{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9302325581395349, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.09302325581395349, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.09302325581395349, "eval_loss": NaN, "eval_runtime": 1.5519, "eval_samples_per_second": 3.222, "eval_steps_per_second": 1.933, "step": 1 }, { "epoch": 0.18604651162790697, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.27906976744186046, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.27906976744186046, "eval_loss": NaN, "eval_runtime": 0.1824, "eval_samples_per_second": 27.41, "eval_steps_per_second": 16.446, "step": 3 }, { "epoch": 0.37209302325581395, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.46511627906976744, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.5581395348837209, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.5581395348837209, "eval_loss": NaN, "eval_runtime": 0.1838, "eval_samples_per_second": 27.21, "eval_steps_per_second": 16.326, "step": 6 }, { "epoch": 0.6511627906976745, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.7441860465116279, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.8372093023255814, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.8372093023255814, "eval_loss": NaN, "eval_runtime": 0.1807, "eval_samples_per_second": 27.667, "eval_steps_per_second": 16.6, "step": 9 }, { "epoch": 0.9302325581395349, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1849564248145920.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }