{ "best_metric": 0.665397047996521, "best_model_checkpoint": "/tmp/model/checkpoint-38", "epoch": 1.0, "eval_steps": 500, "global_step": 38, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03, "learning_rate": 3.2e-06, "loss": 0.6931, "step": 1 }, { "epoch": 0.05, "learning_rate": 6.4e-06, "loss": 0.6931, "step": 2 }, { "epoch": 0.08, "learning_rate": 9.6e-06, "loss": 0.6931, "step": 3 }, { "epoch": 0.11, "learning_rate": 1.28e-05, "loss": 0.693, "step": 4 }, { "epoch": 0.13, "learning_rate": 1.6e-05, "loss": 0.6929, "step": 5 }, { "epoch": 0.16, "learning_rate": 1.92e-05, "loss": 0.6927, "step": 6 }, { "epoch": 0.18, "learning_rate": 2.24e-05, "loss": 0.6921, "step": 7 }, { "epoch": 0.21, "learning_rate": 2.56e-05, "loss": 0.6916, "step": 8 }, { "epoch": 0.24, "learning_rate": 2.88e-05, "loss": 0.6903, "step": 9 }, { "epoch": 0.26, "learning_rate": 3.2e-05, "loss": 0.692, "step": 10 }, { "epoch": 0.29, "learning_rate": 3.52e-05, "loss": 0.6883, "step": 11 }, { "epoch": 0.32, "learning_rate": 3.84e-05, "loss": 0.6922, "step": 12 }, { "epoch": 0.34, "learning_rate": 4.1599999999999995e-05, "loss": 0.6872, "step": 13 }, { "epoch": 0.37, "learning_rate": 4.48e-05, "loss": 0.6915, "step": 14 }, { "epoch": 0.39, "learning_rate": 4.8e-05, "loss": 0.6924, "step": 15 }, { "epoch": 0.42, "learning_rate": 5.12e-05, "loss": 0.6924, "step": 16 }, { "epoch": 0.45, "learning_rate": 5.08235294117647e-05, "loss": 0.6804, "step": 17 }, { "epoch": 0.47, "learning_rate": 5.0447058823529415e-05, "loss": 0.6788, "step": 18 }, { "epoch": 0.5, "learning_rate": 5.007058823529411e-05, "loss": 0.6869, "step": 19 }, { "epoch": 0.53, "learning_rate": 4.969411764705882e-05, "loss": 0.681, "step": 20 }, { "epoch": 0.55, "learning_rate": 4.931764705882353e-05, "loss": 0.6895, "step": 21 }, { "epoch": 0.58, "learning_rate": 4.8941176470588235e-05, "loss": 0.6844, "step": 22 }, { "epoch": 0.61, "learning_rate": 4.856470588235294e-05, "loss": 0.6761, "step": 23 }, { "epoch": 0.63, "learning_rate": 4.8188235294117645e-05, "loss": 0.6691, "step": 24 }, { "epoch": 0.66, "learning_rate": 4.781176470588235e-05, "loss": 0.6717, "step": 25 }, { "epoch": 0.68, "learning_rate": 4.7435294117647055e-05, "loss": 0.6752, "step": 26 }, { "epoch": 0.71, "learning_rate": 4.705882352941176e-05, "loss": 0.6837, "step": 27 }, { "epoch": 0.74, "learning_rate": 4.6682352941176466e-05, "loss": 0.6834, "step": 28 }, { "epoch": 0.76, "learning_rate": 4.630588235294118e-05, "loss": 0.6646, "step": 29 }, { "epoch": 0.79, "learning_rate": 4.592941176470588e-05, "loss": 0.6719, "step": 30 }, { "epoch": 0.82, "learning_rate": 4.555294117647058e-05, "loss": 0.667, "step": 31 }, { "epoch": 0.84, "learning_rate": 4.517647058823529e-05, "loss": 0.6774, "step": 32 }, { "epoch": 0.87, "learning_rate": 4.48e-05, "loss": 0.678, "step": 33 }, { "epoch": 0.89, "learning_rate": 4.44235294117647e-05, "loss": 0.6657, "step": 34 }, { "epoch": 0.92, "learning_rate": 4.4047058823529415e-05, "loss": 0.6539, "step": 35 }, { "epoch": 0.95, "learning_rate": 4.367058823529411e-05, "loss": 0.662, "step": 36 }, { "epoch": 0.97, "learning_rate": 4.329411764705882e-05, "loss": 0.7082, "step": 37 }, { "epoch": 1.0, "learning_rate": 4.291764705882353e-05, "loss": 0.6554, "step": 38 }, { "epoch": 1.0, "eval_accuracy": 0.6052631578947368, "eval_auc": 0.9916264090177134, "eval_f1": 0.0, "eval_loss": 0.665397047996521, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 14.6602, "eval_samples_per_second": 7.776, "eval_steps_per_second": 0.341, "step": 38 } ], "logging_steps": 1, "max_steps": 152, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "total_flos": 9662108559667200.0, "train_batch_size": 12, "trial_name": null, "trial_params": null }