{ "best_metric": 0.9646761984861227, "best_model_checkpoint": "Brain_Tumor_Classification/checkpoint-415", "epoch": 4.991044776119403, "global_step": 415, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.12, "learning_rate": 1.1904761904761905e-05, "loss": 1.3844, "step": 10 }, { "epoch": 0.24, "learning_rate": 2.380952380952381e-05, "loss": 1.2375, "step": 20 }, { "epoch": 0.36, "learning_rate": 3.571428571428572e-05, "loss": 0.9742, "step": 30 }, { "epoch": 0.48, "learning_rate": 4.761904761904762e-05, "loss": 0.7601, "step": 40 }, { "epoch": 0.6, "learning_rate": 4.8927613941018765e-05, "loss": 0.7047, "step": 50 }, { "epoch": 0.72, "learning_rate": 4.7587131367292224e-05, "loss": 0.5255, "step": 60 }, { "epoch": 0.84, "learning_rate": 4.624664879356568e-05, "loss": 0.5059, "step": 70 }, { "epoch": 0.96, "learning_rate": 4.490616621983915e-05, "loss": 0.4856, "step": 80 }, { "epoch": 0.99, "eval_accuracy": 0.8444070647603028, "eval_f1": 0.8444070647603028, "eval_loss": 0.3771306276321411, "eval_precision": 0.8444070647603028, "eval_recall": 0.8444070647603028, "eval_runtime": 65.7487, "eval_samples_per_second": 18.084, "eval_steps_per_second": 0.578, "step": 83 }, { "epoch": 1.08, "learning_rate": 4.35656836461126e-05, "loss": 0.4626, "step": 90 }, { "epoch": 1.2, "learning_rate": 4.222520107238606e-05, "loss": 0.4249, "step": 100 }, { "epoch": 1.32, "learning_rate": 4.088471849865952e-05, "loss": 0.3855, "step": 110 }, { "epoch": 1.44, "learning_rate": 3.954423592493298e-05, "loss": 0.385, "step": 120 }, { "epoch": 1.56, "learning_rate": 3.8203753351206436e-05, "loss": 0.3522, "step": 130 }, { "epoch": 1.68, "learning_rate": 3.6863270777479895e-05, "loss": 0.367, "step": 140 }, { "epoch": 1.8, "learning_rate": 3.5522788203753354e-05, "loss": 0.3172, "step": 150 }, { "epoch": 1.92, "learning_rate": 3.418230563002681e-05, "loss": 0.3495, "step": 160 }, { "epoch": 1.99, "eval_accuracy": 0.894869638351556, "eval_f1": 0.894869638351556, "eval_loss": 0.2608145773410797, "eval_precision": 0.894869638351556, "eval_recall": 0.894869638351556, "eval_runtime": 66.7411, "eval_samples_per_second": 17.815, "eval_steps_per_second": 0.569, "step": 166 }, { "epoch": 2.05, "learning_rate": 3.284182305630027e-05, "loss": 0.3677, "step": 170 }, { "epoch": 2.17, "learning_rate": 3.1501340482573724e-05, "loss": 0.2809, "step": 180 }, { "epoch": 2.29, "learning_rate": 3.0160857908847186e-05, "loss": 0.297, "step": 190 }, { "epoch": 2.41, "learning_rate": 2.8820375335120648e-05, "loss": 0.3134, "step": 200 }, { "epoch": 2.53, "learning_rate": 2.7479892761394104e-05, "loss": 0.2306, "step": 210 }, { "epoch": 2.64, "learning_rate": 2.6139410187667563e-05, "loss": 0.2442, "step": 220 }, { "epoch": 2.76, "learning_rate": 2.479892761394102e-05, "loss": 0.2885, "step": 230 }, { "epoch": 2.88, "learning_rate": 2.3458445040214477e-05, "loss": 0.252, "step": 240 }, { "epoch": 2.99, "eval_accuracy": 0.9486963835155593, "eval_f1": 0.9486963835155594, "eval_loss": 0.14449167251586914, "eval_precision": 0.9486963835155593, "eval_recall": 0.9486963835155593, "eval_runtime": 64.3986, "eval_samples_per_second": 18.463, "eval_steps_per_second": 0.59, "step": 249 }, { "epoch": 3.01, "learning_rate": 2.211796246648794e-05, "loss": 0.2939, "step": 250 }, { "epoch": 3.13, "learning_rate": 2.0777479892761395e-05, "loss": 0.2099, "step": 260 }, { "epoch": 3.25, "learning_rate": 1.9436997319034853e-05, "loss": 0.2477, "step": 270 }, { "epoch": 3.37, "learning_rate": 1.8096514745308312e-05, "loss": 0.2674, "step": 280 }, { "epoch": 3.49, "learning_rate": 1.675603217158177e-05, "loss": 0.2538, "step": 290 }, { "epoch": 3.61, "learning_rate": 1.5415549597855227e-05, "loss": 0.2201, "step": 300 }, { "epoch": 3.73, "learning_rate": 1.4075067024128689e-05, "loss": 0.2591, "step": 310 }, { "epoch": 3.85, "learning_rate": 1.2734584450402146e-05, "loss": 0.2087, "step": 320 }, { "epoch": 3.97, "learning_rate": 1.1394101876675605e-05, "loss": 0.2364, "step": 330 }, { "epoch": 3.99, "eval_accuracy": 0.95878889823381, "eval_f1": 0.95878889823381, "eval_loss": 0.10286473482847214, "eval_precision": 0.95878889823381, "eval_recall": 0.95878889823381, "eval_runtime": 65.1006, "eval_samples_per_second": 18.264, "eval_steps_per_second": 0.584, "step": 332 }, { "epoch": 4.1, "learning_rate": 1.0053619302949062e-05, "loss": 0.2312, "step": 340 }, { "epoch": 4.21, "learning_rate": 8.71313672922252e-06, "loss": 0.2011, "step": 350 }, { "epoch": 4.33, "learning_rate": 7.372654155495978e-06, "loss": 0.1961, "step": 360 }, { "epoch": 4.45, "learning_rate": 6.032171581769437e-06, "loss": 0.2277, "step": 370 }, { "epoch": 4.57, "learning_rate": 4.691689008042896e-06, "loss": 0.2084, "step": 380 }, { "epoch": 4.69, "learning_rate": 3.351206434316354e-06, "loss": 0.2478, "step": 390 }, { "epoch": 4.81, "learning_rate": 2.0107238605898126e-06, "loss": 0.1992, "step": 400 }, { "epoch": 4.93, "learning_rate": 6.702412868632708e-07, "loss": 0.2178, "step": 410 }, { "epoch": 4.99, "eval_accuracy": 0.9646761984861227, "eval_f1": 0.9646761984861227, "eval_loss": 0.10117336362600327, "eval_precision": 0.9646761984861227, "eval_recall": 0.9646761984861227, "eval_runtime": 66.0046, "eval_samples_per_second": 18.014, "eval_steps_per_second": 0.576, "step": 415 }, { "epoch": 4.99, "step": 415, "total_flos": 1.3278811358711808e+18, "train_loss": 0.383831198531461, "train_runtime": 7560.7227, "train_samples_per_second": 7.075, "train_steps_per_second": 0.055 } ], "max_steps": 415, "num_train_epochs": 5, "total_flos": 1.3278811358711808e+18, "trial_name": null, "trial_params": null }