selfcorrexp2

AI & ML interests

None defined yet.

selfcorrexp2 's datasets 288

selfcorrexp2/llama3_openmath_em_ep1_tmp07_gold_reward

Viewer • Updated Jan 7, 2025 • 5k • 4

selfcorrexp2/llama3_openmath_em_ep1_tmp07

Viewer • Updated Jan 7, 2025 • 5k • 8

selfcorrexp2/llama3_openmath_em_ep1_tmp10_with_gold_rewards

Viewer • Updated Jan 7, 2025 • 5k • 4

selfcorrexp2/llama3_openmath_em_ep1_tmp10_gold_reward

Viewer • Updated Jan 7, 2025 • 5k • 5

selfcorrexp2/llama3_openmath_em_ep1_tmp10_with_morecorr_orm_rewards

Viewer • Updated Jan 7, 2025 • 5k • 4

selfcorrexp2/llama3_openmath_em_ep1_tmp10_with_balanced_orm_rewards

Viewer • Updated Jan 7, 2025 • 5k • 4

selfcorrexp2/llama3_openmath_em_ep1_tmp10

Viewer • Updated Jan 7, 2025 • 5k • 4

selfcorrexp2/llama3_sft_2ep_math_first_wrong_prompt

Viewer • Updated Jan 6, 2025 • 114k • 6

selfcorrexp2/llama3_sft_2ep_math_first_corr_regular_process

Viewer • Updated Jan 6, 2025 • 111k • 6

selfcorrexp2/llama3_sft_2ep_math_first_corr_prompt

Viewer • Updated Jan 6, 2025 • 111k • 6

selfcorrexp2/llama3_sft_2ep_math_base_merged_process

Viewer • Updated Jan 6, 2025 • 225k • 4

selfcorrexp2/llama3_sft_2ep_math_base_merged

Viewer • Updated Jan 6, 2025 • 14.1k • 5

selfcorrexp2/llama3_sft_2ep_math_base2

Viewer • Updated Jan 6, 2025 • 7.5k • 5

selfcorrexp2/llama3_sft_first_corr_prompt_generation4

Viewer • Updated Jan 6, 2025 • 937 • 5

selfcorrexp2/llama3_sft_first_corr_prompt_generation3

Viewer • Updated Jan 6, 2025 • 937 • 5

selfcorrexp2/llama3_sft_first_corr_prompt_generation7

Viewer • Updated Jan 6, 2025 • 937 • 5

selfcorrexp2/llama3_sft_first_corr_prompt_generation5

Viewer • Updated Jan 6, 2025 • 937 • 5

selfcorrexp2/llama3_sft_first_corr_prompt_generation2

Viewer • Updated Jan 6, 2025 • 937 • 4

selfcorrexp2/llama3_sft_first_corr_prompt_generation1

Viewer • Updated Jan 6, 2025 • 937 • 5

selfcorrexp2/llama3_sft_first_corr_prompt_generation0

Viewer • Updated Jan 6, 2025 • 937 • 5

selfcorrexp2/llama3_sft_first_corr_prompt_generation6

Viewer • Updated Jan 6, 2025 • 937 • 5

selfcorrexp2/llama3_sft_2ep_math_base1

Viewer • Updated Jan 6, 2025 • 6.56k • 5

selfcorrexp2/w2r125k_r2r115k_r125k

Viewer • Updated Jan 6, 2025 • 361k • 6

selfcorrexp2/w2r125k_r2r60k_r150k

Viewer • Updated Jan 6, 2025 • 333k • 5

selfcorrexp2/w2r125k_r2r90k_r125k

Viewer • Updated Jan 6, 2025 • 339k • 6

selfcorrexp2/llama3_sft_first_corr_processed_old_format_new

Viewer • Updated Jan 6, 2025 • 112k • 6

selfcorrexp2/llama3_sft_first_corr_processed_old_format_2

Viewer • Updated Jan 6, 2025 • 53.3k • 6

selfcorrexp2/llama3_sft_first_corr_processed_old_format_1

Viewer • Updated Jan 6, 2025 • 58.5k • 6

selfcorrexp2/llama3_sft_balanced_rr60k_orm_training

Viewer • Updated Jan 5, 2025 • 249k • 6

selfcorrexp2/llama3_sft_less_corr_rr60k_orm_training

Viewer • Updated Jan 5, 2025 • 183k • 6