| { | |
| "best_metric": 0.7137995958328247, | |
| "best_model_checkpoint": "dogs_70_breeds_image_detection/checkpoint-7020", | |
| "epoch": 30.0, | |
| "eval_steps": 500, | |
| "global_step": 7020, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5700534759358289, | |
| "eval_loss": 3.8619625568389893, | |
| "eval_runtime": 16.943, | |
| "eval_samples_per_second": 110.37, | |
| "eval_steps_per_second": 13.811, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7903743315508022, | |
| "eval_loss": 3.442793846130371, | |
| "eval_runtime": 16.7743, | |
| "eval_samples_per_second": 111.48, | |
| "eval_steps_per_second": 13.95, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.354375896700143e-06, | |
| "loss": 3.8066, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8385026737967914, | |
| "eval_loss": 3.106651782989502, | |
| "eval_runtime": 16.721, | |
| "eval_samples_per_second": 111.835, | |
| "eval_steps_per_second": 13.994, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8625668449197861, | |
| "eval_loss": 2.8242247104644775, | |
| "eval_runtime": 16.6814, | |
| "eval_samples_per_second": 112.101, | |
| "eval_steps_per_second": 14.028, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 8.637015781922526e-06, | |
| "loss": 2.9436, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8748663101604278, | |
| "eval_loss": 2.583355665206909, | |
| "eval_runtime": 16.6174, | |
| "eval_samples_per_second": 112.533, | |
| "eval_steps_per_second": 14.082, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8903743315508021, | |
| "eval_loss": 2.3684189319610596, | |
| "eval_runtime": 16.679, | |
| "eval_samples_per_second": 112.117, | |
| "eval_steps_per_second": 14.03, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 7.919655667144908e-06, | |
| "loss": 2.3544, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8935828877005347, | |
| "eval_loss": 2.177172899246216, | |
| "eval_runtime": 16.7621, | |
| "eval_samples_per_second": 111.561, | |
| "eval_steps_per_second": 13.96, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9058823529411765, | |
| "eval_loss": 2.007451295852661, | |
| "eval_runtime": 16.6026, | |
| "eval_samples_per_second": 112.633, | |
| "eval_steps_per_second": 14.094, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 7.202295552367289e-06, | |
| "loss": 1.9032, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.902139037433155, | |
| "eval_loss": 1.8538062572479248, | |
| "eval_runtime": 16.685, | |
| "eval_samples_per_second": 112.077, | |
| "eval_steps_per_second": 14.025, | |
| "step": 2106 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9058823529411765, | |
| "eval_loss": 1.7170625925064087, | |
| "eval_runtime": 16.7001, | |
| "eval_samples_per_second": 111.975, | |
| "eval_steps_per_second": 14.012, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 6.48493543758967e-06, | |
| "loss": 1.5446, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9074866310160428, | |
| "eval_loss": 1.5915807485580444, | |
| "eval_runtime": 16.4868, | |
| "eval_samples_per_second": 113.424, | |
| "eval_steps_per_second": 14.193, | |
| "step": 2574 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9117647058823529, | |
| "eval_loss": 1.4730502367019653, | |
| "eval_runtime": 16.6406, | |
| "eval_samples_per_second": 112.376, | |
| "eval_steps_per_second": 14.062, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 5.767575322812053e-06, | |
| "loss": 1.2629, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9187165775401069, | |
| "eval_loss": 1.3681436777114868, | |
| "eval_runtime": 16.7454, | |
| "eval_samples_per_second": 111.672, | |
| "eval_steps_per_second": 13.974, | |
| "step": 3042 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9165775401069519, | |
| "eval_loss": 1.2735283374786377, | |
| "eval_runtime": 16.5505, | |
| "eval_samples_per_second": 112.987, | |
| "eval_steps_per_second": 14.139, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 5.050215208034433e-06, | |
| "loss": 1.0405, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9181818181818182, | |
| "eval_loss": 1.1897326707839966, | |
| "eval_runtime": 16.574, | |
| "eval_samples_per_second": 112.827, | |
| "eval_steps_per_second": 14.118, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9229946524064171, | |
| "eval_loss": 1.1123002767562866, | |
| "eval_runtime": 16.7899, | |
| "eval_samples_per_second": 111.377, | |
| "eval_steps_per_second": 13.937, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9262032085561497, | |
| "eval_loss": 1.0538486242294312, | |
| "eval_runtime": 16.5745, | |
| "eval_samples_per_second": 112.824, | |
| "eval_steps_per_second": 14.118, | |
| "step": 3978 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "learning_rate": 4.332855093256815e-06, | |
| "loss": 0.8665, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.925668449197861, | |
| "eval_loss": 0.9949386715888977, | |
| "eval_runtime": 16.5637, | |
| "eval_samples_per_second": 112.897, | |
| "eval_steps_per_second": 14.127, | |
| "step": 4212 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9262032085561497, | |
| "eval_loss": 0.9491089582443237, | |
| "eval_runtime": 16.5976, | |
| "eval_samples_per_second": 112.667, | |
| "eval_steps_per_second": 14.098, | |
| "step": 4446 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 3.615494978479197e-06, | |
| "loss": 0.7318, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9315508021390374, | |
| "eval_loss": 0.8963261246681213, | |
| "eval_runtime": 16.6332, | |
| "eval_samples_per_second": 112.426, | |
| "eval_steps_per_second": 14.068, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9294117647058824, | |
| "eval_loss": 0.8556962609291077, | |
| "eval_runtime": 17.2231, | |
| "eval_samples_per_second": 108.575, | |
| "eval_steps_per_second": 13.586, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 21.37, | |
| "learning_rate": 2.898134863701578e-06, | |
| "loss": 0.6322, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9336898395721925, | |
| "eval_loss": 0.8246510624885559, | |
| "eval_runtime": 16.769, | |
| "eval_samples_per_second": 111.515, | |
| "eval_steps_per_second": 13.954, | |
| "step": 5148 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.932620320855615, | |
| "eval_loss": 0.8025164604187012, | |
| "eval_runtime": 16.8215, | |
| "eval_samples_per_second": 111.167, | |
| "eval_steps_per_second": 13.911, | |
| "step": 5382 | |
| }, | |
| { | |
| "epoch": 23.5, | |
| "learning_rate": 2.18077474892396e-06, | |
| "loss": 0.5623, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9299465240641711, | |
| "eval_loss": 0.778028666973114, | |
| "eval_runtime": 16.7832, | |
| "eval_samples_per_second": 111.421, | |
| "eval_steps_per_second": 13.943, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9347593582887701, | |
| "eval_loss": 0.7549712657928467, | |
| "eval_runtime": 16.589, | |
| "eval_samples_per_second": 112.725, | |
| "eval_steps_per_second": 14.106, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 1.4634146341463414e-06, | |
| "loss": 0.5055, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9336898395721925, | |
| "eval_loss": 0.7411012649536133, | |
| "eval_runtime": 16.9543, | |
| "eval_samples_per_second": 110.297, | |
| "eval_steps_per_second": 13.802, | |
| "step": 6084 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9358288770053476, | |
| "eval_loss": 0.729629397392273, | |
| "eval_runtime": 16.9047, | |
| "eval_samples_per_second": 110.62, | |
| "eval_steps_per_second": 13.842, | |
| "step": 6318 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 7.460545193687231e-07, | |
| "loss": 0.4743, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9331550802139037, | |
| "eval_loss": 0.7210513949394226, | |
| "eval_runtime": 16.6036, | |
| "eval_samples_per_second": 112.626, | |
| "eval_steps_per_second": 14.093, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9358288770053476, | |
| "eval_loss": 0.7155081629753113, | |
| "eval_runtime": 16.7145, | |
| "eval_samples_per_second": 111.879, | |
| "eval_steps_per_second": 14.0, | |
| "step": 6786 | |
| }, | |
| { | |
| "epoch": 29.91, | |
| "learning_rate": 2.869440459110474e-08, | |
| "loss": 0.457, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9352941176470588, | |
| "eval_loss": 0.7137995958328247, | |
| "eval_runtime": 16.6482, | |
| "eval_samples_per_second": 112.325, | |
| "eval_steps_per_second": 14.056, | |
| "step": 7020 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 7020, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.7390651600583475e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |