logical-reasoning / data /Qwen2.5-0.5B-Instruct_metrics.csv
dh-mc's picture
fix bug in perf calc
11f2c15
raw
history blame
1.76 kB
epoch,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
0.0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct_torch.float16_lf,0.443,0.5490534863315207,0.443,0.43178235266224163,0.594
0.2,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-35_torch.float16_lf,0.525,0.5819221558338251,0.525,0.4586682135998428,1.0
0.4,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-70_torch.float16_lf,0.54,0.6445255881472232,0.54,0.5293020271128788,1.0
0.6,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-105_torch.float16_lf,0.43766666666666665,0.6565760150511494,0.43766666666666665,0.49167707971005714,1.0
0.8,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-140_torch.float16_lf,0.49933333333333335,0.6513093602943617,0.49933333333333335,0.49913143191054443,1.0
1.0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-175_torch.float16_lf,0.5523333333333333,0.6622075519433389,0.5523333333333333,0.5627283867177305,1.0
1.2,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-210_torch.float16_lf,0.5403333333333333,0.64319564963495,0.5403333333333333,0.5598419070210608,1.0
1.4,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-245_torch.float16_lf,0.5843333333333334,0.6559808590166016,0.5843333333333334,0.6086767064128167,1.0
1.6,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-280_torch.float16_lf,0.5216666666666666,0.6604678981061621,0.5216666666666666,0.5615446578399996,1.0
1.8,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-315_torch.float16_lf,0.524,0.6673441240188523,0.524,0.5607458201939703,1.0
2.0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-350_torch.float16_lf,0.507,0.6597337077954278,0.5070000000000001,0.5492280882625964,1.0