{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.009101251422070534, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0018202502844141069, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0018202502844141069, "eval_loss": NaN, "eval_runtime": 46.3418, "eval_samples_per_second": 19.982, "eval_steps_per_second": 9.991, "step": 1 }, { "epoch": 0.0036405005688282138, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0036405005688282138, "eval_loss": NaN, "eval_runtime": 7.0729, "eval_samples_per_second": 130.923, "eval_steps_per_second": 65.461, "step": 2 }, { "epoch": 0.005460750853242321, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0072810011376564275, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0072810011376564275, "eval_loss": NaN, "eval_runtime": 7.2363, "eval_samples_per_second": 127.966, "eval_steps_per_second": 63.983, "step": 4 }, { "epoch": 0.009101251422070534, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "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": 178076327608320.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }