{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.029390154298310066, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0029390154298310064, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0029390154298310064, "eval_loss": NaN, "eval_runtime": 9.2057, "eval_samples_per_second": 15.643, "eval_steps_per_second": 7.821, "step": 1 }, { "epoch": 0.005878030859662013, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.00881704628949302, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.00881704628949302, "eval_loss": NaN, "eval_runtime": 7.8441, "eval_samples_per_second": 18.358, "eval_steps_per_second": 9.179, "step": 3 }, { "epoch": 0.011756061719324026, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.014695077149155033, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.01763409257898604, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.01763409257898604, "eval_loss": NaN, "eval_runtime": 7.8556, "eval_samples_per_second": 18.331, "eval_steps_per_second": 9.165, "step": 6 }, { "epoch": 0.020573108008817047, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.02351212343864805, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.02645113886847906, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.02645113886847906, "eval_loss": NaN, "eval_runtime": 7.8563, "eval_samples_per_second": 18.329, "eval_steps_per_second": 9.165, "step": 9 }, { "epoch": 0.029390154298310066, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3699128496291840.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }