| objective,best,learning_rate,num_train_epochs,per_device_train_batch_size,warmup_steps,weight_decay,time_this_iter_s | |
| 0.6375283056594502,False,2.2682993818119634e-05,4,8,250,0.11257883483123868,62.295817613601685 | |
| 0.6379352675229796,False,3.590880126653354e-05,3,16,1000,0.04950127542303912,57.21566104888916 | |
| 0.6430101919356234,False,1.3305018813937754e-05,5,16,0,0.12477446104218509,57.07160472869873 | |
| 0.5816271212668901,False,4.3719292103728615e-05,4,16,0,0.1691336373423109,58.25519013404846 | |
| 0.6034066935437185,False,4.5066082606416965e-05,2,8,0,0.14557098270440524,63.2433078289032 | |
| 0.565798317351568,False,4.5661870380314306e-05,5,8,250,0.2447905231269368,63.3815643787384 | |
| 0.608610258345654,False,4.2309504791301604e-05,2,8,500,0.10748446501369772,63.30465888977051 | |
| 0.6436338860188018,True,3.270513699172022e-05,4,16,0,0.07303439372733585,57.2542085647583 | |
| 0.6128416978240078,False,4.0694553908891e-05,4,16,0,0.02683040797439604,58.1628360748291 | |
| 0.6023919757272725,False,4.636122094405269e-05,1,8,1000,0.2126251167385789,64.2628378868103 | |