| { | |
| "best_metric": 0.8523111612175873, | |
| "best_model_checkpoint": "vit-huge-patch14-224-in21k-finetuned-galaxy10-decals/checkpoint-875", | |
| "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": 5.376344086021506e-06, | |
| "loss": 2.3036, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.262, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 2.2008, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 2.0989, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 1.9477, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.7563, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.5095828635851184, | |
| "eval_f1": 0.44146087786795973, | |
| "eval_loss": 1.6011251211166382, | |
| "eval_precision": 0.46941064066552085, | |
| "eval_recall": 0.5095828635851184, | |
| "eval_runtime": 37.7529, | |
| "eval_samples_per_second": 46.99, | |
| "eval_steps_per_second": 0.742, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 1.617, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 1.4715, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 1.3331, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 1.2315, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 5.913978494623657e-05, | |
| "loss": 1.1221, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 1.0516, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.766065388951522, | |
| "eval_f1": 0.7525282943415311, | |
| "eval_loss": 0.9114971160888672, | |
| "eval_precision": 0.7678819767534787, | |
| "eval_recall": 0.766065388951522, | |
| "eval_runtime": 35.5067, | |
| "eval_samples_per_second": 49.962, | |
| "eval_steps_per_second": 0.789, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 6.989247311827958e-05, | |
| "loss": 1.0139, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.9538, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.9096, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.8998, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 9.13978494623656e-05, | |
| "loss": 0.8906, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.8551, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.7705749718151071, | |
| "eval_f1": 0.7652622854025727, | |
| "eval_loss": 0.7590190172195435, | |
| "eval_precision": 0.7859809881154541, | |
| "eval_recall": 0.7705749718151071, | |
| "eval_runtime": 35.6661, | |
| "eval_samples_per_second": 49.739, | |
| "eval_steps_per_second": 0.785, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.97610513739546e-05, | |
| "loss": 0.8695, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.916367980884111e-05, | |
| "loss": 0.783, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 9.85663082437276e-05, | |
| "loss": 0.7533, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.79689366786141e-05, | |
| "loss": 0.7789, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 9.73715651135006e-05, | |
| "loss": 0.7158, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.744, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.61768219832736e-05, | |
| "loss": 0.6701, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8094701240135288, | |
| "eval_f1": 0.7984966960451485, | |
| "eval_loss": 0.6252894997596741, | |
| "eval_precision": 0.8012975712835072, | |
| "eval_recall": 0.8094701240135288, | |
| "eval_runtime": 35.5963, | |
| "eval_samples_per_second": 49.837, | |
| "eval_steps_per_second": 0.787, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.55794504181601e-05, | |
| "loss": 0.6965, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 9.49820788530466e-05, | |
| "loss": 0.6638, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.438470728793309e-05, | |
| "loss": 0.6444, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 9.378733572281961e-05, | |
| "loss": 0.6651, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.31899641577061e-05, | |
| "loss": 0.6879, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 0.6112, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8094701240135288, | |
| "eval_f1": 0.8083199200988649, | |
| "eval_loss": 0.6058443188667297, | |
| "eval_precision": 0.8120020569600309, | |
| "eval_recall": 0.8094701240135288, | |
| "eval_runtime": 35.6373, | |
| "eval_samples_per_second": 49.779, | |
| "eval_steps_per_second": 0.786, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 9.199522102747909e-05, | |
| "loss": 0.6385, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 9.13978494623656e-05, | |
| "loss": 0.6439, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 9.080047789725208e-05, | |
| "loss": 0.6185, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 9.02031063321386e-05, | |
| "loss": 0.5979, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.960573476702509e-05, | |
| "loss": 0.5899, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 8.900836320191159e-05, | |
| "loss": 0.6109, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8291995490417137, | |
| "eval_f1": 0.8196379646148686, | |
| "eval_loss": 0.5428421497344971, | |
| "eval_precision": 0.835292064650394, | |
| "eval_recall": 0.8291995490417137, | |
| "eval_runtime": 35.6312, | |
| "eval_samples_per_second": 49.788, | |
| "eval_steps_per_second": 0.786, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.84109916367981e-05, | |
| "loss": 0.5827, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 8.781362007168459e-05, | |
| "loss": 0.5871, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 8.72162485065711e-05, | |
| "loss": 0.5507, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 8.661887694145759e-05, | |
| "loss": 0.5726, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.5648, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 8.542413381123058e-05, | |
| "loss": 0.5643, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8342728297632469, | |
| "eval_f1": 0.8332447054189591, | |
| "eval_loss": 0.5230061411857605, | |
| "eval_precision": 0.8349734430533635, | |
| "eval_recall": 0.8342728297632469, | |
| "eval_runtime": 35.6212, | |
| "eval_samples_per_second": 49.802, | |
| "eval_steps_per_second": 0.786, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 8.482676224611709e-05, | |
| "loss": 0.5628, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 8.422939068100359e-05, | |
| "loss": 0.5721, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 8.363201911589009e-05, | |
| "loss": 0.5168, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 8.30346475507766e-05, | |
| "loss": 0.5499, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 8.243727598566309e-05, | |
| "loss": 0.5013, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 8.183990442054959e-05, | |
| "loss": 0.5143, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.124253285543608e-05, | |
| "loss": 0.5204, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8365276211950394, | |
| "eval_f1": 0.8344294764027218, | |
| "eval_loss": 0.5010474920272827, | |
| "eval_precision": 0.8391362540191604, | |
| "eval_recall": 0.8365276211950394, | |
| "eval_runtime": 35.6558, | |
| "eval_samples_per_second": 49.753, | |
| "eval_steps_per_second": 0.785, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 8.064516129032258e-05, | |
| "loss": 0.4862, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.004778972520908e-05, | |
| "loss": 0.4815, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.945041816009559e-05, | |
| "loss": 0.5148, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.885304659498209e-05, | |
| "loss": 0.4943, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 7.825567502986858e-05, | |
| "loss": 0.5383, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 7.765830346475508e-05, | |
| "loss": 0.4918, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8365276211950394, | |
| "eval_f1": 0.8347505093667409, | |
| "eval_loss": 0.49997678399086, | |
| "eval_precision": 0.8418775863015479, | |
| "eval_recall": 0.8365276211950394, | |
| "eval_runtime": 35.6257, | |
| "eval_samples_per_second": 49.796, | |
| "eval_steps_per_second": 0.786, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 7.706093189964157e-05, | |
| "loss": 0.4731, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.646356033452809e-05, | |
| "loss": 0.4794, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 7.586618876941458e-05, | |
| "loss": 0.4764, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.4891, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 7.467144563918757e-05, | |
| "loss": 0.4488, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.4673, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8371067976331331, | |
| "eval_loss": 0.4948519170284271, | |
| "eval_precision": 0.8394328276148111, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 35.5817, | |
| "eval_samples_per_second": 49.857, | |
| "eval_steps_per_second": 0.787, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 7.347670250896058e-05, | |
| "loss": 0.4646, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 7.287933094384708e-05, | |
| "loss": 0.4653, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 7.228195937873358e-05, | |
| "loss": 0.4955, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 7.168458781362007e-05, | |
| "loss": 0.4541, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 7.108721624850657e-05, | |
| "loss": 0.4427, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 7.048984468339306e-05, | |
| "loss": 0.4569, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.846674182638106, | |
| "eval_f1": 0.8446171105961164, | |
| "eval_loss": 0.48026424646377563, | |
| "eval_precision": 0.8451023402588742, | |
| "eval_recall": 0.846674182638106, | |
| "eval_runtime": 35.6271, | |
| "eval_samples_per_second": 49.794, | |
| "eval_steps_per_second": 0.786, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 6.989247311827958e-05, | |
| "loss": 0.4164, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 6.929510155316607e-05, | |
| "loss": 0.4116, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 6.869772998805257e-05, | |
| "loss": 0.4039, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.810035842293908e-05, | |
| "loss": 0.4145, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 6.750298685782557e-05, | |
| "loss": 0.4426, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 6.690561529271207e-05, | |
| "loss": 0.4245, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.630824372759857e-05, | |
| "loss": 0.4164, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8325817361894025, | |
| "eval_f1": 0.829510053634, | |
| "eval_loss": 0.5012163519859314, | |
| "eval_precision": 0.8314391700835552, | |
| "eval_recall": 0.8325817361894025, | |
| "eval_runtime": 35.5771, | |
| "eval_samples_per_second": 49.863, | |
| "eval_steps_per_second": 0.787, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 6.571087216248507e-05, | |
| "loss": 0.3963, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 6.511350059737156e-05, | |
| "loss": 0.3846, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.4137, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 6.391875746714456e-05, | |
| "loss": 0.4189, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 6.332138590203107e-05, | |
| "loss": 0.4095, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 6.272401433691756e-05, | |
| "loss": 0.424, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8382342542318046, | |
| "eval_loss": 0.49403664469718933, | |
| "eval_precision": 0.8454364149011512, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 35.6442, | |
| "eval_samples_per_second": 49.77, | |
| "eval_steps_per_second": 0.786, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 6.212664277180407e-05, | |
| "loss": 0.3826, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 6.152927120669057e-05, | |
| "loss": 0.3782, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 6.093189964157706e-05, | |
| "loss": 0.4212, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 6.033452807646356e-05, | |
| "loss": 0.3638, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 5.9737156511350064e-05, | |
| "loss": 0.4038, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 5.913978494623657e-05, | |
| "loss": 0.4045, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8523111612175873, | |
| "eval_f1": 0.848886963068661, | |
| "eval_loss": 0.49271348118782043, | |
| "eval_precision": 0.8537584151509556, | |
| "eval_recall": 0.8523111612175873, | |
| "eval_runtime": 35.4939, | |
| "eval_samples_per_second": 49.98, | |
| "eval_steps_per_second": 0.789, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 5.8542413381123063e-05, | |
| "loss": 0.3779, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 5.794504181600956e-05, | |
| "loss": 0.3572, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 5.7347670250896056e-05, | |
| "loss": 0.363, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 5.675029868578255e-05, | |
| "loss": 0.3896, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 5.615292712066906e-05, | |
| "loss": 0.3896, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.3651, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.8416009019165727, | |
| "eval_f1": 0.8402639395733231, | |
| "eval_loss": 0.480947881937027, | |
| "eval_precision": 0.8396382728577194, | |
| "eval_recall": 0.8416009019165727, | |
| "eval_runtime": 35.6517, | |
| "eval_samples_per_second": 49.759, | |
| "eval_steps_per_second": 0.785, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.495818399044206e-05, | |
| "loss": 0.3597, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 5.436081242532856e-05, | |
| "loss": 0.3635, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.3412, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 5.316606929510155e-05, | |
| "loss": 0.3738, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 5.256869772998806e-05, | |
| "loss": 0.3272, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 5.1971326164874556e-05, | |
| "loss": 0.3547, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.137395459976105e-05, | |
| "loss": 0.3512, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8331454340473506, | |
| "eval_f1": 0.830726198234869, | |
| "eval_loss": 0.49547287821769714, | |
| "eval_precision": 0.8305575267132672, | |
| "eval_recall": 0.8331454340473506, | |
| "eval_runtime": 35.6304, | |
| "eval_samples_per_second": 49.789, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 5.077658303464755e-05, | |
| "loss": 0.3414, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 5.017921146953405e-05, | |
| "loss": 0.3029, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.3307, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.369, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.3334, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.2922, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8399098083427283, | |
| "eval_f1": 0.8358814297561209, | |
| "eval_loss": 0.5103182196617126, | |
| "eval_precision": 0.8357038780266931, | |
| "eval_recall": 0.8399098083427283, | |
| "eval_runtime": 35.6513, | |
| "eval_samples_per_second": 49.76, | |
| "eval_steps_per_second": 0.785, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.3288, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.3161, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.3358, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.3296, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.3206, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.3212, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8438556933483653, | |
| "eval_f1": 0.8411969373942092, | |
| "eval_loss": 0.5197161436080933, | |
| "eval_precision": 0.8407570120125888, | |
| "eval_recall": 0.8438556933483653, | |
| "eval_runtime": 35.6281, | |
| "eval_samples_per_second": 49.792, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.3241, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.2948, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.2922, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.2961, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.2903, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.3171, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.8348365276211951, | |
| "eval_f1": 0.8335426988116097, | |
| "eval_loss": 0.5252840518951416, | |
| "eval_precision": 0.8335202810105914, | |
| "eval_recall": 0.8348365276211951, | |
| "eval_runtime": 35.6435, | |
| "eval_samples_per_second": 49.771, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.3135, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.2808, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.3034, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.2929, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.2846, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2922, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.2896, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.846674182638106, | |
| "eval_f1": 0.8438142887270133, | |
| "eval_loss": 0.5303400754928589, | |
| "eval_precision": 0.8456129307593285, | |
| "eval_recall": 0.846674182638106, | |
| "eval_runtime": 35.5817, | |
| "eval_samples_per_second": 49.857, | |
| "eval_steps_per_second": 0.787, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.2911, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.2767, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.2668, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.2809, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.2778, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.271, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8393461104847801, | |
| "eval_f1": 0.8366409219984158, | |
| "eval_loss": 0.5571314692497253, | |
| "eval_precision": 0.8390865438529314, | |
| "eval_recall": 0.8393461104847801, | |
| "eval_runtime": 35.5781, | |
| "eval_samples_per_second": 49.862, | |
| "eval_steps_per_second": 0.787, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.2627, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.2641, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.2567, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.2619, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.2813, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.2996, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8421645997745209, | |
| "eval_f1": 0.8403607454013937, | |
| "eval_loss": 0.5467995405197144, | |
| "eval_precision": 0.8410643648435987, | |
| "eval_recall": 0.8421645997745209, | |
| "eval_runtime": 35.5993, | |
| "eval_samples_per_second": 49.832, | |
| "eval_steps_per_second": 0.787, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.2592, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.2376, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.2602, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.2701, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.2531, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.2663, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.8404735062006764, | |
| "eval_f1": 0.839265581016922, | |
| "eval_loss": 0.5619862675666809, | |
| "eval_precision": 0.8392610256771211, | |
| "eval_recall": 0.8404735062006764, | |
| "eval_runtime": 35.6722, | |
| "eval_samples_per_second": 49.731, | |
| "eval_steps_per_second": 0.785, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.2497, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.2459, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.2438, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.2467, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.2843, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.232, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.2513, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.846674182638106, | |
| "eval_f1": 0.8450416619843624, | |
| "eval_loss": 0.5337529182434082, | |
| "eval_precision": 0.8448410574567515, | |
| "eval_recall": 0.846674182638106, | |
| "eval_runtime": 35.5884, | |
| "eval_samples_per_second": 49.848, | |
| "eval_steps_per_second": 0.787, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.2478, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.2752, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.2443, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.2374, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2512, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.2453, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.8446161005440144, | |
| "eval_loss": 0.5561683773994446, | |
| "eval_precision": 0.8452004433295517, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 35.588, | |
| "eval_samples_per_second": 49.848, | |
| "eval_steps_per_second": 0.787, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.2241, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.2126, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.226, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.234, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.2166, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.2237, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.846674182638106, | |
| "eval_f1": 0.8442299256285252, | |
| "eval_loss": 0.5619068741798401, | |
| "eval_precision": 0.8449535852866724, | |
| "eval_recall": 0.846674182638106, | |
| "eval_runtime": 35.6106, | |
| "eval_samples_per_second": 49.817, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.2304, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.2337, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.2317, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.2154, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.2428, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2296, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.8464267193268318, | |
| "eval_loss": 0.5750566124916077, | |
| "eval_precision": 0.8495675943996633, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 35.6013, | |
| "eval_samples_per_second": 49.83, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.2315, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2165, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.2516, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2245, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.1973, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.2256, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.2479, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8461104847801578, | |
| "eval_f1": 0.843079245427948, | |
| "eval_loss": 0.5782006978988647, | |
| "eval_precision": 0.8440859727334082, | |
| "eval_recall": 0.8461104847801578, | |
| "eval_runtime": 35.6064, | |
| "eval_samples_per_second": 49.823, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2196, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.2156, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.2167, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.2168, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2222, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.2207, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8377996929806101, | |
| "eval_loss": 0.5746100544929504, | |
| "eval_precision": 0.8380769040655287, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 35.6046, | |
| "eval_samples_per_second": 49.825, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.2207, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.2121, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.2139, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.2152, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.2125, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.8416009019165727, | |
| "eval_f1": 0.8382661502247386, | |
| "eval_loss": 0.5753834843635559, | |
| "eval_precision": 0.8392997595394867, | |
| "eval_recall": 0.8416009019165727, | |
| "eval_runtime": 35.6117, | |
| "eval_samples_per_second": 49.815, | |
| "eval_steps_per_second": 0.786, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 1860, | |
| "total_flos": 2.70639664915371e+20, | |
| "train_loss": 0.4823262771611573, | |
| "train_runtime": 24536.8963, | |
| "train_samples_per_second": 19.516, | |
| "train_steps_per_second": 0.076 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 2.70639664915371e+20, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |