| { | |
| "best_metric": 0.9365918097754293, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-213", | |
| "epoch": 9.68421052631579, | |
| "eval_steps": 500, | |
| "global_step": 230, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 8.034697532653809, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 0.3573, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 7.977205753326416, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.3125, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.968421052631579, | |
| "eval_accuracy": 0.8731836195508587, | |
| "eval_loss": 0.3340586721897125, | |
| "eval_runtime": 7.3502, | |
| "eval_samples_per_second": 102.991, | |
| "eval_steps_per_second": 3.265, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 9.418652534484863, | |
| "learning_rate": 4.830917874396135e-05, | |
| "loss": 0.2766, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 11.136240005493164, | |
| "learning_rate": 4.589371980676328e-05, | |
| "loss": 0.2977, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9789473684210526, | |
| "eval_accuracy": 0.9062087186261559, | |
| "eval_loss": 0.2942771017551422, | |
| "eval_runtime": 7.3815, | |
| "eval_samples_per_second": 102.554, | |
| "eval_steps_per_second": 3.251, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 8.324960708618164, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.2961, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 7.641033172607422, | |
| "learning_rate": 4.106280193236715e-05, | |
| "loss": 0.2195, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 8.356009483337402, | |
| "learning_rate": 3.864734299516908e-05, | |
| "loss": 0.2677, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.9894736842105263, | |
| "eval_accuracy": 0.916776750330251, | |
| "eval_loss": 0.2374182939529419, | |
| "eval_runtime": 10.1855, | |
| "eval_samples_per_second": 74.322, | |
| "eval_steps_per_second": 2.356, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 3.3684210526315788, | |
| "grad_norm": 7.1681694984436035, | |
| "learning_rate": 3.6231884057971014e-05, | |
| "loss": 0.2403, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.7894736842105265, | |
| "grad_norm": 4.950290203094482, | |
| "learning_rate": 3.381642512077295e-05, | |
| "loss": 0.2483, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9207397622192867, | |
| "eval_loss": 0.22298040986061096, | |
| "eval_runtime": 7.1036, | |
| "eval_samples_per_second": 106.565, | |
| "eval_steps_per_second": 3.379, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 4.2105263157894735, | |
| "grad_norm": 6.089962959289551, | |
| "learning_rate": 3.140096618357488e-05, | |
| "loss": 0.2446, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.631578947368421, | |
| "grad_norm": 5.7862677574157715, | |
| "learning_rate": 2.8985507246376814e-05, | |
| "loss": 0.2331, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.968421052631579, | |
| "eval_accuracy": 0.9233817701453104, | |
| "eval_loss": 0.21976187825202942, | |
| "eval_runtime": 7.5299, | |
| "eval_samples_per_second": 100.533, | |
| "eval_steps_per_second": 3.187, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 5.052631578947368, | |
| "grad_norm": 3.7768943309783936, | |
| "learning_rate": 2.6570048309178748e-05, | |
| "loss": 0.22, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 5.473684210526316, | |
| "grad_norm": 7.145321846008301, | |
| "learning_rate": 2.4154589371980676e-05, | |
| "loss": 0.2209, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.894736842105263, | |
| "grad_norm": 9.237335205078125, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 0.2315, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.978947368421053, | |
| "eval_accuracy": 0.9180977542932629, | |
| "eval_loss": 0.2150202840566635, | |
| "eval_runtime": 6.91, | |
| "eval_samples_per_second": 109.551, | |
| "eval_steps_per_second": 3.473, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 6.315789473684211, | |
| "grad_norm": 6.9982428550720215, | |
| "learning_rate": 1.932367149758454e-05, | |
| "loss": 0.1987, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.7368421052631575, | |
| "grad_norm": 7.03655481338501, | |
| "learning_rate": 1.6908212560386476e-05, | |
| "loss": 0.2249, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.989473684210527, | |
| "eval_accuracy": 0.9233817701453104, | |
| "eval_loss": 0.21770989894866943, | |
| "eval_runtime": 7.2386, | |
| "eval_samples_per_second": 104.578, | |
| "eval_steps_per_second": 3.316, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 7.157894736842105, | |
| "grad_norm": 5.7152581214904785, | |
| "learning_rate": 1.4492753623188407e-05, | |
| "loss": 0.1732, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 7.578947368421053, | |
| "grad_norm": 6.694705009460449, | |
| "learning_rate": 1.2077294685990338e-05, | |
| "loss": 0.2026, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 5.67457389831543, | |
| "learning_rate": 9.66183574879227e-06, | |
| "loss": 0.1683, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9326287978863936, | |
| "eval_loss": 0.20676808059215546, | |
| "eval_runtime": 7.2386, | |
| "eval_samples_per_second": 104.578, | |
| "eval_steps_per_second": 3.316, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 8.421052631578947, | |
| "grad_norm": 5.295100688934326, | |
| "learning_rate": 7.246376811594203e-06, | |
| "loss": 0.1825, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 8.842105263157894, | |
| "grad_norm": 8.137918472290039, | |
| "learning_rate": 4.830917874396135e-06, | |
| "loss": 0.1725, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 8.968421052631578, | |
| "eval_accuracy": 0.9365918097754293, | |
| "eval_loss": 0.20404939353466034, | |
| "eval_runtime": 7.0704, | |
| "eval_samples_per_second": 107.066, | |
| "eval_steps_per_second": 3.394, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 9.263157894736842, | |
| "grad_norm": 6.243011474609375, | |
| "learning_rate": 2.4154589371980677e-06, | |
| "loss": 0.1653, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 9.68421052631579, | |
| "grad_norm": 5.12047004699707, | |
| "learning_rate": 0.0, | |
| "loss": 0.1789, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 9.68421052631579, | |
| "eval_accuracy": 0.9365918097754293, | |
| "eval_loss": 0.20334188640117645, | |
| "eval_runtime": 7.0261, | |
| "eval_samples_per_second": 107.741, | |
| "eval_steps_per_second": 3.416, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 9.68421052631579, | |
| "step": 230, | |
| "total_flos": 7.494072602457047e+17, | |
| "train_loss": 0.23186731493991355, | |
| "train_runtime": 640.6828, | |
| "train_samples_per_second": 47.262, | |
| "train_steps_per_second": 0.359 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 230, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 7.494072602457047e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |