{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0012758356723653994, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00012758356723653993, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00012758356723653993, "eval_loss": NaN, "eval_runtime": 311.859, "eval_samples_per_second": 2.649, "eval_steps_per_second": 2.649, "step": 1 }, { "epoch": 0.00025516713447307985, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0003827507017096198, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0003827507017096198, "eval_loss": NaN, "eval_runtime": 311.6998, "eval_samples_per_second": 2.65, "eval_steps_per_second": 2.65, "step": 3 }, { "epoch": 0.0005103342689461597, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0006379178361826997, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0007655014034192396, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0007655014034192396, "eval_loss": NaN, "eval_runtime": 311.5865, "eval_samples_per_second": 2.651, "eval_steps_per_second": 2.651, "step": 6 }, { "epoch": 0.0008930849706557795, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0010206685378923194, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0011482521051288594, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0011482521051288594, "eval_loss": NaN, "eval_runtime": 311.3988, "eval_samples_per_second": 2.653, "eval_steps_per_second": 2.653, "step": 9 }, { "epoch": 0.0012758356723653994, "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": 1844410790707200.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }