TAUR-dev/sft_acronym_5o_1100_end1300
Viewer
• Updated
• 1.4k • 5
TAUR-dev/sft_letter_countdown_5o_700_end1000
Viewer
• Updated
• 2.1k • 6
TAUR-dev/sft_letter_countdown_5o_1000_end1200
Viewer
• Updated
• 1.4k • 5
TAUR-dev/sft_acronym_5o_900_end1100
Viewer
• Updated
• 1.4k • 6
TAUR-dev/D-EXP_ask_lm_if_is_correct__cd4arg__M-cd3arg-should_verify-rl
Viewer
• Updated
• 1k • 7
TAUR-dev/D-EXP_ask_lm_if_is_correct__cd4arg__M-cd3arg-should_verify-sft
Viewer
• Updated
• 1k • 7
TAUR-dev/D-EXP_ask_lm_if_is_correct__cd4arg__Qwen2.5-1.5B-Instruct
Viewer
• Updated
• 1k • 6
Viewer
• Updated
• 3.29k • 22
• 1
TAUR-dev/D-ExpTracker__RC_FixedBF_pv_v2-RL__v1
Viewer
• Updated
• 3.31k • 7
TAUR-dev/D-EVAL__standard_eval_v3__RC_FixedBF_pv_v2-RL-eval_rl
Viewer
• Updated
• 3.29k • 7
TAUR-dev/D-ExpTracker__RC_BF_ab-ss_our_structure-SFT__v1
Viewer
• Updated
• 3.31k • 7
TAUR-dev/D-ExpTracker__RC_FixedBF_pv_v2_mll-RL__v1
Viewer
• Updated
• 3 • 7
TAUR-dev/D-ExpTracker__RC_rl_only_3args_RL__v1
Viewer
• Updated
• 3.3k • 7
TAUR-dev/D-ExpTracker__RC_pv_v2_RL__v1
Viewer
• Updated
• 3.3k • 7
TAUR-dev/D-EVAL__standard_eval_v3__RC_rl_only_3args_RL-eval_rl
Viewer
• Updated
• 3.29k • 7
TAUR-dev/D-EVAL__standard_eval_v3__RC_pv_v2_RL-eval_rl
Viewer
• Updated
• 3.29k • 6
TAUR-dev/D-ExpTracker__1e_csqa_and_gsm8k_run__v1
Viewer
• Updated
• 412 • 6
TAUR-dev/D-EVAL__standard_eval_v3__1e_csqa_and_gsm8k_run-eval_rl
Viewer
• Updated
• 400 • 6
TAUR-dev/sft_acronym_5o_700_end900
Viewer
• Updated
• 1.4k • 6
TAUR-dev/D-ExpTracker__eval-0903_rl_reflect__0epoch_3args__grpo_minibs32_lr1e-6_rollout16-rl__v1
Viewer
• Updated
• 15 • 7
TAUR-dev/D-ExpTracker__RC_BF_base_qwen__v1
Viewer
• Updated
• 3.3k • 7
TAUR-dev/D-EVAL__standard_eval_v3__RC_BF_base_qwen-eval_0
Viewer
• Updated
• 3.29k • 7
TAUR-dev/D-EVAL__standard_eval_v3__RC_BF_pv_v2-SFT-eval_sft
Viewer
• Updated
• 3.29k • 7
TAUR-dev/D-EVAL__standard_eval_v3__RC_BF_pv_v2-RL-eval_rl
Viewer
• Updated
• 3.29k • 7
TAUR-dev/D-EVAL__standard_eval_v3__RC_BF_low_qual_ref-RL-eval_rl
Viewer
• Updated
• 3.29k • 7
TAUR-dev/D-EVAL__standard_eval_v3__RC_BF_3args_rl_only-RL-eval_rl
Viewer
• Updated
• 3.29k • 6
TAUR-dev/D-EVAL__standard_eval_v3__eval-sft_exp_1e_zayneprompts_v2-sft-eval_sft
Viewer
• Updated
• 3.29k • 7
TAUR-dev/sft_acronym_5o_500_end700
Viewer
• Updated
• 1.4k • 5
TAUR-dev/sft_letter_countdown_5o_500_end700
Viewer
• Updated
• 1.4k • 6
TAUR-dev/D-EVAL__standard_eval_v3__RC_BF_ab-orig_only-RL-eval_rl
Viewer
• Updated
• 3.29k • 7