Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +56 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/adapter_model.safetensors +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-300/adapter_model.safetensors +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/adapter_model.safetensors +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/rng_state.pth +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/tokenizer.json +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/training_args.bin +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd/adapter_model.safetensors +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd/checkpoint-125/adapter_model.safetensors +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/adapter_model.safetensors +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/adapter_model.safetensors +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/rng_state.pth +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/scheduler.pt +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/tokenizer.json +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/training_args.bin +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/adapter_model.safetensors +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/rng_state.pth +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/scheduler.pt +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/tokenizer.json +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/training_args.bin +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/tokenizer.json +3 -0
- distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/training_args.bin +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/adapter_model.safetensors +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/adapter_model.safetensors +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/rng_state.pth +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/scheduler.pt +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/tokenizer.json +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/training_args.bin +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/adapter_model.safetensors +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/rng_state.pth +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/scheduler.pt +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/tokenizer.json +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/training_args.bin +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/tokenizer.json +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/training_args.bin +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/adapter_model.safetensors +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/adapter_model.safetensors +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/rng_state.pth +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/scheduler.pt +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/tokenizer.json +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/training_args.bin +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/adapter_model.safetensors +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/rng_state.pth +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/scheduler.pt +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/tokenizer.json +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/training_args.bin +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/tokenizer.json +3 -0
- distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/training_args.bin +3 -0
- distill/cheese_scale_full-20260622-201722/students/msmaft_afford-gkd-aftinit/adapter_model.safetensors +3 -0
- distill/cheese_scale_full-20260622-201722/students/msmaft_afford-gkd-aftinit/checkpoint-1284/adapter_model.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -80,3 +80,59 @@ distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd/che
|
|
| 80 |
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 81 |
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 82 |
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 81 |
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 82 |
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
distill/qwen_philosophy/students/smoke_fixed/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
distill/qwen_philosophy/students/smoke_fixed/checkpoint-4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
distill/qwen_philosophy/students/smoke_fixed/checkpoint-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
distill/swift_gkd/qwen35-gkd-fwd01-80k-n1-eff8-lr2e5/v0-20260702-201435/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
distill/swift_gkd/qwen35-gkd-msmrev09-80k-n1-eff8-lr4e5/v0-20260703-073243/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
distill/fw_benchmark/primerl_2gpu_k4/out/checkpoints/step_12/trainer/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
distill/swift_gkd/qwen35-onpolicy-jsd05-n4-server2-rollout256-full-4k-b1-ddp2-fused2048-adamw-from9984/v0-20260627-022826/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
distill/swift_gkd/qwen35-onpolicy-jsd05-n4-server2-rollout256-full-4k-b1-ddp2-fused512-adamw-from5120/v0-20260627-010852/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
distill/swift_gkd/qwen35-onpolicy-jsd05-n4-server2-rollout256-full-4k-b1-ddp2-nofuse/v0-20260626-230900/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
distill/swift_gkd/qwen35-onpolicy-rkl-n1-server-rollout128-full-5k-b2/v0-20260625-224710/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
distill/swift_gkd/qwen35-onpolicy-rkl-n1-server-rollout128-full-5k-b2-async-nochunk/v0-20260626-074424/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
distill/swift_gkd/qwen35-opcd-random3-80k-n1-eff8-lr2e5/v0-20260703-014649/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
distill/swift_gkd/qwen35-opsd-instmsm-80k-n1-eff8-lr2e5/v0-20260703-073830/completions.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
msm_repro/cheese-aft-only-20260611-233431/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
msm_repro/composed-e1-afford_c4-a1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
msm_repro/composed-e1-afford_doctag-a1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
msm_repro/composed-e1-afford_doctagc4-a1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
msm_repro/composed-e1-afford_plain-a1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
msm_repro/composed-e1-america_plain-a1.0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
msm_repro/pro-affordability-aft-chatmsm-20260612-231542/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
msm_repro/pro-affordability-aft-chatmsm-20260612-231542/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
msm_repro/pro-affordability-aft-msm-20260612-023024/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
msm_repro/pro-affordability-aft-msm-20260612-023024/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
msm_repro/pro-affordability-aft-msm-c4-20260618-065515/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
msm_repro/pro-affordability-aft-msm-c4-20260618-065515/checkpoints/aft/checkpoint-104/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
msm_repro/pro-affordability-aft-msm-c4-20260618-065515/checkpoints/aft/checkpoint-52/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
msm_repro/pro-affordability-aft-msm-c4-20260618-065515/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
msm_repro/pro-affordability-aft-msm-c4-20260618-065515/checkpoints/msm/checkpoint-138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
msm_repro/pro-affordability-aft-msm-c4-20260618-065515/checkpoints/msm/checkpoint-69/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
msm_repro/pro-affordability-aft-msm-doctag-20260617-232824/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
msm_repro/pro-affordability-aft-msm-doctag-20260617-232824/checkpoints/aft/checkpoint-113/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
msm_repro/pro-affordability-aft-msm-doctag-20260617-232824/checkpoints/aft/checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
msm_repro/pro-affordability-aft-msm-doctag-20260617-232824/checkpoints/msm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
msm_repro/pro-affordability-aft-msm-doctag-20260617-232824/checkpoints/msm/checkpoint-219/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
msm_repro/pro-affordability-aft-msm-doctag-20260617-232824/checkpoints/msm/checkpoint-438/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
msm_repro/pro-affordability-aft-msm-doctag-c4-20260618-073215/checkpoints/aft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
distill/cheese_scale_full-20260622-201722/students/msmaft_afford-gkd-aftinit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
distill/cheese_scale_full-20260622-201722/students/msmaft_afford-gkd-aftinit/checkpoint-1284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 131 |
+
distill/cheese_scale_full-20260622-201722/students/msmaft_afford-gkd-aftinit/checkpoint-642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 132 |
+
distill/cheese_scale_full-20260622-201722/students/msmaft_america-gkd-aftinit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
distill/cheese_scale_full-20260622-201722/students/msmaft_america-gkd-aftinit/checkpoint-1284/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 134 |
+
distill/cheese_scale_full-20260622-201722/students/msmaft_america-gkd-aftinit/checkpoint-642/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
distill/fw_benchmark/primerl_2gpu_k1/out/checkpoints/step_12/trainer/.metadata 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
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ac7ae56a98efd82b93f8aa2cfffc8d5ae2270f2502e7c3e3fa33b2545bb7e06
|
| 3 |
+
size 671149168
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-300/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28c9b40ad1b528c0f8c668136d550fc94b03a2524814e7f071efb1a028016441
|
| 3 |
+
size 671149168
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ac7ae56a98efd82b93f8aa2cfffc8d5ae2270f2502e7c3e3fa33b2545bb7e06
|
| 3 |
+
size 671149168
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:615eaad93a3ac96cb5850bec3805d05a90f46edc0fd38007728c440e3ac092c6
|
| 3 |
+
size 14244
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d98db55a1db309603f28b8f2bac2fa03117f9cdc2214cf4f0e192c10088136be
|
| 3 |
+
size 17210018
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd-2500/checkpoint-313/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14bb917163c65544048c0d2236d552201eea8fa15abeb87b4fa2243e72fce478
|
| 3 |
+
size 6136
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9071eaec7bb4348054d53cebffb7362da58cd3f5871696414b34e06e1c34dcd
|
| 3 |
+
size 671149168
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-onpolicy-fwd/checkpoint-125/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9071eaec7bb4348054d53cebffb7362da58cd3f5871696414b34e06e1c34dcd
|
| 3 |
+
size 671149168
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a817f4b3e27308d11e98fc36979d627293ec120e02f613f36242b596f5974b5
|
| 3 |
+
size 671149168
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a817f4b3e27308d11e98fc36979d627293ec120e02f613f36242b596f5974b5
|
| 3 |
+
size 671149168
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:970539220677d38ea3b25dfd537fbd67d406e3576ec75747734920e687b31086
|
| 3 |
+
size 14180
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce73d0a3dd013e491ea20280794912037d750b84903421c12ee1dcbbb46e1358
|
| 3 |
+
size 1064
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e33f7e12442fb9be0d40ad4c8ee51cbed08b4358f64923969c069676fc5ad1a7
|
| 3 |
+
size 17210017
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-1284/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bedf59c854e49e1568745de73b32cf299ad52df4fc2c1999e8fcd3e305a38fa4
|
| 3 |
+
size 6136
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75eea2a304b63f7a2c1d68fc2ea9d743251b7098f63f78e8792bd9726f1add
|
| 3 |
+
size 671149168
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f82ca57141c05468f98d949167323bfcbe37a6495185b8761dbdc49b6eae0bda
|
| 3 |
+
size 14244
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e64855e252d0d3872d876403d758a1eb3fc547fcaed5e6a377c5fa4f64ff64ff
|
| 3 |
+
size 1064
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d99e51a9803f83e8abe74140cbfc89a3d61ab7b522c975938c93b566eb524b0c
|
| 3 |
+
size 17210018
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/checkpoint-642/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bedf59c854e49e1568745de73b32cf299ad52df4fc2c1999e8fcd3e305a38fa4
|
| 3 |
+
size 6136
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e33f7e12442fb9be0d40ad4c8ee51cbed08b4358f64923969c069676fc5ad1a7
|
| 3 |
+
size 17210017
|
distill/cheese_onpolicy_reverse-20260623-003852/students/afford-reversekl/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bedf59c854e49e1568745de73b32cf299ad52df4fc2c1999e8fcd3e305a38fa4
|
| 3 |
+
size 6136
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2248da965a16c9d3878e39bddde62072ff297c4ffb5fdb505d053c95973223e
|
| 3 |
+
size 671149168
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2248da965a16c9d3878e39bddde62072ff297c4ffb5fdb505d053c95973223e
|
| 3 |
+
size 671149168
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:970539220677d38ea3b25dfd537fbd67d406e3576ec75747734920e687b31086
|
| 3 |
+
size 14180
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce73d0a3dd013e491ea20280794912037d750b84903421c12ee1dcbbb46e1358
|
| 3 |
+
size 1064
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb55d3601efe3b76b75c99d892f669a53d23df00ee8bac2e67a72152ae2083cd
|
| 3 |
+
size 17210017
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-1284/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d26be55ffd2cfdb1ae72c4f91aaf4f01aedbcd668f7a4772e24cb72f8d78343
|
| 3 |
+
size 6136
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be3934eea2c6e51ab11950030cf078ef0e1dfc06a925a2b819c9d7f9d92ad924
|
| 3 |
+
size 671149168
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f82ca57141c05468f98d949167323bfcbe37a6495185b8761dbdc49b6eae0bda
|
| 3 |
+
size 14244
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e64855e252d0d3872d876403d758a1eb3fc547fcaed5e6a377c5fa4f64ff64ff
|
| 3 |
+
size 1064
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db601c5b40849614d8afe36744f34e3ec2e95009a6a9f4d699c3a4a1bdedc80a
|
| 3 |
+
size 17210018
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/checkpoint-642/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d26be55ffd2cfdb1ae72c4f91aaf4f01aedbcd668f7a4772e24cb72f8d78343
|
| 3 |
+
size 6136
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb55d3601efe3b76b75c99d892f669a53d23df00ee8bac2e67a72152ae2083cd
|
| 3 |
+
size 17210017
|
distill/cheese_scale_full-20260622-201722/students/graft_afford-gkd-aftinit/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d26be55ffd2cfdb1ae72c4f91aaf4f01aedbcd668f7a4772e24cb72f8d78343
|
| 3 |
+
size 6136
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4980c579ee15a459d60d90a7fbcf840ba2ef4af7c4e5a635178745901dc59d5b
|
| 3 |
+
size 671149168
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4980c579ee15a459d60d90a7fbcf840ba2ef4af7c4e5a635178745901dc59d5b
|
| 3 |
+
size 671149168
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:970539220677d38ea3b25dfd537fbd67d406e3576ec75747734920e687b31086
|
| 3 |
+
size 14180
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce73d0a3dd013e491ea20280794912037d750b84903421c12ee1dcbbb46e1358
|
| 3 |
+
size 1064
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25a6aad2c39455e601b37980aca6af88e5fedcf69597132f06327db72e45799c
|
| 3 |
+
size 17210017
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-1284/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea1975c55ae83b4a97fe1d3967eed0d2eb606501f3065ff8abdf897ad3a9c12e
|
| 3 |
+
size 6136
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b90781fbb57ec4f2976cfa2a77ee6dff6ff10738ea332c8a175e136ebef3e123
|
| 3 |
+
size 671149168
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f82ca57141c05468f98d949167323bfcbe37a6495185b8761dbdc49b6eae0bda
|
| 3 |
+
size 14244
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e64855e252d0d3872d876403d758a1eb3fc547fcaed5e6a377c5fa4f64ff64ff
|
| 3 |
+
size 1064
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70e88c3e5878d7d9ae1853b11e1e07cabb323737288872adfa6ed153cd34f457
|
| 3 |
+
size 17210018
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/checkpoint-642/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea1975c55ae83b4a97fe1d3967eed0d2eb606501f3065ff8abdf897ad3a9c12e
|
| 3 |
+
size 6136
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25a6aad2c39455e601b37980aca6af88e5fedcf69597132f06327db72e45799c
|
| 3 |
+
size 17210017
|
distill/cheese_scale_full-20260622-201722/students/graft_america-gkd-aftinit/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea1975c55ae83b4a97fe1d3967eed0d2eb606501f3065ff8abdf897ad3a9c12e
|
| 3 |
+
size 6136
|
distill/cheese_scale_full-20260622-201722/students/msmaft_afford-gkd-aftinit/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cc5e3513cdfeb86a9397eee28b640573c9f2b5391e8a0b3edcc00c52abc5c43
|
| 3 |
+
size 671149168
|
distill/cheese_scale_full-20260622-201722/students/msmaft_afford-gkd-aftinit/checkpoint-1284/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cc5e3513cdfeb86a9397eee28b640573c9f2b5391e8a0b3edcc00c52abc5c43
|
| 3 |
+
size 671149168
|