| { | |
| "best_metric": 0.8635851183765502, | |
| "best_model_checkpoint": "convnextv2-tiny-22k-224-finetuned-galaxy10-decals/checkpoint-812", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 1860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 2.4657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 2.3572, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 2.1918, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.0129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 1.8042, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.5665, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.5287485907553551, | |
| "eval_f1": 0.489670591555268, | |
| "eval_loss": 1.3995580673217773, | |
| "eval_precision": 0.51797432448005, | |
| "eval_recall": 0.5287485907553551, | |
| "eval_runtime": 11.329, | |
| "eval_samples_per_second": 156.589, | |
| "eval_steps_per_second": 2.472, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 1.441, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.2789, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 1.1099, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 1.0068, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 0.9106, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.8598, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7463359639233371, | |
| "eval_f1": 0.7396145660112816, | |
| "eval_loss": 0.7433394193649292, | |
| "eval_precision": 0.7489582838021376, | |
| "eval_recall": 0.7463359639233371, | |
| "eval_runtime": 11.3311, | |
| "eval_samples_per_second": 156.56, | |
| "eval_steps_per_second": 2.471, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.8245, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.7828, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.7571, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.7349, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.7143, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.7163, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.7948139797068771, | |
| "eval_f1": 0.7862922946814768, | |
| "eval_loss": 0.5702754259109497, | |
| "eval_precision": 0.7918763498970974, | |
| "eval_recall": 0.7948139797068771, | |
| "eval_runtime": 11.3419, | |
| "eval_samples_per_second": 156.411, | |
| "eval_steps_per_second": 2.469, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.98805256869773e-05, | |
| "loss": 0.7189, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.664, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 4.92831541218638e-05, | |
| "loss": 0.6506, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.6786, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 4.86857825567503e-05, | |
| "loss": 0.6011, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.6325, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.80884109916368e-05, | |
| "loss": 0.5858, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.826944757609921, | |
| "eval_f1": 0.8190134794811148, | |
| "eval_loss": 0.519364058971405, | |
| "eval_precision": 0.8292030124360797, | |
| "eval_recall": 0.826944757609921, | |
| "eval_runtime": 11.3185, | |
| "eval_samples_per_second": 156.735, | |
| "eval_steps_per_second": 2.474, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.5894, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.74910394265233e-05, | |
| "loss": 0.5751, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.5717, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.6893667861409805e-05, | |
| "loss": 0.5544, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.5899, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5382, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.830890642615558, | |
| "eval_f1": 0.830249639360655, | |
| "eval_loss": 0.4935523569583893, | |
| "eval_precision": 0.8313710296529401, | |
| "eval_recall": 0.830890642615558, | |
| "eval_runtime": 11.3392, | |
| "eval_samples_per_second": 156.449, | |
| "eval_steps_per_second": 2.469, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.5351, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.552, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.535, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.51015531660693e-05, | |
| "loss": 0.5324, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.5171, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 4.4504181600955796e-05, | |
| "loss": 0.5546, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8291995490417137, | |
| "eval_f1": 0.8234170921225906, | |
| "eval_loss": 0.5054420232772827, | |
| "eval_precision": 0.8365553431707085, | |
| "eval_recall": 0.8291995490417137, | |
| "eval_runtime": 11.3389, | |
| "eval_samples_per_second": 156.453, | |
| "eval_steps_per_second": 2.469, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.5213, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 4.390681003584229e-05, | |
| "loss": 0.5162, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.4894, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 4.3309438470728796e-05, | |
| "loss": 0.511, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.4979, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 4.271206690561529e-05, | |
| "loss": 0.5067, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8280721533258174, | |
| "eval_f1": 0.8277982154267723, | |
| "eval_loss": 0.4816959798336029, | |
| "eval_precision": 0.8323523201307719, | |
| "eval_recall": 0.8280721533258174, | |
| "eval_runtime": 11.3174, | |
| "eval_samples_per_second": 156.75, | |
| "eval_steps_per_second": 2.474, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.5347, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 4.2114695340501795e-05, | |
| "loss": 0.5225, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.4679, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 4.15173237753883e-05, | |
| "loss": 0.5065, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.4809, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 4.0919952210274794e-05, | |
| "loss": 0.4711, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.4617, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8500563697857948, | |
| "eval_f1": 0.8497170739525509, | |
| "eval_loss": 0.4565054178237915, | |
| "eval_precision": 0.8544529191709447, | |
| "eval_recall": 0.8500563697857948, | |
| "eval_runtime": 11.3395, | |
| "eval_samples_per_second": 156.444, | |
| "eval_steps_per_second": 2.469, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.4491, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.4722, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 3.972520908004779e-05, | |
| "loss": 0.4888, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.4532, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 3.912783751493429e-05, | |
| "loss": 0.479, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.4619, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.8497921813863216, | |
| "eval_loss": 0.4382183253765106, | |
| "eval_precision": 0.8519737469081643, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 11.3861, | |
| "eval_samples_per_second": 155.805, | |
| "eval_steps_per_second": 2.459, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.8530465949820786e-05, | |
| "loss": 0.4417, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.4339, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 3.793309438470729e-05, | |
| "loss": 0.4203, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.4344, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 3.7335722819593785e-05, | |
| "loss": 0.415, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4416, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8528748590755355, | |
| "eval_f1": 0.8503504951623672, | |
| "eval_loss": 0.43299004435539246, | |
| "eval_precision": 0.8505191801891326, | |
| "eval_recall": 0.8528748590755355, | |
| "eval_runtime": 11.3081, | |
| "eval_samples_per_second": 156.879, | |
| "eval_steps_per_second": 2.476, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 3.673835125448029e-05, | |
| "loss": 0.4363, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.44, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 3.614097968936679e-05, | |
| "loss": 0.4546, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.4261, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 3.554360812425329e-05, | |
| "loss": 0.4161, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.4267, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.8573844419391207, | |
| "eval_f1": 0.8566452706056421, | |
| "eval_loss": 0.4274262487888336, | |
| "eval_precision": 0.8575497959170474, | |
| "eval_recall": 0.8573844419391207, | |
| "eval_runtime": 11.3338, | |
| "eval_samples_per_second": 156.524, | |
| "eval_steps_per_second": 2.47, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.3929, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.4001, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 3.4348864994026287e-05, | |
| "loss": 0.3917, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.3879, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 3.375149342891278e-05, | |
| "loss": 0.4089, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.3952, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.3154121863799286e-05, | |
| "loss": 0.3919, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8585118376550169, | |
| "eval_f1": 0.8563266312380678, | |
| "eval_loss": 0.44069355726242065, | |
| "eval_precision": 0.860402375264597, | |
| "eval_recall": 0.8585118376550169, | |
| "eval_runtime": 11.334, | |
| "eval_samples_per_second": 156.52, | |
| "eval_steps_per_second": 2.47, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.3763, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 3.255675029868578e-05, | |
| "loss": 0.3695, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.3747, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 3.195937873357228e-05, | |
| "loss": 0.4177, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.3804, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 3.136200716845878e-05, | |
| "loss": 0.3929, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8635851183765502, | |
| "eval_f1": 0.8603228034452383, | |
| "eval_loss": 0.4372858703136444, | |
| "eval_precision": 0.8625008943872746, | |
| "eval_recall": 0.8635851183765502, | |
| "eval_runtime": 11.3209, | |
| "eval_samples_per_second": 156.701, | |
| "eval_steps_per_second": 2.473, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.364, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 3.0764635603345284e-05, | |
| "loss": 0.3701, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.4004, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.016726403823178e-05, | |
| "loss": 0.3615, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.3908, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 0.3989, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8585118376550169, | |
| "eval_f1": 0.8577266574904324, | |
| "eval_loss": 0.4350617825984955, | |
| "eval_precision": 0.8602399940966811, | |
| "eval_recall": 0.8585118376550169, | |
| "eval_runtime": 11.2852, | |
| "eval_samples_per_second": 157.198, | |
| "eval_steps_per_second": 2.481, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.37, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 2.897252090800478e-05, | |
| "loss": 0.3426, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.3557, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 2.8375149342891276e-05, | |
| "loss": 0.381, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.376, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3426, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.8494926719278467, | |
| "eval_f1": 0.8483774142310309, | |
| "eval_loss": 0.4475528299808502, | |
| "eval_precision": 0.8499504614493899, | |
| "eval_recall": 0.8494926719278467, | |
| "eval_runtime": 11.3286, | |
| "eval_samples_per_second": 156.595, | |
| "eval_steps_per_second": 2.472, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.3623, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.718040621266428e-05, | |
| "loss": 0.3344, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.3467, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 2.6583034647550775e-05, | |
| "loss": 0.3489, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.3393, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.5985663082437278e-05, | |
| "loss": 0.3561, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.361, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8517474633596392, | |
| "eval_f1": 0.8500881682367122, | |
| "eval_loss": 0.44634684920310974, | |
| "eval_precision": 0.850455029593299, | |
| "eval_recall": 0.8517474633596392, | |
| "eval_runtime": 11.3131, | |
| "eval_samples_per_second": 156.81, | |
| "eval_steps_per_second": 2.475, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 2.5388291517323774e-05, | |
| "loss": 0.3442, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.3185, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.4790919952210277e-05, | |
| "loss": 0.3503, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.3698, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.3496, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.2996, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8596392333709132, | |
| "eval_f1": 0.8578593933614712, | |
| "eval_loss": 0.46942204236984253, | |
| "eval_precision": 0.8603579482237215, | |
| "eval_recall": 0.8596392333709132, | |
| "eval_runtime": 11.3506, | |
| "eval_samples_per_second": 156.291, | |
| "eval_steps_per_second": 2.467, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 2.3596176821983273e-05, | |
| "loss": 0.3245, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.3327, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 2.2998805256869773e-05, | |
| "loss": 0.3544, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.3302, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 2.2401433691756272e-05, | |
| "loss": 0.3224, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.3394, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8523111612175873, | |
| "eval_f1": 0.8517134471609608, | |
| "eval_loss": 0.44935789704322815, | |
| "eval_precision": 0.8526088281716775, | |
| "eval_recall": 0.8523111612175873, | |
| "eval_runtime": 11.3399, | |
| "eval_samples_per_second": 156.439, | |
| "eval_steps_per_second": 2.469, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 2.1804062126642775e-05, | |
| "loss": 0.328, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.3093, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.120669056152927e-05, | |
| "loss": 0.3136, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.3047, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.060931899641577e-05, | |
| "loss": 0.3137, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.3207, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.850620067643743, | |
| "eval_f1": 0.8496143664854563, | |
| "eval_loss": 0.48628443479537964, | |
| "eval_precision": 0.850216342064178, | |
| "eval_recall": 0.850620067643743, | |
| "eval_runtime": 11.3395, | |
| "eval_samples_per_second": 156.445, | |
| "eval_steps_per_second": 2.469, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 2.001194743130227e-05, | |
| "loss": 0.3218, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.2991, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.941457586618877e-05, | |
| "loss": 0.3057, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.3147, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 0.2981, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3185, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.821983273596177e-05, | |
| "loss": 0.2993, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.855129650507328, | |
| "eval_f1": 0.852098281420853, | |
| "eval_loss": 0.47476866841316223, | |
| "eval_precision": 0.8516075789957255, | |
| "eval_recall": 0.855129650507328, | |
| "eval_runtime": 11.2995, | |
| "eval_samples_per_second": 156.997, | |
| "eval_steps_per_second": 2.478, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.2857, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 1.7622461170848266e-05, | |
| "loss": 0.3071, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.2907, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 1.702508960573477e-05, | |
| "loss": 0.2889, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.3033, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 1.642771804062127e-05, | |
| "loss": 0.287, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.846674182638106, | |
| "eval_f1": 0.8434154679322435, | |
| "eval_loss": 0.4980190098285675, | |
| "eval_precision": 0.843551812912198, | |
| "eval_recall": 0.846674182638106, | |
| "eval_runtime": 11.3289, | |
| "eval_samples_per_second": 156.591, | |
| "eval_steps_per_second": 2.472, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.2713, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 1.5830346475507768e-05, | |
| "loss": 0.2935, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.2771, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 1.5232974910394265e-05, | |
| "loss": 0.2885, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.3013, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 1.4635603345280766e-05, | |
| "loss": 0.3331, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.85456595264938, | |
| "eval_f1": 0.8519463352449678, | |
| "eval_loss": 0.4828510582447052, | |
| "eval_precision": 0.8530241408546018, | |
| "eval_recall": 0.85456595264938, | |
| "eval_runtime": 11.3531, | |
| "eval_samples_per_second": 156.257, | |
| "eval_steps_per_second": 2.466, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.2798, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 1.4038231780167265e-05, | |
| "loss": 0.2706, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.2859, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 0.2716, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.2962, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 1.2843488649940263e-05, | |
| "loss": 0.2852, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.8511837655016911, | |
| "eval_f1": 0.850849134011751, | |
| "eval_loss": 0.4942522943019867, | |
| "eval_precision": 0.8520335676228308, | |
| "eval_recall": 0.8511837655016911, | |
| "eval_runtime": 11.3377, | |
| "eval_samples_per_second": 156.469, | |
| "eval_steps_per_second": 2.47, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.2917, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 1.2246117084826763e-05, | |
| "loss": 0.2816, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.2829, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 1.1648745519713262e-05, | |
| "loss": 0.2754, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.3208, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 1.1051373954599762e-05, | |
| "loss": 0.2626, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2813, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8573844419391207, | |
| "eval_f1": 0.8568191444546512, | |
| "eval_loss": 0.4796256721019745, | |
| "eval_precision": 0.8573783356569683, | |
| "eval_recall": 0.8573844419391207, | |
| "eval_runtime": 11.3073, | |
| "eval_samples_per_second": 156.889, | |
| "eval_steps_per_second": 2.476, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 1.0454002389486262e-05, | |
| "loss": 0.2853, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.3056, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 9.856630824372761e-06, | |
| "loss": 0.2852, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2657, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.2702, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.2807, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8596392333709132, | |
| "eval_f1": 0.8576239524924387, | |
| "eval_loss": 0.4811071455478668, | |
| "eval_precision": 0.8575824204793644, | |
| "eval_recall": 0.8596392333709132, | |
| "eval_runtime": 11.3381, | |
| "eval_samples_per_second": 156.464, | |
| "eval_steps_per_second": 2.47, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 8.661887694145759e-06, | |
| "loss": 0.2629, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2548, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.2578, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.2808, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 7.467144563918758e-06, | |
| "loss": 0.2589, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.2609, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8607666290868095, | |
| "eval_f1": 0.8591947449791174, | |
| "eval_loss": 0.4785688817501068, | |
| "eval_precision": 0.858924769636293, | |
| "eval_recall": 0.8607666290868095, | |
| "eval_runtime": 11.3078, | |
| "eval_samples_per_second": 156.883, | |
| "eval_steps_per_second": 2.476, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 6.869772998805258e-06, | |
| "loss": 0.258, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.2816, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 6.2724014336917564e-06, | |
| "loss": 0.2596, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.253, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 5.675029868578255e-06, | |
| "loss": 0.27, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.2571, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.8607666290868095, | |
| "eval_f1": 0.8602141649163884, | |
| "eval_loss": 0.47767895460128784, | |
| "eval_precision": 0.8605408244201141, | |
| "eval_recall": 0.8607666290868095, | |
| "eval_runtime": 11.6082, | |
| "eval_samples_per_second": 152.823, | |
| "eval_steps_per_second": 2.412, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 5.077658303464755e-06, | |
| "loss": 0.2711, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.2617, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 4.4802867383512545e-06, | |
| "loss": 0.2858, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.2622, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 3.882915173237754e-06, | |
| "loss": 0.2398, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2636, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.2855436081242537e-06, | |
| "loss": 0.2807, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8596392333709132, | |
| "eval_f1": 0.8581903613576354, | |
| "eval_loss": 0.48787200450897217, | |
| "eval_precision": 0.8579572233582533, | |
| "eval_recall": 0.8596392333709132, | |
| "eval_runtime": 11.5348, | |
| "eval_samples_per_second": 153.795, | |
| "eval_steps_per_second": 2.427, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.2639, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 0.2682, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.2497, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 2.090800477897252e-06, | |
| "loss": 0.2527, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.2622, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.4934289127837516e-06, | |
| "loss": 0.2578, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8556933483652762, | |
| "eval_f1": 0.8549276982708169, | |
| "eval_loss": 0.4829048216342926, | |
| "eval_precision": 0.8550274822038406, | |
| "eval_recall": 0.8556933483652762, | |
| "eval_runtime": 11.3255, | |
| "eval_samples_per_second": 156.638, | |
| "eval_steps_per_second": 2.472, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.2621, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 8.960573476702509e-07, | |
| "loss": 0.2469, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.2523, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 2.9868578255675034e-07, | |
| "loss": 0.252, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.2543, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.8562570462232244, | |
| "eval_f1": 0.8554397941706012, | |
| "eval_loss": 0.4832927882671356, | |
| "eval_precision": 0.8555234926248159, | |
| "eval_recall": 0.8562570462232244, | |
| "eval_runtime": 11.3662, | |
| "eval_samples_per_second": 156.077, | |
| "eval_steps_per_second": 2.463, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 1860, | |
| "total_flos": 1.1959619744316432e+19, | |
| "train_loss": 0.46238761537818496, | |
| "train_runtime": 4125.4091, | |
| "train_samples_per_second": 116.076, | |
| "train_steps_per_second": 0.451 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.1959619744316432e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |