Upload experiments/weak_to_strong/reasoning/self_reference/ours/260806-rcd-self_reference-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_30/actor/optim_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/model_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/model_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/best_validation_checkpoint.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/latest_checkpoint.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/data.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/ours/260806-rcd-self_reference-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_30/actor/optim_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/model_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/model_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/huggingface/tokenizer_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/huggingface/tokenizer.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/huggingface/generation_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/huggingface/config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/huggingface/chat_template.jinja with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/fsdp_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.checkpoint_complete.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_120/data.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260805r1-grpo-self_reference-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/self_reference/ours/260806-rcd-self_reference-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/tokenizer_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/tokenizer.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/generation_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/huggingface/chat_template.jinja with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/fsdp_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/extra_state_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/extra_state_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/extra_state_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/extra_state_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/intermediate_integration/baseline/260806-grpo-intermediate_integration-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_45/actor/.worker_sidecars_ready_world_size_4_rank_3.json with huggingface_hub
