{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.6650041562759768, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.013300083125519535, "eval_loss": NaN, "eval_runtime": 20.18, "eval_samples_per_second": 25.124, "eval_steps_per_second": 3.171, "step": 1 }, { "epoch": 0.13300083125519535, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.13300083125519535, "eval_loss": NaN, "eval_runtime": 19.1556, "eval_samples_per_second": 26.467, "eval_steps_per_second": 3.341, "step": 10 }, { "epoch": 0.2660016625103907, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.2660016625103907, "eval_loss": NaN, "eval_runtime": 19.1801, "eval_samples_per_second": 26.434, "eval_steps_per_second": 3.337, "step": 20 }, { "epoch": 0.39900249376558605, "grad_norm": NaN, "learning_rate": 3.705904774487396e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.39900249376558605, "eval_loss": NaN, "eval_runtime": 19.1799, "eval_samples_per_second": 26.434, "eval_steps_per_second": 3.337, "step": 30 }, { "epoch": 0.5320033250207814, "grad_norm": NaN, "learning_rate": 1.0332332985438248e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.5320033250207814, "eval_loss": NaN, "eval_runtime": 19.1884, "eval_samples_per_second": 26.422, "eval_steps_per_second": 3.335, "step": 40 }, { "epoch": 0.6650041562759768, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.6650041562759768, "eval_loss": NaN, "eval_runtime": 19.3211, "eval_samples_per_second": 26.241, "eval_steps_per_second": 3.312, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.18877213622272e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }