| { | |
| "best_metric": 0.9767441860465116, | |
| "best_model_checkpoint": "delivery_truck_classification/checkpoint-9", | |
| "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": 0.9534883720930233, | |
| "eval_loss": 0.1490669548511505, | |
| "eval_runtime": 2.9917, | |
| "eval_samples_per_second": 14.373, | |
| "eval_steps_per_second": 0.669, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.14621073007583618, | |
| "eval_runtime": 3.3898, | |
| "eval_samples_per_second": 12.685, | |
| "eval_steps_per_second": 0.59, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.14032752811908722, | |
| "eval_runtime": 3.2019, | |
| "eval_samples_per_second": 13.429, | |
| "eval_steps_per_second": 0.625, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.14311185479164124, | |
| "eval_runtime": 2.9749, | |
| "eval_samples_per_second": 14.455, | |
| "eval_steps_per_second": 0.672, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.17613790929317474, | |
| "eval_runtime": 3.2124, | |
| "eval_samples_per_second": 13.386, | |
| "eval_steps_per_second": 0.623, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.19303567707538605, | |
| "eval_runtime": 3.2899, | |
| "eval_samples_per_second": 13.07, | |
| "eval_steps_per_second": 0.608, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.2637, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.16774171590805054, | |
| "eval_runtime": 2.9265, | |
| "eval_samples_per_second": 14.693, | |
| "eval_steps_per_second": 0.683, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.18350879848003387, | |
| "eval_runtime": 3.3322, | |
| "eval_samples_per_second": 12.904, | |
| "eval_steps_per_second": 0.6, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.18035028874874115, | |
| "eval_runtime": 3.1848, | |
| "eval_samples_per_second": 13.501, | |
| "eval_steps_per_second": 0.628, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.18557493388652802, | |
| "eval_runtime": 3.0604, | |
| "eval_samples_per_second": 14.051, | |
| "eval_steps_per_second": 0.654, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.17186354100704193, | |
| "eval_runtime": 3.2354, | |
| "eval_samples_per_second": 13.291, | |
| "eval_steps_per_second": 0.618, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.16796864569187164, | |
| "eval_runtime": 3.1706, | |
| "eval_samples_per_second": 13.562, | |
| "eval_steps_per_second": 0.631, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.15706905722618103, | |
| "eval_runtime": 2.9572, | |
| "eval_samples_per_second": 14.541, | |
| "eval_steps_per_second": 0.676, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1687, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.13334713876247406, | |
| "eval_runtime": 3.2093, | |
| "eval_samples_per_second": 13.398, | |
| "eval_steps_per_second": 0.623, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.12847872078418732, | |
| "eval_runtime": 3.2531, | |
| "eval_samples_per_second": 13.218, | |
| "eval_steps_per_second": 0.615, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.12928344309329987, | |
| "eval_runtime": 3.0101, | |
| "eval_samples_per_second": 14.285, | |
| "eval_steps_per_second": 0.664, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.12077976763248444, | |
| "eval_runtime": 3.2048, | |
| "eval_samples_per_second": 13.417, | |
| "eval_steps_per_second": 0.624, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.1060628667473793, | |
| "eval_runtime": 3.2421, | |
| "eval_samples_per_second": 13.263, | |
| "eval_steps_per_second": 0.617, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.09775999933481216, | |
| "eval_runtime": 2.9563, | |
| "eval_samples_per_second": 14.545, | |
| "eval_steps_per_second": 0.677, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1435, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.11002050340175629, | |
| "eval_runtime": 3.164, | |
| "eval_samples_per_second": 13.59, | |
| "eval_steps_per_second": 0.632, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.1205144003033638, | |
| "eval_runtime": 3.223, | |
| "eval_samples_per_second": 13.342, | |
| "eval_steps_per_second": 0.621, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.10268723964691162, | |
| "eval_runtime": 2.9505, | |
| "eval_samples_per_second": 14.574, | |
| "eval_steps_per_second": 0.678, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.10407420247793198, | |
| "eval_runtime": 3.2576, | |
| "eval_samples_per_second": 13.2, | |
| "eval_steps_per_second": 0.614, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.10208708792924881, | |
| "eval_runtime": 3.1867, | |
| "eval_samples_per_second": 13.494, | |
| "eval_steps_per_second": 0.628, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.09740080684423447, | |
| "eval_runtime": 2.9153, | |
| "eval_samples_per_second": 14.75, | |
| "eval_steps_per_second": 0.686, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.10056695342063904, | |
| "eval_runtime": 3.2051, | |
| "eval_samples_per_second": 13.416, | |
| "eval_steps_per_second": 0.624, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1361, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.10110510140657425, | |
| "eval_runtime": 3.2233, | |
| "eval_samples_per_second": 13.34, | |
| "eval_steps_per_second": 0.62, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.09926853328943253, | |
| "eval_runtime": 2.9231, | |
| "eval_samples_per_second": 14.711, | |
| "eval_steps_per_second": 0.684, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.09514892101287842, | |
| "eval_runtime": 3.1715, | |
| "eval_samples_per_second": 13.558, | |
| "eval_steps_per_second": 0.631, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.09706470370292664, | |
| "eval_runtime": 3.2972, | |
| "eval_samples_per_second": 13.041, | |
| "eval_steps_per_second": 0.607, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.10362450033426285, | |
| "eval_runtime": 2.9574, | |
| "eval_samples_per_second": 14.54, | |
| "eval_steps_per_second": 0.676, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.10851310193538666, | |
| "eval_runtime": 3.2605, | |
| "eval_samples_per_second": 13.188, | |
| "eval_steps_per_second": 0.613, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.10988349467515945, | |
| "eval_runtime": 3.2152, | |
| "eval_samples_per_second": 13.374, | |
| "eval_steps_per_second": 0.622, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1221, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.11153779178857803, | |
| "eval_runtime": 2.9113, | |
| "eval_samples_per_second": 14.77, | |
| "eval_steps_per_second": 0.687, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.9767441860465116, | |
| "eval_loss": 0.11329730600118637, | |
| "eval_runtime": 3.208, | |
| "eval_samples_per_second": 13.404, | |
| "eval_steps_per_second": 0.623, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.11842045933008194, | |
| "eval_runtime": 3.2236, | |
| "eval_samples_per_second": 13.339, | |
| "eval_steps_per_second": 0.62, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.12152226269245148, | |
| "eval_runtime": 2.9306, | |
| "eval_samples_per_second": 14.673, | |
| "eval_steps_per_second": 0.682, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.12237626314163208, | |
| "eval_runtime": 3.2687, | |
| "eval_samples_per_second": 13.155, | |
| "eval_steps_per_second": 0.612, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.12215745449066162, | |
| "eval_runtime": 3.2407, | |
| "eval_samples_per_second": 13.269, | |
| "eval_steps_per_second": 0.617, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1135, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9534883720930233, | |
| "eval_loss": 0.1217384859919548, | |
| "eval_runtime": 2.9059, | |
| "eval_samples_per_second": 14.797, | |
| "eval_steps_per_second": 0.688, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 120, | |
| "total_flos": 3.7685890970025984e+17, | |
| "train_loss": 0.15792271693547566, | |
| "train_runtime": 1762.7321, | |
| "train_samples_per_second": 8.6, | |
| "train_steps_per_second": 0.068 | |
| } | |
| ], | |
| "max_steps": 120, | |
| "num_train_epochs": 40, | |
| "total_flos": 3.7685890970025984e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |