{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.23738872403560832, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04747774480712166, "grad_norm": 34.152164459228516, "learning_rate": 1e-05, "loss": 10.7595, "step": 1 }, { "epoch": 0.04747774480712166, "eval_loss": 11.51902961730957, "eval_runtime": 32.0704, "eval_samples_per_second": 1.123, "eval_steps_per_second": 0.561, "step": 1 }, { "epoch": 0.09495548961424333, "grad_norm": 41.95406723022461, "learning_rate": 2e-05, "loss": 11.0491, "step": 2 }, { "epoch": 0.09495548961424333, "eval_loss": 11.02177906036377, "eval_runtime": 0.8148, "eval_samples_per_second": 44.184, "eval_steps_per_second": 22.092, "step": 2 }, { "epoch": 0.142433234421365, "grad_norm": 41.50265884399414, "learning_rate": 3e-05, "loss": 10.9377, "step": 3 }, { "epoch": 0.18991097922848665, "grad_norm": 35.109596252441406, "learning_rate": 4e-05, "loss": 9.9652, "step": 4 }, { "epoch": 0.18991097922848665, "eval_loss": 9.634675025939941, "eval_runtime": 0.8335, "eval_samples_per_second": 43.19, "eval_steps_per_second": 21.595, "step": 4 }, { "epoch": 0.23738872403560832, "grad_norm": 38.7088737487793, "learning_rate": 5e-05, "loss": 9.6777, "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": 978955586764800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }