ardauzunoglu/c4_lowq_200m2b_grpo_prompt_smollm2_17b_instruct_0609_dclmfasttext_and_influence_rerun Viewer • Updated 4 days ago • 800k • 29
ardauzunoglu/dpoed_ckpt160_smollm2_17b_instruct_0527_c4_lowq_200m2b_grpo_prompt Viewer • Updated 4 days ago • 800k • 38
ardauzunoglu/c4_lowq_200m2b_grpo_prompt_smollm2_17b_instruct_0609_dclmfasttext_and_influence Viewer • Updated 6 days ago • 800k • 33
ardauzunoglu/smollm2_17b_instruct_double_rewritten_both_dclmft_and_inf Viewer • Updated 7 days ago • 95.3k • 26
ardauzunoglu/smollm2_17b_instruct_0609_dclmft_and_inf5k3kog_ckpt160_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 8 days ago • 100k • 33
ardauzunoglu/smollm2_17b_instruct_0609_dclmft_and_inf10k_ckpt160_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 8 days ago • 100k • 37
ardauzunoglu/smollm2_17b_instruct_0609_dclmft_and_inf_ckpt160_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 9 days ago • 100k • 33
ardauzunoglu/trytoreplicatethebestmodel_5k_from3k_originals_ckpt160_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 9 days ago • 100k • 33
ardauzunoglu/smollm2_17b_instruct_0609_fasttext_dclm_global_ckpt160_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 9 days ago • 100k • 34
ardauzunoglu/smollm2_17b_instruct_0609_fasttext_dclm_local_ckpt160_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 9 days ago • 100k • 37
ardauzunoglu/smollm2_17b_instruct_0609temp07topp08topk20_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 10 days ago • 100k • 25
ardauzunoglu/smollm2_17b_instruct_0609_25kckpt360_inf_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 10 days ago • 100k • 24
ardauzunoglu/smollm2_17b_instruct_0609_inf_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 11 days ago • 100k • 26
ardauzunoglu/smollm2_17b_instruct_0531_inf_eli5_softgate_dpoed_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 14 days ago • 100k • 25
ardauzunoglu/smollm2_17b_instruct_0531_inf_eli5_product_dpoed_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 14 days ago • 100k • 25
ardauzunoglu/dataman_dpoed_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 14 days ago • 100k • 25
ardauzunoglu/influence_dpoed_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 15 days ago • 100k • 30
ardauzunoglu/dclm_random200m_dpoed_ckpt160_smollm2_17b_instruct_0527_c4_lowq_200m2b_grpo_prompt_random400m Viewer • Updated 17 days ago • 648k • 49
ardauzunoglu/mbert_reward_dpoed_model_ckpt20_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 19 days ago • 100k • 26
ardauzunoglu/dpo_smollm2_0531_fwedu_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 20 days ago • 100k • 32
ardauzunoglu/dpo_smollm2_0531_preselect_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 20 days ago • 100k • 38
ardauzunoglu/dpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt_temp0 Viewer • Updated 22 days ago • 100k • 36
ardauzunoglu/dpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt_temp07 Viewer • Updated 22 days ago • 100k • 41
ardauzunoglu/dpo_smollm2_17b_instruct_0528_ckpt60_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 23 days ago • 100k • 45
ardauzunoglu/dpo_smollm2_17b_instruct_0528_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 23 days ago • 100k • 42
ardauzunoglu/dpo_smollm2_17b_grpo_0524_fasttext_eli5_no_deconf_20steps_c4_lowq_200m2b_subsample20m Viewer • Updated 23 days ago • 100k • 65
ardauzunoglu/dpo_smollm2_17b_grpo_0524_fasttext_eli5_no_deconf_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 23 days ago • 100k • 67