logical-reasoning / results /mgtv-qwen2_7b_instruct_p1_full_metrics.csv
HaotianHu's picture
upload qwen2_7b_instruct p1,p2, llama3.1_8b_p2
6114e2d
raw
history blame
1.43 kB
epoch,model,accuracy,precision,recall,f1
0.0,Qwen/Qwen2-7B-Instruct_torch.float16_lf,0.6263333333333333,0.7591042317022715,0.6263333333333333,0.6785820008892073
0.2,Qwen/Qwen2-7B-Instruct/checkpoint-35_torch.float16_lf,0.725,0.7871098162147435,0.725,0.74939544116392
0.4,Qwen/Qwen2-7B-Instruct/checkpoint-70_torch.float16_lf,0.7513333333333333,0.8020499347814307,0.7513333333333333,0.7714082485343072
0.6,Qwen/Qwen2-7B-Instruct/checkpoint-105_torch.float16_lf,0.6843333333333333,0.8011223407536904,0.6843333333333333,0.7273417955195597
0.8,Qwen/Qwen2-7B-Instruct/checkpoint-140_torch.float16_lf,0.7196666666666667,0.7901188594373724,0.7196666666666667,0.741719758398597
1.0,Qwen/Qwen2-7B-Instruct/checkpoint-175_torch.float16_lf,0.674,0.7743575698788213,0.674,0.7072971059584063
1.2,Qwen/Qwen2-7B-Instruct/checkpoint-210_torch.float16_lf,0.6996666666666667,0.7951625272365199,0.6996666666666667,0.7339089692988213
1.4,Qwen/Qwen2-7B-Instruct/checkpoint-245_torch.float16_lf,0.7336666666666667,0.7907876730085539,0.7336666666666667,0.7555586934112002
1.6,Qwen/Qwen2-7B-Instruct/checkpoint-280_torch.float16_lf,0.7006666666666667,0.7859041414222372,0.7006666666666667,0.7310473937199747
1.8,Qwen/Qwen2-7B-Instruct/checkpoint-315_torch.float16_lf,0.6773333333333333,0.7949757806163953,0.6773333333333333,0.719378508729944
2.0,Qwen/Qwen2-7B-Instruct/checkpoint-350_torch.float16_lf,0.683,0.787966533686809,0.683,0.7212373172393933