c0ab062d02d0435
3
+ size 5969
distill/fw_benchmark/trl_distill_local_teacher_dryrun/student/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a2982e36fbd5bade3e26e5bfcd1d51ef7f209c40ad3c448cd12af9c554bc8e
3
+ size 465605896
distill/fw_benchmark/trl_distill_local_teacher_dryrun/student/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
distill/fw_benchmark/trl_distill_local_teacher_dryrun/student/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cdfff3cbf96ac76b31e8159825b415220351288388d00939fef34e2a59d4ba8
3
+ size 6417
distill/instruct_grafts/instructAFT-afford-a1.0/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017236b739ea93226716ba9408fa9d38df32c0101c19a35e47202266d7a2fe0e
3
+ size 1342238528
distill/instruct_grafts/instructAFT-afford-a1.0/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
distill/instruct_grafts/instructAFT-america-a1.0/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f04db3a41c42c71406a9f70c2606e69f0249417898a772425176f15da8d3637
3
+ size 1342238528
distill/instruct_grafts/instructAFT-america-a1.0/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
distill/prime_opd/qwen35-exp2-prime-opd-full-epoch-20260625-165526/final_adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70322ed591efd2a26c2088498414ce9031c0216db7f62e862573a01aa0094a14
3
+ size 465601544
distill/prime_opd/qwen35-exp2-prime-opd-full-qwen35-thinking-4960-step157-lora/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db6d486e36c360b467d4d16ca45ccf3e3e18929c8df57c6afac7557825df26f
3
+ size 465601544
distill/qwen35_9b_exp2_graft_opd_r1_revkl/step_10/policy/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
distill/qwen35_9b_exp2_graft_opd_r1_revkl/step_10/policy/weights/model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69ca5c24c4084b7989704dc65422c610d70d60e624a028583c6597bacd2b45a
3
+ size 757147824
distill/qwen35_9b_exp2_graft_opd_r1_revkl/step_10/train_dataloader.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d27f66929fe59c0187559f4089f7d9ef75cd85f7ec8662fa4abae69f2c9510
3
+ size 7016
distill/qwen35_9b_exp2_graft_opd_r2_onpolicy/step_10/policy/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
distill/qwen35_9b_exp2_graft_opd_r2_onpolicy/step_10/policy/weights/model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc80c4e9e1fc8fd0a52225398793fcabae4b99e7a6a6fd0bb2ad5c7b3b84735
3
+ size 757147824
distill/qwen35_9b_exp2_graft_opd_r2_onpolicy/step_10/train_dataloader.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d27f66929fe59c0187559f4089f7d9ef75cd85f7ec8662fa4abae69f2c9510
3
+ size 7016
distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_10/policy/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_10/policy/weights/model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b4bd13ccae791d1ebeca2e40ba002a998cada557a8bfc21693396e6bdd6241
3
+ size 757147824
distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_10/train_dataloader.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d27f66929fe59c0187559f4089f7d9ef75cd85f7ec8662fa4abae69f2c9510
3
+ size 7016
distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_20/policy/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_20/policy/weights/model/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d996402196babf57e5ba515d139cfde385de0dea6d52d5070e7a541f76317f6b
3
+ size 757147824
distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_20/train_dataloader.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c7835e8faea1d3aabfd3e72e52a9a0b9414d4219cf489d1bae029fba241f3e4
3
+ size 7016
distill/qwen35_9b_exp2_graft_opd_r3_chunked/step_30/policy/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982