| { | |
| "best_metric": 0.8613303269447576, | |
| "best_model_checkpoint": "dinov2-small-finetuned-galaxy10-decals/checkpoint-843", | |
| "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": 5.376344086021506e-06, | |
| "loss": 2.4305, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 1.7384, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.279, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.64543404735062, | |
| "eval_f1": 0.6242340263402473, | |
| "eval_loss": 0.9926303625106812, | |
| "eval_precision": 0.6589011432073757, | |
| "eval_recall": 0.64543404735062, | |
| "eval_runtime": 9.3596, | |
| "eval_samples_per_second": 189.538, | |
| "eval_steps_per_second": 1.496, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.0405, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.8614, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.8187, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.7948139797068771, | |
| "eval_f1": 0.7947500876210484, | |
| "eval_loss": 0.601404070854187, | |
| "eval_precision": 0.815133947285654, | |
| "eval_recall": 0.7948139797068771, | |
| "eval_runtime": 9.494, | |
| "eval_samples_per_second": 186.855, | |
| "eval_steps_per_second": 1.475, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.804, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.8018, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.77, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.7818489289740699, | |
| "eval_f1": 0.7777498847922488, | |
| "eval_loss": 0.6322661638259888, | |
| "eval_precision": 0.792845144303136, | |
| "eval_recall": 0.7818489289740699, | |
| "eval_runtime": 9.3073, | |
| "eval_samples_per_second": 190.603, | |
| "eval_steps_per_second": 1.504, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.8237, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.7688, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.6743, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8139797068771139, | |
| "eval_f1": 0.8083410489046907, | |
| "eval_loss": 0.5554975867271423, | |
| "eval_precision": 0.8149070860867645, | |
| "eval_recall": 0.8139797068771139, | |
| "eval_runtime": 9.2832, | |
| "eval_samples_per_second": 191.097, | |
| "eval_steps_per_second": 1.508, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.6708, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.6506, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.6407, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8077790304396844, | |
| "eval_f1": 0.8096290518551817, | |
| "eval_loss": 0.5731789469718933, | |
| "eval_precision": 0.8173808911652968, | |
| "eval_recall": 0.8077790304396844, | |
| "eval_runtime": 10.0887, | |
| "eval_samples_per_second": 175.84, | |
| "eval_steps_per_second": 1.388, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.6176, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.6407, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.64, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.8359639233370914, | |
| "eval_f1": 0.8320665323451614, | |
| "eval_loss": 0.49118176102638245, | |
| "eval_precision": 0.8344483546731383, | |
| "eval_recall": 0.8359639233370914, | |
| "eval_runtime": 9.7793, | |
| "eval_samples_per_second": 181.404, | |
| "eval_steps_per_second": 1.432, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.6076, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.6048, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.5685, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.818489289740699, | |
| "eval_f1": 0.8163008296617178, | |
| "eval_loss": 0.5089312195777893, | |
| "eval_precision": 0.8194969459682901, | |
| "eval_recall": 0.818489289740699, | |
| "eval_runtime": 9.8459, | |
| "eval_samples_per_second": 180.176, | |
| "eval_steps_per_second": 1.422, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.5828, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.5658, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.5621, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.5438, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8320180383314544, | |
| "eval_f1": 0.8293166855099415, | |
| "eval_loss": 0.48060280084609985, | |
| "eval_precision": 0.8324876613114235, | |
| "eval_recall": 0.8320180383314544, | |
| "eval_runtime": 10.2661, | |
| "eval_samples_per_second": 172.802, | |
| "eval_steps_per_second": 1.364, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.5032, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.5369, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.5455, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8406080099403899, | |
| "eval_loss": 0.4780590534210205, | |
| "eval_precision": 0.8442146002171846, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 9.9357, | |
| "eval_samples_per_second": 178.549, | |
| "eval_steps_per_second": 1.409, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.5103, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.5276, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5002, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.8478015783540023, | |
| "eval_f1": 0.8451845858868778, | |
| "eval_loss": 0.44031190872192383, | |
| "eval_precision": 0.8456549868370505, | |
| "eval_recall": 0.8478015783540023, | |
| "eval_runtime": 9.9555, | |
| "eval_samples_per_second": 178.194, | |
| "eval_steps_per_second": 1.406, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.5065, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.5299, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.5003, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.8151071025930101, | |
| "eval_f1": 0.8156343828661431, | |
| "eval_loss": 0.5079108476638794, | |
| "eval_precision": 0.8355471801083442, | |
| "eval_recall": 0.8151071025930101, | |
| "eval_runtime": 9.4315, | |
| "eval_samples_per_second": 188.093, | |
| "eval_steps_per_second": 1.484, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.4944, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.4664, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.4828, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8190529875986471, | |
| "eval_f1": 0.8146851277474468, | |
| "eval_loss": 0.5306578874588013, | |
| "eval_precision": 0.8196844043471049, | |
| "eval_recall": 0.8190529875986471, | |
| "eval_runtime": 9.2903, | |
| "eval_samples_per_second": 190.951, | |
| "eval_steps_per_second": 1.507, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.4653, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.4663, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.4674, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8444193912063134, | |
| "eval_f1": 0.8430917605672317, | |
| "eval_loss": 0.4731869101524353, | |
| "eval_precision": 0.8449597828117058, | |
| "eval_recall": 0.8444193912063134, | |
| "eval_runtime": 9.3676, | |
| "eval_samples_per_second": 189.377, | |
| "eval_steps_per_second": 1.495, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.4459, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.4516, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.4646, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_accuracy": 0.8280721533258174, | |
| "eval_f1": 0.8250541740714602, | |
| "eval_loss": 0.49517446756362915, | |
| "eval_precision": 0.8341535339626841, | |
| "eval_recall": 0.8280721533258174, | |
| "eval_runtime": 9.3472, | |
| "eval_samples_per_second": 189.789, | |
| "eval_steps_per_second": 1.498, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.4704, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.4273, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.4477, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_accuracy": 0.8523111612175873, | |
| "eval_f1": 0.851424593229574, | |
| "eval_loss": 0.46072810888290405, | |
| "eval_precision": 0.8516225149535614, | |
| "eval_recall": 0.8523111612175873, | |
| "eval_runtime": 9.3756, | |
| "eval_samples_per_second": 189.215, | |
| "eval_steps_per_second": 1.493, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.4123, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.3969, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.4122, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.4224, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.850620067643743, | |
| "eval_f1": 0.8494661464143937, | |
| "eval_loss": 0.45143523812294006, | |
| "eval_precision": 0.8515937584391022, | |
| "eval_recall": 0.850620067643743, | |
| "eval_runtime": 9.3567, | |
| "eval_samples_per_second": 189.597, | |
| "eval_steps_per_second": 1.496, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.3961, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.4067, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.3751, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.8471762712292636, | |
| "eval_loss": 0.4664769172668457, | |
| "eval_precision": 0.8480191707831453, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 9.2158, | |
| "eval_samples_per_second": 192.496, | |
| "eval_steps_per_second": 1.519, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.3949, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.4007, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.3874, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_accuracy": 0.8489289740698985, | |
| "eval_f1": 0.8476872697009592, | |
| "eval_loss": 0.4461875259876251, | |
| "eval_precision": 0.8488536060848715, | |
| "eval_recall": 0.8489289740698985, | |
| "eval_runtime": 9.3651, | |
| "eval_samples_per_second": 189.427, | |
| "eval_steps_per_second": 1.495, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.3669, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.3703, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.3675, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.8471316837014181, | |
| "eval_loss": 0.46742817759513855, | |
| "eval_precision": 0.8507897089204829, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 9.3157, | |
| "eval_samples_per_second": 190.43, | |
| "eval_steps_per_second": 1.503, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.363, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.3561, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3434, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8511837655016911, | |
| "eval_f1": 0.8462300511726165, | |
| "eval_loss": 0.4643685519695282, | |
| "eval_precision": 0.8485763166557468, | |
| "eval_recall": 0.8511837655016911, | |
| "eval_runtime": 9.458, | |
| "eval_samples_per_second": 187.567, | |
| "eval_steps_per_second": 1.48, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.3409, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.3309, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.3332, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8556933483652762, | |
| "eval_f1": 0.8525291061586084, | |
| "eval_loss": 0.47109487652778625, | |
| "eval_precision": 0.8548396749990268, | |
| "eval_recall": 0.8556933483652762, | |
| "eval_runtime": 9.4367, | |
| "eval_samples_per_second": 187.99, | |
| "eval_steps_per_second": 1.484, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.3161, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.3126, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.3187, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.8523790763674031, | |
| "eval_loss": 0.4664561152458191, | |
| "eval_precision": 0.8539347187356369, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 9.3613, | |
| "eval_samples_per_second": 189.504, | |
| "eval_steps_per_second": 1.496, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.3295, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.3064, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.3039, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.8438556933483653, | |
| "eval_f1": 0.8423406295566305, | |
| "eval_loss": 0.5015249848365784, | |
| "eval_precision": 0.8427081666869208, | |
| "eval_recall": 0.8438556933483653, | |
| "eval_runtime": 9.3244, | |
| "eval_samples_per_second": 190.253, | |
| "eval_steps_per_second": 1.501, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.3037, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.2933, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.3083, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.282, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8562570462232244, | |
| "eval_f1": 0.8558695619667928, | |
| "eval_loss": 0.4782754182815552, | |
| "eval_precision": 0.856302163200596, | |
| "eval_recall": 0.8562570462232244, | |
| "eval_runtime": 9.4264, | |
| "eval_samples_per_second": 188.195, | |
| "eval_steps_per_second": 1.485, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.2996, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2778, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.2843, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.8513643676170913, | |
| "eval_loss": 0.5064074397087097, | |
| "eval_precision": 0.8518978579098605, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 9.4519, | |
| "eval_samples_per_second": 187.687, | |
| "eval_steps_per_second": 1.481, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2571, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.271, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.2661, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 25.98, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.8459949962688994, | |
| "eval_loss": 0.5021128058433533, | |
| "eval_precision": 0.8476393382479328, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 9.3566, | |
| "eval_samples_per_second": 189.598, | |
| "eval_steps_per_second": 1.496, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.2817, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2615, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.2595, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "eval_accuracy": 0.8613303269447576, | |
| "eval_f1": 0.861465358212238, | |
| "eval_loss": 0.48520544171333313, | |
| "eval_precision": 0.8626143442892683, | |
| "eval_recall": 0.8613303269447576, | |
| "eval_runtime": 9.328, | |
| "eval_samples_per_second": 190.181, | |
| "eval_steps_per_second": 1.501, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.2545, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.2669, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2442, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.8542669512232386, | |
| "eval_loss": 0.49029698967933655, | |
| "eval_precision": 0.8546300815174016, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 9.4608, | |
| "eval_samples_per_second": 187.51, | |
| "eval_steps_per_second": 1.48, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.2568, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.2445, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.2477, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8585118376550169, | |
| "eval_f1": 0.8569651539184984, | |
| "eval_loss": 0.4780934751033783, | |
| "eval_precision": 0.8569316478704299, | |
| "eval_recall": 0.8585118376550169, | |
| "eval_runtime": 9.4954, | |
| "eval_samples_per_second": 186.827, | |
| "eval_steps_per_second": 1.474, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.2435, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.2307, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.2437, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.8585118376550169, | |
| "eval_f1": 0.8577007947643565, | |
| "eval_loss": 0.47721412777900696, | |
| "eval_precision": 0.8579618397115243, | |
| "eval_recall": 0.8585118376550169, | |
| "eval_runtime": 9.6381, | |
| "eval_samples_per_second": 184.062, | |
| "eval_steps_per_second": 1.453, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 930, | |
| "total_flos": 1.2364841575625785e+19, | |
| "train_loss": 0.49311745294960596, | |
| "train_runtime": 4214.8321, | |
| "train_samples_per_second": 113.613, | |
| "train_steps_per_second": 0.221 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 930, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.2364841575625785e+19, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |