| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "delivery_truck_classification/checkpoint-93", | |
| "epoch": 39.857142857142854, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.22448979591836735, | |
| "eval_loss": 1.7165862321853638, | |
| "eval_runtime": 3.3593, | |
| "eval_samples_per_second": 14.586, | |
| "eval_steps_per_second": 0.595, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_accuracy": 0.40816326530612246, | |
| "eval_loss": 1.5815682411193848, | |
| "eval_runtime": 3.8537, | |
| "eval_samples_per_second": 12.715, | |
| "eval_steps_per_second": 0.519, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.5510204081632653, | |
| "eval_loss": 1.4084097146987915, | |
| "eval_runtime": 3.6101, | |
| "eval_samples_per_second": 13.573, | |
| "eval_steps_per_second": 0.554, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "eval_accuracy": 0.6326530612244898, | |
| "eval_loss": 1.1761205196380615, | |
| "eval_runtime": 3.605, | |
| "eval_samples_per_second": 13.592, | |
| "eval_steps_per_second": 0.555, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.7346938775510204, | |
| "eval_loss": 0.924461841583252, | |
| "eval_runtime": 3.397, | |
| "eval_samples_per_second": 14.424, | |
| "eval_steps_per_second": 0.589, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "eval_accuracy": 0.7959183673469388, | |
| "eval_loss": 0.6986315250396729, | |
| "eval_runtime": 3.6429, | |
| "eval_samples_per_second": 13.451, | |
| "eval_steps_per_second": 0.549, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.608, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.8367346938775511, | |
| "eval_loss": 0.5158075094223022, | |
| "eval_runtime": 3.6761, | |
| "eval_samples_per_second": 13.329, | |
| "eval_steps_per_second": 0.544, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "eval_accuracy": 0.8775510204081632, | |
| "eval_loss": 0.37532907724380493, | |
| "eval_runtime": 3.6821, | |
| "eval_samples_per_second": 13.308, | |
| "eval_steps_per_second": 0.543, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.8979591836734694, | |
| "eval_loss": 0.30922260880470276, | |
| "eval_runtime": 3.4322, | |
| "eval_samples_per_second": 14.276, | |
| "eval_steps_per_second": 0.583, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "eval_accuracy": 0.9387755102040817, | |
| "eval_loss": 0.2584000825881958, | |
| "eval_runtime": 3.7632, | |
| "eval_samples_per_second": 13.021, | |
| "eval_steps_per_second": 0.531, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.9183673469387755, | |
| "eval_loss": 0.2158631533384323, | |
| "eval_runtime": 3.7248, | |
| "eval_samples_per_second": 13.155, | |
| "eval_steps_per_second": 0.537, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.19079165160655975, | |
| "eval_runtime": 3.4555, | |
| "eval_samples_per_second": 14.18, | |
| "eval_steps_per_second": 0.579, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.1801912933588028, | |
| "eval_runtime": 3.6849, | |
| "eval_samples_per_second": 13.298, | |
| "eval_steps_per_second": 0.543, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.6473, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 13.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.16818924248218536, | |
| "eval_runtime": 3.6554, | |
| "eval_samples_per_second": 13.405, | |
| "eval_steps_per_second": 0.547, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.15600401163101196, | |
| "eval_runtime": 3.4217, | |
| "eval_samples_per_second": 14.32, | |
| "eval_steps_per_second": 0.585, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 15.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.13216617703437805, | |
| "eval_runtime": 3.736, | |
| "eval_samples_per_second": 13.116, | |
| "eval_steps_per_second": 0.535, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.11014676839113235, | |
| "eval_runtime": 3.6145, | |
| "eval_samples_per_second": 13.557, | |
| "eval_steps_per_second": 0.553, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.0938219353556633, | |
| "eval_runtime": 3.6148, | |
| "eval_samples_per_second": 13.555, | |
| "eval_steps_per_second": 0.553, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.9795918367346939, | |
| "eval_loss": 0.08886948227882385, | |
| "eval_runtime": 3.3763, | |
| "eval_samples_per_second": 14.513, | |
| "eval_steps_per_second": 0.592, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3855, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "eval_accuracy": 0.9795918367346939, | |
| "eval_loss": 0.10251900553703308, | |
| "eval_runtime": 3.6959, | |
| "eval_samples_per_second": 13.258, | |
| "eval_steps_per_second": 0.541, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.9795918367346939, | |
| "eval_loss": 0.09841162711381912, | |
| "eval_runtime": 3.6698, | |
| "eval_samples_per_second": 13.352, | |
| "eval_steps_per_second": 0.545, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 21.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.08669053018093109, | |
| "eval_runtime": 3.4251, | |
| "eval_samples_per_second": 14.306, | |
| "eval_steps_per_second": 0.584, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.08126597851514816, | |
| "eval_runtime": 3.4044, | |
| "eval_samples_per_second": 14.393, | |
| "eval_steps_per_second": 0.587, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 23.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.07681093364953995, | |
| "eval_runtime": 3.6377, | |
| "eval_samples_per_second": 13.47, | |
| "eval_steps_per_second": 0.55, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.9795918367346939, | |
| "eval_loss": 0.07339165359735489, | |
| "eval_runtime": 3.6437, | |
| "eval_samples_per_second": 13.448, | |
| "eval_steps_per_second": 0.549, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 25.86, | |
| "eval_accuracy": 0.9795918367346939, | |
| "eval_loss": 0.0697600468993187, | |
| "eval_runtime": 3.6092, | |
| "eval_samples_per_second": 13.577, | |
| "eval_steps_per_second": 0.554, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 26.57, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.306, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.061838988214731216, | |
| "eval_runtime": 3.3297, | |
| "eval_samples_per_second": 14.716, | |
| "eval_steps_per_second": 0.601, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "eval_accuracy": 0.9795918367346939, | |
| "eval_loss": 0.05467281490564346, | |
| "eval_runtime": 3.6132, | |
| "eval_samples_per_second": 13.562, | |
| "eval_steps_per_second": 0.554, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.053797200322151184, | |
| "eval_runtime": 3.6286, | |
| "eval_samples_per_second": 13.504, | |
| "eval_steps_per_second": 0.551, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "eval_accuracy": 0.9795918367346939, | |
| "eval_loss": 0.048745423555374146, | |
| "eval_runtime": 3.5673, | |
| "eval_samples_per_second": 13.736, | |
| "eval_steps_per_second": 0.561, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04471803084015846, | |
| "eval_runtime": 3.3732, | |
| "eval_samples_per_second": 14.526, | |
| "eval_steps_per_second": 0.593, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 31.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04248499870300293, | |
| "eval_runtime": 3.634, | |
| "eval_samples_per_second": 13.484, | |
| "eval_steps_per_second": 0.55, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04510816931724548, | |
| "eval_runtime": 3.5707, | |
| "eval_samples_per_second": 13.723, | |
| "eval_steps_per_second": 0.56, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 33.29, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.2966, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 33.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04972054436802864, | |
| "eval_runtime": 3.5902, | |
| "eval_samples_per_second": 13.648, | |
| "eval_steps_per_second": 0.557, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.05577036738395691, | |
| "eval_runtime": 3.3881, | |
| "eval_samples_per_second": 14.462, | |
| "eval_steps_per_second": 0.59, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 35.86, | |
| "eval_accuracy": 0.9795918367346939, | |
| "eval_loss": 0.05818271264433861, | |
| "eval_runtime": 3.6322, | |
| "eval_samples_per_second": 13.491, | |
| "eval_steps_per_second": 0.551, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 36.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.061642248183488846, | |
| "eval_runtime": 3.5883, | |
| "eval_samples_per_second": 13.655, | |
| "eval_steps_per_second": 0.557, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 37.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.06565477699041367, | |
| "eval_runtime": 3.6509, | |
| "eval_samples_per_second": 13.421, | |
| "eval_steps_per_second": 0.548, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 38.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.067948117852211, | |
| "eval_runtime": 3.3455, | |
| "eval_samples_per_second": 14.647, | |
| "eval_steps_per_second": 0.598, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "learning_rate": 0.0, | |
| "loss": 0.2535, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "eval_accuracy": 0.9591836734693877, | |
| "eval_loss": 0.06835878640413284, | |
| "eval_runtime": 3.6892, | |
| "eval_samples_per_second": 13.282, | |
| "eval_steps_per_second": 0.542, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "step": 120, | |
| "total_flos": 4.283662751949128e+17, | |
| "train_loss": 0.5828357299168905, | |
| "train_runtime": 1853.5405, | |
| "train_samples_per_second": 9.323, | |
| "train_steps_per_second": 0.065 | |
| } | |
| ], | |
| "max_steps": 120, | |
| "num_train_epochs": 40, | |
| "total_flos": 4.283662751949128e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |