Commit History

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/optim_world_size_4_rank_1.pt with huggingface_hub
611f40d
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/optim_world_size_4_rank_0.pt with huggingface_hub
d85822d
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/model_world_size_4_rank_3.pt with huggingface_hub
a212a8b
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/model_world_size_4_rank_2.pt with huggingface_hub
95e60e9
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/model_world_size_4_rank_1.pt with huggingface_hub
5d6b9f5
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/model_world_size_4_rank_0.pt with huggingface_hub
8e5e2da
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/tokenizer_config.json with huggingface_hub
2478d4e
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/tokenizer.json with huggingface_hub
eba9a4d
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/generation_config.json with huggingface_hub
5de9416
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/config.json with huggingface_hub
3f8724b
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/chat_template.jinja with huggingface_hub
9c74dd7
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/fsdp_config.json with huggingface_hub
c4c2512
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_3.pt with huggingface_hub
7e9029a
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_2.pt with huggingface_hub
799c0bc
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_1.pt with huggingface_hub
5648a38
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_0.pt with huggingface_hub
f30acdc
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.json with huggingface_hub
0bcfa92
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.json with huggingface_hub
6bdbb2d
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.json with huggingface_hub
739cea0
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.json with huggingface_hub
63850a1
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.checkpoint_complete.json with huggingface_hub
8a5cb49
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.json with huggingface_hub
9bece5f
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.json with huggingface_hub
1b8cdc1
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.json with huggingface_hub
8771d90
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.json with huggingface_hub
0a70625
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.json with huggingface_hub
d81459b
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.json with huggingface_hub
38f5e79
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.json with huggingface_hub
7d91ebd
verified

cossmoss commited on

Upload experiments/weak_to_strong/math/ours/260804-rcd-fixedlambda-plus2p0-minus2p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.json with huggingface_hub
e6c6970
verified

cossmoss commited on

Delete experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_75/actor/optim_world_size_4_rank_3.pt with huggingface_hub
943abaf
verified

cossmoss commited on

Delete experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_75/actor/optim_world_size_4_rank_2.pt with huggingface_hub
8be99ef
verified

cossmoss commited on

Delete experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_75/actor/optim_world_size_4_rank_1.pt with huggingface_hub
b4f54cc
verified

cossmoss commited on

Delete experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_75/actor/optim_world_size_4_rank_0.pt with huggingface_hub
f5a102e
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/data.pt with huggingface_hub
015260d
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/optim_world_size_4_rank_3.pt with huggingface_hub
3afd7c5
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/optim_world_size_4_rank_2.pt with huggingface_hub
0568f9f
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/optim_world_size_4_rank_1.pt with huggingface_hub
47ee27c
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/optim_world_size_4_rank_0.pt with huggingface_hub
fdbbc79
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/model_world_size_4_rank_3.pt with huggingface_hub
c31541b
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/model_world_size_4_rank_2.pt with huggingface_hub
0488b25
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/model_world_size_4_rank_1.pt with huggingface_hub
beff09a
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/model_world_size_4_rank_0.pt with huggingface_hub
757a311
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/huggingface/tokenizer_config.json with huggingface_hub
bf3a5c5
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/huggingface/tokenizer.json with huggingface_hub
a50d6f5
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/huggingface/generation_config.json with huggingface_hub
e9e3b8c
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/huggingface/config.json with huggingface_hub
95f1dc0
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/huggingface/chat_template.jinja with huggingface_hub
49b863a
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/fsdp_config.json with huggingface_hub
b5c8cde
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/extra_state_world_size_4_rank_3.pt with huggingface_hub
53b0cfb
verified

cossmoss commited on

Upload experiments/weak_to_strong/reasoning/rg4_parallel/ours/260803-rg4-multiteacher-oprd-q3-8b-base-t4b-s105-s300-b64n8-mb32-dp4-seed42/global_step_105/actor/extra_state_world_size_4_rank_2.pt with huggingface_hub
d2d15a0
verified

cossmoss commited on