| { | |
| "best_metric": 0.8421645997745209, | |
| "best_model_checkpoint": "vit-base-patch32-224-in21k-finetuned-galaxy10-decals/checkpoint-781", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 930, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.312, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 2.2482, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 2.0954, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.3737316798196167, | |
| "eval_f1": 0.24518346206137118, | |
| "eval_loss": 1.9513884782791138, | |
| "eval_precision": 0.33217237543670486, | |
| "eval_recall": 0.3737316798196167, | |
| "eval_runtime": 11.6797, | |
| "eval_samples_per_second": 151.888, | |
| "eval_steps_per_second": 1.199, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 1.8937, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 1.6741, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 1.4835, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.6183765501691093, | |
| "eval_f1": 0.5877526291997739, | |
| "eval_loss": 1.3283952474594116, | |
| "eval_precision": 0.6016136630730339, | |
| "eval_recall": 0.6183765501691093, | |
| "eval_runtime": 11.9142, | |
| "eval_samples_per_second": 148.898, | |
| "eval_steps_per_second": 1.175, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 1.3361, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 1.2168, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 1.1252, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.729988726042841, | |
| "eval_f1": 0.7004267340414606, | |
| "eval_loss": 0.9771297574043274, | |
| "eval_precision": 0.740029090489535, | |
| "eval_recall": 0.729988726042841, | |
| "eval_runtime": 11.8273, | |
| "eval_samples_per_second": 149.992, | |
| "eval_steps_per_second": 1.184, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.916367980884111e-05, | |
| "loss": 1.0518, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.79689366786141e-05, | |
| "loss": 0.9865, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.9605, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7570462232243518, | |
| "eval_f1": 0.7367554560091125, | |
| "eval_loss": 0.8374465107917786, | |
| "eval_precision": 0.775445254215589, | |
| "eval_recall": 0.7570462232243518, | |
| "eval_runtime": 11.8347, | |
| "eval_samples_per_second": 149.898, | |
| "eval_steps_per_second": 1.183, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.55794504181601e-05, | |
| "loss": 0.9104, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.438470728793309e-05, | |
| "loss": 0.8842, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.31899641577061e-05, | |
| "loss": 0.8383, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.7762119503945885, | |
| "eval_f1": 0.7650286718629015, | |
| "eval_loss": 0.7286148071289062, | |
| "eval_precision": 0.77283312178642, | |
| "eval_recall": 0.7762119503945885, | |
| "eval_runtime": 11.7968, | |
| "eval_samples_per_second": 150.38, | |
| "eval_steps_per_second": 1.187, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 9.199522102747909e-05, | |
| "loss": 0.8079, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 9.080047789725208e-05, | |
| "loss": 0.8107, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.960573476702509e-05, | |
| "loss": 0.7665, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.7688838782412627, | |
| "eval_f1": 0.7586283350957846, | |
| "eval_loss": 0.7256137132644653, | |
| "eval_precision": 0.768272922111939, | |
| "eval_recall": 0.7688838782412627, | |
| "eval_runtime": 12.2433, | |
| "eval_samples_per_second": 144.895, | |
| "eval_steps_per_second": 1.143, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.84109916367981e-05, | |
| "loss": 0.7766, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 8.72162485065711e-05, | |
| "loss": 0.7248, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.7305, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.7948139797068771, | |
| "eval_f1": 0.7965809387491306, | |
| "eval_loss": 0.6639725565910339, | |
| "eval_precision": 0.803143252037919, | |
| "eval_recall": 0.7948139797068771, | |
| "eval_runtime": 11.7905, | |
| "eval_samples_per_second": 150.46, | |
| "eval_steps_per_second": 1.187, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 8.482676224611709e-05, | |
| "loss": 0.7502, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 8.363201911589009e-05, | |
| "loss": 0.7204, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 8.243727598566309e-05, | |
| "loss": 0.7109, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.124253285543608e-05, | |
| "loss": 0.6689, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7807215332581736, | |
| "eval_f1": 0.7708028159706269, | |
| "eval_loss": 0.6792281270027161, | |
| "eval_precision": 0.7859204813520014, | |
| "eval_recall": 0.7807215332581736, | |
| "eval_runtime": 11.6775, | |
| "eval_samples_per_second": 151.916, | |
| "eval_steps_per_second": 1.199, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.004778972520908e-05, | |
| "loss": 0.6615, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.885304659498209e-05, | |
| "loss": 0.69, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 7.765830346475508e-05, | |
| "loss": 0.6783, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8117249154453213, | |
| "eval_f1": 0.8071494978726911, | |
| "eval_loss": 0.5985357761383057, | |
| "eval_precision": 0.8076422700121768, | |
| "eval_recall": 0.8117249154453213, | |
| "eval_runtime": 11.8074, | |
| "eval_samples_per_second": 150.245, | |
| "eval_steps_per_second": 1.186, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.646356033452809e-05, | |
| "loss": 0.6543, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.6445, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.6225, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.8049605411499436, | |
| "eval_f1": 0.8025329833326958, | |
| "eval_loss": 0.6117879748344421, | |
| "eval_precision": 0.8036366262553031, | |
| "eval_recall": 0.8049605411499436, | |
| "eval_runtime": 11.913, | |
| "eval_samples_per_second": 148.913, | |
| "eval_steps_per_second": 1.175, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 7.287933094384708e-05, | |
| "loss": 0.6196, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 7.168458781362007e-05, | |
| "loss": 0.6364, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 7.048984468339306e-05, | |
| "loss": 0.6081, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.8111612175873731, | |
| "eval_f1": 0.8080221876099083, | |
| "eval_loss": 0.5966309905052185, | |
| "eval_precision": 0.8107688170503072, | |
| "eval_recall": 0.8111612175873731, | |
| "eval_runtime": 12.0921, | |
| "eval_samples_per_second": 146.708, | |
| "eval_steps_per_second": 1.158, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 6.929510155316607e-05, | |
| "loss": 0.5842, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.810035842293908e-05, | |
| "loss": 0.5863, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 6.690561529271207e-05, | |
| "loss": 0.6028, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8201803833145435, | |
| "eval_f1": 0.8199066022930014, | |
| "eval_loss": 0.5707828402519226, | |
| "eval_precision": 0.8238548644279975, | |
| "eval_recall": 0.8201803833145435, | |
| "eval_runtime": 11.8231, | |
| "eval_samples_per_second": 150.045, | |
| "eval_steps_per_second": 1.184, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 6.571087216248507e-05, | |
| "loss": 0.5751, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.5591, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 6.332138590203107e-05, | |
| "loss": 0.6052, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8010146561443067, | |
| "eval_f1": 0.7982157638887677, | |
| "eval_loss": 0.6035460233688354, | |
| "eval_precision": 0.8116248197004097, | |
| "eval_recall": 0.8010146561443067, | |
| "eval_runtime": 12.1153, | |
| "eval_samples_per_second": 146.426, | |
| "eval_steps_per_second": 1.156, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 6.212664277180407e-05, | |
| "loss": 0.5725, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 6.093189964157706e-05, | |
| "loss": 0.5736, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 5.9737156511350064e-05, | |
| "loss": 0.5553, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_accuracy": 0.8196166854565953, | |
| "eval_f1": 0.8142886549837638, | |
| "eval_loss": 0.5542031526565552, | |
| "eval_precision": 0.8199332652085517, | |
| "eval_recall": 0.8196166854565953, | |
| "eval_runtime": 11.9012, | |
| "eval_samples_per_second": 149.061, | |
| "eval_steps_per_second": 1.176, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 5.8542413381123063e-05, | |
| "loss": 0.5613, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 5.7347670250896056e-05, | |
| "loss": 0.5361, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 5.615292712066906e-05, | |
| "loss": 0.5526, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_accuracy": 0.8325817361894025, | |
| "eval_f1": 0.8317325308279557, | |
| "eval_loss": 0.5384666919708252, | |
| "eval_precision": 0.8346296777333253, | |
| "eval_recall": 0.8325817361894025, | |
| "eval_runtime": 11.7826, | |
| "eval_samples_per_second": 150.561, | |
| "eval_steps_per_second": 1.188, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.495818399044206e-05, | |
| "loss": 0.5279, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.514, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 5.256869772998806e-05, | |
| "loss": 0.5313, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.137395459976105e-05, | |
| "loss": 0.5199, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8218714768883878, | |
| "eval_f1": 0.8172075357575121, | |
| "eval_loss": 0.5298073887825012, | |
| "eval_precision": 0.8191892050396907, | |
| "eval_recall": 0.8218714768883878, | |
| "eval_runtime": 11.8247, | |
| "eval_samples_per_second": 150.025, | |
| "eval_steps_per_second": 1.184, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 5.017921146953405e-05, | |
| "loss": 0.5081, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.5218, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.4974, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8297632468996617, | |
| "eval_f1": 0.8260300771536644, | |
| "eval_loss": 0.5291145443916321, | |
| "eval_precision": 0.8305613673782328, | |
| "eval_recall": 0.8297632468996617, | |
| "eval_runtime": 11.8235, | |
| "eval_samples_per_second": 150.04, | |
| "eval_steps_per_second": 1.184, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.4926, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.5213, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.5015, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_accuracy": 0.8275084554678692, | |
| "eval_f1": 0.826689249379074, | |
| "eval_loss": 0.5244095921516418, | |
| "eval_precision": 0.8280270614696695, | |
| "eval_recall": 0.8275084554678692, | |
| "eval_runtime": 12.0466, | |
| "eval_samples_per_second": 147.262, | |
| "eval_steps_per_second": 1.162, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.487, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.4687, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.4763, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "eval_accuracy": 0.8354002254791432, | |
| "eval_f1": 0.8315969202435224, | |
| "eval_loss": 0.519017219543457, | |
| "eval_precision": 0.8357436218505646, | |
| "eval_recall": 0.8354002254791432, | |
| "eval_runtime": 11.8194, | |
| "eval_samples_per_second": 150.092, | |
| "eval_steps_per_second": 1.184, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.4702, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.4703, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4763, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.826381059751973, | |
| "eval_f1": 0.8249118845771362, | |
| "eval_loss": 0.524064302444458, | |
| "eval_precision": 0.8286104751372974, | |
| "eval_recall": 0.826381059751973, | |
| "eval_runtime": 11.8016, | |
| "eval_samples_per_second": 150.319, | |
| "eval_steps_per_second": 1.186, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.4545, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.4579, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.4592, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8406452914994846, | |
| "eval_loss": 0.5060973763465881, | |
| "eval_precision": 0.8438563418236732, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 11.7152, | |
| "eval_samples_per_second": 151.427, | |
| "eval_steps_per_second": 1.195, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.4344, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.4301, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.4414, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_accuracy": 0.826944757609921, | |
| "eval_f1": 0.8260337661767315, | |
| "eval_loss": 0.520653486251831, | |
| "eval_precision": 0.8265185500559458, | |
| "eval_recall": 0.826944757609921, | |
| "eval_runtime": 11.75, | |
| "eval_samples_per_second": 150.979, | |
| "eval_steps_per_second": 1.191, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.4465, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.4267, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.4372, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.8252536640360767, | |
| "eval_f1": 0.8254411081851928, | |
| "eval_loss": 0.5342437028884888, | |
| "eval_precision": 0.8283187021046747, | |
| "eval_recall": 0.8252536640360767, | |
| "eval_runtime": 11.8003, | |
| "eval_samples_per_second": 150.335, | |
| "eval_steps_per_second": 1.186, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.4433, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.4252, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.4321, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.4118, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8275084554678692, | |
| "eval_f1": 0.8274415103844889, | |
| "eval_loss": 0.52556973695755, | |
| "eval_precision": 0.82908708235406, | |
| "eval_recall": 0.8275084554678692, | |
| "eval_runtime": 11.9952, | |
| "eval_samples_per_second": 147.892, | |
| "eval_steps_per_second": 1.167, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.4362, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.4084, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.4319, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8421645997745209, | |
| "eval_f1": 0.8406253679527831, | |
| "eval_loss": 0.5055125951766968, | |
| "eval_precision": 0.8413396884147756, | |
| "eval_recall": 0.8421645997745209, | |
| "eval_runtime": 11.8832, | |
| "eval_samples_per_second": 149.286, | |
| "eval_steps_per_second": 1.178, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.4063, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.4112, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.3807, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 25.98, | |
| "eval_accuracy": 0.8376550169109357, | |
| "eval_f1": 0.8361089062252794, | |
| "eval_loss": 0.5187022089958191, | |
| "eval_precision": 0.8374899987391139, | |
| "eval_recall": 0.8376550169109357, | |
| "eval_runtime": 11.7831, | |
| "eval_samples_per_second": 150.554, | |
| "eval_steps_per_second": 1.188, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.4088, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.4019, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.4066, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "eval_accuracy": 0.8348365276211951, | |
| "eval_f1": 0.8326230667681819, | |
| "eval_loss": 0.5202544331550598, | |
| "eval_precision": 0.8332997037515752, | |
| "eval_recall": 0.8348365276211951, | |
| "eval_runtime": 12.0958, | |
| "eval_samples_per_second": 146.663, | |
| "eval_steps_per_second": 1.157, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.4049, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.3954, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.376, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8365276211950394, | |
| "eval_f1": 0.8348349027674612, | |
| "eval_loss": 0.5127692222595215, | |
| "eval_precision": 0.8361471148547891, | |
| "eval_recall": 0.8365276211950394, | |
| "eval_runtime": 11.7924, | |
| "eval_samples_per_second": 150.435, | |
| "eval_steps_per_second": 1.187, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.4072, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.3939, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.3992, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8376550169109357, | |
| "eval_f1": 0.8363666367912383, | |
| "eval_loss": 0.5108409523963928, | |
| "eval_precision": 0.8375235626831261, | |
| "eval_recall": 0.8376550169109357, | |
| "eval_runtime": 11.7866, | |
| "eval_samples_per_second": 150.51, | |
| "eval_steps_per_second": 1.188, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.3957, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.3677, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.3743, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.8387824126268321, | |
| "eval_f1": 0.8378229587958315, | |
| "eval_loss": 0.508699357509613, | |
| "eval_precision": 0.8388749603154989, | |
| "eval_recall": 0.8387824126268321, | |
| "eval_runtime": 11.7925, | |
| "eval_samples_per_second": 150.435, | |
| "eval_steps_per_second": 1.187, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 930, | |
| "total_flos": 3.752659499534114e+19, | |
| "train_loss": 0.6672555587624991, | |
| "train_runtime": 4353.9594, | |
| "train_samples_per_second": 109.983, | |
| "train_steps_per_second": 0.214 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 930, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 3.752659499534114e+19, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |