| { | |
| "best_metric": 0.8382187147688839, | |
| "best_model_checkpoint": "vit-large-patch32-224-in21k-finetuned-galaxy10-decals/checkpoint-343", | |
| "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": 2.3005, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 2.1598, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.8923, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.4599774520856821, | |
| "eval_f1": 0.36818539105134135, | |
| "eval_loss": 1.6724576950073242, | |
| "eval_precision": 0.5537412962661489, | |
| "eval_recall": 0.4599774520856821, | |
| "eval_runtime": 13.908, | |
| "eval_samples_per_second": 127.553, | |
| "eval_steps_per_second": 1.007, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 1.6252, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 1.374, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 1.1787, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.733934611048478, | |
| "eval_f1": 0.7095413298923192, | |
| "eval_loss": 0.9948903918266296, | |
| "eval_precision": 0.7513280698764072, | |
| "eval_recall": 0.733934611048478, | |
| "eval_runtime": 13.6836, | |
| "eval_samples_per_second": 129.644, | |
| "eval_steps_per_second": 1.023, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 1.0564, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.9695, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.9165, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.770011273957159, | |
| "eval_f1": 0.7540108447224593, | |
| "eval_loss": 0.7946078181266785, | |
| "eval_precision": 0.7694119599791991, | |
| "eval_recall": 0.770011273957159, | |
| "eval_runtime": 13.9239, | |
| "eval_samples_per_second": 127.407, | |
| "eval_steps_per_second": 1.005, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.916367980884111e-05, | |
| "loss": 0.8982, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.79689366786141e-05, | |
| "loss": 0.8313, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.802, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7948139797068771, | |
| "eval_f1": 0.7843494012602573, | |
| "eval_loss": 0.6747179627418518, | |
| "eval_precision": 0.795387126369686, | |
| "eval_recall": 0.7948139797068771, | |
| "eval_runtime": 14.1264, | |
| "eval_samples_per_second": 125.581, | |
| "eval_steps_per_second": 0.991, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.55794504181601e-05, | |
| "loss": 0.7681, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.438470728793309e-05, | |
| "loss": 0.7362, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.31899641577061e-05, | |
| "loss": 0.7074, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8117249154453213, | |
| "eval_f1": 0.8115345249432343, | |
| "eval_loss": 0.6196042895317078, | |
| "eval_precision": 0.8139405296667617, | |
| "eval_recall": 0.8117249154453213, | |
| "eval_runtime": 13.922, | |
| "eval_samples_per_second": 127.424, | |
| "eval_steps_per_second": 1.006, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 9.199522102747909e-05, | |
| "loss": 0.6855, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 9.080047789725208e-05, | |
| "loss": 0.6881, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.960573476702509e-05, | |
| "loss": 0.6424, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.8021420518602029, | |
| "eval_f1": 0.7961437261818466, | |
| "eval_loss": 0.6204531192779541, | |
| "eval_precision": 0.8074926673896575, | |
| "eval_recall": 0.8021420518602029, | |
| "eval_runtime": 13.7635, | |
| "eval_samples_per_second": 128.891, | |
| "eval_steps_per_second": 1.017, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.84109916367981e-05, | |
| "loss": 0.6484, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 8.72162485065711e-05, | |
| "loss": 0.624, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.6309, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.8117249154453213, | |
| "eval_f1": 0.8127171755353659, | |
| "eval_loss": 0.5759598016738892, | |
| "eval_precision": 0.8230864221733758, | |
| "eval_recall": 0.8117249154453213, | |
| "eval_runtime": 13.9932, | |
| "eval_samples_per_second": 126.776, | |
| "eval_steps_per_second": 1.0, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 8.482676224611709e-05, | |
| "loss": 0.6485, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 8.363201911589009e-05, | |
| "loss": 0.622, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 8.243727598566309e-05, | |
| "loss": 0.6082, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.124253285543608e-05, | |
| "loss": 0.5682, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8151071025930101, | |
| "eval_f1": 0.815748718679729, | |
| "eval_loss": 0.5748494863510132, | |
| "eval_precision": 0.819638540013667, | |
| "eval_recall": 0.8151071025930101, | |
| "eval_runtime": 13.7341, | |
| "eval_samples_per_second": 129.168, | |
| "eval_steps_per_second": 1.019, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.004778972520908e-05, | |
| "loss": 0.5578, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.885304659498209e-05, | |
| "loss": 0.5808, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 7.765830346475508e-05, | |
| "loss": 0.5981, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8213077790304397, | |
| "eval_f1": 0.8157691286644828, | |
| "eval_loss": 0.5704066157341003, | |
| "eval_precision": 0.8268776889509669, | |
| "eval_recall": 0.8213077790304397, | |
| "eval_runtime": 14.3553, | |
| "eval_samples_per_second": 123.578, | |
| "eval_steps_per_second": 0.975, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.646356033452809e-05, | |
| "loss": 0.5581, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.5585, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.547, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.8376550169109357, | |
| "eval_f1": 0.8344504939462281, | |
| "eval_loss": 0.5282090902328491, | |
| "eval_precision": 0.8352471416146373, | |
| "eval_recall": 0.8376550169109357, | |
| "eval_runtime": 13.9665, | |
| "eval_samples_per_second": 127.018, | |
| "eval_steps_per_second": 1.002, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 7.287933094384708e-05, | |
| "loss": 0.5197, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 7.168458781362007e-05, | |
| "loss": 0.5413, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 7.048984468339306e-05, | |
| "loss": 0.5067, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.8382187147688839, | |
| "eval_f1": 0.8355644052274377, | |
| "eval_loss": 0.5280851721763611, | |
| "eval_precision": 0.8371941971933433, | |
| "eval_recall": 0.8382187147688839, | |
| "eval_runtime": 13.8989, | |
| "eval_samples_per_second": 127.636, | |
| "eval_steps_per_second": 1.007, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 6.929510155316607e-05, | |
| "loss": 0.4844, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.810035842293908e-05, | |
| "loss": 0.4829, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 6.690561529271207e-05, | |
| "loss": 0.5066, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8246899661781285, | |
| "eval_f1": 0.82193071428432, | |
| "eval_loss": 0.5440835952758789, | |
| "eval_precision": 0.8285928304505648, | |
| "eval_recall": 0.8246899661781285, | |
| "eval_runtime": 14.0682, | |
| "eval_samples_per_second": 126.1, | |
| "eval_steps_per_second": 0.995, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 6.571087216248507e-05, | |
| "loss": 0.4778, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.4653, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 6.332138590203107e-05, | |
| "loss": 0.4919, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8156708004509583, | |
| "eval_f1": 0.8155334582595456, | |
| "eval_loss": 0.5579707026481628, | |
| "eval_precision": 0.8235518646692552, | |
| "eval_recall": 0.8156708004509583, | |
| "eval_runtime": 13.6039, | |
| "eval_samples_per_second": 130.404, | |
| "eval_steps_per_second": 1.029, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 6.212664277180407e-05, | |
| "loss": 0.4659, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 6.093189964157706e-05, | |
| "loss": 0.4625, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 5.9737156511350064e-05, | |
| "loss": 0.4508, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_accuracy": 0.8303269447576099, | |
| "eval_f1": 0.8279428714077549, | |
| "eval_loss": 0.526913046836853, | |
| "eval_precision": 0.8330911890059709, | |
| "eval_recall": 0.8303269447576099, | |
| "eval_runtime": 14.1136, | |
| "eval_samples_per_second": 125.695, | |
| "eval_steps_per_second": 0.992, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 5.8542413381123063e-05, | |
| "loss": 0.4588, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 5.7347670250896056e-05, | |
| "loss": 0.4312, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 5.615292712066906e-05, | |
| "loss": 0.4415, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_accuracy": 0.818489289740699, | |
| "eval_f1": 0.8203104704622532, | |
| "eval_loss": 0.5398772954940796, | |
| "eval_precision": 0.824911350006833, | |
| "eval_recall": 0.818489289740699, | |
| "eval_runtime": 14.3225, | |
| "eval_samples_per_second": 123.861, | |
| "eval_steps_per_second": 0.977, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.495818399044206e-05, | |
| "loss": 0.4234, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.4074, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 5.256869772998806e-05, | |
| "loss": 0.409, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.137395459976105e-05, | |
| "loss": 0.4178, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8320180383314544, | |
| "eval_f1": 0.8300827004836914, | |
| "eval_loss": 0.5229005813598633, | |
| "eval_precision": 0.8357823255635188, | |
| "eval_recall": 0.8320180383314544, | |
| "eval_runtime": 14.0799, | |
| "eval_samples_per_second": 125.995, | |
| "eval_steps_per_second": 0.994, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 5.017921146953405e-05, | |
| "loss": 0.3928, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.4174, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.366, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8275084554678692, | |
| "eval_f1": 0.8240548194511355, | |
| "eval_loss": 0.5427183508872986, | |
| "eval_precision": 0.828135455879007, | |
| "eval_recall": 0.8275084554678692, | |
| "eval_runtime": 13.7519, | |
| "eval_samples_per_second": 129.0, | |
| "eval_steps_per_second": 1.018, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.3746, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.3956, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.3706, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_accuracy": 0.8241262683201804, | |
| "eval_f1": 0.8229564605373075, | |
| "eval_loss": 0.5389071702957153, | |
| "eval_precision": 0.8242056890621828, | |
| "eval_recall": 0.8241262683201804, | |
| "eval_runtime": 13.7189, | |
| "eval_samples_per_second": 129.31, | |
| "eval_steps_per_second": 1.02, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.3715, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.3419, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.3609, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "eval_accuracy": 0.8246899661781285, | |
| "eval_f1": 0.8238722113026624, | |
| "eval_loss": 0.5573083758354187, | |
| "eval_precision": 0.8261543816529526, | |
| "eval_recall": 0.8246899661781285, | |
| "eval_runtime": 13.8749, | |
| "eval_samples_per_second": 127.857, | |
| "eval_steps_per_second": 1.009, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.3694, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.3574, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3443, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8320180383314544, | |
| "eval_f1": 0.8302429910863938, | |
| "eval_loss": 0.5605015754699707, | |
| "eval_precision": 0.8325444592064266, | |
| "eval_recall": 0.8320180383314544, | |
| "eval_runtime": 13.8905, | |
| "eval_samples_per_second": 127.713, | |
| "eval_steps_per_second": 1.008, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.3302, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.3309, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.3214, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8280721533258174, | |
| "eval_f1": 0.8254240015965836, | |
| "eval_loss": 0.5667029619216919, | |
| "eval_precision": 0.8295428318312357, | |
| "eval_recall": 0.8280721533258174, | |
| "eval_runtime": 14.1177, | |
| "eval_samples_per_second": 125.658, | |
| "eval_steps_per_second": 0.992, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.3121, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.3157, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.3262, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_accuracy": 0.8235625704622322, | |
| "eval_f1": 0.8214055556480262, | |
| "eval_loss": 0.579714298248291, | |
| "eval_precision": 0.8237105353518115, | |
| "eval_recall": 0.8235625704622322, | |
| "eval_runtime": 13.8715, | |
| "eval_samples_per_second": 127.888, | |
| "eval_steps_per_second": 1.009, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.3185, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.3017, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.299, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.8201803833145435, | |
| "eval_f1": 0.819536745894237, | |
| "eval_loss": 0.5938186645507812, | |
| "eval_precision": 0.8225417256475036, | |
| "eval_recall": 0.8201803833145435, | |
| "eval_runtime": 14.0359, | |
| "eval_samples_per_second": 126.39, | |
| "eval_steps_per_second": 0.997, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.3023, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.2978, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.3062, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.2792, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8275084554678692, | |
| "eval_f1": 0.8251168354340412, | |
| "eval_loss": 0.5909499526023865, | |
| "eval_precision": 0.8258356043850564, | |
| "eval_recall": 0.8275084554678692, | |
| "eval_runtime": 13.9981, | |
| "eval_samples_per_second": 126.731, | |
| "eval_steps_per_second": 1.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.3042, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.2904, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.2969, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.830890642615558, | |
| "eval_f1": 0.8306159214761004, | |
| "eval_loss": 0.5657971501350403, | |
| "eval_precision": 0.8319469060175432, | |
| "eval_recall": 0.830890642615558, | |
| "eval_runtime": 14.1611, | |
| "eval_samples_per_second": 125.273, | |
| "eval_steps_per_second": 0.989, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.2692, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.2793, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.2559, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 25.98, | |
| "eval_accuracy": 0.830890642615558, | |
| "eval_f1": 0.8293693314290957, | |
| "eval_loss": 0.5936293601989746, | |
| "eval_precision": 0.8294137513471009, | |
| "eval_recall": 0.830890642615558, | |
| "eval_runtime": 14.2541, | |
| "eval_samples_per_second": 124.456, | |
| "eval_steps_per_second": 0.982, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.2791, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.2716, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2756, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "eval_accuracy": 0.8291995490417137, | |
| "eval_f1": 0.8286998803671861, | |
| "eval_loss": 0.5898094177246094, | |
| "eval_precision": 0.8294813897487977, | |
| "eval_recall": 0.8291995490417137, | |
| "eval_runtime": 14.0481, | |
| "eval_samples_per_second": 126.28, | |
| "eval_steps_per_second": 0.997, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2711, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2746, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.254, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8303269447576099, | |
| "eval_f1": 0.8288956275009821, | |
| "eval_loss": 0.6043339967727661, | |
| "eval_precision": 0.8319314565453743, | |
| "eval_recall": 0.8303269447576099, | |
| "eval_runtime": 14.06, | |
| "eval_samples_per_second": 126.173, | |
| "eval_steps_per_second": 0.996, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2682, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.2572, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2674, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8370913190529876, | |
| "eval_f1": 0.8352849737173643, | |
| "eval_loss": 0.5950246453285217, | |
| "eval_precision": 0.836485810805898, | |
| "eval_recall": 0.8370913190529876, | |
| "eval_runtime": 14.0119, | |
| "eval_samples_per_second": 126.607, | |
| "eval_steps_per_second": 0.999, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.2611, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.2527, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.2432, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.8359639233370914, | |
| "eval_f1": 0.8344836129088197, | |
| "eval_loss": 0.5906554460525513, | |
| "eval_precision": 0.8348369465962998, | |
| "eval_recall": 0.8359639233370914, | |
| "eval_runtime": 13.9075, | |
| "eval_samples_per_second": 127.557, | |
| "eval_steps_per_second": 1.007, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 930, | |
| "total_flos": 1.310858296646362e+20, | |
| "train_loss": 0.5398157842697636, | |
| "train_runtime": 7078.6752, | |
| "train_samples_per_second": 67.648, | |
| "train_steps_per_second": 0.131 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 930, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.310858296646362e+20, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |