| { |
| "best_metric": 0.9928844151336341, |
| "best_model_checkpoint": "vit-base-aihub_model/checkpoint-505", |
| "epoch": 4.975369458128079, |
| "global_step": 505, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "learning_rate": 9.803921568627451e-06, |
| "loss": 1.7678, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 1.9607843137254903e-05, |
| "loss": 1.6588, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 2.9411764705882354e-05, |
| "loss": 1.4279, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 3.9215686274509805e-05, |
| "loss": 1.1053, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 4.901960784313725e-05, |
| "loss": 0.7867, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 4.900881057268723e-05, |
| "loss": 0.5811, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 4.790748898678414e-05, |
| "loss": 0.4555, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 4.680616740088106e-05, |
| "loss": 0.3709, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 4.5704845814977974e-05, |
| "loss": 0.3156, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 4.46035242290749e-05, |
| "loss": 0.2905, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9651162790697675, |
| "eval_loss": 0.24726606905460358, |
| "eval_runtime": 78.0378, |
| "eval_samples_per_second": 73.836, |
| "eval_steps_per_second": 0.589, |
| "step": 101 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 4.3502202643171806e-05, |
| "loss": 0.268, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 4.240088105726873e-05, |
| "loss": 0.2355, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 4.129955947136564e-05, |
| "loss": 0.2228, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 4.019823788546256e-05, |
| "loss": 0.2134, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 3.909691629955947e-05, |
| "loss": 0.1868, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 3.799559471365639e-05, |
| "loss": 0.1681, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 3.689427312775331e-05, |
| "loss": 0.1641, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 3.579295154185022e-05, |
| "loss": 0.1532, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 3.469162995594714e-05, |
| "loss": 0.1507, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 3.3590308370044054e-05, |
| "loss": 0.1456, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9807358556056924, |
| "eval_loss": 0.1328154057264328, |
| "eval_runtime": 77.2608, |
| "eval_samples_per_second": 74.579, |
| "eval_steps_per_second": 0.595, |
| "step": 203 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 3.2488986784140976e-05, |
| "loss": 0.1406, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 3.1387665198237885e-05, |
| "loss": 0.1294, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 3.0286343612334804e-05, |
| "loss": 0.1316, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 2.918502202643172e-05, |
| "loss": 0.1237, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 2.8083700440528636e-05, |
| "loss": 0.1172, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 2.698237885462555e-05, |
| "loss": 0.1196, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 2.588105726872247e-05, |
| "loss": 0.1054, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 2.4779735682819386e-05, |
| "loss": 0.109, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 2.3678414096916302e-05, |
| "loss": 0.0986, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 2.2577092511013218e-05, |
| "loss": 0.1013, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9925373134328358, |
| "eval_loss": 0.08586321026086807, |
| "eval_runtime": 76.4972, |
| "eval_samples_per_second": 75.323, |
| "eval_steps_per_second": 0.601, |
| "step": 304 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 2.1475770925110134e-05, |
| "loss": 0.104, |
| "step": 310 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 2.037444933920705e-05, |
| "loss": 0.0937, |
| "step": 320 |
| }, |
| { |
| "epoch": 3.25, |
| "learning_rate": 1.9273127753303965e-05, |
| "loss": 0.0963, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.35, |
| "learning_rate": 1.817180616740088e-05, |
| "loss": 0.0937, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.45, |
| "learning_rate": 1.7070484581497796e-05, |
| "loss": 0.0886, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 1.5969162995594712e-05, |
| "loss": 0.0889, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.65, |
| "learning_rate": 1.486784140969163e-05, |
| "loss": 0.0788, |
| "step": 370 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 1.3766519823788545e-05, |
| "loss": 0.0845, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 1.2665198237885464e-05, |
| "loss": 0.084, |
| "step": 390 |
| }, |
| { |
| "epoch": 3.94, |
| "learning_rate": 1.1563876651982378e-05, |
| "loss": 0.0754, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.990628254078445, |
| "eval_loss": 0.0793519839644432, |
| "eval_runtime": 74.187, |
| "eval_samples_per_second": 77.669, |
| "eval_steps_per_second": 0.62, |
| "step": 406 |
| }, |
| { |
| "epoch": 4.04, |
| "learning_rate": 1.0462555066079296e-05, |
| "loss": 0.085, |
| "step": 410 |
| }, |
| { |
| "epoch": 4.14, |
| "learning_rate": 9.361233480176213e-06, |
| "loss": 0.0793, |
| "step": 420 |
| }, |
| { |
| "epoch": 4.24, |
| "learning_rate": 8.259911894273129e-06, |
| "loss": 0.0826, |
| "step": 430 |
| }, |
| { |
| "epoch": 4.33, |
| "learning_rate": 7.1585903083700445e-06, |
| "loss": 0.0813, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.43, |
| "learning_rate": 6.05726872246696e-06, |
| "loss": 0.0791, |
| "step": 450 |
| }, |
| { |
| "epoch": 4.53, |
| "learning_rate": 4.955947136563877e-06, |
| "loss": 0.0744, |
| "step": 460 |
| }, |
| { |
| "epoch": 4.63, |
| "learning_rate": 3.854625550660793e-06, |
| "loss": 0.0752, |
| "step": 470 |
| }, |
| { |
| "epoch": 4.73, |
| "learning_rate": 2.7533039647577095e-06, |
| "loss": 0.0756, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.83, |
| "learning_rate": 1.6519823788546256e-06, |
| "loss": 0.076, |
| "step": 490 |
| }, |
| { |
| "epoch": 4.93, |
| "learning_rate": 5.506607929515419e-07, |
| "loss": 0.0721, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.98, |
| "eval_accuracy": 0.9928844151336341, |
| "eval_loss": 0.06965512782335281, |
| "eval_runtime": 73.5675, |
| "eval_samples_per_second": 78.323, |
| "eval_steps_per_second": 0.625, |
| "step": 505 |
| }, |
| { |
| "epoch": 4.98, |
| "step": 505, |
| "total_flos": 2.0000469621477704e+19, |
| "train_loss": 0.2682455536162499, |
| "train_runtime": 3849.7558, |
| "train_samples_per_second": 67.342, |
| "train_steps_per_second": 0.131 |
| } |
| ], |
| "max_steps": 505, |
| "num_train_epochs": 5, |
| "total_flos": 2.0000469621477704e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
