{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.012012012012012012, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0024024024024024023, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0024024024024024023, "eval_loss": NaN, "eval_runtime": 15.2757, "eval_samples_per_second": 45.89, "eval_steps_per_second": 22.978, "step": 1 }, { "epoch": 0.004804804804804805, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.004804804804804805, "eval_loss": NaN, "eval_runtime": 0.9516, "eval_samples_per_second": 736.644, "eval_steps_per_second": 368.848, "step": 2 }, { "epoch": 0.007207207207207207, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.00960960960960961, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.00960960960960961, "eval_loss": NaN, "eval_runtime": 0.9587, "eval_samples_per_second": 731.226, "eval_steps_per_second": 366.134, "step": 4 }, { "epoch": 0.012012012012012012, "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": 513296302080.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }