logical-reasoning / results /mgtv-results_p1_full_metrics.csv
dh-mc's picture
final internlm 2.5 results
d176c35
raw
history blame
595 Bytes
epoch,model,accuracy,precision,recall,f1
0,internlm/internlm2_5-7b-chat-1m,0.7596666666666667,0.7418540983920331,0.7810143934201508,0.7588869952101361
1,internlm/internlm2_5-7b-chat-1m_checkpoint-44,0.7616666666666667,0.8108727599781873,0.7616666666666667,0.780018019439933
2,internlm/internlm2_5-7b-chat-1m_checkpoint-88,0.7413333333333333,0.8161818707270968,0.7413333333333333,0.7695238425053844
3,internlm/internlm2_5-7b-chat-1m_checkpoint-132,0.755,0.8098286657868853,0.755,0.775657157343396
4,internlm/internlm2_5-7b-chat-1m_checkpoint-176,0.719,0.8033073302806261,0.719,0.7503194138525128