{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0005870094802031052, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00011740189604062105, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00011740189604062105, "eval_loss": NaN, "eval_runtime": 263.1033, "eval_samples_per_second": 54.526, "eval_steps_per_second": 27.263, "step": 1 }, { "epoch": 0.0002348037920812421, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0002348037920812421, "eval_loss": NaN, "eval_runtime": 157.7611, "eval_samples_per_second": 90.935, "eval_steps_per_second": 45.467, "step": 2 }, { "epoch": 0.00035220568812186317, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0004696075841624842, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0004696075841624842, "eval_loss": NaN, "eval_runtime": 158.1404, "eval_samples_per_second": 90.717, "eval_steps_per_second": 45.358, "step": 4 }, { "epoch": 0.0005870094802031052, "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": 356152655216640.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }