{ "best_metric": 0.941358024691358, "best_model_checkpoint": "convnext-tiny-224-finetuned-eurosat/checkpoint-171", "epoch": 3.0, "eval_steps": 500, "global_step": 171, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.17543859649122806, "grad_norm": 1.6056560277938843, "learning_rate": 2.777777777777778e-05, "loss": 2.3048, "step": 10 }, { "epoch": 0.3508771929824561, "grad_norm": 3.1393508911132812, "learning_rate": 4.9346405228758174e-05, "loss": 2.1547, "step": 20 }, { "epoch": 0.5263157894736842, "grad_norm": 2.2008461952209473, "learning_rate": 4.607843137254902e-05, "loss": 1.873, "step": 30 }, { "epoch": 0.7017543859649122, "grad_norm": 2.88468861579895, "learning_rate": 4.281045751633987e-05, "loss": 1.5467, "step": 40 }, { "epoch": 0.8771929824561403, "grad_norm": 4.3117899894714355, "learning_rate": 3.954248366013072e-05, "loss": 1.2852, "step": 50 }, { "epoch": 1.0, "eval_accuracy": 0.8728395061728395, "eval_loss": 0.9943345189094543, "eval_runtime": 112.9902, "eval_samples_per_second": 14.338, "eval_steps_per_second": 0.23, "step": 57 }, { "epoch": 1.0526315789473684, "grad_norm": 2.6797170639038086, "learning_rate": 3.627450980392157e-05, "loss": 1.0323, "step": 60 }, { "epoch": 1.2280701754385965, "grad_norm": 3.286217212677002, "learning_rate": 3.300653594771242e-05, "loss": 0.8614, "step": 70 }, { "epoch": 1.4035087719298245, "grad_norm": 3.1749117374420166, "learning_rate": 2.9738562091503268e-05, "loss": 0.7304, "step": 80 }, { "epoch": 1.5789473684210527, "grad_norm": 2.400712728500366, "learning_rate": 2.647058823529412e-05, "loss": 0.6561, "step": 90 }, { "epoch": 1.7543859649122808, "grad_norm": 3.6787238121032715, "learning_rate": 2.320261437908497e-05, "loss": 0.576, "step": 100 }, { "epoch": 1.9298245614035088, "grad_norm": 3.9098289012908936, "learning_rate": 1.993464052287582e-05, "loss": 0.5203, "step": 110 }, { "epoch": 2.0, "eval_accuracy": 0.932716049382716, "eval_loss": 0.4477611482143402, "eval_runtime": 115.8395, "eval_samples_per_second": 13.985, "eval_steps_per_second": 0.224, "step": 114 }, { "epoch": 2.1052631578947367, "grad_norm": 1.8085237741470337, "learning_rate": 1.6666666666666667e-05, "loss": 0.4635, "step": 120 }, { "epoch": 2.280701754385965, "grad_norm": 2.8854968547821045, "learning_rate": 1.3398692810457516e-05, "loss": 0.4567, "step": 130 }, { "epoch": 2.456140350877193, "grad_norm": 3.9845328330993652, "learning_rate": 1.0130718954248367e-05, "loss": 0.3967, "step": 140 }, { "epoch": 2.6315789473684212, "grad_norm": 3.0889475345611572, "learning_rate": 6.862745098039216e-06, "loss": 0.4008, "step": 150 }, { "epoch": 2.807017543859649, "grad_norm": 3.4937639236450195, "learning_rate": 3.5947712418300652e-06, "loss": 0.3938, "step": 160 }, { "epoch": 2.982456140350877, "grad_norm": 4.640423774719238, "learning_rate": 3.2679738562091505e-07, "loss": 0.3931, "step": 170 }, { "epoch": 3.0, "eval_accuracy": 0.941358024691358, "eval_loss": 0.338970422744751, "eval_runtime": 108.2196, "eval_samples_per_second": 14.97, "eval_steps_per_second": 0.24, "step": 171 }, { "epoch": 3.0, "step": 171, "total_flos": 1.0993259373775258e+18, "train_loss": 0.9407536648867423, "train_runtime": 3757.4507, "train_samples_per_second": 11.641, "train_steps_per_second": 0.046 } ], "logging_steps": 10, "max_steps": 171, "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": 1.0993259373775258e+18, "train_batch_size": 64, "trial_name": null, "trial_params": null }