{ "best_metric": 0.9372822299651568, "best_model_checkpoint": "brain-tumor-classification/checkpoint-81", "epoch": 4.938271604938271, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.49382716049382713, "grad_norm": 11.951680183410645, "learning_rate": 5e-05, "loss": 1.2238, "step": 10 }, { "epoch": 0.9876543209876543, "grad_norm": 11.546021461486816, "learning_rate": 4.4444444444444447e-05, "loss": 0.8509, "step": 20 }, { "epoch": 0.9876543209876543, "eval_accuracy": 0.8466898954703833, "eval_loss": 0.5305207967758179, "eval_runtime": 2.7821, "eval_samples_per_second": 103.16, "eval_steps_per_second": 3.235, "step": 20 }, { "epoch": 1.4814814814814814, "grad_norm": 13.172475814819336, "learning_rate": 3.888888888888889e-05, "loss": 0.5721, "step": 30 }, { "epoch": 1.9753086419753085, "grad_norm": 7.819632530212402, "learning_rate": 3.3333333333333335e-05, "loss": 0.4478, "step": 40 }, { "epoch": 1.9753086419753085, "eval_accuracy": 0.9094076655052264, "eval_loss": 0.3092304468154907, "eval_runtime": 2.5037, "eval_samples_per_second": 114.631, "eval_steps_per_second": 3.595, "step": 40 }, { "epoch": 2.4691358024691357, "grad_norm": 10.437914848327637, "learning_rate": 2.777777777777778e-05, "loss": 0.3668, "step": 50 }, { "epoch": 2.962962962962963, "grad_norm": 9.35677433013916, "learning_rate": 2.2222222222222223e-05, "loss": 0.3313, "step": 60 }, { "epoch": 2.962962962962963, "eval_accuracy": 0.9233449477351916, "eval_loss": 0.24220147728919983, "eval_runtime": 2.4542, "eval_samples_per_second": 116.944, "eval_steps_per_second": 3.667, "step": 60 }, { "epoch": 3.45679012345679, "grad_norm": 8.183242797851562, "learning_rate": 1.6666666666666667e-05, "loss": 0.2979, "step": 70 }, { "epoch": 3.950617283950617, "grad_norm": 8.208118438720703, "learning_rate": 1.1111111111111112e-05, "loss": 0.2777, "step": 80 }, { "epoch": 4.0, "eval_accuracy": 0.9372822299651568, "eval_loss": 0.1715514212846756, "eval_runtime": 2.7133, "eval_samples_per_second": 105.776, "eval_steps_per_second": 3.317, "step": 81 }, { "epoch": 4.444444444444445, "grad_norm": 8.672185897827148, "learning_rate": 5.555555555555556e-06, "loss": 0.2684, "step": 90 }, { "epoch": 4.938271604938271, "grad_norm": 10.231292724609375, "learning_rate": 0.0, "loss": 0.2465, "step": 100 }, { "epoch": 4.938271604938271, "eval_accuracy": 0.9372822299651568, "eval_loss": 0.16363371908664703, "eval_runtime": 2.7577, "eval_samples_per_second": 104.074, "eval_steps_per_second": 3.264, "step": 100 }, { "epoch": 4.938271604938271, "step": 100, "total_flos": 3.1727957353537536e+17, "train_loss": 0.4883076953887939, "train_runtime": 265.3223, "train_samples_per_second": 48.677, "train_steps_per_second": 0.377 }, { "epoch": 4.938271604938271, "eval_accuracy": 0.9372822299651568, "eval_loss": 0.1715514212846756, "eval_runtime": 2.7579, "eval_samples_per_second": 104.066, "eval_steps_per_second": 3.263, "step": 100 }, { "epoch": 4.938271604938271, "eval_accuracy": 0.9156020131629887, "eval_loss": 0.22556395828723907, "eval_runtime": 22.7546, "eval_samples_per_second": 113.516, "eval_steps_per_second": 3.56, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 5, "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": 3.1727957353537536e+17, "train_batch_size": 32, "trial_name": null, "trial_params": null }