logical-reasoning / results /mgtv-qwen2_7b_instruct_p2_full_metrics.csv
HaotianHu's picture
upload qwen2_7b_instruct p1,p2, llama3.1_8b_p2
6114e2d
epoch,model,accuracy,precision,recall,f1
0.0,Qwen/Qwen2-7B-Instruct_torch.float16_lf,0.6203333333333333,0.7554720257311661,0.6203333333333333,0.6731632664545455
0.2,Qwen/Qwen2-7B-Instruct/checkpoint-35_torch.float16_lf,0.725,0.7837219420829536,0.725,0.7488571220608156
0.4,Qwen/Qwen2-7B-Instruct/checkpoint-70_torch.float16_lf,0.759,0.8005303465799652,0.759,0.7748745026535183
0.6,Qwen/Qwen2-7B-Instruct/checkpoint-105_torch.float16_lf,0.6926666666666667,0.8039176975550218,0.6926666666666667,0.7332481528585848
0.8,Qwen/Qwen2-7B-Instruct/checkpoint-140_torch.float16_lf,0.725,0.7952719247171957,0.725,0.7476238017654298
1.0,Qwen/Qwen2-7B-Instruct/checkpoint-175_torch.float16_lf,0.6756666666666666,0.7810148934939715,0.6756666666666666,0.708653993277772
1.2,Qwen/Qwen2-7B-Instruct/checkpoint-210_torch.float16_lf,0.7013333333333334,0.7969562600853992,0.7013333333333334,0.7362679665494508
1.4,Qwen/Qwen2-7B-Instruct/checkpoint-245_torch.float16_lf,0.733,0.7923079863412145,0.733,0.7556265259556338
1.6,Qwen/Qwen2-7B-Instruct/checkpoint-280_torch.float16_lf,0.6983333333333334,0.785127298428753,0.6983333333333334,0.7292251109166867
1.8,Qwen/Qwen2-7B-Instruct/checkpoint-315_torch.float16_lf,0.6783333333333333,0.785390767631834,0.6783333333333333,0.7164131321837346
2.0,Qwen/Qwen2-7B-Instruct/checkpoint-350_torch.float16_lf,0.689,0.7929715746898984,0.689,0.7259993126510194