{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.024821594787465096, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004964318957493019, "grad_norm": 50.673465728759766, "learning_rate": 1e-05, "loss": 21.3814, "step": 1 }, { "epoch": 0.004964318957493019, "eval_loss": 21.190950393676758, "eval_runtime": 70.4577, "eval_samples_per_second": 4.826, "eval_steps_per_second": 2.413, "step": 1 }, { "epoch": 0.009928637914986037, "grad_norm": 52.17545700073242, "learning_rate": 2e-05, "loss": 21.0181, "step": 2 }, { "epoch": 0.009928637914986037, "eval_loss": 20.469270706176758, "eval_runtime": 25.0561, "eval_samples_per_second": 13.57, "eval_steps_per_second": 6.785, "step": 2 }, { "epoch": 0.014892956872479057, "grad_norm": 48.04680252075195, "learning_rate": 3e-05, "loss": 20.1382, "step": 3 }, { "epoch": 0.019857275829972074, "grad_norm": 47.30276107788086, "learning_rate": 4e-05, "loss": 19.2874, "step": 4 }, { "epoch": 0.019857275829972074, "eval_loss": 17.303936004638672, "eval_runtime": 25.0968, "eval_samples_per_second": 13.548, "eval_steps_per_second": 6.774, "step": 4 }, { "epoch": 0.024821594787465096, "grad_norm": 51.19380569458008, "learning_rate": 5e-05, "loss": 16.9652, "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": 3822182832537600.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }