logical-reasoning / results /mgtv-results_p2_full_metrics.csv
dh-mc's picture
final internlm 2.5 results
d176c35
raw
history blame
834 Bytes
epoch,model,accuracy,precision,recall,f1
0,internlm/internlm2_5-7b-chat-1m,0.766,0.7479690198649127,0.7875257025359835,0.7649220492304646
1,internlm/internlm2_5-7b-chat-1m_checkpoint-88,0.7963333333333333,0.8082318701472306,0.7963333333333333,0.7981603484404942
2,internlm/internlm2_5-7b-chat-1m_checkpoint-176,0.7813333333333333,0.8047159646469545,0.7813333333333333,0.7885809515702639
3,internlm/internlm2_5-7b-chat-1m_checkpoint-264,0.759,0.8055016850419279,0.759,0.7772366362599777
4,internlm/internlm2_5-7b-chat-1m_checkpoint-352,0.7303333333333333,0.790676222309579,0.7303333333333333,0.7537162708213547
5,internlm/internlm2_5-7b-chat-1m_checkpoint-440,0.7303333333333333,0.7904201181031161,0.7303333333333333,0.7537502448450035
6,internlm/internlm2_5-7b-chat-1m_checkpoint-528,0.716,0.7898918870718658,0.716,0.7448330530646626