{ "best_metric": 0.5625, "best_model_checkpoint": "resnet-50-finetuned-eurosat/checkpoint-9", "epoch": 13.0, "eval_steps": 500, "global_step": 39, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.5, "eval_loss": 0.6890198588371277, "eval_runtime": 9.1578, "eval_samples_per_second": 3.494, "eval_steps_per_second": 0.109, "step": 3 }, { "epoch": 2.0, "eval_accuracy": 0.5, "eval_loss": 0.6856250166893005, "eval_runtime": 9.6892, "eval_samples_per_second": 3.303, "eval_steps_per_second": 0.103, "step": 6 }, { "epoch": 3.0, "eval_accuracy": 0.5625, "eval_loss": 0.6796374917030334, "eval_runtime": 8.1871, "eval_samples_per_second": 3.909, "eval_steps_per_second": 0.122, "step": 9 }, { "epoch": 3.4444444444444446, "grad_norm": 6.238272666931152, "learning_rate": 5e-05, "loss": 2.1334, "step": 10 }, { "epoch": 4.0, "eval_accuracy": 0.53125, "eval_loss": 0.6711597442626953, "eval_runtime": 11.5033, "eval_samples_per_second": 2.782, "eval_steps_per_second": 0.087, "step": 12 }, { "epoch": 5.0, "eval_accuracy": 0.53125, "eval_loss": 0.6669355630874634, "eval_runtime": 9.588, "eval_samples_per_second": 3.338, "eval_steps_per_second": 0.104, "step": 15 }, { "epoch": 6.0, "eval_accuracy": 0.53125, "eval_loss": 0.6575976610183716, "eval_runtime": 7.9262, "eval_samples_per_second": 4.037, "eval_steps_per_second": 0.126, "step": 18 }, { "epoch": 6.888888888888889, "grad_norm": 4.825995445251465, "learning_rate": 4.4444444444444447e-05, "loss": 2.0715, "step": 20 }, { "epoch": 7.0, "eval_accuracy": 0.53125, "eval_loss": 0.6581233739852905, "eval_runtime": 9.5086, "eval_samples_per_second": 3.365, "eval_steps_per_second": 0.105, "step": 21 }, { "epoch": 8.0, "eval_accuracy": 0.5625, "eval_loss": 0.6548225283622742, "eval_runtime": 9.6182, "eval_samples_per_second": 3.327, "eval_steps_per_second": 0.104, "step": 24 }, { "epoch": 9.0, "eval_accuracy": 0.5625, "eval_loss": 0.6479971408843994, "eval_runtime": 9.7014, "eval_samples_per_second": 3.298, "eval_steps_per_second": 0.103, "step": 27 }, { "epoch": 10.0, "grad_norm": 2.082106828689575, "learning_rate": 3.888888888888889e-05, "loss": 1.8148, "step": 30 }, { "epoch": 10.0, "eval_accuracy": 0.5625, "eval_loss": 0.6456948518753052, "eval_runtime": 7.9377, "eval_samples_per_second": 4.031, "eval_steps_per_second": 0.126, "step": 30 }, { "epoch": 11.0, "eval_accuracy": 0.5625, "eval_loss": 0.6377989649772644, "eval_runtime": 9.4096, "eval_samples_per_second": 3.401, "eval_steps_per_second": 0.106, "step": 33 }, { "epoch": 12.0, "eval_accuracy": 0.5625, "eval_loss": 0.6368027925491333, "eval_runtime": 8.4914, "eval_samples_per_second": 3.769, "eval_steps_per_second": 0.118, "step": 36 }, { "epoch": 13.0, "eval_accuracy": 0.5625, "eval_loss": 0.6324682235717773, "eval_runtime": 9.2297, "eval_samples_per_second": 3.467, "eval_steps_per_second": 0.108, "step": 39 }, { "epoch": 13.0, "step": 39, "total_flos": 7.702080823277568e+16, "train_loss": 1.9811313824775891, "train_runtime": 3450.3358, "train_samples_per_second": 4.043, "train_steps_per_second": 0.029 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 50, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 10, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 10 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7.702080823277568e+16, "train_batch_size": 32, "trial_name": null, "trial_params": null }