| { | |
| "best_metric": 0.39378238341968913, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-65", | |
| "epoch": 4.814814814814815, | |
| "eval_steps": 500, | |
| "global_step": 65, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 2.7531347274780273, | |
| "learning_rate": 4.741379310344828e-05, | |
| "loss": 2.6414, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9629629629629629, | |
| "eval_accuracy": 0.27461139896373055, | |
| "eval_loss": 2.4260499477386475, | |
| "eval_runtime": 4.2205, | |
| "eval_samples_per_second": 45.729, | |
| "eval_steps_per_second": 1.659, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 6.018283843994141, | |
| "learning_rate": 3.8793103448275865e-05, | |
| "loss": 2.4558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.33678756476683935, | |
| "eval_loss": 2.15580415725708, | |
| "eval_runtime": 4.3823, | |
| "eval_samples_per_second": 44.04, | |
| "eval_steps_per_second": 1.597, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 8.673904418945312, | |
| "learning_rate": 3.017241379310345e-05, | |
| "loss": 2.2726, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 10.522686004638672, | |
| "learning_rate": 2.1551724137931033e-05, | |
| "loss": 2.1176, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "eval_accuracy": 0.38341968911917096, | |
| "eval_loss": 2.01640248298645, | |
| "eval_runtime": 4.245, | |
| "eval_samples_per_second": 45.465, | |
| "eval_steps_per_second": 1.649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.7037037037037037, | |
| "grad_norm": 12.191962242126465, | |
| "learning_rate": 1.2931034482758622e-05, | |
| "loss": 2.0264, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.38860103626943004, | |
| "eval_loss": 1.9313786029815674, | |
| "eval_runtime": 4.1882, | |
| "eval_samples_per_second": 46.082, | |
| "eval_steps_per_second": 1.671, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 8.964757919311523, | |
| "learning_rate": 4.310344827586207e-06, | |
| "loss": 1.9409, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.814814814814815, | |
| "eval_accuracy": 0.39378238341968913, | |
| "eval_loss": 1.9148268699645996, | |
| "eval_runtime": 4.182, | |
| "eval_samples_per_second": 46.15, | |
| "eval_steps_per_second": 1.674, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.814814814814815, | |
| "step": 65, | |
| "total_flos": 1.0808265111345562e+18, | |
| "train_loss": 2.2193346903874325, | |
| "train_runtime": 316.4726, | |
| "train_samples_per_second": 27.301, | |
| "train_steps_per_second": 0.205 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 65, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 1.0808265111345562e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |