{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0032665060634518802, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006533012126903761, "grad_norm": 1.4845623970031738, "learning_rate": 1e-05, "loss": 177.25, "step": 1 }, { "epoch": 0.0006533012126903761, "eval_loss": 11.06982135772705, "eval_runtime": 16.3973, "eval_samples_per_second": 157.221, "eval_steps_per_second": 78.611, "step": 1 }, { "epoch": 0.0013066024253807521, "grad_norm": 1.5945957899093628, "learning_rate": 2e-05, "loss": 177.0, "step": 2 }, { "epoch": 0.0013066024253807521, "eval_loss": 11.06982135772705, "eval_runtime": 6.2711, "eval_samples_per_second": 411.091, "eval_steps_per_second": 205.545, "step": 2 }, { "epoch": 0.0019599036380711283, "grad_norm": 1.6178580522537231, "learning_rate": 3e-05, "loss": 177.0625, "step": 3 }, { "epoch": 0.0026132048507615043, "grad_norm": 1.3707138299942017, "learning_rate": 4e-05, "loss": 177.3125, "step": 4 }, { "epoch": 0.0026132048507615043, "eval_loss": 11.069772720336914, "eval_runtime": 5.2073, "eval_samples_per_second": 495.071, "eval_steps_per_second": 247.536, "step": 4 }, { "epoch": 0.0032665060634518802, "grad_norm": 1.4526948928833008, "learning_rate": 5e-05, "loss": 177.125, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 16062873600.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }