| { | |
| "best_metric": 0.8571428571428571, | |
| "best_model_checkpoint": "delivery_truck_classification/checkpoint-27", | |
| "epoch": 40.0, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.14285714285714285, | |
| "eval_loss": 1.9874809980392456, | |
| "eval_runtime": 0.555, | |
| "eval_samples_per_second": 12.612, | |
| "eval_steps_per_second": 1.802, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.14285714285714285, | |
| "eval_loss": 1.9131802320480347, | |
| "eval_runtime": 0.612, | |
| "eval_samples_per_second": 11.438, | |
| "eval_steps_per_second": 1.634, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.7584645748138428, | |
| "eval_runtime": 0.6123, | |
| "eval_samples_per_second": 11.432, | |
| "eval_steps_per_second": 1.633, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.5935114622116089, | |
| "eval_runtime": 0.6224, | |
| "eval_samples_per_second": 11.247, | |
| "eval_steps_per_second": 1.607, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.5026111602783203, | |
| "eval_runtime": 0.5902, | |
| "eval_samples_per_second": 11.86, | |
| "eval_steps_per_second": 1.694, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.4698925018310547, | |
| "eval_runtime": 0.6228, | |
| "eval_samples_per_second": 11.239, | |
| "eval_steps_per_second": 1.606, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.4360735416412354, | |
| "eval_runtime": 0.5993, | |
| "eval_samples_per_second": 11.681, | |
| "eval_steps_per_second": 1.669, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.3962326049804688, | |
| "eval_runtime": 0.6058, | |
| "eval_samples_per_second": 11.555, | |
| "eval_steps_per_second": 1.651, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.3457258939743042, | |
| "eval_runtime": 0.6198, | |
| "eval_samples_per_second": 11.293, | |
| "eval_steps_per_second": 1.613, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.2874202728271484, | |
| "eval_runtime": 0.6157, | |
| "eval_samples_per_second": 11.369, | |
| "eval_steps_per_second": 1.624, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.2239570617675781, | |
| "eval_runtime": 0.6193, | |
| "eval_samples_per_second": 11.304, | |
| "eval_steps_per_second": 1.615, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_loss": 1.1642504930496216, | |
| "eval_runtime": 0.6288, | |
| "eval_samples_per_second": 11.132, | |
| "eval_steps_per_second": 1.59, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 1.101585030555725, | |
| "eval_runtime": 0.6087, | |
| "eval_samples_per_second": 11.5, | |
| "eval_steps_per_second": 1.643, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5714285714285714, | |
| "eval_loss": 1.0355511903762817, | |
| "eval_runtime": 0.5997, | |
| "eval_samples_per_second": 11.673, | |
| "eval_steps_per_second": 1.668, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.9718684554100037, | |
| "eval_runtime": 0.5696, | |
| "eval_samples_per_second": 12.29, | |
| "eval_steps_per_second": 1.756, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.91197669506073, | |
| "eval_runtime": 0.6278, | |
| "eval_samples_per_second": 11.15, | |
| "eval_steps_per_second": 1.593, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.8606060743331909, | |
| "eval_runtime": 0.6159, | |
| "eval_samples_per_second": 11.365, | |
| "eval_steps_per_second": 1.624, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.8117322325706482, | |
| "eval_runtime": 0.628, | |
| "eval_samples_per_second": 11.147, | |
| "eval_steps_per_second": 1.592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.7706560492515564, | |
| "eval_runtime": 0.6266, | |
| "eval_samples_per_second": 11.171, | |
| "eval_steps_per_second": 1.596, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5111, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.7366718649864197, | |
| "eval_runtime": 0.601, | |
| "eval_samples_per_second": 11.646, | |
| "eval_steps_per_second": 1.664, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.7156747579574585, | |
| "eval_runtime": 0.619, | |
| "eval_samples_per_second": 11.308, | |
| "eval_steps_per_second": 1.615, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.706693172454834, | |
| "eval_runtime": 0.6179, | |
| "eval_samples_per_second": 11.329, | |
| "eval_steps_per_second": 1.618, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.7012028098106384, | |
| "eval_runtime": 0.6214, | |
| "eval_samples_per_second": 11.265, | |
| "eval_steps_per_second": 1.609, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.697659432888031, | |
| "eval_runtime": 0.6273, | |
| "eval_samples_per_second": 11.16, | |
| "eval_steps_per_second": 1.594, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.6974306106567383, | |
| "eval_runtime": 0.6326, | |
| "eval_samples_per_second": 11.065, | |
| "eval_steps_per_second": 1.581, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_loss": 0.6976919770240784, | |
| "eval_runtime": 0.6266, | |
| "eval_samples_per_second": 11.171, | |
| "eval_steps_per_second": 1.596, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.703612744808197, | |
| "eval_runtime": 0.626, | |
| "eval_samples_per_second": 11.182, | |
| "eval_steps_per_second": 1.597, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.7074456810951233, | |
| "eval_runtime": 0.624, | |
| "eval_samples_per_second": 11.218, | |
| "eval_steps_per_second": 1.603, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.7061924338340759, | |
| "eval_runtime": 0.5569, | |
| "eval_samples_per_second": 12.569, | |
| "eval_steps_per_second": 1.796, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.7056497931480408, | |
| "eval_runtime": 0.6221, | |
| "eval_samples_per_second": 11.252, | |
| "eval_steps_per_second": 1.607, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.7049512267112732, | |
| "eval_runtime": 0.6315, | |
| "eval_samples_per_second": 11.084, | |
| "eval_steps_per_second": 1.583, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.7050389647483826, | |
| "eval_runtime": 0.6239, | |
| "eval_samples_per_second": 11.22, | |
| "eval_steps_per_second": 1.603, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.703091025352478, | |
| "eval_runtime": 0.633, | |
| "eval_samples_per_second": 11.058, | |
| "eval_steps_per_second": 1.58, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.7015966773033142, | |
| "eval_runtime": 0.6318, | |
| "eval_samples_per_second": 11.079, | |
| "eval_steps_per_second": 1.583, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.6995734572410583, | |
| "eval_runtime": 0.6327, | |
| "eval_samples_per_second": 11.064, | |
| "eval_steps_per_second": 1.581, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.6970993280410767, | |
| "eval_runtime": 0.6284, | |
| "eval_samples_per_second": 11.139, | |
| "eval_steps_per_second": 1.591, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.6953268647193909, | |
| "eval_runtime": 0.6135, | |
| "eval_samples_per_second": 11.41, | |
| "eval_steps_per_second": 1.63, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.6938610672950745, | |
| "eval_runtime": 0.7702, | |
| "eval_samples_per_second": 9.089, | |
| "eval_steps_per_second": 1.298, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.6938490867614746, | |
| "eval_runtime": 0.6214, | |
| "eval_samples_per_second": 11.265, | |
| "eval_steps_per_second": 1.609, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1719, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_loss": 0.6936034560203552, | |
| "eval_runtime": 0.6132, | |
| "eval_samples_per_second": 11.416, | |
| "eval_steps_per_second": 1.631, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 40, | |
| "total_flos": 6.164974248394752e+16, | |
| "train_loss": 0.3415180742740631, | |
| "train_runtime": 367.0026, | |
| "train_samples_per_second": 6.757, | |
| "train_steps_per_second": 0.109 | |
| } | |
| ], | |
| "max_steps": 40, | |
| "num_train_epochs": 40, | |
| "total_flos": 6.164974248394752e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |