| { | |
| "best_metric": 0.8363636363636363, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/Classification/ViT/models/resnet-18-finetuned-eurosat/checkpoint-303", | |
| "epoch": 19.753086419753085, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.3227, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3846, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.7575757575757576, | |
| "eval_loss": 0.6352207660675049, | |
| "eval_runtime": 46.0823, | |
| "eval_samples_per_second": 7.161, | |
| "eval_steps_per_second": 0.239, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.3732, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5009, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.7484848484848485, | |
| "eval_loss": 0.6438900828361511, | |
| "eval_runtime": 49.1686, | |
| "eval_samples_per_second": 6.712, | |
| "eval_steps_per_second": 0.224, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.4765, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.5625, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.7909090909090909, | |
| "eval_loss": 0.5722424387931824, | |
| "eval_runtime": 46.1274, | |
| "eval_samples_per_second": 7.154, | |
| "eval_steps_per_second": 0.238, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.5104, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.4928, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.796969696969697, | |
| "eval_loss": 0.5514332056045532, | |
| "eval_runtime": 45.9331, | |
| "eval_samples_per_second": 7.184, | |
| "eval_steps_per_second": 0.239, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.5148, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.4621, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.7696969696969697, | |
| "eval_loss": 0.6103599071502686, | |
| "eval_runtime": 47.2344, | |
| "eval_samples_per_second": 6.986, | |
| "eval_steps_per_second": 0.233, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.4939, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.4367, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.793939393939394, | |
| "eval_loss": 0.573406994342804, | |
| "eval_runtime": 46.1152, | |
| "eval_samples_per_second": 7.156, | |
| "eval_steps_per_second": 0.239, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.4252, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.4238, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.5557721853256226, | |
| "eval_runtime": 48.2781, | |
| "eval_samples_per_second": 6.835, | |
| "eval_steps_per_second": 0.228, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.4367, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4011, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.803030303030303, | |
| "eval_loss": 0.554872989654541, | |
| "eval_runtime": 46.9595, | |
| "eval_samples_per_second": 7.027, | |
| "eval_steps_per_second": 0.234, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.4059, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.4129, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.806060606060606, | |
| "eval_loss": 0.5553537607192993, | |
| "eval_runtime": 46.217, | |
| "eval_samples_per_second": 7.14, | |
| "eval_steps_per_second": 0.238, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.4125, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.384, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.8151515151515152, | |
| "eval_loss": 0.5550632476806641, | |
| "eval_runtime": 47.8897, | |
| "eval_samples_per_second": 6.891, | |
| "eval_steps_per_second": 0.23, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.3823, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3839, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "eval_accuracy": 0.8090909090909091, | |
| "eval_loss": 0.5741792917251587, | |
| "eval_runtime": 46.8547, | |
| "eval_samples_per_second": 7.043, | |
| "eval_steps_per_second": 0.235, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.4025, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 11.85, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.3496, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8303030303030303, | |
| "eval_loss": 0.5517680048942566, | |
| "eval_runtime": 45.796, | |
| "eval_samples_per_second": 7.206, | |
| "eval_steps_per_second": 0.24, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 12.35, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.3389, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.3482, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8303030303030303, | |
| "eval_loss": 0.5389552116394043, | |
| "eval_runtime": 45.5677, | |
| "eval_samples_per_second": 7.242, | |
| "eval_steps_per_second": 0.241, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.3486, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.357, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 0.5543653964996338, | |
| "eval_runtime": 45.3586, | |
| "eval_samples_per_second": 7.275, | |
| "eval_steps_per_second": 0.243, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.3397, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3341, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "eval_accuracy": 0.8363636363636363, | |
| "eval_loss": 0.5505930185317993, | |
| "eval_runtime": 45.3368, | |
| "eval_samples_per_second": 7.279, | |
| "eval_steps_per_second": 0.243, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.3923, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3605, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8212121212121212, | |
| "eval_loss": 0.5546284914016724, | |
| "eval_runtime": 45.4708, | |
| "eval_samples_per_second": 7.257, | |
| "eval_steps_per_second": 0.242, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.3401, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 16.79, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.3041, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8212121212121212, | |
| "eval_loss": 0.5597090125083923, | |
| "eval_runtime": 45.2134, | |
| "eval_samples_per_second": 7.299, | |
| "eval_steps_per_second": 0.243, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.3422, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3364, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_accuracy": 0.8090909090909091, | |
| "eval_loss": 0.5729926228523254, | |
| "eval_runtime": 45.0505, | |
| "eval_samples_per_second": 7.325, | |
| "eval_steps_per_second": 0.244, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.3156, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 18.77, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.2976, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 18.96, | |
| "eval_accuracy": 0.8090909090909091, | |
| "eval_loss": 0.5741696357727051, | |
| "eval_runtime": 45.8457, | |
| "eval_samples_per_second": 7.198, | |
| "eval_steps_per_second": 0.24, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 19.26, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.3209, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "learning_rate": 0.0, | |
| "loss": 0.3229, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "eval_accuracy": 0.8121212121212121, | |
| "eval_loss": 0.5653126835823059, | |
| "eval_runtime": 41.6194, | |
| "eval_samples_per_second": 7.929, | |
| "eval_steps_per_second": 0.264, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "step": 400, | |
| "total_flos": 5.1138191421254246e+17, | |
| "train_loss": 0.39375978350639346, | |
| "train_runtime": 7915.8379, | |
| "train_samples_per_second": 6.476, | |
| "train_steps_per_second": 0.051 | |
| } | |
| ], | |
| "max_steps": 400, | |
| "num_train_epochs": 20, | |
| "total_flos": 5.1138191421254246e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |