TAUR-dev/sft_data_mix_9_13_25_3argsO_zaynev3
Viewer
• Updated
• 31.4k • 6
TAUR-dev/9_8_25__countdown_4arg__sft_data_multiprompts_ckpt_chunk_8
Viewer
• Updated
• 2k • 6
TAUR-dev/9_8_25__countdown_4arg__sft_data_multiprompts_ckpt_chunk_7
Viewer
• Updated
• 2k • 5
TAUR-dev/9_8_25__countdown_4arg__sft_data_multiprompts_ckpt_chunk_6
Viewer
• Updated
• 2k • 4
TAUR-dev/9_8_25__countdown_4arg__sft_data_multiprompts_ckpt_chunk_5
Viewer
• Updated
• 2k • 6
TAUR-dev/D-EVAL__acronym_task_four_letter_distractor__qwen_base__eval
Viewer
• Updated
• 45 • 7
TAUR-dev/D-EVAL__acronym_generation__all__qwen_base__eval
Viewer
• Updated
• 75 • 6
TAUR-dev/D-EVAL__standard_eval_v3__sft_v2_eval_rl_model_9_11zaynev2-rl_eval-eval_rl
Viewer
• Updated
• 4.9k • 5
TAUR-dev/D-EVAL__acronym_generation__all_easy__qwen_base__eval
Viewer
• Updated
• 45 • 6
TAUR-dev/D-EVAL__letter_countdown__freq_words__all__qwen_base__eval
Viewer
• Updated
• 45 • 7
TAUR-dev/D-EVAL__letter_countdown__freq_words__all_easy__qwen_base__eval
Viewer
• Updated
• 45 • 7
TAUR-dev/D-EVAL__acronym__easy_qwen_base_eval
Viewer
• Updated
• 30 • 7
TAUR-dev/D-EVAL__letter_countdown__easy_qwen_base_eval
Viewer
• Updated
• 30 • 7
TAUR-dev/acronym_task_four_letter_distractor
Viewer
• Updated
• 300 • 6
TAUR-dev/sft_data_mix_9_11_25_3argsO_zaynev2__all
Viewer
• Updated
• 238k • 5
TAUR-dev/D-EVAL__acronym__qwen_base_eval
Viewer
• Updated
• 50 • 7
TAUR-dev/letter_countdown__freq_words__all_easy
Viewer
• Updated
• 300 • 6
TAUR-dev/D-EVAL__letter_countdown__qwen_base_eval
Viewer
• Updated
• 30 • 6
TAUR-dev/acronym_generation__all_easy
Viewer
• Updated
• 264 • 6
TAUR-dev/acronym_generation__all
Viewer
• Updated
• 405 • 6
TAUR-dev/letter_countdown__freq_words__all
Viewer
• Updated
• 300 • 6
TAUR-dev/sft_data_mix_9_11_25_3argsO_zaynev2
Viewer
• Updated
• 35.9k • 5
TAUR-dev/D-EVAL__acronym____7__sft_v2_run_at_checkpoint_140_eval
Viewer
• Updated
• 30 • 6
TAUR-dev/D-EVAL__letter_countdown____7__sft_v2_run_at_checkpoint_140_eval
Viewer
• Updated
• 30 • 6
TAUR-dev/D-EVAL__acronym____6__sft_v2_run_at_checkpoint_140_eval
Viewer
• Updated
• 30 • 6
TAUR-dev/D-EVAL__letter_countdown____6__sft_v2_run_at_checkpoint_140_eval
Viewer
• Updated
• 30 • 6
TAUR-dev/D-EVAL__acronym____5__sft_v2_run_at_checkpoint_140_eval
Viewer
• Updated
• 30 • 6
TAUR-dev/D-EVAL__letter_countdown____5__sft_v2_run_at_checkpoint_140_eval
Viewer
• Updated
• 30 • 7
TAUR-dev/D-EVAL__acronym____4__sft_v2_run_at_checkpoint_140_eval
Viewer
• Updated
• 30 • 6
TAUR-dev/D-EVAL__letter_countdown____4__sft_v2_run_at_checkpoint_140_eval
Viewer
• Updated
• 30 • 6