{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "grad_norm": 1.394713282585144, "learning_rate": 2e-05, "loss": 1.5103, "step": 10 }, { "epoch": 0.2, "grad_norm": 1.7702547311782837, "learning_rate": 1.9396926207859085e-05, "loss": 1.2272, "step": 20 }, { "epoch": 0.3, "grad_norm": 1.7972954511642456, "learning_rate": 1.766044443118978e-05, "loss": 1.0918, "step": 30 }, { "epoch": 0.4, "grad_norm": 1.4144309759140015, "learning_rate": 1.5000000000000002e-05, "loss": 1.0666, "step": 40 }, { "epoch": 0.5, "grad_norm": 1.6088738441467285, "learning_rate": 1.1736481776669307e-05, "loss": 0.9902, "step": 50 }, { "epoch": 0.6, "grad_norm": 1.517215609550476, "learning_rate": 8.263518223330698e-06, "loss": 0.8776, "step": 60 }, { "epoch": 0.7, "grad_norm": 1.463085651397705, "learning_rate": 5.000000000000003e-06, "loss": 0.8724, "step": 70 }, { "epoch": 0.8, "grad_norm": 1.6904792785644531, "learning_rate": 2.339555568810221e-06, "loss": 0.935, "step": 80 }, { "epoch": 0.9, "grad_norm": 1.6216388940811157, "learning_rate": 6.030737921409169e-07, "loss": 0.9456, "step": 90 }, { "epoch": 1.0, "grad_norm": 1.4895377159118652, "learning_rate": 0.0, "loss": 0.8522, "step": 100 }, { "epoch": 1.0, "step": 100, "total_flos": 2315448779538432.0, "train_loss": 1.0368848323822022, "train_runtime": 182.4958, "train_samples_per_second": 1.096, "train_steps_per_second": 0.548 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2315448779538432.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }