Upload experiments/weak_to_strong/reasoning/self_reference/baseline/260806-grpo-self_reference-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-eval15-tistoken-b64-mb32-dp4/global_step_15/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_150/actor/huggingface/tokenizer.json 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_90/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_120/actor/huggingface/tokenizer.json 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_75/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_90/actor/huggingface/tokenizer.json 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_60/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_60/actor/huggingface/tokenizer.json with huggingface_hub
