{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 81, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.12345679012345678, "grad_norm": 18.884857177734375, "learning_rate": 8.765432098765433e-05, "loss": 11.7134, "step": 10 }, { "epoch": 0.24691358024691357, "grad_norm": 1.8587737083435059, "learning_rate": 7.530864197530865e-05, "loss": 1.5567, "step": 20 }, { "epoch": 0.37037037037037035, "grad_norm": 0.13458853960037231, "learning_rate": 6.296296296296296e-05, "loss": 0.0378, "step": 30 }, { "epoch": 0.49382716049382713, "grad_norm": 0.05857311934232712, "learning_rate": 5.061728395061729e-05, "loss": 0.0212, "step": 40 }, { "epoch": 0.6172839506172839, "grad_norm": 0.009554409421980381, "learning_rate": 3.82716049382716e-05, "loss": 0.0069, "step": 50 }, { "epoch": 0.7407407407407407, "grad_norm": 0.0058960807509720325, "learning_rate": 2.5925925925925925e-05, "loss": 0.0027, "step": 60 }, { "epoch": 0.8641975308641975, "grad_norm": 0.0033985786139965057, "learning_rate": 1.3580246913580247e-05, "loss": 0.0026, "step": 70 }, { "epoch": 0.9876543209876543, "grad_norm": 0.002752589527517557, "learning_rate": 1.234567901234568e-06, "loss": 0.0026, "step": 80 }, { "epoch": 1.0, "step": 81, "total_flos": 1.6678153976020992e+16, "train_loss": 0.0, "train_runtime": 0.009, "train_samples_per_second": 18069.762, "train_steps_per_second": 9034.881 } ], "logging_steps": 10, "max_steps": 81, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.6678153976020992e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }