{ "best_global_step": 10, "best_metric": 0.6678542494773865, "best_model_checkpoint": "build_advice_results/checkpoint-10", "epoch": 3.0, "eval_steps": 10, "global_step": 15, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4, "grad_norm": 1.5401430959734617, "learning_rate": 0.0004, "loss": 2.0043, "step": 2 }, { "epoch": 0.8, "grad_norm": 0.37247683757617084, "learning_rate": 0.00036923076923076927, "loss": 1.6466, "step": 4 }, { "epoch": 1.2, "grad_norm": 0.2656771064483186, "learning_rate": 0.0003076923076923077, "loss": 0.9797, "step": 6 }, { "epoch": 1.6, "grad_norm": 0.20811056348079962, "learning_rate": 0.0002461538461538462, "loss": 0.8044, "step": 8 }, { "epoch": 2.0, "grad_norm": 0.17555369266614715, "learning_rate": 0.00018461538461538463, "loss": 0.6931, "step": 10 }, { "epoch": 2.0, "eval_accuracy": 0.8117575597059256, "eval_loss": 0.6678542494773865, "eval_runtime": 63.3038, "eval_samples_per_second": 0.521, "eval_steps_per_second": 0.079, "step": 10 }, { "epoch": 2.4, "grad_norm": 0.16558603840358166, "learning_rate": 0.0001230769230769231, "loss": 0.6206, "step": 12 }, { "epoch": 2.8, "grad_norm": 0.14335467645372332, "learning_rate": 6.153846153846155e-05, "loss": 0.5265, "step": 14 }, { "epoch": 3.0, "step": 15, "total_flos": 2724798922752.0, "train_loss": 1.0087621808052063, "train_runtime": 1033.1417, "train_samples_per_second": 0.226, "train_steps_per_second": 0.015 } ], "logging_steps": 2, "max_steps": 15, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2724798922752.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }