ardauzunoglu/dpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt_temp0 Viewer • Updated May 29 • 100k • 3
ardauzunoglu/dpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt_temp07 Viewer • Updated May 29 • 100k • 9
ardauzunoglu/dpo_smollm2_17b_instruct_0528_ckpt60_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 29 • 100k • 19
ardauzunoglu/dpo_smollm2_17b_instruct_0528_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 29 • 100k • 3
ardauzunoglu/dpo_smollm2_17b_grpo_0524_fasttext_eli5_no_deconf_20steps_c4_lowq_200m2b_subsample20m Viewer • Updated May 29 • 100k • 8
ardauzunoglu/dpo_smollm2_17b_grpo_0524_fasttext_eli5_no_deconf_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 29 • 100k • 17
ardauzunoglu/dpo_smollm2_ckpt80_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 28 • 100k • 66
ardauzunoglu/dpo_smollm2_17b_grpo_0524_ckpt100_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 28 • 100k • 8
ardauzunoglu/dpo_rpo_smollm2_17b_grpo_0524_ckpt600_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 28 • 100k • 6
ardauzunoglu/dpo_rpo_smollm2_17b_grpo_0524_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 28 • 100k • 9
ardauzunoglu/dporpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 28 • 100k • 18
ardauzunoglu/v18_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 27 • 100k • 21 • 1
ardauzunoglu/smollm2_grpofasttext_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 27 • 100k • 13
ardauzunoglu/smollm2_v17grpo_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 26 • 100k • 8
ardauzunoglu/smollm2_nogrpo_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 26 • 100k • 6
ardauzunoglu/smollm2_grpocb_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated May 25 • 100k • 15
ardauzunoglu/c4_lowq_200m2b_subsample20m_prompt_table_smollm2_rewrites Viewer • Updated May 23 • 100k • 1