{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.6872852233676976, "eval_steps": 10, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.013745704467353952, "eval_loss": NaN, "eval_runtime": 18.0815, "eval_samples_per_second": 27.1, "eval_steps_per_second": 3.429, "step": 1 }, { "epoch": 0.13745704467353953, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.13745704467353953, "eval_loss": NaN, "eval_runtime": 16.4273, "eval_samples_per_second": 29.828, "eval_steps_per_second": 3.774, "step": 10 }, { "epoch": 0.27491408934707906, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.27491408934707906, "eval_loss": NaN, "eval_runtime": 16.3568, "eval_samples_per_second": 29.957, "eval_steps_per_second": 3.79, "step": 20 }, { "epoch": 0.41237113402061853, "grad_norm": NaN, "learning_rate": 3.705904774487396e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.41237113402061853, "eval_loss": NaN, "eval_runtime": 16.4258, "eval_samples_per_second": 29.831, "eval_steps_per_second": 3.775, "step": 30 }, { "epoch": 0.5498281786941581, "grad_norm": NaN, "learning_rate": 1.0332332985438248e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.5498281786941581, "eval_loss": NaN, "eval_runtime": 16.3891, "eval_samples_per_second": 29.898, "eval_steps_per_second": 3.783, "step": 40 }, { "epoch": 0.6872852233676976, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.6872852233676976, "eval_loss": NaN, "eval_runtime": 16.3844, "eval_samples_per_second": 29.907, "eval_steps_per_second": 3.784, "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": 4.472072984906957e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }