{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.019024970273483946, "eval_steps": 2, "global_step": 2, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009512485136741973, "grad_norm": 2.358306884765625, "learning_rate": 1e-05, "loss": 27.4781, "step": 1 }, { "epoch": 0.009512485136741973, "eval_loss": 1.6872767210006714, "eval_runtime": 68.9331, "eval_samples_per_second": 2.582, "eval_steps_per_second": 1.291, "step": 1 }, { "epoch": 0.019024970273483946, "grad_norm": 2.2945337295532227, "learning_rate": 2e-05, "loss": 26.7268, "step": 2 }, { "epoch": 0.019024970273483946, "eval_loss": 1.6841931343078613, "eval_runtime": 25.2645, "eval_samples_per_second": 7.045, "eval_steps_per_second": 3.523, "step": 2 } ], "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": false }, "attributes": {} } }, "total_flos": 4432685841776640.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }