final internlm 2.5 results

results/mgtv-results_p1_full_metrics.csv

@@ -0,0 +1,6 @@
+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

results/mgtv-results_p2_full_metrics.csv

@@ -0,0 +1,8 @@
+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