mo8_combined_lora / evaluations

Ctrl+K

1 contributor

History: 2 commits

jprivera44

Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks)

729281b verified about 1 month ago

baseline
Upload evaluation results about 1 month ago
baseline_monitor
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
baseline_monitor_allcorrect
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
baseline_monitor_allwrong
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
cell1_baseline_x_baseline
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
cell2_ft_x_baseline
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
cell3_baseline_x_ft
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
cell4_ft_x_ft
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
lmeval_tasks
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
mo8_combined_monitor
Upload evaluation results about 1 month ago
mo8_combined_policy
Upload evaluation results about 1 month ago
mo8_monitor_allcorrect
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
mo8_monitor_allwrong
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
mo8_policy_only
Upload evaluation results about 1 month ago
2x2_full_analysis.txt

16.5 kB
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
2x2_monitor_policy_matrix_results.txt

8.66 kB
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago
monitor_clean_eval_results.txt

11.7 kB
Upload remaining eval results (2x2 matrix, allcorrect/allwrong, extra lmeval tasks) about 1 month ago