{ "best_metric": 0.0, "best_model_checkpoint": "resnet-18-finetuned-fraud/checkpoint-2", "epoch": 10.0, "eval_steps": 500, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5738, "eval_samples_per_second": 12.2, "eval_steps_per_second": 1.743, "step": 2 }, { "epoch": 2.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5015, "eval_samples_per_second": 13.958, "eval_steps_per_second": 1.994, "step": 4 }, { "epoch": 3.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.4768, "eval_samples_per_second": 14.681, "eval_steps_per_second": 2.097, "step": 6 }, { "epoch": 4.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5964, "eval_samples_per_second": 11.737, "eval_steps_per_second": 1.677, "step": 8 }, { "epoch": 5.0, "grad_norm": 14.733216285705566, "learning_rate": 2.777777777777778e-05, "loss": 2.5692767593311503e+18, "step": 10 }, { "epoch": 5.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5942, "eval_samples_per_second": 11.781, "eval_steps_per_second": 1.683, "step": 10 }, { "epoch": 6.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5529, "eval_samples_per_second": 12.661, "eval_steps_per_second": 1.809, "step": 12 }, { "epoch": 7.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5729, "eval_samples_per_second": 12.218, "eval_steps_per_second": 1.745, "step": 14 }, { "epoch": 8.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5633, "eval_samples_per_second": 12.426, "eval_steps_per_second": 1.775, "step": 16 }, { "epoch": 9.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5508, "eval_samples_per_second": 12.709, "eval_steps_per_second": 1.816, "step": 18 }, { "epoch": 10.0, "grad_norm": 18.8521728515625, "learning_rate": 0.0, "loss": 2.411513773224362e+18, "step": 20 }, { "epoch": 10.0, "eval_loss": 2.060572751382446e+18, "eval_precision": 0.0, "eval_runtime": 0.5394, "eval_samples_per_second": 12.977, "eval_steps_per_second": 1.854, "step": 20 }, { "epoch": 10.0, "step": 20, "total_flos": 5754260945018880.0, "train_loss": 2.490395266277756e+18, "train_runtime": 105.1446, "train_samples_per_second": 5.421, "train_steps_per_second": 0.19 } ], "logging_steps": 10, "max_steps": 20, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "total_flos": 5754260945018880.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }