RegularizedSelfPlay/sppo_forwardimportance10-0.01-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3 Text Generation • Updated 28 days ago • 23
RegularizedSelfPlay/sppo_forwardimportance10-0.01-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter2 Text Generation • Updated 28 days ago • 21
RegularizedSelfPlay/sppo_forwardimportance10-0.01-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter1 Text Generation • Updated 28 days ago • 22
RegularizedSelfPlay/sppo_forwardimportance10-0.01-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3 Text Generation • Updated 28 days ago • 23
RegularizedSelfPlay/sppo_forwardimportance10-0.01-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter2 Text Generation • Updated 28 days ago • 21
RegularizedSelfPlay/sppo_forwardimportance10-0.01-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter1 Text Generation • Updated 28 days ago • 22
RegularizedSelfPlay/sppo_forwardimportance10-0.1-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter2 Text Generation • Updated Jan 25 • 7
RegularizedSelfPlay/sppo_forwardimportance10-0.1-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3 Text Generation • Updated Jan 25 • 8
RegularizedSelfPlay/sppo_reversekl-0.05-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3 Text Generation • Updated Jan 25 • 10
RegularizedSelfPlay/sppo_forwardimportance10-0.1-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter2 Text Generation • Updated Jan 25 • 7
RegularizedSelfPlay/sppo_forward1reverse5-0.1-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3 Text Generation • Updated Jan 25 • 9
RegularizedSelfPlay/sppo_forward1reverse5-0.1-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter2 Text Generation • Updated Jan 25 • 9
RegularizedSelfPlay/sppo_forwardimportance10-0.1-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter1 Text Generation • Updated Jan 25 • 10
RegularizedSelfPlay/sppo_reversekl-2-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter2 Text Generation • Updated Jan 25 • 8
RegularizedSelfPlay/sppo_reversekl-2-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3 Text Generation • Updated Jan 25 • 12
RegularizedSelfPlay/sppo_reversekl-0.05-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3 Text Generation • Updated Jan 25 • 10
RegularizedSelfPlay/sppo_forward1reverse5-0.1-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter3 Text Generation • Updated Jan 25 • 9
RegularizedSelfPlay/sppo_forward1reverse5-0.1-PromptABC-LLAMA-3-8B-Instruct-SPPO-Iter2 Text Generation • Updated Jan 25 • 9