| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "delivery_truck_classification\\checkpoint-18", | |
| "epoch": 40.0, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.95, | |
| "eval_loss": 0.16261602938175201, | |
| "eval_runtime": 8.6031, | |
| "eval_samples_per_second": 4.649, | |
| "eval_steps_per_second": 0.232, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.95, | |
| "eval_loss": 0.1592799872159958, | |
| "eval_runtime": 8.1709, | |
| "eval_samples_per_second": 4.895, | |
| "eval_steps_per_second": 0.245, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.95, | |
| "eval_loss": 0.13422292470932007, | |
| "eval_runtime": 8.0249, | |
| "eval_samples_per_second": 4.984, | |
| "eval_steps_per_second": 0.249, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.08705286681652069, | |
| "eval_runtime": 8.0216, | |
| "eval_samples_per_second": 4.987, | |
| "eval_steps_per_second": 0.249, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.06115349009633064, | |
| "eval_runtime": 7.8977, | |
| "eval_samples_per_second": 5.065, | |
| "eval_steps_per_second": 0.253, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04307302460074425, | |
| "eval_runtime": 8.1309, | |
| "eval_samples_per_second": 4.92, | |
| "eval_steps_per_second": 0.246, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.2745, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.03329644352197647, | |
| "eval_runtime": 8.4823, | |
| "eval_samples_per_second": 4.716, | |
| "eval_steps_per_second": 0.236, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.048651862889528275, | |
| "eval_runtime": 7.9701, | |
| "eval_samples_per_second": 5.019, | |
| "eval_steps_per_second": 0.251, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.045587461441755295, | |
| "eval_runtime": 7.8557, | |
| "eval_samples_per_second": 5.092, | |
| "eval_steps_per_second": 0.255, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.02726823464035988, | |
| "eval_runtime": 8.1787, | |
| "eval_samples_per_second": 4.891, | |
| "eval_steps_per_second": 0.245, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.017963390797376633, | |
| "eval_runtime": 8.3083, | |
| "eval_samples_per_second": 4.814, | |
| "eval_steps_per_second": 0.241, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.016819924116134644, | |
| "eval_runtime": 8.1002, | |
| "eval_samples_per_second": 4.938, | |
| "eval_steps_per_second": 0.247, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.031003978103399277, | |
| "eval_runtime": 8.1225, | |
| "eval_samples_per_second": 4.925, | |
| "eval_steps_per_second": 0.246, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1782, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.043801963329315186, | |
| "eval_runtime": 8.6445, | |
| "eval_samples_per_second": 4.627, | |
| "eval_steps_per_second": 0.231, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.07503340393304825, | |
| "eval_runtime": 7.8763, | |
| "eval_samples_per_second": 5.079, | |
| "eval_steps_per_second": 0.254, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.03957166522741318, | |
| "eval_runtime": 8.3356, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 0.24, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.017652835696935654, | |
| "eval_runtime": 7.9389, | |
| "eval_samples_per_second": 5.038, | |
| "eval_steps_per_second": 0.252, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.02170238085091114, | |
| "eval_runtime": 8.0236, | |
| "eval_samples_per_second": 4.985, | |
| "eval_steps_per_second": 0.249, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.011599823832511902, | |
| "eval_runtime": 8.0424, | |
| "eval_samples_per_second": 4.974, | |
| "eval_steps_per_second": 0.249, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1624, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.008052630349993706, | |
| "eval_runtime": 8.0111, | |
| "eval_samples_per_second": 4.993, | |
| "eval_steps_per_second": 0.25, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.006596912629902363, | |
| "eval_runtime": 8.4146, | |
| "eval_samples_per_second": 4.754, | |
| "eval_steps_per_second": 0.238, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.008253499865531921, | |
| "eval_runtime": 8.4625, | |
| "eval_samples_per_second": 4.727, | |
| "eval_steps_per_second": 0.236, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.012594206258654594, | |
| "eval_runtime": 8.1933, | |
| "eval_samples_per_second": 4.882, | |
| "eval_steps_per_second": 0.244, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.015849163755774498, | |
| "eval_runtime": 7.9982, | |
| "eval_samples_per_second": 5.001, | |
| "eval_steps_per_second": 0.25, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01883917860686779, | |
| "eval_runtime": 7.9429, | |
| "eval_samples_per_second": 5.036, | |
| "eval_steps_per_second": 0.252, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.014945434406399727, | |
| "eval_runtime": 8.0615, | |
| "eval_samples_per_second": 4.962, | |
| "eval_steps_per_second": 0.248, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1475, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010075708851218224, | |
| "eval_runtime": 8.0344, | |
| "eval_samples_per_second": 4.979, | |
| "eval_steps_per_second": 0.249, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.006395348347723484, | |
| "eval_runtime": 7.9204, | |
| "eval_samples_per_second": 5.05, | |
| "eval_steps_per_second": 0.253, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.004969631787389517, | |
| "eval_runtime": 8.1818, | |
| "eval_samples_per_second": 4.889, | |
| "eval_steps_per_second": 0.244, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.005222103092819452, | |
| "eval_runtime": 7.9872, | |
| "eval_samples_per_second": 5.008, | |
| "eval_steps_per_second": 0.25, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.006443561054766178, | |
| "eval_runtime": 7.9514, | |
| "eval_samples_per_second": 5.031, | |
| "eval_steps_per_second": 0.252, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.006998550146818161, | |
| "eval_runtime": 7.9811, | |
| "eval_samples_per_second": 5.012, | |
| "eval_steps_per_second": 0.251, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.006886245217174292, | |
| "eval_runtime": 7.9804, | |
| "eval_samples_per_second": 5.012, | |
| "eval_steps_per_second": 0.251, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1345, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.005939379800111055, | |
| "eval_runtime": 7.962, | |
| "eval_samples_per_second": 5.024, | |
| "eval_steps_per_second": 0.251, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.004927521105855703, | |
| "eval_runtime": 7.9624, | |
| "eval_samples_per_second": 5.024, | |
| "eval_steps_per_second": 0.251, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.004319839645177126, | |
| "eval_runtime": 8.2724, | |
| "eval_samples_per_second": 4.835, | |
| "eval_steps_per_second": 0.242, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0039680288173258305, | |
| "eval_runtime": 7.994, | |
| "eval_samples_per_second": 5.004, | |
| "eval_steps_per_second": 0.25, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.003840196877717972, | |
| "eval_runtime": 7.8877, | |
| "eval_samples_per_second": 5.071, | |
| "eval_steps_per_second": 0.254, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0038244160823524, | |
| "eval_runtime": 8.0172, | |
| "eval_samples_per_second": 4.989, | |
| "eval_steps_per_second": 0.249, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1232, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.003828426357358694, | |
| "eval_runtime": 7.9122, | |
| "eval_samples_per_second": 5.055, | |
| "eval_steps_per_second": 0.253, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 120, | |
| "total_flos": 3.579662466809856e+17, | |
| "train_loss": 0.17003339926401775, | |
| "train_runtime": 8221.5625, | |
| "train_samples_per_second": 1.751, | |
| "train_steps_per_second": 0.015 | |
| } | |
| ], | |
| "max_steps": 120, | |
| "num_train_epochs": 40, | |
| "total_flos": 3.579662466809856e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |