{ "best_metric": 0.9555555555555556, "best_model_checkpoint": "delivery_truck_classification/checkpoint-27", "epoch": 39.92307692307692, "global_step": 120, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.92, "eval_accuracy": 0.9111111111111111, "eval_loss": 0.3269350230693817, "eval_runtime": 3.0493, "eval_samples_per_second": 14.757, "eval_steps_per_second": 0.656, "step": 3 }, { "epoch": 1.92, "eval_accuracy": 0.9333333333333333, "eval_loss": 0.28137677907943726, "eval_runtime": 3.5544, "eval_samples_per_second": 12.66, "eval_steps_per_second": 0.563, "step": 6 }, { "epoch": 2.92, "eval_accuracy": 0.9333333333333333, "eval_loss": 0.26246681809425354, "eval_runtime": 3.3113, "eval_samples_per_second": 13.59, "eval_steps_per_second": 0.604, "step": 9 }, { "epoch": 3.92, "eval_accuracy": 0.9333333333333333, "eval_loss": 0.2771083414554596, "eval_runtime": 2.9987, "eval_samples_per_second": 15.006, "eval_steps_per_second": 0.667, "step": 12 }, { "epoch": 4.92, "eval_accuracy": 0.9333333333333333, "eval_loss": 0.24194401502609253, "eval_runtime": 3.2862, "eval_samples_per_second": 13.694, "eval_steps_per_second": 0.609, "step": 15 }, { "epoch": 5.92, "eval_accuracy": 0.9111111111111111, "eval_loss": 0.2263958752155304, "eval_runtime": 3.8859, "eval_samples_per_second": 11.58, "eval_steps_per_second": 0.515, "step": 18 }, { "epoch": 6.62, "learning_rate": 4.62962962962963e-05, "loss": 0.3207, "step": 20 }, { "epoch": 6.92, "eval_accuracy": 0.9333333333333333, "eval_loss": 0.25299549102783203, "eval_runtime": 3.0094, "eval_samples_per_second": 14.953, "eval_steps_per_second": 0.665, "step": 21 }, { "epoch": 7.92, "eval_accuracy": 0.9333333333333333, "eval_loss": 0.22416652739048004, "eval_runtime": 3.3422, "eval_samples_per_second": 13.464, "eval_steps_per_second": 0.598, "step": 24 }, { "epoch": 8.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20596002042293549, "eval_runtime": 3.2888, "eval_samples_per_second": 13.683, "eval_steps_per_second": 0.608, "step": 27 }, { "epoch": 9.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.18088287115097046, "eval_runtime": 3.0438, "eval_samples_per_second": 14.784, "eval_steps_per_second": 0.657, "step": 30 }, { "epoch": 10.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20699164271354675, "eval_runtime": 3.347, "eval_samples_per_second": 13.445, "eval_steps_per_second": 0.598, "step": 33 }, { "epoch": 11.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.1999157965183258, "eval_runtime": 3.2411, "eval_samples_per_second": 13.884, "eval_steps_per_second": 0.617, "step": 36 }, { "epoch": 12.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20134444534778595, "eval_runtime": 3.001, "eval_samples_per_second": 14.995, "eval_steps_per_second": 0.666, "step": 39 }, { "epoch": 13.31, "learning_rate": 3.7037037037037037e-05, "loss": 0.2066, "step": 40 }, { "epoch": 13.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.2026776820421219, "eval_runtime": 3.2971, "eval_samples_per_second": 13.648, "eval_steps_per_second": 0.607, "step": 42 }, { "epoch": 14.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.1808823049068451, "eval_runtime": 3.3018, "eval_samples_per_second": 13.629, "eval_steps_per_second": 0.606, "step": 45 }, { "epoch": 15.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.16574886441230774, "eval_runtime": 3.1007, "eval_samples_per_second": 14.513, "eval_steps_per_second": 0.645, "step": 48 }, { "epoch": 16.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.17283517122268677, "eval_runtime": 3.305, "eval_samples_per_second": 13.616, "eval_steps_per_second": 0.605, "step": 51 }, { "epoch": 17.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20132465660572052, "eval_runtime": 3.258, "eval_samples_per_second": 13.812, "eval_steps_per_second": 0.614, "step": 54 }, { "epoch": 18.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.22262603044509888, "eval_runtime": 3.0138, "eval_samples_per_second": 14.931, "eval_steps_per_second": 0.664, "step": 57 }, { "epoch": 19.92, "learning_rate": 2.777777777777778e-05, "loss": 0.1894, "step": 60 }, { "epoch": 19.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20911100506782532, "eval_runtime": 3.2366, "eval_samples_per_second": 13.903, "eval_steps_per_second": 0.618, "step": 60 }, { "epoch": 20.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.19400011003017426, "eval_runtime": 3.2491, "eval_samples_per_second": 13.85, "eval_steps_per_second": 0.616, "step": 63 }, { "epoch": 21.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.19758270680904388, "eval_runtime": 3.0406, "eval_samples_per_second": 14.8, "eval_steps_per_second": 0.658, "step": 66 }, { "epoch": 22.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.22320419549942017, "eval_runtime": 3.2519, "eval_samples_per_second": 13.838, "eval_steps_per_second": 0.615, "step": 69 }, { "epoch": 23.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.2381269484758377, "eval_runtime": 3.3206, "eval_samples_per_second": 13.552, "eval_steps_per_second": 0.602, "step": 72 }, { "epoch": 24.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.24054782092571259, "eval_runtime": 2.9599, "eval_samples_per_second": 15.203, "eval_steps_per_second": 0.676, "step": 75 }, { "epoch": 25.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.224700927734375, "eval_runtime": 3.266, "eval_samples_per_second": 13.778, "eval_steps_per_second": 0.612, "step": 78 }, { "epoch": 26.62, "learning_rate": 1.8518518518518518e-05, "loss": 0.1713, "step": 80 }, { "epoch": 26.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.18945971131324768, "eval_runtime": 3.2466, "eval_samples_per_second": 13.861, "eval_steps_per_second": 0.616, "step": 81 }, { "epoch": 27.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.18361297249794006, "eval_runtime": 2.9994, "eval_samples_per_second": 15.003, "eval_steps_per_second": 0.667, "step": 84 }, { "epoch": 28.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.19853755831718445, "eval_runtime": 3.2778, "eval_samples_per_second": 13.729, "eval_steps_per_second": 0.61, "step": 87 }, { "epoch": 29.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.2126913219690323, "eval_runtime": 3.2397, "eval_samples_per_second": 13.89, "eval_steps_per_second": 0.617, "step": 90 }, { "epoch": 30.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20982736349105835, "eval_runtime": 2.9929, "eval_samples_per_second": 15.035, "eval_steps_per_second": 0.668, "step": 93 }, { "epoch": 31.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20032857358455658, "eval_runtime": 3.2633, "eval_samples_per_second": 13.79, "eval_steps_per_second": 0.613, "step": 96 }, { "epoch": 32.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.18492181599140167, "eval_runtime": 3.3119, "eval_samples_per_second": 13.588, "eval_steps_per_second": 0.604, "step": 99 }, { "epoch": 33.31, "learning_rate": 9.259259259259259e-06, "loss": 0.1428, "step": 100 }, { "epoch": 33.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.1842741221189499, "eval_runtime": 2.9406, "eval_samples_per_second": 15.303, "eval_steps_per_second": 0.68, "step": 102 }, { "epoch": 34.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.1899583339691162, "eval_runtime": 3.2029, "eval_samples_per_second": 14.05, "eval_steps_per_second": 0.624, "step": 105 }, { "epoch": 35.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.19720764458179474, "eval_runtime": 3.2124, "eval_samples_per_second": 14.008, "eval_steps_per_second": 0.623, "step": 108 }, { "epoch": 36.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20228949189186096, "eval_runtime": 2.9912, "eval_samples_per_second": 15.044, "eval_steps_per_second": 0.669, "step": 111 }, { "epoch": 37.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20600810647010803, "eval_runtime": 3.269, "eval_samples_per_second": 13.766, "eval_steps_per_second": 0.612, "step": 114 }, { "epoch": 38.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.20927244424819946, "eval_runtime": 3.214, "eval_samples_per_second": 14.001, "eval_steps_per_second": 0.622, "step": 117 }, { "epoch": 39.92, "learning_rate": 0.0, "loss": 0.1443, "step": 120 }, { "epoch": 39.92, "eval_accuracy": 0.9555555555555556, "eval_loss": 0.21063438057899475, "eval_runtime": 3.0071, "eval_samples_per_second": 14.965, "eval_steps_per_second": 0.665, "step": 120 }, { "epoch": 39.92, "step": 120, "total_flos": 3.992815176520827e+17, "train_loss": 0.1958512246608734, "train_runtime": 1830.7134, "train_samples_per_second": 8.783, "train_steps_per_second": 0.066 } ], "max_steps": 120, "num_train_epochs": 40, "total_flos": 3.992815176520827e+17, "trial_name": null, "trial_params": null }