{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.551724137931035, "eval_steps": 25, "global_step": 6, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5517241379310345, "grad_norm": 0.08105026930570602, "learning_rate": 9.330127018922194e-05, "loss": 10.3614, "step": 1 }, { "epoch": 0.5517241379310345, "eval_loss": 10.35869312286377, "eval_runtime": 0.0196, "eval_samples_per_second": 610.925, "eval_steps_per_second": 101.821, "step": 1 }, { "epoch": 1.4137931034482758, "grad_norm": 0.14930689334869385, "learning_rate": 7.500000000000001e-05, "loss": 18.1631, "step": 2 }, { "epoch": 2.2758620689655173, "grad_norm": 0.15816818177700043, "learning_rate": 5e-05, "loss": 18.2277, "step": 3 }, { "epoch": 3.1379310344827585, "grad_norm": 0.14398109912872314, "learning_rate": 2.500000000000001e-05, "loss": 18.093, "step": 4 }, { "epoch": 3.689655172413793, "grad_norm": 0.13334262371063232, "learning_rate": 6.698729810778065e-06, "loss": 18.0604, "step": 5 }, { "epoch": 4.551724137931035, "grad_norm": 0.07414166629314423, "learning_rate": 0.0, "loss": 10.3645, "step": 6 } ], "logging_steps": 1, "max_steps": 6, "num_input_tokens_seen": 0, "num_train_epochs": 6, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5132167151616.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }