| { | |
| "best_metric": 0.6911338883028688, | |
| "best_model_checkpoint": "../save/jtrans-malware-2f-100c/checkpoint-1000", | |
| "epoch": 2.2573363431151243, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.97742663656885e-05, | |
| "loss": 0.4844, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.954853273137697e-05, | |
| "loss": 0.2551, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.932279909706546e-05, | |
| "loss": 0.1549, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.909706546275395e-05, | |
| "loss": 0.11, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.887133182844243e-05, | |
| "loss": 0.0974, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.864559819413092e-05, | |
| "loss": 0.0891, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.841986455981941e-05, | |
| "loss": 0.0876, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.81941309255079e-05, | |
| "loss": 0.0867, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.79683972911964e-05, | |
| "loss": 0.0825, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.774266365688489e-05, | |
| "loss": 0.0877, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.9824731182795698, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.08570680022239685, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_roc_auc_score": 0.6331024634550682, | |
| "eval_runtime": 2.0856, | |
| "eval_samples_per_second": 89.183, | |
| "eval_steps_per_second": 5.754, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.751693002257338e-05, | |
| "loss": 0.0791, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.729119638826185e-05, | |
| "loss": 0.0853, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 9.706546275395035e-05, | |
| "loss": 0.0892, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 9.683972911963884e-05, | |
| "loss": 0.0834, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 9.661399548532731e-05, | |
| "loss": 0.0862, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.63882618510158e-05, | |
| "loss": 0.0792, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.61625282167043e-05, | |
| "loss": 0.0826, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.593679458239279e-05, | |
| "loss": 0.0818, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.571106094808126e-05, | |
| "loss": 0.0813, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.548532731376975e-05, | |
| "loss": 0.0843, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.9824731182795698, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.08487475663423538, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_roc_auc_score": 0.6533783457136124, | |
| "eval_runtime": 2.1066, | |
| "eval_samples_per_second": 88.295, | |
| "eval_steps_per_second": 5.696, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.525959367945825e-05, | |
| "loss": 0.0805, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.503386004514672e-05, | |
| "loss": 0.0844, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.480812641083521e-05, | |
| "loss": 0.0919, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.45823927765237e-05, | |
| "loss": 0.0818, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.43566591422122e-05, | |
| "loss": 0.0866, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.413092550790069e-05, | |
| "loss": 0.0814, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.390519187358918e-05, | |
| "loss": 0.082, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.367945823927767e-05, | |
| "loss": 0.0845, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.345372460496615e-05, | |
| "loss": 0.083, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.322799097065464e-05, | |
| "loss": 0.0767, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.9824731182795698, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.08511281758546829, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_roc_auc_score": 0.6500109780834482, | |
| "eval_runtime": 2.0864, | |
| "eval_samples_per_second": 89.151, | |
| "eval_steps_per_second": 5.752, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.300225733634313e-05, | |
| "loss": 0.0889, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.27765237020316e-05, | |
| "loss": 0.0896, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.25507900677201e-05, | |
| "loss": 0.0782, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 9.232505643340859e-05, | |
| "loss": 0.0796, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 9.209932279909706e-05, | |
| "loss": 0.0865, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.187358916478555e-05, | |
| "loss": 0.0849, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 9.164785553047405e-05, | |
| "loss": 0.0806, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 9.142212189616254e-05, | |
| "loss": 0.084, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 9.119638826185101e-05, | |
| "loss": 0.0842, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.09706546275395e-05, | |
| "loss": 0.086, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.9824731182795698, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.0845983698964119, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_roc_auc_score": 0.6398895712235897, | |
| "eval_runtime": 2.0786, | |
| "eval_samples_per_second": 89.482, | |
| "eval_steps_per_second": 5.773, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.0744920993228e-05, | |
| "loss": 0.0811, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.051918735891649e-05, | |
| "loss": 0.0812, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.029345372460498e-05, | |
| "loss": 0.0856, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.006772009029347e-05, | |
| "loss": 0.0808, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 8.984198645598195e-05, | |
| "loss": 0.0867, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 8.961625282167044e-05, | |
| "loss": 0.0851, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 8.939051918735893e-05, | |
| "loss": 0.0788, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 8.91647855530474e-05, | |
| "loss": 0.083, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 8.89390519187359e-05, | |
| "loss": 0.0823, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 8.871331828442439e-05, | |
| "loss": 0.0853, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 0.9831182795698925, | |
| "eval_f1": 0.07647058823529411, | |
| "eval_loss": 0.08377581834793091, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.03987730061349693, | |
| "eval_roc_auc_score": 0.6488065782556061, | |
| "eval_runtime": 2.2005, | |
| "eval_samples_per_second": 84.524, | |
| "eval_steps_per_second": 5.453, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 8.848758465011288e-05, | |
| "loss": 0.0827, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 8.826185101580135e-05, | |
| "loss": 0.0753, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.803611738148985e-05, | |
| "loss": 0.0823, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 8.781038374717834e-05, | |
| "loss": 0.0811, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 8.758465011286681e-05, | |
| "loss": 0.0825, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 8.73589164785553e-05, | |
| "loss": 0.0848, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.71331828442438e-05, | |
| "loss": 0.0871, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 8.690744920993227e-05, | |
| "loss": 0.0807, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 8.668171557562076e-05, | |
| "loss": 0.0781, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.645598194130925e-05, | |
| "loss": 0.0812, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_accuracy": 0.9831182795698925, | |
| "eval_f1": 0.07647058823529411, | |
| "eval_loss": 0.08219148218631744, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.03987730061349693, | |
| "eval_roc_auc_score": 0.6788379312590687, | |
| "eval_runtime": 2.0981, | |
| "eval_samples_per_second": 88.65, | |
| "eval_steps_per_second": 5.719, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 8.623024830699775e-05, | |
| "loss": 0.0807, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 8.600451467268624e-05, | |
| "loss": 0.0771, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 8.577878103837473e-05, | |
| "loss": 0.0789, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.555304740406322e-05, | |
| "loss": 0.0826, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.53273137697517e-05, | |
| "loss": 0.0816, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.510158013544019e-05, | |
| "loss": 0.0813, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 8.487584650112868e-05, | |
| "loss": 0.0811, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 8.465011286681715e-05, | |
| "loss": 0.0803, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 8.442437923250564e-05, | |
| "loss": 0.0866, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 8.419864559819414e-05, | |
| "loss": 0.0786, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_accuracy": 0.9831182795698925, | |
| "eval_f1": 0.07647058823529411, | |
| "eval_loss": 0.08220940083265305, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.03987730061349693, | |
| "eval_roc_auc_score": 0.6817703720663841, | |
| "eval_runtime": 2.081, | |
| "eval_samples_per_second": 89.38, | |
| "eval_steps_per_second": 5.766, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.397291196388263e-05, | |
| "loss": 0.0798, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 8.37471783295711e-05, | |
| "loss": 0.0826, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 8.35214446952596e-05, | |
| "loss": 0.0816, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 8.329571106094809e-05, | |
| "loss": 0.0815, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.306997742663656e-05, | |
| "loss": 0.0828, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 8.284424379232505e-05, | |
| "loss": 0.0761, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 8.261851015801354e-05, | |
| "loss": 0.088, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 8.239277652370204e-05, | |
| "loss": 0.074, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 8.216704288939053e-05, | |
| "loss": 0.0848, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 8.194130925507902e-05, | |
| "loss": 0.081, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_accuracy": 0.9831182795698925, | |
| "eval_f1": 0.07647058823529411, | |
| "eval_loss": 0.08278104662895203, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.03987730061349693, | |
| "eval_roc_auc_score": 0.6632475420171875, | |
| "eval_runtime": 2.1218, | |
| "eval_samples_per_second": 87.663, | |
| "eval_steps_per_second": 5.656, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.17155756207675e-05, | |
| "loss": 0.0734, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 8.148984198645599e-05, | |
| "loss": 0.0814, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.126410835214448e-05, | |
| "loss": 0.0817, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 8.103837471783297e-05, | |
| "loss": 0.0781, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 8.081264108352144e-05, | |
| "loss": 0.074, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.058690744920994e-05, | |
| "loss": 0.084, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.036117381489843e-05, | |
| "loss": 0.0831, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 8.01354401805869e-05, | |
| "loss": 0.0822, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.99097065462754e-05, | |
| "loss": 0.0769, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 7.968397291196389e-05, | |
| "loss": 0.0827, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.9831182795698925, | |
| "eval_f1": 0.07647058823529411, | |
| "eval_loss": 0.08223988860845566, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.03987730061349693, | |
| "eval_roc_auc_score": 0.6819600545479816, | |
| "eval_runtime": 2.088, | |
| "eval_samples_per_second": 89.078, | |
| "eval_steps_per_second": 5.747, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 7.945823927765236e-05, | |
| "loss": 0.0764, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 7.923250564334085e-05, | |
| "loss": 0.084, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 7.900677200902934e-05, | |
| "loss": 0.0823, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 7.878103837471784e-05, | |
| "loss": 0.0767, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 7.855530474040633e-05, | |
| "loss": 0.0803, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 7.832957110609482e-05, | |
| "loss": 0.0799, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 7.810383747178331e-05, | |
| "loss": 0.0811, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 7.787810383747179e-05, | |
| "loss": 0.0858, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.765237020316028e-05, | |
| "loss": 0.081, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.742663656884877e-05, | |
| "loss": 0.0783, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_accuracy": 0.9831182795698925, | |
| "eval_f1": 0.07647058823529411, | |
| "eval_loss": 0.08187016099691391, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.03987730061349693, | |
| "eval_roc_auc_score": 0.6911338883028688, | |
| "eval_runtime": 2.0861, | |
| "eval_samples_per_second": 89.164, | |
| "eval_steps_per_second": 5.752, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 4430, | |
| "num_train_epochs": 10, | |
| "total_flos": 4240426445832192.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |