{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.03508771929824561, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.007017543859649123, "grad_norm": 0.5216090679168701, "learning_rate": 1e-05, "loss": 0.5271, "step": 1 }, { "epoch": 0.007017543859649123, "eval_loss": 0.5302073359489441, "eval_runtime": 56.9297, "eval_samples_per_second": 4.216, "eval_steps_per_second": 2.108, "step": 1 }, { "epoch": 0.014035087719298246, "grad_norm": 0.47789695858955383, "learning_rate": 2e-05, "loss": 0.5502, "step": 2 }, { "epoch": 0.014035087719298246, "eval_loss": 0.49564963579177856, "eval_runtime": 11.2365, "eval_samples_per_second": 21.359, "eval_steps_per_second": 10.679, "step": 2 }, { "epoch": 0.021052631578947368, "grad_norm": 0.4889359772205353, "learning_rate": 3e-05, "loss": 0.4988, "step": 3 }, { "epoch": 0.028070175438596492, "grad_norm": 0.4712343215942383, "learning_rate": 4e-05, "loss": 0.4643, "step": 4 }, { "epoch": 0.028070175438596492, "eval_loss": 0.46725717186927795, "eval_runtime": 12.5186, "eval_samples_per_second": 19.172, "eval_steps_per_second": 9.586, "step": 4 }, { "epoch": 0.03508771929824561, "grad_norm": 0.49490612745285034, "learning_rate": 5e-05, "loss": 0.4744, "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": 3485272092180480.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }