{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00507700118463361, "eval_steps": 8, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00016923337282112033, "eval_loss": NaN, "eval_runtime": 424.2021, "eval_samples_per_second": 5.867, "eval_steps_per_second": 2.935, "step": 1 }, { "epoch": 0.000507700118463361, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.001015400236926722, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.0013538669825689626, "eval_loss": NaN, "eval_runtime": 424.949, "eval_samples_per_second": 5.857, "eval_steps_per_second": 2.93, "step": 8 }, { "epoch": 0.001523100355390083, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.002030800473853444, "grad_norm": NaN, "learning_rate": 9.755282581475769e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.002538500592316805, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.0027077339651379252, "eval_loss": NaN, "eval_runtime": 424.8746, "eval_samples_per_second": 5.858, "eval_steps_per_second": 2.93, "step": 16 }, { "epoch": 0.003046200710780166, "grad_norm": NaN, "learning_rate": 6.545084971874738e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.0035539008292435267, "grad_norm": NaN, "learning_rate": 4.2178276747988446e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.004061600947706888, "grad_norm": NaN, "learning_rate": 2.061073738537635e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.004061600947706888, "eval_loss": NaN, "eval_runtime": 425.8089, "eval_samples_per_second": 5.845, "eval_steps_per_second": 2.924, "step": 24 }, { "epoch": 0.0045693010661702485, "grad_norm": NaN, "learning_rate": 5.449673790581611e-06, "loss": 0.0, "step": 27 }, { "epoch": 0.00507700118463361, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 30 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 1.572377393627136e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }