{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0010695044183901285, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002139008836780257, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0002139008836780257, "eval_loss": NaN, "eval_runtime": 419.2169, "eval_samples_per_second": 18.783, "eval_steps_per_second": 9.391, "step": 1 }, { "epoch": 0.0004278017673560514, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0004278017673560514, "eval_loss": NaN, "eval_runtime": 205.9279, "eval_samples_per_second": 38.237, "eval_steps_per_second": 19.118, "step": 2 }, { "epoch": 0.0006417026510340771, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0008556035347121027, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0008556035347121027, "eval_loss": NaN, "eval_runtime": 240.2044, "eval_samples_per_second": 32.78, "eval_steps_per_second": 16.39, "step": 4 }, { "epoch": 0.0010695044183901285, "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": 3861435931164672.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }