| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-212", | |
| "epoch": 2.976303317535545, | |
| "eval_steps": 500, | |
| "global_step": 315, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0947867298578199, | |
| "grad_norm": 7.812982082366943, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 6.4564, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1895734597156398, | |
| "grad_norm": 8.798693656921387, | |
| "learning_rate": 3.125e-05, | |
| "loss": 6.366, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2843601895734597, | |
| "grad_norm": 36.50003433227539, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 5.9633, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3791469194312796, | |
| "grad_norm": 34.34447479248047, | |
| "learning_rate": 4.858657243816255e-05, | |
| "loss": 4.1076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47393364928909953, | |
| "grad_norm": 188.84632873535156, | |
| "learning_rate": 4.6819787985865726e-05, | |
| "loss": 2.403, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5687203791469194, | |
| "grad_norm": 55.603084564208984, | |
| "learning_rate": 4.50530035335689e-05, | |
| "loss": 1.5914, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6635071090047393, | |
| "grad_norm": 48.88166427612305, | |
| "learning_rate": 4.328621908127209e-05, | |
| "loss": 0.8822, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "grad_norm": 34.93512725830078, | |
| "learning_rate": 4.1519434628975266e-05, | |
| "loss": 0.6805, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8530805687203792, | |
| "grad_norm": 42.45512771606445, | |
| "learning_rate": 3.975265017667845e-05, | |
| "loss": 0.4599, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "grad_norm": 25.569683074951172, | |
| "learning_rate": 3.7985865724381624e-05, | |
| "loss": 0.3571, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.992, | |
| "eval_loss": 0.046910375356674194, | |
| "eval_runtime": 14.0627, | |
| "eval_samples_per_second": 106.665, | |
| "eval_steps_per_second": 3.342, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.037914691943128, | |
| "grad_norm": 22.71461296081543, | |
| "learning_rate": 3.621908127208481e-05, | |
| "loss": 0.339, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.132701421800948, | |
| "grad_norm": 39.072593688964844, | |
| "learning_rate": 3.445229681978799e-05, | |
| "loss": 0.674, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2274881516587677, | |
| "grad_norm": 28.356447219848633, | |
| "learning_rate": 3.2685512367491163e-05, | |
| "loss": 0.4667, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3222748815165877, | |
| "grad_norm": 27.163755416870117, | |
| "learning_rate": 3.0918727915194346e-05, | |
| "loss": 0.3833, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4170616113744074, | |
| "grad_norm": 53.821319580078125, | |
| "learning_rate": 2.915194346289753e-05, | |
| "loss": 0.2353, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5118483412322274, | |
| "grad_norm": 15.961763381958008, | |
| "learning_rate": 2.738515901060071e-05, | |
| "loss": 0.2735, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6066350710900474, | |
| "grad_norm": 23.296354293823242, | |
| "learning_rate": 2.5618374558303885e-05, | |
| "loss": 0.2108, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.7014218009478674, | |
| "grad_norm": 14.222640037536621, | |
| "learning_rate": 2.3851590106007068e-05, | |
| "loss": 0.2073, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7962085308056872, | |
| "grad_norm": 17.987783432006836, | |
| "learning_rate": 2.2084805653710246e-05, | |
| "loss": 0.1279, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.890995260663507, | |
| "grad_norm": 34.04901123046875, | |
| "learning_rate": 2.031802120141343e-05, | |
| "loss": 0.2281, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.985781990521327, | |
| "grad_norm": 13.81363296508789, | |
| "learning_rate": 1.855123674911661e-05, | |
| "loss": 0.1158, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.001326344907283783, | |
| "eval_runtime": 14.0164, | |
| "eval_samples_per_second": 107.018, | |
| "eval_steps_per_second": 3.353, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.075829383886256, | |
| "grad_norm": 41.3836784362793, | |
| "learning_rate": 1.678445229681979e-05, | |
| "loss": 0.1724, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.170616113744076, | |
| "grad_norm": 25.138639450073242, | |
| "learning_rate": 1.501766784452297e-05, | |
| "loss": 0.1802, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.265402843601896, | |
| "grad_norm": 5.671016216278076, | |
| "learning_rate": 1.3250883392226149e-05, | |
| "loss": 0.1261, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.360189573459716, | |
| "grad_norm": 32.47148895263672, | |
| "learning_rate": 1.148409893992933e-05, | |
| "loss": 0.1031, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.4549763033175354, | |
| "grad_norm": 22.735076904296875, | |
| "learning_rate": 9.717314487632508e-06, | |
| "loss": 0.1143, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.5497630331753554, | |
| "grad_norm": 20.33681297302246, | |
| "learning_rate": 7.950530035335689e-06, | |
| "loss": 0.2151, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.6445497630331753, | |
| "grad_norm": 31.386720657348633, | |
| "learning_rate": 6.18374558303887e-06, | |
| "loss": 0.1495, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.7393364928909953, | |
| "grad_norm": 0.9427671432495117, | |
| "learning_rate": 4.41696113074205e-06, | |
| "loss": 0.1053, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.834123222748815, | |
| "grad_norm": 12.637048721313477, | |
| "learning_rate": 2.65017667844523e-06, | |
| "loss": 0.089, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.9289099526066353, | |
| "grad_norm": 24.29412841796875, | |
| "learning_rate": 8.8339222614841e-07, | |
| "loss": 0.0934, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.976303317535545, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0002889372408390045, | |
| "eval_runtime": 13.4256, | |
| "eval_samples_per_second": 111.727, | |
| "eval_steps_per_second": 3.501, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.976303317535545, | |
| "step": 315, | |
| "total_flos": 9.988967891346555e+17, | |
| "train_loss": 1.077162364172557, | |
| "train_runtime": 1497.697, | |
| "train_samples_per_second": 27.042, | |
| "train_steps_per_second": 0.21 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 315, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.988967891346555e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |